Transformer-based models have facilitated significant advances in object detection.However,their extensive computational consumption and suboptimal detection of dense small objects curtail their applicability in unman...Transformer-based models have facilitated significant advances in object detection.However,their extensive computational consumption and suboptimal detection of dense small objects curtail their applicability in unmanned aerial vehicle(UAV)imagery.Addressing these limitations,we propose a hybrid transformer-based detector,H-DETR,and enhance it for dense small objects,leading to an accurate and efficient model.Firstly,we introduce a hybrid transformer encoder,which integrates a convolutional neural network-based cross-scale fusion module with the original encoder to handle multi-scale feature sequences more efficiently.Furthermore,we propose two novel strategies to enhance detection performance without incurring additional inference computation.Query filter is designed to cope with the dense clustering inherent in drone-captured images by counteracting similar queries with a training-aware non-maximum suppression.Adversarial denoising learning is a novel enhancement method inspired by adversarial learning,which improves the detection of numerous small targets by counteracting the effects of artificial spatial and semantic noise.Extensive experiments on the VisDrone and UAVDT datasets substantiate the effectiveness of our approach,achieving a significant improvement in accuracy with a reduction in computational complexity.Our method achieves 31.9%and 21.1%AP on the VisDrone and UAVDT datasets,respectively,and has a faster inference speed,making it a competitive model in UAV image object detection.展开更多
Object detection in unmanned aerial vehicle(UAV)aerial images has become increasingly important in military and civil applications.General object detection models are not robust enough against interclass similarity an...Object detection in unmanned aerial vehicle(UAV)aerial images has become increasingly important in military and civil applications.General object detection models are not robust enough against interclass similarity and intraclass variability of small objects,and UAV-specific nuisances such as uncontrolledweather conditions.Unlike previous approaches focusing on high-level semantic information,we report the importance of underlying features to improve detection accuracy and robustness fromthe information-theoretic perspective.Specifically,we propose a robust and discriminative feature learning approach through mutual information maximization(RD-MIM),which can be integrated into numerous object detection methods for aerial images.Firstly,we present the rank sample mining method to reduce underlying feature differences between the natural image domain and the aerial image domain.Then,we design a momentum contrast learning strategy to make object features similar to the same category and dissimilar to different categories.Finally,we construct a transformer-based global attention mechanism to boost object location semantics by leveraging the high interrelation of different receptive fields.We conduct extensive experiments on the VisDrone and Unmanned Aerial Vehicle Benchmark Object Detection and Tracking(UAVDT)datasets to prove the effectiveness of the proposed method.The experimental results show that our approach brings considerable robustness gains to basic detectors and advanced detection methods,achieving relative growth rates of 51.0%and 39.4%in corruption robustness,respectively.Our code is available at https://github.com/cq100/RD-MIM(accessed on 2 August 2024).展开更多
In clinical practice,the microscopic examination of urine sediment is considered an important in vitro examination with many broad applications.Measuring the amount of each type of urine sediment allows for screening,...In clinical practice,the microscopic examination of urine sediment is considered an important in vitro examination with many broad applications.Measuring the amount of each type of urine sediment allows for screening,diagnosis and evaluation of kidney and urinary tract disease,providing insight into the specific type and severity.However,manual urine sediment examination is labor-intensive,time-consuming,and subjective.Traditional machine learning based object detection methods require hand-crafted features for localization and classification,which have poor generalization capabilities and are difficult to quickly and accurately detect the number of urine sediments.Deep learning based object detection methods have the potential to address the challenges mentioned above,but these methods require access to large urine sediment image datasets.Unfortunately,only a limited number of publicly available urine sediment datasets are currently available.To alleviate the lack of urine sediment datasets in medical image analysis,we propose a new dataset named UriSed2K,which contains 2465 high-quality images annotated with expert guidance.Two main challenges are associated with our dataset:a large number of small objects and the occlusion between these small objects.Our manuscript focuses on applying deep learning object detection methods to the urine sediment dataset and addressing the challenges presented by this dataset.Specifically,our goal is to improve the accuracy and efficiency of the detection algorithm and,in doing so,provide medical professionals with an automatic detector that saves time and effort.We propose an improved lightweight one-stage object detection algorithm called Discriminatory-YOLO.The proposed algorithm comprises a local context attention module and a global background suppression module,which aid the detector in distinguishing urine sediment features in the image.The local context attention module captures context information beyond the object region,while the global background suppression module emphasizes objects in uninformative backgrounds.We comprehensively evaluate our method on the UriSed2K dataset,which includes seven categories of urine sediments,such as erythrocytes(red blood cells),leukocytes(white blood cells),epithelial cells,crystals,mycetes,broken erythrocytes,and broken leukocytes,achieving the best average precision(AP)of 95.3%while taking only 10 ms per image.The source code and dataset are available at https://github.com/binghuiwu98/discriminatoryyolov5.展开更多
Multi-label image classification is recognized as an important task within the field of computer vision,a discipline that has experienced a significant escalation in research endeavors in recent years.The widespread a...Multi-label image classification is recognized as an important task within the field of computer vision,a discipline that has experienced a significant escalation in research endeavors in recent years.The widespread adoption of convolutional neural networks(CNNs)has catalyzed the remarkable success of architectures such as ResNet-101 within the domain of image classification.However,inmulti-label image classification tasks,it is crucial to consider the correlation between labels.In order to improve the accuracy and performance of multi-label classification and fully combine visual and semantic features,many existing studies use graph convolutional networks(GCN)for modeling.Object detection and multi-label image classification exhibit a degree of conceptual overlap;however,the integration of these two tasks within a unified framework has been relatively underexplored in the existing literature.In this paper,we come up with Object-GCN framework,a model combining object detection network YOLOv5 and graph convolutional network,and we carry out a thorough experimental analysis using a range of well-established public datasets.The designed framework Object-GCN achieves significantly better performance than existing studies in public datasets COCO2014,VOC2007,VOC2012.The final results achieved are 86.9%,96.7%,and 96.3%mean Average Precision(mAP)across the three datasets.展开更多
