Aiming at the problems of short duration,low intensity,and difficult detection of micro-expressions(MEs),the global and local features of ME video frames are extracted by combining spatial feature extraction and tempo...Aiming at the problems of short duration,low intensity,and difficult detection of micro-expressions(MEs),the global and local features of ME video frames are extracted by combining spatial feature extraction and temporal feature extraction.Based on traditional convolution neural network(CNN)and long short-term memory(LSTM),a recognition method combining global identification attention network(GIA),block identification attention network(BIA)and bi-directional long short-term memory(Bi-LSTM)is proposed.In the BIA,the ME video frame will be cropped,and the training will be carried out by cropping into 24 identification blocks(IBs),10 IBs and uncropped IBs.To alleviate the overfitting problem in training,we first extract the basic features of the preprocessed sequence through the transfer learning layer,and then extract the global and local spatial features of the output data through the GIA layer and the BIA layer,respectively.In the BIA layer,the input data will be cropped into local feature vectors with attention weights to extract the local features of the ME frames;in the GIA layer,the global features of the ME frames will be extracted.Finally,after fusing the global and local feature vectors,the ME time-series information is extracted by Bi-LSTM.The experimental results show that using IBs can significantly improve the model’s ability to extract subtle facial features,and the model works best when 10 IBs are used.展开更多
Micro-expressions are spontaneous, unconscious movements that reveal true emotions.Accurate facial movement information and network training learning methods are crucial for micro-expression recognition.However, most ...Micro-expressions are spontaneous, unconscious movements that reveal true emotions.Accurate facial movement information and network training learning methods are crucial for micro-expression recognition.However, most existing micro-expression recognition technologies so far focus on modeling the single category of micro-expression images and neural network structure.Aiming at the problems of low recognition rate and weak model generalization ability in micro-expression recognition, a micro-expression recognition algorithm is proposed based on graph convolution network(GCN) and Transformer model.Firstly, action unit(AU) feature detection is extracted and facial muscle nodes in the neighborhood are divided into three subsets for recognition.Then, graph convolution layer is used to find the layout of dependencies between AU nodes of micro-expression classification.Finally, multiple attentional features of each facial action are enriched with Transformer model to include more sequence information before calculating the overall correlation of each region.The proposed method is validated in CASME II and CAS(ME)^2 datasets, and the recognition rate reached 69.85%.展开更多
Background The use of micro-expression recognition to recognize human emotions is one of the most critical challenges in human-computer interaction applications. In recent years, cross-database micro-expression recogn...Background The use of micro-expression recognition to recognize human emotions is one of the most critical challenges in human-computer interaction applications. In recent years, cross-database micro-expression recognition(CDMER) has emerged as a significant challenge in micro-expression recognition and analysis. Because the training and testing data in CDMER come from different micro-expression databases, CDMER is more challenging than conventional micro-expression recognition. Methods In this paper, an adaptive spatio-temporal attention neural network(ASTANN) using an attention mechanism is presented to address this challenge. To this end, the micro-expression databases SMIC and CASME II are first preprocessed using an optical flow approach,which extracts motion information among video frames that represent discriminative features of micro-expression.After preprocessing, a novel adaptive framework with a spatiotemporal attention module was designed to assign spatial and temporal weights to enhance the most discriminative features. The deep neural network then extracts the cross-domain feature, in which the second-order statistics of the sample features in the source domain are aligned with those in the target domain by minimizing the correlation alignment(CORAL) loss such that the source and target databases share similar distributions. Results To evaluate the performance of ASTANN, experiments were conducted based on the SMIC and CASME II databases under the standard experimental evaluation protocol of CDMER. The experimental results demonstrate that ASTANN outperformed other methods in relevant crossdatabase tasks. Conclusions Extensive experiments were conducted on benchmark tasks, and the results show that ASTANN has superior performance compared with other approaches. This demonstrates the superiority of our method in solving the CDMER problem.展开更多
Aiming at the problem of unsatisfactory effects of traditional micro-expression recognition algorithms,an efficient micro-expression recognition algorithm is proposed,which uses convolutional neural networks(CNN)to ex...Aiming at the problem of unsatisfactory effects of traditional micro-expression recognition algorithms,an efficient micro-expression recognition algorithm is proposed,which uses convolutional neural networks(CNN)to extract spatial features of micro-expressions,and long short-term memory network(LSTM)to extract time domain features.CNN and LSTM are combined as the basis of micro-expression recognition.In many CNN structures,the visual geometry group(VGG)using a small convolution kernel is finally selected as the pre-network through comparison.Due to the difficulty of deep learning training and over-fitting,the dropout method and batch normalization method are used to solve the problem in the VGG network.Two data sets CASME and CASME II are used for test comparison,in order to solve the problem of insufficient data sets,randomly determine the starting frame,and a fixedlength frame sequence is used as the standard,and repeatedly read all sample frames of the entire data set to achieve trayersal and data amplification.Finallv.a hieh recognition rate of 67.48% is achieved.展开更多
The micro-expression lasts for a very short time and the intensity is very subtle.Aiming at the problem of its low recognition rate,this paper proposes a new micro-expression recognition algorithm based on a three-dim...The micro-expression lasts for a very short time and the intensity is very subtle.Aiming at the problem of its low recognition rate,this paper proposes a new micro-expression recognition algorithm based on a three-dimensional convolutional neural network(3D-CNN),which can extract two-di-mensional features in spatial domain and one-dimensional features in time domain,simultaneously.The network structure design is based on the deep learning framework Keras,and the discarding method and batch normalization(BN)algorithm are effectively combined with three-dimensional vis-ual geometry group block(3D-VGG-Block)to reduce the risk of overfitting while improving training speed.Aiming at the problem of the lack of samples in the data set,two methods of image flipping and small amplitude flipping are used for data amplification.Finally,the recognition rate on the data set is as high as 69.11%.Compared with the current international average micro-expression recog-nition rate of about 67%,the proposed algorithm has obvious advantages in recognition rate.展开更多
