Real-Time Detection and Instance Segmentation of Strawberry in Unstructured Environment

The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-ronment is a challenging task.Current instance segmentation algorithms for strawberries suffer from issues such as poor real-time performance and low accuracy.To this end,the present study proposes an Efficient YOLACT(E-YOLACT)algorithm for strawberry detection and segmentation based on the YOLACT framework.The key enhancements of the E-YOLACT encompass the development of a lightweight attention mechanism,pyramid squeeze shuffle attention(PSSA),for efficient feature extraction.Additionally,an attention-guided context-feature pyramid network(AC-FPN)is employed instead of FPN to optimize the architecture’s performance.Furthermore,a feature-enhanced model(FEM)is introduced to enhance the prediction head’s capabilities,while efficient fast non-maximum suppression(EF-NMS)is devised to improve non-maximum suppression.The experimental results demonstrate that the E-YOLACT achieves a Box-mAP and Mask-mAP of 77.9 and 76.6,respectively,on the custom dataset.Moreover,it exhibits an impressive category accuracy of 93.5%.Notably,the E-YOLACT also demonstrates a remarkable real-time detection capability with a speed of 34.8 FPS.The method proposed in this article presents an efficient approach for the vision system of a strawberry-picking robot.

Real-Time Object Detection and Face Recognition Application for the Visually Impaired

The advancement of navigation systems for the visually impaired has significantly enhanced their mobility by mitigating the risk of encountering obstacles and guiding them along safe,navigable routes.Traditional approaches primarily focus on broad applications such as wayfinding,obstacle detection,and fall prevention.However,there is a notable discrepancy in applying these technologies to more specific scenarios,like identifying distinct food crop types or recognizing faces.This study proposes a real-time application designed for visually impaired individuals,aiming to bridge this research-application gap.It introduces a system capable of detecting 20 different food crop types and recognizing faces with impressive accuracies of 83.27%and 95.64%,respectively.These results represent a significant contribution to the field of assistive technologies,providing visually impaired users with detailed and relevant information about their surroundings,thereby enhancing their mobility and ensuring their safety.Additionally,it addresses the vital aspects of social engagements,acknowledging the challenges faced by visually impaired individuals in recognizing acquaintances without auditory or tactile signals,and highlights recent developments in prototype systems aimed at assisting with face recognition tasks.This comprehensive approach not only promises enhanced navigational aids but also aims to enrich the social well-being and safety of visually impaired communities.

Analyzing the Impact of Scene Transitions on Indoor Camera Localization through Scene Change Detection in Real-Time

Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.

A YOLOv8-CE-based real-time traffic sign detection and identification method for autonomous vehicles

Traffic sign detection in real scenarios is challenging due to their complexity and small size,often preventing existing deep learning models from achieving both high accuracy and real-time performance.An improved YOLOv8 model for traffic sign detection is proposed.Firstly,by adding Coordinate Attention(CA)to the Backbone,the model gains location information,improving detection accuracy.Secondly,we also introduce EIoU to the localization function to address the ambiguity in aspect ratio descriptions by calculating the width-height difference based on CIoU.Additionally,Focal Loss is incorporated to balance sample difficulty,enhancing regression accuracy.Finally,the model,YOLOv8-CE(YOLOv8-Coordinate Attention-EIoU),is tested on the Jetson Nano,achieving real-time street scene detection and outperforming the Raspberry Pi 4B.Experimental results show that YOLOv8-CE excels in various complex scenarios,improving mAP by 2.8%over the original YOLOv8.The model size and computational effort remain similar,with the Jetson Nano achieving an inference time of 96 ms,significantly faster than the Raspberry Pi 4B.

A CNN-Based Single-Stage Occlusion Real-Time Target Detection Method

Aiming at the problem of low accuracy of traditional target detection methods for target detection in endoscopes in substation environments, a CNN-based real-time detection method for masked targets is proposed. The method adopts the overall design of backbone network, detection network and algorithmic parameter optimisation method, completes the model training on the self-constructed occlusion target dataset, and adopts the multi-scale perception method for target detection. The HNM algorithm is used to screen positive and negative samples during the training process, and the NMS algorithm is used to post-process the prediction results during the detection process to improve the detection efficiency. After experimental validation, the obtained model has the multi-class average predicted value (mAP) of the dataset. It has general advantages over traditional target detection methods. The detection time of a single target on FDDB dataset is 39 ms, which can meet the need of real-time target detection. In addition, the project team has successfully deployed the method into substations and put it into use in many places in Beijing, which is important for achieving the anomaly of occlusion target detection.

Customized Convolutional Neural Network for Accurate Detection of Deep Fake Images in Video Collections

The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their detection.The proposed Customized Convolutional Neural Network method involves extracting structured data from video frames using facial landmark detection,which is then used as input to the CNN.The customized Convolutional Neural Network method is the date augmented-based CNN model to generate‘fake data’or‘fake images’.This study was carried out using Python and its libraries.We used 242 films from the dataset gathered by the Deep Fake Detection Challenge,of which 199 were made up and the remaining 53 were real.Ten seconds were allotted for each video.There were 318 videos used in all,199 of which were fake and 119 of which were real.Our proposedmethod achieved a testing accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming two alternative approaches,CNN and MLP-CNN.Furthermore,our method succeeded in greater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,VGG-16,and DST-Net.The novelty of this investigation is the development of a new Convolutional Neural Network(CNN)learning model that can accurately detect deep fake face photos.