In the study of oriented bounding boxes(OBB)object detection in high-resolution remote sensing images,the problem of missed and wrong detection of small targets occurs because the targets are too small and have differ...In the study of oriented bounding boxes(OBB)object detection in high-resolution remote sensing images,the problem of missed and wrong detection of small targets occurs because the targets are too small and have different orientations.Existing OBB object detection for remote sensing images,although making good progress,mainly focuses on directional modeling,while less consideration is given to the size of the object as well as the problem of missed detection.In this study,a method based on improved YOLOv8 was proposed for detecting oriented objects in remote sensing images,which can improve the detection precision of oriented objects in remote sensing images.Firstly,the ResCBAMG module was innovatively designed,which could better extract channel and spatial correlation information.Secondly,the innovative top-down feature fusion layer network structure was proposed in conjunction with the Efficient Channel Attention(ECA)attention module,which helped to capture inter-local cross-channel interaction information appropriately.Finally,we introduced an innovative ResCBAMG module between the different C2f modules and detection heads of the bottom-up feature fusion layer.This innovative structure helped the model to better focus on the target area.The precision and robustness of oriented target detection were also improved.Experimental results on the DOTA-v1.5 dataset showed that the detection Precision,mAP@0.5,and mAP@0.5:0.95 metrics of the improved model are better compared to the original model.This improvement is effective in detecting small targets and complex scenes.展开更多
Real-time detection for object size has now become a hot topic in the testing field and image processing is the core algorithm. This paper focuses on the processing and display of the collected dynamic images to achie...Real-time detection for object size has now become a hot topic in the testing field and image processing is the core algorithm. This paper focuses on the processing and display of the collected dynamic images to achieve a real-time image pro- cessing for the moving objects. Firstly, the median filtering, gain calibration, image segmentation, image binarization, cor- ner detection and edge fitting are employed to process the images of the moving objects to make the image close to the real object. Then, the processed images are simultaneously displayed on a real-time basis to make it easier to analyze, understand and identify them, and thus it reduces the computation complexity. Finally, human-computer interaction (HCI)-friendly in- terface based on VC ++ is designed to accomplish the digital logic transform, image processing and real-time display of the objects. The experiment shows that the proposed algorithm and software design have better real-time performance and accu- racy which can meet the industrial needs.展开更多
Automatically detecting and locating remote occlusion small objects from the images of complex traffic environments is a valuable and challenging research.Since the boundary box location is not sufficiently accurate a...Automatically detecting and locating remote occlusion small objects from the images of complex traffic environments is a valuable and challenging research.Since the boundary box location is not sufficiently accurate and it is difficult to distinguish overlapping and occluded objects,the authors propose a network model with a second-order term attention mechanism and occlusion loss.First,the backbone network is built on CSPDarkNet53.Then a method is designed for the feature extraction network based on an item-wise attention mechanism,which uses the filtered weighted feature vector to replace the original residual fusion and adds a second-order term to reduce the information loss in the process of fusion and accelerate the convergence of the model.Finally,an objected occlusion regression loss function is studied to reduce the problems of missed detections caused by dense objects.Sufficient experimental results demonstrate that the authors’method achieved state-of-the-art performance without reducing the detection speed.The mAP@.5 of the method is 85.8%on the Foggy_cityscapes dataset and the mAP@.5 of the method is 97.8%on the KITTI dataset.展开更多
Large structures,such as bridges,highways,etc.,need to be inspected to evaluate their actual physical and functional condition,to predict future conditions,and to help decision makers allocating maintenance and rehabi...Large structures,such as bridges,highways,etc.,need to be inspected to evaluate their actual physical and functional condition,to predict future conditions,and to help decision makers allocating maintenance and rehabilitation resources.The assessment of civil infrastructure condition is carried out through information obtained by inspection and/or monitoring operations.Traditional techniques in structural health monitoring(SHM)involve visual inspection related to inspection standards that can be time-consuming data collection,expensive,labor intensive,and dangerous.To address these limitations,machine vision-based inspection procedures have increasingly been investigated within the research community.In this context,this paper proposes and compares four different computer vision procedures to identify damage by image processing:Otsu method thresholding,Markov random fields segmentation,RGB color detection technique,and K-means clustering algorithm.The first method is based on segmentation by thresholding that returns a binary image from a grayscale image.The Markov random fields technique uses a probabilistic approach to assign labels to model the spatial dependencies in image pixels.The RGB technique uses color detection to evaluate the defect extensions.Finally,K-means algorithm is based on Euclidean distance for clustering of the images.The benefits and limitations of each technique are discussed,and the challenges of using the techniques are highlighted.To show the effectiveness of the described techniques in damage detection of civil infrastructures,a case study is presented.Results show that various types of corrosion and cracks can be detected by image processing techniques making the proposed techniques a suitable tool for the prediction of the damage evolution in civil infrastructures.展开更多
Currently,worldwide industries and communities are concerned with building,expanding,and exploring the assets and resources found in the oceans and seas.More precisely,to analyze a stock,archaeology,and surveillance,s...Currently,worldwide industries and communities are concerned with building,expanding,and exploring the assets and resources found in the oceans and seas.More precisely,to analyze a stock,archaeology,and surveillance,sev-eral cameras are installed underseas to collect videos.However,on the other hand,these large size videos require a lot of time and memory for their processing to extract relevant information.Hence,to automate this manual procedure of video assessment,an accurate and efficient automated system is a greater necessity.From this perspective,we intend to present a complete framework solution for the task of video summarization and object detection in underwater videos.We employed a perceived motion energy(PME)method tofirst extract the keyframes followed by an object detection model approach namely YoloV3 to perform object detection in underwater videos.The issues of blurriness and low contrast in underwater images are also taken into account in the presented approach by applying the image enhancement method.Furthermore,the suggested framework of underwater video summarization and object detection has been evaluated on a publicly available brackish dataset.It is observed that the proposed framework shows good performance and hence ultimately assists several marine researchers or scientists related to thefield of underwater archaeology,stock assessment,and surveillance.展开更多