Micro-expression recognition has attracted growing research interests in the field of compute vision.However,micro-expression usually lasts a few seconds,thus it is difficult to detect.This paper presents a new framew...Micro-expression recognition has attracted growing research interests in the field of compute vision.However,micro-expression usually lasts a few seconds,thus it is difficult to detect.This paper presents a new framework to recognize micro-expression using pyramid histogram of Centralized Gabor Binary Pattern from Three Orthogonal Panels(CGBP-TOP)which is an extension of Local Gabor Binary Pattern from Three Orthogonal Panels feature.CGBP-TOP performs spatial and temporal analysis to capture the local facial characteristics of micro-expression image sequences.In order to keep more local information of the face,CGBP-TOP is extracted based on pyramid subregions of the micro-expression video frame.The combination of CGBP-TOP and spatial pyramid can represent well and truly the facial movements of the micro-expression image sequences.However,the dimension of our pyramid CGBP-TOP tends to be very high,which may lead to high data redundancy problem.In addition,it is clear that people of different genders usually have different ways of micro-expression.Therefore,in this paper,in order to select the relevant features of micro-expression,the gender-specific sparse multi-task learning method with adaptive regularization term is adopted to learn a compact subset of pyramid CGBP-TOP feature for micro-expression classification of different sexes.Finally,extensive experiments on widely used CASME II and SMIC databases demonstrate that our method can efficiently extract micro-expression motion features in the micro-expression video clip.Moreover,our proposed approach achieves comparable results with the state-of-the-art methods.展开更多
Micro-expression is manifested through subtle and brief facial movements that relay the genuine person’s hidden emotion.In a sequence of videos,there is a frame that captures the maximum facial differences,which is c...Micro-expression is manifested through subtle and brief facial movements that relay the genuine person’s hidden emotion.In a sequence of videos,there is a frame that captures the maximum facial differences,which is called the apex frame.Therefore,apex frame spotting is a crucial sub-module in a micro-expression recognition system.However,this spotting task is very challenging due to the characteristics of micro-expression that occurs in a short duration with low-intensity muscle movements.Moreover,most of the existing automated works face difficulties in differentiating micro-expressions from other facial movements.Therefore,this paper presents a deep learning model with an attention mechanism to spot the micro-expression apex frame from optical flow images.The attention mechanism is embedded into the model so that more weights can be allocated to the regions that manifest the facial movements with higher intensity.The method proposed in this paper has been tested and verified on two spontaneous micro-expression databases,namely Spontaneous Micro-facial Movement(SAMM)and Chinese Academy of Sciences Micro-expression(CASME)II databases.The proposed system performance is evaluated by using the Mean Absolute Error(MAE)metric that measures the distance between the predicted apex frame and the ground truth label.The best MAE of 14.90 was obtained when a combination of five convolutional layers,local response normalization,and attention mechanism is used to model the apex frame spotting.Even with limited datasets,the results have proven that the attention mechanism has better emphasized the regions where the facial movements likely to occur and hence,improves the spotting performance.展开更多
Micro-expression recognition is a substantive cross-study of psychology and computer science,and it has a wide range of applications(e.g.,psychological and clinical diagnosis,emotional analysis,criminal investigation,...Micro-expression recognition is a substantive cross-study of psychology and computer science,and it has a wide range of applications(e.g.,psychological and clinical diagnosis,emotional analysis,criminal investigation,etc.).However,the subtle and diverse changes in facial muscles make it difficult for existing methods to extract effective features,which limits the improvement of micro-expression recognition accuracy.Therefore,we propose a multi-scale joint feature network based on optical flow images for micro-expression recognition.First,we generate an optical flow image that reflects subtle facial motion information.The optical flow image is then fed into the multi-scale joint network for feature extraction and classification.The proposed joint feature module(JFM)integrates features from different layers,which is beneficial for the capture of micro-expression features with different amplitudes.To improve the recognition ability of the model,we also adopt a strategy for fusing the feature prediction results of the three JFMs with the backbone network.Our experimental results show that our method is superior to state-of-the-art methods on three benchmark datasets(SMIC,CASME II,and SAMM)and a combined dataset(3 DB).展开更多
Facial micro-expressions are short and imperceptible expressions that involuntarily reveal the true emotions that a person may be attempting to suppress,hide,disguise,or conceal.Such expressions can reflect a person...Facial micro-expressions are short and imperceptible expressions that involuntarily reveal the true emotions that a person may be attempting to suppress,hide,disguise,or conceal.Such expressions can reflect a person's real emotions and have a wide range of application in public safety and clinical diagnosis.The analysis of facial micro-expressions in video sequences through computer vision is still relatively recent.In this research,a comprehensive review on the topic of spotting and recognition used in micro expression analysis databases and methods,is conducted,and advanced technologies in this area are summarized.In addition,we discuss challenges that remain unresolved alongside future work to be completed in the field of micro-expression analysis.展开更多
The intensity of the micro-expression is weak,although the directional low frequency components in the image are preserved by many algorithms,the extracted micro-expression ft^ature information is not sufficient to ac...The intensity of the micro-expression is weak,although the directional low frequency components in the image are preserved by many algorithms,the extracted micro-expression ft^ature information is not sufficient to accurately represent its sequences.In order to improve the accuracy of micro-expression recognition,first,each frame image is extracted from,its sequences,and the image frame is pre-processed by using gray normalization,size normalization,and two-dimensional principal component analysis(2DPCA);then,the optical flow method is used to extract the motion characteristics of the reduced-dimensional image,the information entropy value of the optical flow characteristic image is calculated by the information entropy principle,and the information entropy value is analyzed to obtain the eigenvalue.Therefore,more micro-expression feature information is extracted,including more important information,which can further improve the accuracy of micro-expression classification and recognition;finally,the feature images are classified by using the support vector machine(SVM).The experimental results show that the micro-expression feature image obtained by the information entropy statistics can effectively improve the accuracy of micro-expression recognition.展开更多
Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security.Currently,with the emergence of massive high-resolution multi...Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security.Currently,with the emergence of massive high-resolution multi-modality images,the use of multi-modality images for fine-grained recognition has become a promising technology.Fine-grained recognition of multi-modality images imposes higher requirements on the dataset samples.The key to the problem is how to extract and fuse the complementary features of multi-modality images to obtain more discriminative fusion features.The attention mechanism helps the model to pinpoint the key information in the image,resulting in a significant improvement in the model’s performance.In this paper,a dataset for fine-grained recognition of ships based on visible and near-infrared multi-modality remote sensing images has been proposed first,named Dataset for Multimodal Fine-grained Recognition of Ships(DMFGRS).It includes 1,635 pairs of visible and near-infrared remote sensing images divided into 20 categories,collated from digital orthophotos model provided by commercial remote sensing satellites.DMFGRS provides two types of annotation format files,as well as segmentation mask images corresponding to the ship targets.Then,a Multimodal Information Cross-Enhancement Network(MICE-Net)fusing features of visible and near-infrared remote sensing images,has been proposed.In the network,a dual-branch feature extraction and fusion module has been designed to obtain more expressive features.The Feature Cross Enhancement Module(FCEM)achieves the fusion enhancement of the two modal features by making the channel attention and spatial attention work cross-functionally on the feature map.A benchmark is established by evaluating state-of-the-art object recognition algorithms on DMFGRS.MICE-Net conducted experiments on DMFGRS,and the precision,recall,mAP0.5 and mAP0.5:0.95 reached 87%,77.1%,83.8%and 63.9%,respectively.Extensive experiments demonstrate that the proposed MICE-Net has more excellent performance on DMFGRS.Built on lightweight network YOLO,the model has excellent generalizability,and thus has good potential for application in real-life scenarios.展开更多
Regular exercise is a crucial aspect of daily life, as it enables individuals to stay physically active, lowers thelikelihood of developing illnesses, and enhances life expectancy. The recognition of workout actions i...Regular exercise is a crucial aspect of daily life, as it enables individuals to stay physically active, lowers thelikelihood of developing illnesses, and enhances life expectancy. The recognition of workout actions in videostreams holds significant importance in computer vision research, as it aims to enhance exercise adherence, enableinstant recognition, advance fitness tracking technologies, and optimize fitness routines. However, existing actiondatasets often lack diversity and specificity for workout actions, hindering the development of accurate recognitionmodels. To address this gap, the Workout Action Video dataset (WAVd) has been introduced as a significantcontribution. WAVd comprises a diverse collection of labeled workout action videos, meticulously curated toencompass various exercises performed by numerous individuals in different settings. This research proposes aninnovative framework based on the Attention driven Residual Deep Convolutional-Gated Recurrent Unit (ResDCGRU)network for workout action recognition in video streams. Unlike image-based action recognition, videoscontain spatio-temporal information, making the task more complex and challenging. While substantial progresshas been made in this area, challenges persist in detecting subtle and complex actions, handling occlusions,and managing the computational demands of deep learning approaches. The proposed ResDC-GRU Attentionmodel demonstrated exceptional classification performance with 95.81% accuracy in classifying workout actionvideos and also outperformed various state-of-the-art models. The method also yielded 81.6%, 97.2%, 95.6%, and93.2% accuracy on established benchmark datasets, namely HMDB51, Youtube Actions, UCF50, and UCF101,respectively, showcasing its superiority and robustness in action recognition. The findings suggest practicalimplications in real-world scenarios where precise video action recognition is paramount, addressing the persistingchallenges in the field. TheWAVd dataset serves as a catalyst for the development ofmore robust and effective fitnesstracking systems and ultimately promotes healthier lifestyles through improved exercise monitoring and analysis.展开更多
Sign language,a visual-gestural language used by the deaf and hard-of-hearing community,plays a crucial role in facilitating communication and promoting inclusivity.Sign language recognition(SLR),the process of automa...Sign language,a visual-gestural language used by the deaf and hard-of-hearing community,plays a crucial role in facilitating communication and promoting inclusivity.Sign language recognition(SLR),the process of automatically recognizing and interpreting sign language gestures,has gained significant attention in recent years due to its potential to bridge the communication gap between the hearing impaired and the hearing world.The emergence and continuous development of deep learning techniques have provided inspiration and momentum for advancing SLR.This paper presents a comprehensive and up-to-date analysis of the advancements,challenges,and opportunities in deep learning-based sign language recognition,focusing on the past five years of research.We explore various aspects of SLR,including sign data acquisition technologies,sign language datasets,evaluation methods,and different types of neural networks.Convolutional Neural Networks(CNN)and Recurrent Neural Networks(RNN)have shown promising results in fingerspelling and isolated sign recognition.However,the continuous nature of sign language poses challenges,leading to the exploration of advanced neural network models such as the Transformer model for continuous sign language recognition(CSLR).Despite significant advancements,several challenges remain in the field of SLR.These challenges include expanding sign language datasets,achieving user independence in recognition systems,exploring different input modalities,effectively fusing features,modeling co-articulation,and improving semantic and syntactic understanding.Additionally,developing lightweight network architectures for mobile applications is crucial for practical implementation.By addressing these challenges,we can further advance the field of deep learning for sign language recognition and improve communication for the hearing-impaired community.展开更多
This paper proposes a novel open set recognition method,the Spatial Distribution Feature Extraction Network(SDFEN),to address the problem of electromagnetic signal recognition in an open environment.The spatial distri...This paper proposes a novel open set recognition method,the Spatial Distribution Feature Extraction Network(SDFEN),to address the problem of electromagnetic signal recognition in an open environment.The spatial distribution feature extraction layer in SDFEN replaces convolutional output neural networks with the spatial distribution features that focus more on inter-sample information by incorporating class center vectors.The designed hybrid loss function considers both intra-class distance and inter-class distance,thereby enhancing the similarity among samples of the same class and increasing the dissimilarity between samples of different classes during training.Consequently,this method allows unknown classes to occupy a larger space in the feature space.This reduces the possibility of overlap with known class samples and makes the boundaries between known and unknown samples more distinct.Additionally,the feature comparator threshold can be used to reject unknown samples.For signal open set recognition,seven methods,including the proposed method,are applied to two kinds of electromagnetic signal data:modulation signal and real-world emitter.The experimental results demonstrate that the proposed method outperforms the other six methods overall in a simulated open environment.Specifically,compared to the state-of-the-art Openmax method,the novel method achieves up to 8.87%and 5.25%higher micro-F-measures,respectively.展开更多
Hand gestures have been used as a significant mode of communication since the advent of human civilization.By facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seaml...Hand gestures have been used as a significant mode of communication since the advent of human civilization.By facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seamless and error-free HCI.HGRoc technology is pivotal in healthcare and communication for the deaf community.Despite significant advancements in computer vision-based gesture recognition for language understanding,two considerable challenges persist in this field:(a)limited and common gestures are considered,(b)processing multiple channels of information across a network takes huge computational time during discriminative feature extraction.Therefore,a novel hand vision-based convolutional neural network(CNN)model named(HVCNNM)offers several benefits,notably enhanced accuracy,robustness to variations,real-time performance,reduced channels,and scalability.Additionally,these models can be optimized for real-time performance,learn from large amounts of data,and are scalable to handle complex recognition tasks for efficient human-computer interaction.The proposed model was evaluated on two challenging datasets,namely the Massey University Dataset(MUD)and the American Sign Language(ASL)Alphabet Dataset(ASLAD).On the MUD and ASLAD datasets,HVCNNM achieved a score of 99.23% and 99.00%,respectively.These results demonstrate the effectiveness of CNN as a promising HGRoc approach.The findings suggest that the proposed model have potential roles in applications such as sign language recognition,human-computer interaction,and robotics.展开更多