Cone photoreceptor cell identication is important for the early diagnosis of retinopathy.In this study,an object detection algorithm is used for cone cell identication in confocal adaptive optics scanning laser ophtha...Cone photoreceptor cell identication is important for the early diagnosis of retinopathy.In this study,an object detection algorithm is used for cone cell identication in confocal adaptive optics scanning laser ophthalmoscope(AOSLO)images.An effectiveness evaluation of identication using the proposed method reveals precision,recall,and F_(1)-score of 95.8%,96.5%,and 96.1%,respectively,considering manual identication as the ground truth.Various object detection and identication results from images with different cone photoreceptor cell distributions further demonstrate the performance of the proposed method.Overall,the proposed method can accurately identify cone photoreceptor cells on confocal adaptive optics scanning laser ophthalmoscope images,being comparable to manual identication.展开更多
Object detection plays a vital role in the video surveillance systems.To enhance security,surveillance cameras are now installed in public areas such as traffic signals,roadways,retail malls,train stations,and banks.Ho...Object detection plays a vital role in the video surveillance systems.To enhance security,surveillance cameras are now installed in public areas such as traffic signals,roadways,retail malls,train stations,and banks.However,monitor-ing the video continually at a quicker pace is a challenging job.As a consequence,security cameras are useless and need human monitoring.The primary difficulty with video surveillance is identifying abnormalities such as thefts,accidents,crimes,or other unlawful actions.The anomalous action does not occur at a high-er rate than usual occurrences.To detect the object in a video,first we analyze the images pixel by pixel.In digital image processing,segmentation is the process of segregating the individual image parts into pixels.The performance of segmenta-tion is affected by irregular illumination and/or low illumination.These factors highly affect the real-time object detection process in the video surveillance sys-tem.In this paper,a modified ResNet model(M-Resnet)is proposed to enhance the image which is affected by insufficient light.Experimental results provide the comparison of existing method output and modification architecture of the ResNet model shows the considerable amount improvement in detection objects in the video stream.The proposed model shows better results in the metrics like preci-sion,recall,pixel accuracy,etc.,andfinds a reasonable improvement in the object detection.展开更多
Observing and analyzing surface images is critical for studying the interaction between plasma and irradiated plasma-facing materials.This paper presents a method for the automatic recognition of bubbles in transmissi...Observing and analyzing surface images is critical for studying the interaction between plasma and irradiated plasma-facing materials.This paper presents a method for the automatic recognition of bubbles in transmission electron microscope(TEM)images of W nanofibers using image processing techniques and convolutional neural network(CNN).We employ a three-stage approach consisting of Otsu,local-threshold,and watershed segmentation to extract bubbles from noisy images.To address over-segmentation,we propose a combination of area factor and radial pixel intensity scanning.A CNN is used to recognize bubbles,outperforming traditional neural network models such as Alex Net and Google Net with an accuracy of 97.1%and recall of 98.6%.Our method is tested on both clear and blurred TEM images,and demonstrates humanlike performance in recognizing bubbles.This work contributes to the development of quantitative image analysis in the field of plasma-material interactions,offering a scalable solution for analyzing material defects.Overall,this study's findings establish the potential for automatic defect recognition and its applications in the assessment of plasma-material interactions.This method can be employed in a variety of specialties,including plasma physics and materials science.展开更多
At present days,object detection and tracking concepts have gained more importance among researchers and business people.Presently,deep learning(DL)approaches have been used for object tracking as it increases the per...At present days,object detection and tracking concepts have gained more importance among researchers and business people.Presently,deep learning(DL)approaches have been used for object tracking as it increases the perfor-mance and speed of the tracking process.This paper presents a novel robust DL based object detection and tracking algorithm using Automated Image Anno-tation with ResNet based Faster regional convolutional neural network(R-CNN)named(AIA-FRCNN)model.The AIA-RFRCNN method performs image anno-tation using a Discriminative Correlation Filter(DCF)with Channel and Spatial Reliability tracker(CSR)called DCF-CSRT model.The AIA-RFRCNN model makes use of Faster RCNN as an object detector and tracker,which involves region proposal network(RPN)and Fast R-CNN.The RPN is a full convolution network that concurrently predicts the bounding box and score of different objects.The RPN is a trained model used for the generation of the high-quality region proposals,which are utilized by Fast R-CNN for detection process.Besides,Residual Network(ResNet 101)model is used as a shared convolutional neural network(CNN)for the generation of feature maps.The performance of the ResNet 101 model is further improved by the use of Adam optimizer,which tunes the hyperparameters namely learning rate,batch size,momentum,and weight decay.Finally,softmax layer is applied to classify the images.The performance of the AIA-RFRCNN method has been assessed using a benchmark dataset and a detailed comparative analysis of the results takes place.The outcome of the experiments indicated the superior characteristics of the AIA-RFRCNN model under diverse aspects.展开更多
In image processing, one of the most important steps is image segmentation. The objects in remote sensing images often have to be detected in order toperform next steps in image processing. Remote sensing images usua...In image processing, one of the most important steps is image segmentation. The objects in remote sensing images often have to be detected in order toperform next steps in image processing. Remote sensing images usually havelarge size and various spatial resolutions. Thus, detecting objects in remote sensing images is very complicated. In this paper, we develop a model to detectobjects in remote sensing images based on the combination of picture fuzzy clustering and MapReduce method (denoted as MPFC). Firstly, picture fuzzy clustering is applied to segment the input images. Then, MapReduce is used to reducethe runtime with the guarantee of quality. To convert data for MapReduce processing, two new procedures are introduced, including Map_PFC and Reduce_PFC.The formal representation and details of two these procedures are presented in thispaper. The experiments on satellite image and remote sensing image datasets aregiven to evaluate proposed model. Validity indices and time consuming are usedto compare proposed model to picture fuzzy clustering model. The values ofvalidity indices show that picture fuzzy clustering integrated to MapReduce getsbetter quality of segmentation than using picture fuzzy clustering only. Moreover,on two selected image datasets, the run time of MPFC model is much less thanthat of picture fuzzy clustering.展开更多
It is known that detecting small moving objects in as- tronomical image sequences is a significant research problem in space surveillance. The new theory, compressive sensing, pro- vides a very easy and computationall...It is known that detecting small moving objects in as- tronomical image sequences is a significant research problem in space surveillance. The new theory, compressive sensing, pro- vides a very easy and computationally cheap coding scheme for onboard astronomical remote sensing. An algorithm for small moving space object detection and localization is proposed. The algorithm determines the measurements of objects by comparing the difference between the measurements of the current image and the measurements of the background scene. In contrast to reconstruct the whole image, only a foreground image is recon- structed, which will lead to an effective computational performance, and a high level of localization accuracy is achieved. Experiments and analysis are provided to show the performance of the pro- posed approach on detection and localization.展开更多
Aerial image sequence mosaicking is one of the chal-lenging research fields in computer vision.To obtain large-scale orthophoto maps with object detection information,we propose a vision-based image mosaicking algorit...Aerial image sequence mosaicking is one of the chal-lenging research fields in computer vision.To obtain large-scale orthophoto maps with object detection information,we propose a vision-based image mosaicking algorithm without any extra location data.According to object detection results,we define a complexity factor to describe the importance of each input ima-ge and dynamically optimize the feature extraction process.The feature points extraction and matching processes are mainly guided by the speeded-up robust features(SURF)and the grid motion statistic(GMS)algorithm respectively.A robust refer-ence frame selection method is proposed to eliminate the trans-formation distortion by searching for the center area based on overlaps.Besides,the sparse Levenberg-Marquardt(LM)al-gorithm and the heavy occluded frames removal method are ap-plied to reduce accumulated errors and further improve the mo-saicking performance.The proposed algorithm is performed by using multithreading and graphics processing unit(GPU)accel-eration on several aerial image datasets.Extensive experiment results demonstrate that our algorithm outperforms most of the existing aerial image mosaicking methods in visual quality while guaranteeing a high calculation speed.展开更多
Earth surveillance through aerial images allows more accurate identification and characterization of objects present on the surface from space and airborne platforms.The progression of deep learning and computer visio...Earth surveillance through aerial images allows more accurate identification and characterization of objects present on the surface from space and airborne platforms.The progression of deep learning and computer vision methods and the availability of heterogeneous multispectral remote sensing data make the field more fertile for research.With the evolution of optical sensors,aerial images are becoming more precise and larger,which leads to a new kind of problem for object detection algorithms.This paper proposes the“Sliding Region-based Convolutional Neural Network(SRCNN),”which is an extension of the Faster Region-based Convolutional Neural Network(RCNN)object detection framework to make it independent of the image’s spatial resolution and size.The sliding box strategy is used in the proposed model to segment the image while detecting.The proposed framework outperforms the state-of-the-art Faster RCNN model while processing images with significantly different spatial resolution values.The SRCNN is also capable of detecting objects in images of any size.展开更多
A survey of the population densities of rice planthoppers is important for forecasting decisions and efficient control. Tra- ditional manual surveying of rice planthoppers is time-consuming, fatiguing, and subjective....A survey of the population densities of rice planthoppers is important for forecasting decisions and efficient control. Tra- ditional manual surveying of rice planthoppers is time-consuming, fatiguing, and subjective. A new three-layer detection method was proposed to detect and identify white-backed planthoppers (WBPHs, Sogatella furcifera (Horvath)) and their developmental stages using image processing. In the first two detection layers, we used an AdaBoost classifier that was trained on a histogram of oriented gradient (HOG) features and a support vector machine (SVM) classifier that was trained on Gabor and Local Binary Pattern (LBP) features to detect WBPHs and remove impurities. We achieved a detection rate of 85.6% and a false detection rate of 10.2%. In the third detection layer, a SVM classifier that was trained on the HOG features was used to identify the different developmental stages of the WBPHs, and we achieved an identification rate of 73.1%, a false identification rate of 23.3%, and a 5.6% false detection rate for the images without WBPHs. The proposed three-layer detection method is feasible and effective for the identification of different developmental stages of planthoppers on rice plants in paddy fields.展开更多
The conventional methods of edge detection can roughly delineate edge position of geological bodies,but there are still some problems such as low detection accuracy and being susceptible to noise interference.In this ...The conventional methods of edge detection can roughly delineate edge position of geological bodies,but there are still some problems such as low detection accuracy and being susceptible to noise interference.In this paper,three image processing methods,Canny,Lo G and Sobel operators are briefly introduced,and applied to edge detection to determine the edge of geological bodies.Furthermore,model data is built to analyze the edge detection ability of this image processing methods,and compare with conventional methods.Combined with gravity anomaly of Sichuan basin and magnetic anomaly of Zhurihe area,the detection effect of image processing methods is further verified in real data.The results show that image processing methods can be applied to effectively identify the edge of geological bodies.Moreover,when both positive and negative anomalies exist and noise is abundant,fake edge can be avoided and edge division is clearer,and satisfactory results of edge detection are obtained.展开更多
As a commonly used non-contact flatness detection method, laser triangular detection method is designed with low cost, but it cannot avoid measurement errors caused by strip steel vibration effectively. This paper put...As a commonly used non-contact flatness detection method, laser triangular detection method is designed with low cost, but it cannot avoid measurement errors caused by strip steel vibration effectively. This paper puts forward a dynamic flatness image processing method based on improved laser triangular detection method. According to the practical application of strip steel straightening, it completes the image pre-processing, image feature curve extraction and calculation of flatness elongation using digital image processing technology. Finally it eliminates elongation measurement errors caused by the vibration.展开更多
基金This research was funded by the Natural Science Foundation of Hebei Province(F2021506004).