The task of food image recognition,a nuanced subset of fine-grained image recognition,grapples with substantial intra-class variation and minimal inter-class differences.These challenges are compounded by the irregula...The task of food image recognition,a nuanced subset of fine-grained image recognition,grapples with substantial intra-class variation and minimal inter-class differences.These challenges are compounded by the irregular and multi-scale nature of food images.Addressing these complexities,our study introduces an advanced model that leverages multiple attention mechanisms and multi-stage local fusion,grounded in the ConvNeXt architecture.Our model employs hybrid attention(HA)mechanisms to pinpoint critical discriminative regions within images,substantially mitigating the influence of background noise.Furthermore,it introduces a multi-stage local fusion(MSLF)module,fostering long-distance dependencies between feature maps at varying stages.This approach facilitates the assimilation of complementary features across scales,significantly bolstering the model’s capacity for feature extraction.Furthermore,we constructed a dataset named Roushi60,which consists of 60 different categories of common meat dishes.Empirical evaluation of the ETH Food-101,ChineseFoodNet,and Roushi60 datasets reveals that our model achieves recognition accuracies of 91.12%,82.86%,and 92.50%,respectively.These figures not only mark an improvement of 1.04%,3.42%,and 1.36%over the foundational ConvNeXt network but also surpass the performance of most contemporary food image recognition methods.Such advancements underscore the efficacy of our proposed model in navigating the intricate landscape of food image recognition,setting a new benchmark for the field.展开更多
Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(...Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(LPEN)to efficiently and effectively detect abnormal fall-down and trespass incidents in electric power training scenarios.The LPEN network,comprising three stages—MobileNet,Initial Stage,and Refinement Stage—is employed to swiftly extract image features,detect human key points,and refine them for accurate analysis.Subsequently,a Pose-aware Action Analysis Module(PAAM)captures the positional coordinates of human skeletal points in each frame.Finally,an Abnormal Action Inference Module(AAIM)evaluates whether abnormal fall-down or unauthorized trespass behavior is occurring.For fall-down recognition,three criteria—falling speed,main angles of skeletal points,and the person’s bounding box—are considered.To identify unauthorized trespass,emphasis is placed on the position of the ankles.Extensive experiments validate the effectiveness and efficiency of the proposed system in ensuring the safety and reliability of electric power training.展开更多
Handwritten character recognition(HCR)involves identifying characters in images,documents,and various sources such as forms surveys,questionnaires,and signatures,and transforming them into a machine-readable format fo...Handwritten character recognition(HCR)involves identifying characters in images,documents,and various sources such as forms surveys,questionnaires,and signatures,and transforming them into a machine-readable format for subsequent processing.Successfully recognizing complex and intricately shaped handwritten characters remains a significant obstacle.The use of convolutional neural network(CNN)in recent developments has notably advanced HCR,leveraging the ability to extract discriminative features from extensive sets of raw data.Because of the absence of pre-existing datasets in the Kurdish language,we created a Kurdish handwritten dataset called(KurdSet).The dataset consists of Kurdish characters,digits,texts,and symbols.The dataset consists of 1560 participants and contains 45,240 characters.In this study,we chose characters only from our dataset.We utilized a Kurdish dataset for handwritten character recognition.The study also utilizes various models,including InceptionV3,Xception,DenseNet121,and a customCNNmodel.To show the performance of the KurdSet dataset,we compared it to Arabic handwritten character recognition dataset(AHCD).We applied the models to both datasets to show the performance of our dataset.Additionally,the performance of the models is evaluated using test accuracy,which measures the percentage of correctly classified characters in the evaluation phase.All models performed well in the training phase,DenseNet121 exhibited the highest accuracy among the models,achieving a high accuracy of 99.80%on the Kurdish dataset.And Xception model achieved 98.66%using the Arabic dataset.展开更多
This study proposes a pose estimation-convolutional neural network-bidirectional gated recurrent unit(PSECNN-BiGRU)fusion model for human posture recognition to address low accuracy issues in abnormal posture recognit...This study proposes a pose estimation-convolutional neural network-bidirectional gated recurrent unit(PSECNN-BiGRU)fusion model for human posture recognition to address low accuracy issues in abnormal posture recognition due to the loss of some feature information and the deterioration of comprehensive performance in model detection in complex home environments.Firstly,the deep convolutional network is integrated with the Mediapipe framework to extract high-precision,multi-dimensional information from the key points of the human skeleton,thereby obtaining a human posture feature set.Thereafter,a double-layer BiGRU algorithm is utilized to extract multi-layer,bidirectional temporal features from the human posture feature set,and a CNN network with an exponential linear unit(ELU)activation function is adopted to perform deep convolution of the feature map to extract the spatial feature of the human posture.Furthermore,a squeeze and excitation networks(SENet)module is introduced to adaptively learn the importance weights of each channel,enhancing the network’s focus on important features.Finally,comparative experiments are performed on available datasets,including the public human activity recognition using smartphone dataset(UCIHAR),the public human activity recognition 70 plus dataset(HAR70PLUS),and the independently developed home abnormal behavior recognition dataset(HABRD)created by the authors’team.The results show that the average accuracy of the proposed PSE-CNN-BiGRU fusion model for human posture recognition is 99.56%,89.42%,and 98.90%,respectively,which are 5.24%,5.83%,and 3.19%higher than the average accuracy of the five models proposed in the comparative literature,including CNN,GRU,and others.The F1-score for abnormal posture recognition reaches 98.84%(heartache),97.18%(fall),99.6%(bellyache),and 98.27%(climbing)on the self-builtHABRDdataset,thus verifying the effectiveness,generalization,and robustness of the proposed model in enhancing human posture recognition.展开更多
RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy protection.Existing RFID-based HAR methods use modeling,CNN,or LSTM to extract features effectively.Still...RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy protection.Existing RFID-based HAR methods use modeling,CNN,or LSTM to extract features effectively.Still,they have shortcomings:1)requiring complex hand-crafted data cleaning processes and 2)only addressing single-person activity recognition based on specific RF signals.To solve these problems,this paper proposes a novel device-free method based on Time-streaming Multiscale Transformer called TransTM.This model leverages the Transformer's powerful data fitting capabilities to take raw RFID RSSI data as input without pre-processing.Concretely,we propose a multiscale convolutional hybrid Transformer to capture behavioral features that recognizes singlehuman activities and human-to-human interactions.Compared with existing CNN-and LSTM-based methods,the Transformer-based method has more data fitting power,generalization,and scalability.Furthermore,using RF signals,our method achieves an excellent classification effect on human behaviorbased classification tasks.Experimental results on the actual RFID datasets show that this model achieves a high average recognition accuracy(99.1%).The dataset we collected for detecting RFID-based indoor human activities will be published.展开更多
基金supported by the National Natural Science Foundation of Hunan Province,China(Grant Nos.2021JJ50058,2022JJ50051)the Open Platform Innovation Foundation of Hunan Provincial Education Department(Grant No.20K046)The Scientific Research Fund of Hunan Provincial Education Department,China(Grant Nos.21A0350,21C0439,19A133).
文摘Aiming at the problems of short duration,low intensity,and difficult detection of micro-expressions(MEs),the global and local features of ME video frames are extracted by combining spatial feature extraction and temporal feature extraction.Based on traditional convolution neural network(CNN)and long short-term memory(LSTM),a recognition method combining global identification attention network(GIA),block identification attention network(BIA)and bi-directional long short-term memory(Bi-LSTM)is proposed.In the BIA,the ME video frame will be cropped,and the training will be carried out by cropping into 24 identification blocks(IBs),10 IBs and uncropped IBs.To alleviate the overfitting problem in training,we first extract the basic features of the preprocessed sequence through the transfer learning layer,and then extract the global and local spatial features of the output data through the GIA layer and the BIA layer,respectively.In the BIA layer,the input data will be cropped into local feature vectors with attention weights to extract the local features of the ME frames;in the GIA layer,the global features of the ME frames will be extracted.Finally,after fusing the global and local feature vectors,the ME time-series information is extracted by Bi-LSTM.The experimental results show that using IBs can significantly improve the model’s ability to extract subtle facial features,and the model works best when 10 IBs are used.
基金Supported by Shaanxi Province Key Research and Development Project (2021GY-280)the National Natural Science Foundation of China (No.61834005,61772417,61802304)。
文摘Micro-expressions are spontaneous, unconscious movements that reveal true emotions.Accurate facial movement information and network training learning methods are crucial for micro-expression recognition.However, most existing micro-expression recognition technologies so far focus on modeling the single category of micro-expression images and neural network structure.Aiming at the problems of low recognition rate and weak model generalization ability in micro-expression recognition, a micro-expression recognition algorithm is proposed based on graph convolution network(GCN) and Transformer model.Firstly, action unit(AU) feature detection is extracted and facial muscle nodes in the neighborhood are divided into three subsets for recognition.Then, graph convolution layer is used to find the layout of dependencies between AU nodes of micro-expression classification.Finally, multiple attentional features of each facial action are enriched with Transformer model to include more sequence information before calculating the overall correlation of each region.The proposed method is validated in CASME II and CAS(ME)^2 datasets, and the recognition rate reached 69.85%.
文摘Background The use of micro-expression recognition to recognize human emotions is one of the most critical challenges in human-computer interaction applications. In recent years, cross-database micro-expression recognition(CDMER) has emerged as a significant challenge in micro-expression recognition and analysis. Because the training and testing data in CDMER come from different micro-expression databases, CDMER is more challenging than conventional micro-expression recognition. Methods In this paper, an adaptive spatio-temporal attention neural network(ASTANN) using an attention mechanism is presented to address this challenge. To this end, the micro-expression databases SMIC and CASME II are first preprocessed using an optical flow approach,which extracts motion information among video frames that represent discriminative features of micro-expression.After preprocessing, a novel adaptive framework with a spatiotemporal attention module was designed to assign spatial and temporal weights to enhance the most discriminative features. The deep neural network then extracts the cross-domain feature, in which the second-order statistics of the sample features in the source domain are aligned with those in the target domain by minimizing the correlation alignment(CORAL) loss such that the source and target databases share similar distributions. Results To evaluate the performance of ASTANN, experiments were conducted based on the SMIC and CASME II databases under the standard experimental evaluation protocol of CDMER. The experimental results demonstrate that ASTANN outperformed other methods in relevant crossdatabase tasks. Conclusions Extensive experiments were conducted on benchmark tasks, and the results show that ASTANN has superior performance compared with other approaches. This demonstrates the superiority of our method in solving the CDMER problem.
基金Shaanxi Province Key Research and Development Project(No.2021 GY-280)Shaanxi Province Natural Science Basic Research Program Project(No.2021JM-459)+1 种基金National Natural Science Foundation of China(No.61834005,61772417,61802304,61602377,61634004)Shaanxi Province International Science and Technology Cooperation Project(No.2018KW-006)。
文摘Aiming at the problem of unsatisfactory effects of traditional micro-expression recognition algorithms,an efficient micro-expression recognition algorithm is proposed,which uses convolutional neural networks(CNN)to extract spatial features of micro-expressions,and long short-term memory network(LSTM)to extract time domain features.CNN and LSTM are combined as the basis of micro-expression recognition.In many CNN structures,the visual geometry group(VGG)using a small convolution kernel is finally selected as the pre-network through comparison.Due to the difficulty of deep learning training and over-fitting,the dropout method and batch normalization method are used to solve the problem in the VGG network.Two data sets CASME and CASME II are used for test comparison,in order to solve the problem of insufficient data sets,randomly determine the starting frame,and a fixedlength frame sequence is used as the standard,and repeatedly read all sample frames of the entire data set to achieve trayersal and data amplification.Finallv.a hieh recognition rate of 67.48% is achieved.
基金Supported by the Shaanxi Province Key Research and Development Project(No.2021GY-280)Shaanxi Province Natural Science Basic Re-search Program Project(No.2021JM-459)+1 种基金the National Natural Science Foundation of China(No.61834005,61772417,61802304,61602377,61634004)the Shaanxi Province International Science and Technology Cooperation Project(No.2018KW-006).
文摘The micro-expression lasts for a very short time and the intensity is very subtle.Aiming at the problem of its low recognition rate,this paper proposes a new micro-expression recognition algorithm based on a three-dimensional convolutional neural network(3D-CNN),which can extract two-di-mensional features in spatial domain and one-dimensional features in time domain,simultaneously.The network structure design is based on the deep learning framework Keras,and the discarding method and batch normalization(BN)algorithm are effectively combined with three-dimensional vis-ual geometry group block(3D-VGG-Block)to reduce the risk of overfitting while improving training speed.Aiming at the problem of the lack of samples in the data set,two methods of image flipping and small amplitude flipping are used for data amplification.Finally,the recognition rate on the data set is as high as 69.11%.Compared with the current international average micro-expression recog-nition rate of about 67%,the proposed algorithm has obvious advantages in recognition rate.
基金This work is funded by the natural science foundation of Jiangsu Province(No.BK20150471)the natural science foundation of the higher education institutions of Jiangsu Province(No.17KJB520007)+2 种基金the Key Research and Development Program of Zhenjiang-Social Development(No.SH2018005)the scientific researching fund of Jiangsu University of Science and Technology(No.1132921402,No.1132931803)the basic science and frontier technology research program of Chongqing Municipal Science and Technology Commission(cstc2016jcyjA0407).