文摘Transformer-based models have facilitated significant advances in object detection.However,their extensive computational consumption and suboptimal detection of dense small objects curtail their applicability in unmanned aerial vehicle(UAV)imagery.Addressing these limitations,we propose a hybrid transformer-based detector,H-DETR,and enhance it for dense small objects,leading to an accurate and efficient model.Firstly,we introduce a hybrid transformer encoder,which integrates a convolutional neural network-based cross-scale fusion module with the original encoder to handle multi-scale feature sequences more efficiently.Furthermore,we propose two novel strategies to enhance detection performance without incurring additional inference computation.Query filter is designed to cope with the dense clustering inherent in drone-captured images by counteracting similar queries with a training-aware non-maximum suppression.Adversarial denoising learning is a novel enhancement method inspired by adversarial learning,which improves the detection of numerous small targets by counteracting the effects of artificial spatial and semantic noise.Extensive experiments on the VisDrone and UAVDT datasets substantiate the effectiveness of our approach,achieving a significant improvement in accuracy with a reduction in computational complexity.Our method achieves 31.9%and 21.1%AP on the VisDrone and UAVDT datasets,respectively,and has a faster inference speed,making it a competitive model in UAV image object detection.
基金supported by the National Natural Science Foundation of China under Grant 61671219.
文摘Object detection in unmanned aerial vehicle(UAV)aerial images has become increasingly important in military and civil applications.General object detection models are not robust enough against interclass similarity and intraclass variability of small objects,and UAV-specific nuisances such as uncontrolledweather conditions.Unlike previous approaches focusing on high-level semantic information,we report the importance of underlying features to improve detection accuracy and robustness fromthe information-theoretic perspective.Specifically,we propose a robust and discriminative feature learning approach through mutual information maximization(RD-MIM),which can be integrated into numerous object detection methods for aerial images.Firstly,we present the rank sample mining method to reduce underlying feature differences between the natural image domain and the aerial image domain.Then,we design a momentum contrast learning strategy to make object features similar to the same category and dissimilar to different categories.Finally,we construct a transformer-based global attention mechanism to boost object location semantics by leveraging the high interrelation of different receptive fields.We conduct extensive experiments on the VisDrone and Unmanned Aerial Vehicle Benchmark Object Detection and Tracking(UAVDT)datasets to prove the effectiveness of the proposed method.The experimental results show that our approach brings considerable robustness gains to basic detectors and advanced detection methods,achieving relative growth rates of 51.0%and 39.4%in corruption robustness,respectively.Our code is available at https://github.com/cq100/RD-MIM(accessed on 2 August 2024).
基金This work was partially supported by the National Natural Science Foundation of China(Grant Nos.61906168,U20A20171)Zhejiang Provincial Natural Science Foundation of China(Grant Nos.LY23F020023,LY21F020027)Construction of Hubei Provincial Key Laboratory for Intelligent Visual Monitoring of Hydropower Projects(Grant Nos.2022SDSJ01).
文摘In clinical practice,the microscopic examination of urine sediment is considered an important in vitro examination with many broad applications.Measuring the amount of each type of urine sediment allows for screening,diagnosis and evaluation of kidney and urinary tract disease,providing insight into the specific type and severity.However,manual urine sediment examination is labor-intensive,time-consuming,and subjective.Traditional machine learning based object detection methods require hand-crafted features for localization and classification,which have poor generalization capabilities and are difficult to quickly and accurately detect the number of urine sediments.Deep learning based object detection methods have the potential to address the challenges mentioned above,but these methods require access to large urine sediment image datasets.Unfortunately,only a limited number of publicly available urine sediment datasets are currently available.To alleviate the lack of urine sediment datasets in medical image analysis,we propose a new dataset named UriSed2K,which contains 2465 high-quality images annotated with expert guidance.Two main challenges are associated with our dataset:a large number of small objects and the occlusion between these small objects.Our manuscript focuses on applying deep learning object detection methods to the urine sediment dataset and addressing the challenges presented by this dataset.Specifically,our goal is to improve the accuracy and efficiency of the detection algorithm and,in doing so,provide medical professionals with an automatic detector that saves time and effort.We propose an improved lightweight one-stage object detection algorithm called Discriminatory-YOLO.The proposed algorithm comprises a local context attention module and a global background suppression module,which aid the detector in distinguishing urine sediment features in the image.The local context attention module captures context information beyond the object region,while the global background suppression module emphasizes objects in uninformative backgrounds.We comprehensively evaluate our method on the UriSed2K dataset,which includes seven categories of urine sediments,such as erythrocytes(red blood cells),leukocytes(white blood cells),epithelial cells,crystals,mycetes,broken erythrocytes,and broken leukocytes,achieving the best average precision(AP)of 95.3%while taking only 10 ms per image.The source code and dataset are available at https://github.com/binghuiwu98/discriminatoryyolov5.
文摘Multi-label image classification is recognized as an important task within the field of computer vision,a discipline that has experienced a significant escalation in research endeavors in recent years.The widespread adoption of convolutional neural networks(CNNs)has catalyzed the remarkable success of architectures such as ResNet-101 within the domain of image classification.However,inmulti-label image classification tasks,it is crucial to consider the correlation between labels.In order to improve the accuracy and performance of multi-label classification and fully combine visual and semantic features,many existing studies use graph convolutional networks(GCN)for modeling.Object detection and multi-label image classification exhibit a degree of conceptual overlap;however,the integration of these two tasks within a unified framework has been relatively underexplored in the existing literature.In this paper,we come up with Object-GCN framework,a model combining object detection network YOLOv5 and graph convolutional network,and we carry out a thorough experimental analysis using a range of well-established public datasets.The designed framework Object-GCN achieves significantly better performance than existing studies in public datasets COCO2014,VOC2007,VOC2012.The final results achieved are 86.9%,96.7%,and 96.3%mean Average Precision(mAP)across the three datasets.