文摘Micro-expression recognition has attracted growing research interests in the field of compute vision.However,micro-expression usually lasts a few seconds,thus it is difficult to detect.This paper presents a new framework to recognize micro-expression using pyramid histogram of Centralized Gabor Binary Pattern from Three Orthogonal Panels(CGBP-TOP)which is an extension of Local Gabor Binary Pattern from Three Orthogonal Panels feature.CGBP-TOP performs spatial and temporal analysis to capture the local facial characteristics of micro-expression image sequences.In order to keep more local information of the face,CGBP-TOP is extracted based on pyramid subregions of the micro-expression video frame.The combination of CGBP-TOP and spatial pyramid can represent well and truly the facial movements of the micro-expression image sequences.However,the dimension of our pyramid CGBP-TOP tends to be very high,which may lead to high data redundancy problem.In addition,it is clear that people of different genders usually have different ways of micro-expression.Therefore,in this paper,in order to select the relevant features of micro-expression,the gender-specific sparse multi-task learning method with adaptive regularization term is adopted to learn a compact subset of pyramid CGBP-TOP feature for micro-expression classification of different sexes.Finally,extensive experiments on widely used CASME II and SMIC databases demonstrate that our method can efficiently extract micro-expression motion features in the micro-expression video clip.Moreover,our proposed approach achieves comparable results with the state-of-the-art methods.
基金Authors would like to acknowledge funding from Universiti Kebangsaan Malaysia(Geran Universiti Penyelidikan:GUP-2019-008 and Dana Padanan Kolaborasi:DPK-2021-012).
文摘Micro-expression is manifested through subtle and brief facial movements that relay the genuine person’s hidden emotion.In a sequence of videos,there is a frame that captures the maximum facial differences,which is called the apex frame.Therefore,apex frame spotting is a crucial sub-module in a micro-expression recognition system.However,this spotting task is very challenging due to the characteristics of micro-expression that occurs in a short duration with low-intensity muscle movements.Moreover,most of the existing automated works face difficulties in differentiating micro-expressions from other facial movements.Therefore,this paper presents a deep learning model with an attention mechanism to spot the micro-expression apex frame from optical flow images.The attention mechanism is embedded into the model so that more weights can be allocated to the regions that manifest the facial movements with higher intensity.The method proposed in this paper has been tested and verified on two spontaneous micro-expression databases,namely Spontaneous Micro-facial Movement(SAMM)and Chinese Academy of Sciences Micro-expression(CASME)II databases.The proposed system performance is evaluated by using the Mean Absolute Error(MAE)metric that measures the distance between the predicted apex frame and the ground truth label.The best MAE of 14.90 was obtained when a combination of five convolutional layers,local response normalization,and attention mechanism is used to model the apex frame spotting.Even with limited datasets,the results have proven that the attention mechanism has better emphasized the regions where the facial movements likely to occur and hence,improves the spotting performance.
基金supported by the NSFC–Zhejiang Joint Fund of the Integration of Informatization and Industrialization under Grant No.U1909210the the National Natural Science Foundation of China under Grant No.61772312the Fundamental Research Funds of Shandong University(Grant No.2018JC030)。
文摘Micro-expression recognition is a substantive cross-study of psychology and computer science,and it has a wide range of applications(e.g.,psychological and clinical diagnosis,emotional analysis,criminal investigation,etc.).However,the subtle and diverse changes in facial muscles make it difficult for existing methods to extract effective features,which limits the improvement of micro-expression recognition accuracy.Therefore,we propose a multi-scale joint feature network based on optical flow images for micro-expression recognition.First,we generate an optical flow image that reflects subtle facial motion information.The optical flow image is then fed into the multi-scale joint network for feature extraction and classification.The proposed joint feature module(JFM)integrates features from different layers,which is beneficial for the capture of micro-expression features with different amplitudes.To improve the recognition ability of the model,we also adopt a strategy for fusing the feature prediction results of the three JFMs with the backbone network.Our experimental results show that our method is superior to state-of-the-art methods on three benchmark datasets(SMIC,CASME II,and SAMM)and a combined dataset(3 DB).
文摘Facial micro-expressions are short and imperceptible expressions that involuntarily reveal the true emotions that a person may be attempting to suppress,hide,disguise,or conceal.Such expressions can reflect a person's real emotions and have a wide range of application in public safety and clinical diagnosis.The analysis of facial micro-expressions in video sequences through computer vision is still relatively recent.In this research,a comprehensive review on the topic of spotting and recognition used in micro expression analysis databases and methods,is conducted,and advanced technologies in this area are summarized.In addition,we discuss challenges that remain unresolved alongside future work to be completed in the field of micro-expression analysis.
基金the National Natural Science Foundation of China(Nos.61772417,61634004,and 61602377)the Key R&D Progrm Projects in Shaanxi Province(No.2017GY-060)the Shaanxi Natural Science Basic Research Project(No.018JM4018)。
文摘The intensity of the micro-expression is weak,although the directional low frequency components in the image are preserved by many algorithms,the extracted micro-expression ft^ature information is not sufficient to accurately represent its sequences.In order to improve the accuracy of micro-expression recognition,first,each frame image is extracted from,its sequences,and the image frame is pre-processed by using gray normalization,size normalization,and two-dimensional principal component analysis(2DPCA);then,the optical flow method is used to extract the motion characteristics of the reduced-dimensional image,the information entropy value of the optical flow characteristic image is calculated by the information entropy principle,and the information entropy value is analyzed to obtain the eigenvalue.Therefore,more micro-expression feature information is extracted,including more important information,which can further improve the accuracy of micro-expression classification and recognition;finally,the feature images are classified by using the support vector machine(SVM).The experimental results show that the micro-expression feature image obtained by the information entropy statistics can effectively improve the accuracy of micro-expression recognition.
文摘Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security.Currently,with the emergence of massive high-resolution multi-modality images,the use of multi-modality images for fine-grained recognition has become a promising technology.Fine-grained recognition of multi-modality images imposes higher requirements on the dataset samples.The key to the problem is how to extract and fuse the complementary features of multi-modality images to obtain more discriminative fusion features.The attention mechanism helps the model to pinpoint the key information in the image,resulting in a significant improvement in the model’s performance.In this paper,a dataset for fine-grained recognition of ships based on visible and near-infrared multi-modality remote sensing images has been proposed first,named Dataset for Multimodal Fine-grained Recognition of Ships(DMFGRS).It includes 1,635 pairs of visible and near-infrared remote sensing images divided into 20 categories,collated from digital orthophotos model provided by commercial remote sensing satellites.DMFGRS provides two types of annotation format files,as well as segmentation mask images corresponding to the ship targets.Then,a Multimodal Information Cross-Enhancement Network(MICE-Net)fusing features of visible and near-infrared remote sensing images,has been proposed.In the network,a dual-branch feature extraction and fusion module has been designed to obtain more expressive features.The Feature Cross Enhancement Module(FCEM)achieves the fusion enhancement of the two modal features by making the channel attention and spatial attention work cross-functionally on the feature map.A benchmark is established by evaluating state-of-the-art object recognition algorithms on DMFGRS.MICE-Net conducted experiments on DMFGRS,and the precision,recall,mAP0.5 and mAP0.5:0.95 reached 87%,77.1%,83.8%and 63.9%,respectively.Extensive experiments demonstrate that the proposed MICE-Net has more excellent performance on DMFGRS.Built on lightweight network YOLO,the model has excellent generalizability,and thus has good potential for application in real-life scenarios.
文摘Regular exercise is a crucial aspect of daily life, as it enables individuals to stay physically active, lowers thelikelihood of developing illnesses, and enhances life expectancy. The recognition of workout actions in videostreams holds significant importance in computer vision research, as it aims to enhance exercise adherence, enableinstant recognition, advance fitness tracking technologies, and optimize fitness routines. However, existing actiondatasets often lack diversity and specificity for workout actions, hindering the development of accurate recognitionmodels. To address this gap, the Workout Action Video dataset (WAVd) has been introduced as a significantcontribution. WAVd comprises a diverse collection of labeled workout action videos, meticulously curated toencompass various exercises performed by numerous individuals in different settings. This research proposes aninnovative framework based on the Attention driven Residual Deep Convolutional-Gated Recurrent Unit (ResDCGRU)network for workout action recognition in video streams. Unlike image-based action recognition, videoscontain spatio-temporal information, making the task more complex and challenging. While substantial progresshas been made in this area, challenges persist in detecting subtle and complex actions, handling occlusions,and managing the computational demands of deep learning approaches. The proposed ResDC-GRU Attentionmodel demonstrated exceptional classification performance with 95.81% accuracy in classifying workout actionvideos and also outperformed various state-of-the-art models. The method also yielded 81.6%, 97.2%, 95.6%, and93.2% accuracy on established benchmark datasets, namely HMDB51, Youtube Actions, UCF50, and UCF101,respectively, showcasing its superiority and robustness in action recognition. The findings suggest practicalimplications in real-world scenarios where precise video action recognition is paramount, addressing the persistingchallenges in the field. TheWAVd dataset serves as a catalyst for the development ofmore robust and effective fitnesstracking systems and ultimately promotes healthier lifestyles through improved exercise monitoring and analysis.
基金supported from the National Philosophy and Social Sciences Foundation(Grant No.20BTQ065).
文摘Sign language,a visual-gestural language used by the deaf and hard-of-hearing community,plays a crucial role in facilitating communication and promoting inclusivity.Sign language recognition(SLR),the process of automatically recognizing and interpreting sign language gestures,has gained significant attention in recent years due to its potential to bridge the communication gap between the hearing impaired and the hearing world.The emergence and continuous development of deep learning techniques have provided inspiration and momentum for advancing SLR.This paper presents a comprehensive and up-to-date analysis of the advancements,challenges,and opportunities in deep learning-based sign language recognition,focusing on the past five years of research.We explore various aspects of SLR,including sign data acquisition technologies,sign language datasets,evaluation methods,and different types of neural networks.Convolutional Neural Networks(CNN)and Recurrent Neural Networks(RNN)have shown promising results in fingerspelling and isolated sign recognition.However,the continuous nature of sign language poses challenges,leading to the exploration of advanced neural network models such as the Transformer model for continuous sign language recognition(CSLR).Despite significant advancements,several challenges remain in the field of SLR.These challenges include expanding sign language datasets,achieving user independence in recognition systems,exploring different input modalities,effectively fusing features,modeling co-articulation,and improving semantic and syntactic understanding.Additionally,developing lightweight network architectures for mobile applications is crucial for practical implementation.By addressing these challenges,we can further advance the field of deep learning for sign language recognition and improve communication for the hearing-impaired community.
文摘This paper proposes a novel open set recognition method,the Spatial Distribution Feature Extraction Network(SDFEN),to address the problem of electromagnetic signal recognition in an open environment.The spatial distribution feature extraction layer in SDFEN replaces convolutional output neural networks with the spatial distribution features that focus more on inter-sample information by incorporating class center vectors.The designed hybrid loss function considers both intra-class distance and inter-class distance,thereby enhancing the similarity among samples of the same class and increasing the dissimilarity between samples of different classes during training.Consequently,this method allows unknown classes to occupy a larger space in the feature space.This reduces the possibility of overlap with known class samples and makes the boundaries between known and unknown samples more distinct.Additionally,the feature comparator threshold can be used to reject unknown samples.For signal open set recognition,seven methods,including the proposed method,are applied to two kinds of electromagnetic signal data:modulation signal and real-world emitter.The experimental results demonstrate that the proposed method outperforms the other six methods overall in a simulated open environment.Specifically,compared to the state-of-the-art Openmax method,the novel method achieves up to 8.87%and 5.25%higher micro-F-measures,respectively.
基金funded by Researchers Supporting Project Number(RSPD2024 R947),King Saud University,Riyadh,Saudi Arabia.
文摘Hand gestures have been used as a significant mode of communication since the advent of human civilization.By facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seamless and error-free HCI.HGRoc technology is pivotal in healthcare and communication for the deaf community.Despite significant advancements in computer vision-based gesture recognition for language understanding,two considerable challenges persist in this field:(a)limited and common gestures are considered,(b)processing multiple channels of information across a network takes huge computational time during discriminative feature extraction.Therefore,a novel hand vision-based convolutional neural network(CNN)model named(HVCNNM)offers several benefits,notably enhanced accuracy,robustness to variations,real-time performance,reduced channels,and scalability.Additionally,these models can be optimized for real-time performance,learn from large amounts of data,and are scalable to handle complex recognition tasks for efficient human-computer interaction.The proposed model was evaluated on two challenging datasets,namely the Massey University Dataset(MUD)and the American Sign Language(ASL)Alphabet Dataset(ASLAD).On the MUD and ASLAD datasets,HVCNNM achieved a score of 99.23% and 99.00%,respectively.These results demonstrate the effectiveness of CNN as a promising HGRoc approach.The findings suggest that the proposed model have potential roles in applications such as sign language recognition,human-computer interaction,and robotics.