文摘In the study of oriented bounding boxes(OBB)object detection in high-resolution remote sensing images,the problem of missed and wrong detection of small targets occurs because the targets are too small and have different orientations.Existing OBB object detection for remote sensing images,although making good progress,mainly focuses on directional modeling,while less consideration is given to the size of the object as well as the problem of missed detection.In this study,a method based on improved YOLOv8 was proposed for detecting oriented objects in remote sensing images,which can improve the detection precision of oriented objects in remote sensing images.Firstly,the ResCBAMG module was innovatively designed,which could better extract channel and spatial correlation information.Secondly,the innovative top-down feature fusion layer network structure was proposed in conjunction with the Efficient Channel Attention(ECA)attention module,which helped to capture inter-local cross-channel interaction information appropriately.Finally,we introduced an innovative ResCBAMG module between the different C2f modules and detection heads of the bottom-up feature fusion layer.This innovative structure helped the model to better focus on the target area.The precision and robustness of oriented target detection were also improved.Experimental results on the DOTA-v1.5 dataset showed that the detection Precision,mAP@0.5,and mAP@0.5:0.95 metrics of the improved model are better compared to the original model.This improvement is effective in detecting small targets and complex scenes.
基金National Natural Science Foundation of China(No.61302159,61227003,61301259)Natual Science Foundation of Shanxi Province(No.2012021011-2)+2 种基金Specialized Research Fund for the Doctoral Program of Higher Education,China(No.20121420110006)Top Science and Technology Innovation Teams of Higher Learning Institutions of Shanxi Province,ChinaProject Sponsored by Scientific Research for the Returned Overseas Chinese Scholars,Shanxi Province(No.2013-083)
文摘Real-time detection for object size has now become a hot topic in the testing field and image processing is the core algorithm. This paper focuses on the processing and display of the collected dynamic images to achieve a real-time image pro- cessing for the moving objects. Firstly, the median filtering, gain calibration, image segmentation, image binarization, cor- ner detection and edge fitting are employed to process the images of the moving objects to make the image close to the real object. Then, the processed images are simultaneously displayed on a real-time basis to make it easier to analyze, understand and identify them, and thus it reduces the computation complexity. Finally, human-computer interaction (HCI)-friendly in- terface based on VC ++ is designed to accomplish the digital logic transform, image processing and real-time display of the objects. The experiment shows that the proposed algorithm and software design have better real-time performance and accu- racy which can meet the industrial needs.
基金Doctoral Talent Training Project of Chongqing University of Posts and Telecommunications,Grant/Award Number:BYJS202007Natural Science Foundation of Chongqing,Grant/Award Number:cstc2021jcyj-msxmX0941+1 种基金National Natural Science Foundation of China,Grant/Award Number:62176034Scientific and Technological Research Program of Chongqing Municipal Education Commission,Grant/Award Number:KJQN202101901。
文摘Automatically detecting and locating remote occlusion small objects from the images of complex traffic environments is a valuable and challenging research.Since the boundary box location is not sufficiently accurate and it is difficult to distinguish overlapping and occluded objects,the authors propose a network model with a second-order term attention mechanism and occlusion loss.First,the backbone network is built on CSPDarkNet53.Then a method is designed for the feature extraction network based on an item-wise attention mechanism,which uses the filtered weighted feature vector to replace the original residual fusion and adds a second-order term to reduce the information loss in the process of fusion and accelerate the convergence of the model.Finally,an objected occlusion regression loss function is studied to reduce the problems of missed detections caused by dense objects.Sufficient experimental results demonstrate that the authors’method achieved state-of-the-art performance without reducing the detection speed.The mAP@.5 of the method is 85.8%on the Foggy_cityscapes dataset and the mAP@.5 of the method is 97.8%on the KITTI dataset.
基金Part of the research leading to these results has received funding from the research project DESDEMONA–Detection of Steel Defects by Enhanced MONitoring and Automated procedure for self-inspection and maintenance (grant agreement number RFCS-2018_800687) supported by EU Call RFCS-2017sponsored by the NATO Science for Peace and Security Programme under grant id. G5924。
文摘Large structures,such as bridges,highways,etc.,need to be inspected to evaluate their actual physical and functional condition,to predict future conditions,and to help decision makers allocating maintenance and rehabilitation resources.The assessment of civil infrastructure condition is carried out through information obtained by inspection and/or monitoring operations.Traditional techniques in structural health monitoring(SHM)involve visual inspection related to inspection standards that can be time-consuming data collection,expensive,labor intensive,and dangerous.To address these limitations,machine vision-based inspection procedures have increasingly been investigated within the research community.In this context,this paper proposes and compares four different computer vision procedures to identify damage by image processing:Otsu method thresholding,Markov random fields segmentation,RGB color detection technique,and K-means clustering algorithm.The first method is based on segmentation by thresholding that returns a binary image from a grayscale image.The Markov random fields technique uses a probabilistic approach to assign labels to model the spatial dependencies in image pixels.The RGB technique uses color detection to evaluate the defect extensions.Finally,K-means algorithm is based on Euclidean distance for clustering of the images.The benefits and limitations of each technique are discussed,and the challenges of using the techniques are highlighted.To show the effectiveness of the described techniques in damage detection of civil infrastructures,a case study is presented.Results show that various types of corrosion and cracks can be detected by image processing techniques making the proposed techniques a suitable tool for the prediction of the damage evolution in civil infrastructures.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.2020R1G1A1099559).
文摘Currently,worldwide industries and communities are concerned with building,expanding,and exploring the assets and resources found in the oceans and seas.More precisely,to analyze a stock,archaeology,and surveillance,sev-eral cameras are installed underseas to collect videos.However,on the other hand,these large size videos require a lot of time and memory for their processing to extract relevant information.Hence,to automate this manual procedure of video assessment,an accurate and efficient automated system is a greater necessity.From this perspective,we intend to present a complete framework solution for the task of video summarization and object detection in underwater videos.We employed a perceived motion energy(PME)method tofirst extract the keyframes followed by an object detection model approach namely YoloV3 to perform object detection in underwater videos.The issues of blurriness and low contrast in underwater images are also taken into account in the presented approach by applying the image enhancement method.Furthermore,the suggested framework of underwater video summarization and object detection has been evaluated on a publicly available brackish dataset.It is observed that the proposed framework shows good performance and hence ultimately assists several marine researchers or scientists related to thefield of underwater archaeology,stock assessment,and surveillance.
基金the Natural Science Foundation of Jiangsu Province(BK20200214)National Key R&D Program of China(2017YFB0403701)+5 种基金Jiangsu Province Key R&D Program(BE2019682 and BE2018667)National Natural Science Foundation of China(61605210,61675226,and 62075235)Youth Innovation Promotion Association of Chinese Academy of Sciences(2019320)Frontier Science Research Project of the Chinese Academy of Sciences(QYZDB-SSW-JSC03)Strategic Priority Research Program of the Chinese Academy of Sciences(XDB02060000)and Entrepreneurship and Innova-tion Talents in Jiangsu Province(Innovation of Scienti¯c Research Institutes).
文摘Cone photoreceptor cell identication is important for the early diagnosis of retinopathy.In this study,an object detection algorithm is used for cone cell identication in confocal adaptive optics scanning laser ophthalmoscope(AOSLO)images.An effectiveness evaluation of identication using the proposed method reveals precision,recall,and F_(1)-score of 95.8%,96.5%,and 96.1%,respectively,considering manual identication as the ground truth.Various object detection and identication results from images with different cone photoreceptor cell distributions further demonstrate the performance of the proposed method.Overall,the proposed method can accurately identify cone photoreceptor cells on confocal adaptive optics scanning laser ophthalmoscope images,being comparable to manual identication.
文摘Object detection plays a vital role in the video surveillance systems.To enhance security,surveillance cameras are now installed in public areas such as traffic signals,roadways,retail malls,train stations,and banks.However,monitor-ing the video continually at a quicker pace is a challenging job.As a consequence,security cameras are useless and need human monitoring.The primary difficulty with video surveillance is identifying abnormalities such as thefts,accidents,crimes,or other unlawful actions.The anomalous action does not occur at a high-er rate than usual occurrences.To detect the object in a video,first we analyze the images pixel by pixel.In digital image processing,segmentation is the process of segregating the individual image parts into pixels.The performance of segmenta-tion is affected by irregular illumination and/or low illumination.These factors highly affect the real-time object detection process in the video surveillance sys-tem.In this paper,a modified ResNet model(M-Resnet)is proposed to enhance the image which is affected by insufficient light.Experimental results provide the comparison of existing method output and modification architecture of the ResNet model shows the considerable amount improvement in detection objects in the video stream.The proposed model shows better results in the metrics like preci-sion,recall,pixel accuracy,etc.,andfinds a reasonable improvement in the object detection.
基金supported by the National Key R&D Program of China(No.2017YFE0300106)Dalian Science and Technology Star Project(No.2020RQ136)+1 种基金the Central Guidance on Local Science and Technology Development Fund of Liaoning Province(No.2022010055-JH6/100)the Fundamental Research Funds for the Central Universities(No.DUT21RC(3)066)。
文摘Observing and analyzing surface images is critical for studying the interaction between plasma and irradiated plasma-facing materials.This paper presents a method for the automatic recognition of bubbles in transmission electron microscope(TEM)images of W nanofibers using image processing techniques and convolutional neural network(CNN).We employ a three-stage approach consisting of Otsu,local-threshold,and watershed segmentation to extract bubbles from noisy images.To address over-segmentation,we propose a combination of area factor and radial pixel intensity scanning.A CNN is used to recognize bubbles,outperforming traditional neural network models such as Alex Net and Google Net with an accuracy of 97.1%and recall of 98.6%.Our method is tested on both clear and blurred TEM images,and demonstrates humanlike performance in recognizing bubbles.This work contributes to the development of quantitative image analysis in the field of plasma-material interactions,offering a scalable solution for analyzing material defects.Overall,this study's findings establish the potential for automatic defect recognition and its applications in the assessment of plasma-material interactions.This method can be employed in a variety of specialties,including plasma physics and materials science.
文摘At present days,object detection and tracking concepts have gained more importance among researchers and business people.Presently,deep learning(DL)approaches have been used for object tracking as it increases the perfor-mance and speed of the tracking process.This paper presents a novel robust DL based object detection and tracking algorithm using Automated Image Anno-tation with ResNet based Faster regional convolutional neural network(R-CNN)named(AIA-FRCNN)model.The AIA-RFRCNN method performs image anno-tation using a Discriminative Correlation Filter(DCF)with Channel and Spatial Reliability tracker(CSR)called DCF-CSRT model.The AIA-RFRCNN model makes use of Faster RCNN as an object detector and tracker,which involves region proposal network(RPN)and Fast R-CNN.The RPN is a full convolution network that concurrently predicts the bounding box and score of different objects.The RPN is a trained model used for the generation of the high-quality region proposals,which are utilized by Fast R-CNN for detection process.Besides,Residual Network(ResNet 101)model is used as a shared convolutional neural network(CNN)for the generation of feature maps.The performance of the ResNet 101 model is further improved by the use of Adam optimizer,which tunes the hyperparameters namely learning rate,batch size,momentum,and weight decay.Finally,softmax layer is applied to classify the images.The performance of the AIA-RFRCNN method has been assessed using a benchmark dataset and a detailed comparative analysis of the results takes place.The outcome of the experiments indicated the superior characteristics of the AIA-RFRCNN model under diverse aspects.
基金funded by Thuyloi University Foundation for Science and Technologyunder Grant Number TLU.STF.19-02.
文摘In image processing, one of the most important steps is image segmentation. The objects in remote sensing images often have to be detected in order toperform next steps in image processing. Remote sensing images usually havelarge size and various spatial resolutions. Thus, detecting objects in remote sensing images is very complicated. In this paper, we develop a model to detectobjects in remote sensing images based on the combination of picture fuzzy clustering and MapReduce method (denoted as MPFC). Firstly, picture fuzzy clustering is applied to segment the input images. Then, MapReduce is used to reducethe runtime with the guarantee of quality. To convert data for MapReduce processing, two new procedures are introduced, including Map_PFC and Reduce_PFC.The formal representation and details of two these procedures are presented in thispaper. The experiments on satellite image and remote sensing image datasets aregiven to evaluate proposed model. Validity indices and time consuming are usedto compare proposed model to picture fuzzy clustering model. The values ofvalidity indices show that picture fuzzy clustering integrated to MapReduce getsbetter quality of segmentation than using picture fuzzy clustering only. Moreover,on two selected image datasets, the run time of MPFC model is much less thanthat of picture fuzzy clustering.