基金The support of this research was by Hubei Provincial Natural Science Foundation(2022CFB449)Science Research Foundation of Education Department of Hubei Province(B2020061),are gratefully acknowledged.
文摘The task of food image recognition,a nuanced subset of fine-grained image recognition,grapples with substantial intra-class variation and minimal inter-class differences.These challenges are compounded by the irregular and multi-scale nature of food images.Addressing these complexities,our study introduces an advanced model that leverages multiple attention mechanisms and multi-stage local fusion,grounded in the ConvNeXt architecture.Our model employs hybrid attention(HA)mechanisms to pinpoint critical discriminative regions within images,substantially mitigating the influence of background noise.Furthermore,it introduces a multi-stage local fusion(MSLF)module,fostering long-distance dependencies between feature maps at varying stages.This approach facilitates the assimilation of complementary features across scales,significantly bolstering the model’s capacity for feature extraction.Furthermore,we constructed a dataset named Roushi60,which consists of 60 different categories of common meat dishes.Empirical evaluation of the ETH Food-101,ChineseFoodNet,and Roushi60 datasets reveals that our model achieves recognition accuracies of 91.12%,82.86%,and 92.50%,respectively.These figures not only mark an improvement of 1.04%,3.42%,and 1.36%over the foundational ConvNeXt network but also surpass the performance of most contemporary food image recognition methods.Such advancements underscore the efficacy of our proposed model in navigating the intricate landscape of food image recognition,setting a new benchmark for the field.
基金supportted by Natural Science Foundation of Jiangsu Province(No.BK20230696).
文摘Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(LPEN)to efficiently and effectively detect abnormal fall-down and trespass incidents in electric power training scenarios.The LPEN network,comprising three stages—MobileNet,Initial Stage,and Refinement Stage—is employed to swiftly extract image features,detect human key points,and refine them for accurate analysis.Subsequently,a Pose-aware Action Analysis Module(PAAM)captures the positional coordinates of human skeletal points in each frame.Finally,an Abnormal Action Inference Module(AAIM)evaluates whether abnormal fall-down or unauthorized trespass behavior is occurring.For fall-down recognition,three criteria—falling speed,main angles of skeletal points,and the person’s bounding box—are considered.To identify unauthorized trespass,emphasis is placed on the position of the ankles.Extensive experiments validate the effectiveness and efficiency of the proposed system in ensuring the safety and reliability of electric power training.
文摘Handwritten character recognition(HCR)involves identifying characters in images,documents,and various sources such as forms surveys,questionnaires,and signatures,and transforming them into a machine-readable format for subsequent processing.Successfully recognizing complex and intricately shaped handwritten characters remains a significant obstacle.The use of convolutional neural network(CNN)in recent developments has notably advanced HCR,leveraging the ability to extract discriminative features from extensive sets of raw data.Because of the absence of pre-existing datasets in the Kurdish language,we created a Kurdish handwritten dataset called(KurdSet).The dataset consists of Kurdish characters,digits,texts,and symbols.The dataset consists of 1560 participants and contains 45,240 characters.In this study,we chose characters only from our dataset.We utilized a Kurdish dataset for handwritten character recognition.The study also utilizes various models,including InceptionV3,Xception,DenseNet121,and a customCNNmodel.To show the performance of the KurdSet dataset,we compared it to Arabic handwritten character recognition dataset(AHCD).We applied the models to both datasets to show the performance of our dataset.Additionally,the performance of the models is evaluated using test accuracy,which measures the percentage of correctly classified characters in the evaluation phase.All models performed well in the training phase,DenseNet121 exhibited the highest accuracy among the models,achieving a high accuracy of 99.80%on the Kurdish dataset.And Xception model achieved 98.66%using the Arabic dataset.
基金funded by the Henan Provincial Science and Technology Research Project(222102210086)the Starry Sky Creative Space Innovation Space Innovation Incubation Project of Zhengzhou University of Light Industry(2023ZCKJ211).
文摘This study proposes a pose estimation-convolutional neural network-bidirectional gated recurrent unit(PSECNN-BiGRU)fusion model for human posture recognition to address low accuracy issues in abnormal posture recognition due to the loss of some feature information and the deterioration of comprehensive performance in model detection in complex home environments.Firstly,the deep convolutional network is integrated with the Mediapipe framework to extract high-precision,multi-dimensional information from the key points of the human skeleton,thereby obtaining a human posture feature set.Thereafter,a double-layer BiGRU algorithm is utilized to extract multi-layer,bidirectional temporal features from the human posture feature set,and a CNN network with an exponential linear unit(ELU)activation function is adopted to perform deep convolution of the feature map to extract the spatial feature of the human posture.Furthermore,a squeeze and excitation networks(SENet)module is introduced to adaptively learn the importance weights of each channel,enhancing the network’s focus on important features.Finally,comparative experiments are performed on available datasets,including the public human activity recognition using smartphone dataset(UCIHAR),the public human activity recognition 70 plus dataset(HAR70PLUS),and the independently developed home abnormal behavior recognition dataset(HABRD)created by the authors’team.The results show that the average accuracy of the proposed PSE-CNN-BiGRU fusion model for human posture recognition is 99.56%,89.42%,and 98.90%,respectively,which are 5.24%,5.83%,and 3.19%higher than the average accuracy of the five models proposed in the comparative literature,including CNN,GRU,and others.The F1-score for abnormal posture recognition reaches 98.84%(heartache),97.18%(fall),99.6%(bellyache),and 98.27%(climbing)on the self-builtHABRDdataset,thus verifying the effectiveness,generalization,and robustness of the proposed model in enhancing human posture recognition.
基金the Strategic Priority Research Program of Chinese Academy of Sciences(Grant No.XDC02040300)for this study.
文摘RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy protection.Existing RFID-based HAR methods use modeling,CNN,or LSTM to extract features effectively.Still,they have shortcomings:1)requiring complex hand-crafted data cleaning processes and 2)only addressing single-person activity recognition based on specific RF signals.To solve these problems,this paper proposes a novel device-free method based on Time-streaming Multiscale Transformer called TransTM.This model leverages the Transformer's powerful data fitting capabilities to take raw RFID RSSI data as input without pre-processing.Concretely,we propose a multiscale convolutional hybrid Transformer to capture behavioral features that recognizes singlehuman activities and human-to-human interactions.Compared with existing CNN-and LSTM-based methods,the Transformer-based method has more data fitting power,generalization,and scalability.Furthermore,using RF signals,our method achieves an excellent classification effect on human behaviorbased classification tasks.Experimental results on the actual RFID datasets show that this model achieves a high average recognition accuracy(99.1%).The dataset we collected for detecting RFID-based indoor human activities will be published.