基金supported by the National Natural Science Foundation of China (60903126)the China Postdoctoral Special Science Foundation (201003685)+1 种基金the China Postdoctoral Science Foundation (20090451397)the Northwestern Polytechnical University Foundation for Fundamental Research (JC201120)
文摘It is known that detecting small moving objects in as- tronomical image sequences is a significant research problem in space surveillance. The new theory, compressive sensing, pro- vides a very easy and computationally cheap coding scheme for onboard astronomical remote sensing. An algorithm for small moving space object detection and localization is proposed. The algorithm determines the measurements of objects by comparing the difference between the measurements of the current image and the measurements of the background scene. In contrast to reconstruct the whole image, only a foreground image is recon- structed, which will lead to an effective computational performance, and a high level of localization accuracy is achieved. Experiments and analysis are provided to show the performance of the pro- posed approach on detection and localization.
基金supported by the National Natural Science Foundation of China(6160304061973036).
文摘Aerial image sequence mosaicking is one of the chal-lenging research fields in computer vision.To obtain large-scale orthophoto maps with object detection information,we propose a vision-based image mosaicking algorithm without any extra location data.According to object detection results,we define a complexity factor to describe the importance of each input ima-ge and dynamically optimize the feature extraction process.The feature points extraction and matching processes are mainly guided by the speeded-up robust features(SURF)and the grid motion statistic(GMS)algorithm respectively.A robust refer-ence frame selection method is proposed to eliminate the trans-formation distortion by searching for the center area based on overlaps.Besides,the sparse Levenberg-Marquardt(LM)al-gorithm and the heavy occluded frames removal method are ap-plied to reduce accumulated errors and further improve the mo-saicking performance.The proposed algorithm is performed by using multithreading and graphics processing unit(GPU)accel-eration on several aerial image datasets.Extensive experiment results demonstrate that our algorithm outperforms most of the existing aerial image mosaicking methods in visual quality while guaranteeing a high calculation speed.
文摘Earth surveillance through aerial images allows more accurate identification and characterization of objects present on the surface from space and airborne platforms.The progression of deep learning and computer vision methods and the availability of heterogeneous multispectral remote sensing data make the field more fertile for research.With the evolution of optical sensors,aerial images are becoming more precise and larger,which leads to a new kind of problem for object detection algorithms.This paper proposes the“Sliding Region-based Convolutional Neural Network(SRCNN),”which is an extension of the Faster Region-based Convolutional Neural Network(RCNN)object detection framework to make it independent of the image’s spatial resolution and size.The sliding box strategy is used in the proposed model to segment the image while detecting.The proposed framework outperforms the state-of-the-art Faster RCNN model while processing images with significantly different spatial resolution values.The SRCNN is also capable of detecting objects in images of any size.
基金financially supported by the National High Technology Research and Development Program of China (863 Program, 2013AA102402)the 521 Talent Project of Zhejiang Sci-Tech University, Chinathe Key Research and Development Program of Zhejiang Province, China (2015C03023)
文摘A survey of the population densities of rice planthoppers is important for forecasting decisions and efficient control. Tra- ditional manual surveying of rice planthoppers is time-consuming, fatiguing, and subjective. A new three-layer detection method was proposed to detect and identify white-backed planthoppers (WBPHs, Sogatella furcifera (Horvath)) and their developmental stages using image processing. In the first two detection layers, we used an AdaBoost classifier that was trained on a histogram of oriented gradient (HOG) features and a support vector machine (SVM) classifier that was trained on Gabor and Local Binary Pattern (LBP) features to detect WBPHs and remove impurities. We achieved a detection rate of 85.6% and a false detection rate of 10.2%. In the third detection layer, a SVM classifier that was trained on the HOG features was used to identify the different developmental stages of the WBPHs, and we achieved an identification rate of 73.1%, a false identification rate of 23.3%, and a 5.6% false detection rate for the images without WBPHs. The proposed three-layer detection method is feasible and effective for the identification of different developmental stages of planthoppers on rice plants in paddy fields.
基金Supported by projects of the National Key Research and Development Plan(Nos.2017YFC0602203,2017YFC0601606)the National Science and Technology Major Project Task(No.2016ZX05027-002-003)+1 种基金the National Natural Science Foundation of China(Nos.41604089,41404089)the State Key Program of National Natural Science of China(No.41430322)
文摘The conventional methods of edge detection can roughly delineate edge position of geological bodies,but there are still some problems such as low detection accuracy and being susceptible to noise interference.In this paper,three image processing methods,Canny,Lo G and Sobel operators are briefly introduced,and applied to edge detection to determine the edge of geological bodies.Furthermore,model data is built to analyze the edge detection ability of this image processing methods,and compare with conventional methods.Combined with gravity anomaly of Sichuan basin and magnetic anomaly of Zhurihe area,the detection effect of image processing methods is further verified in real data.The results show that image processing methods can be applied to effectively identify the edge of geological bodies.Moreover,when both positive and negative anomalies exist and noise is abundant,fake edge can be avoided and edge division is clearer,and satisfactory results of edge detection are obtained.
文摘As a commonly used non-contact flatness detection method, laser triangular detection method is designed with low cost, but it cannot avoid measurement errors caused by strip steel vibration effectively. This paper puts forward a dynamic flatness image processing method based on improved laser triangular detection method. According to the practical application of strip steel straightening, it completes the image pre-processing, image feature curve extraction and calculation of flatness elongation using digital image processing technology. Finally it eliminates elongation measurement errors caused by the vibration.