A Unified Model Fusing Region of Interest Detection and Super Resolution for Video Compression

High-resolution video transmission requires a substantial amount of bandwidth.In this paper,we present a novel video processing methodology that innovatively integrates region of interest(ROI)identification and super-resolution enhancement.Our method commences with the accurate detection of ROIs within video sequences,followed by the application of advanced super-resolution techniques to these areas,thereby preserving visual quality while economizing on data transmission.To validate and benchmark our approach,we have curated a new gaming dataset tailored to evaluate the effectiveness of ROI-based super-resolution in practical applications.The proposed model architecture leverages the transformer network framework,guided by a carefully designed multi-task loss function,which facilitates concurrent learning and execution of both ROI identification and resolution enhancement tasks.This unified deep learning model exhibits remarkable performance in achieving super-resolution on our custom dataset.The implications of this research extend to optimizing low-bitrate video streaming scenarios.By selectively enhancing the resolution of critical regions in videos,our solution enables high-quality video delivery under constrained bandwidth conditions.Empirical results demonstrate a 15%reduction in transmission bandwidth compared to traditional super-resolution based compression methods,without any perceivable decline in visual quality.This work thus contributes to the advancement of video compression and enhancement technologies,offering an effective strategy for improving digital media delivery efficiency and user experience,especially in bandwidth-limited environments.The innovative integration of ROI identification and super-resolution presents promising avenues for future research and development in adaptive and intelligent video communication systems.

Multi-Stream Temporally Enhanced Network for Video Salient Object Detection

Video salient object detection(VSOD)aims at locating the most attractive objects in a video by exploring the spatial and temporal features.VSOD poses a challenging task in computer vision,as it involves processing complex spatial data that is also influenced by temporal dynamics.Despite the progress made in existing VSOD models,they still struggle in scenes of great background diversity within and between frames.Additionally,they encounter difficulties related to accumulated noise and high time consumption during the extraction of temporal features over a long-term duration.We propose a multi-stream temporal enhanced network(MSTENet)to address these problems.It investigates saliency cues collaboration in the spatial domain with a multi-stream structure to deal with the great background diversity challenge.A straightforward,yet efficient approach for temporal feature extraction is developed to avoid the accumulative noises and reduce time consumption.The distinction between MSTENet and other VSOD methods stems from its incorporation of both foreground supervision and background supervision,facilitating enhanced extraction of collaborative saliency cues.Another notable differentiation is the innovative integration of spatial and temporal features,wherein the temporal module is integrated into the multi-stream structure,enabling comprehensive spatial-temporal interactions within an end-to-end framework.Extensive experimental results demonstrate that the proposed method achieves state-of-the-art performance on five benchmark datasets while maintaining a real-time speed of 27 fps(Titan XP).Our code and models are available at https://github.com/RuJiaLe/MSTENet.

SwinVid:Enhancing Video Object Detection Using Swin Transformer

What causes object detection in video to be less accurate than it is in still images?Because some video frames have degraded in appearance from fast movement,out-of-focus camera shots,and changes in posture.These reasons have made video object detection(VID)a growing area of research in recent years.Video object detection can be used for various healthcare applications,such as detecting and tracking tumors in medical imaging,monitoring the movement of patients in hospitals and long-term care facilities,and analyzing videos of surgeries to improve technique and training.Additionally,it can be used in telemedicine to help diagnose and monitor patients remotely.Existing VID techniques are based on recurrent neural networks or optical flow for feature aggregation to produce reliable features which can be used for detection.Some of those methods aggregate features on the full-sequence level or from nearby frames.To create feature maps,existing VID techniques frequently use Convolutional Neural Networks(CNNs)as the backbone network.On the other hand,Vision Transformers have outperformed CNNs in various vision tasks,including object detection in still images and image classification.We propose in this research to use Swin-Transformer,a state-of-the-art Vision Transformer,as an alternative to CNN-based backbone networks for object detection in videos.The proposed architecture enhances the accuracy of existing VID methods.The ImageNet VID and EPIC KITCHENS datasets are used to evaluate the suggested methodology.We have demonstrated that our proposed method is efficient by achieving 84.3%mean average precision(mAP)on ImageNet VID using less memory in comparison to other leading VID techniques.The source code is available on the website https://github.com/amaharek/SwinVid.

LDA-ID:An LDA-Based Framework for Real-Time Network Intrusion Detection

Network intrusion poses a severe threat to the Internet.However,existing intrusion detection models cannot effectively distinguish different intrusions with high-degree feature overlap.In addition,efficient real-time detection is an urgent problem.To address the two above problems,we propose a Latent Dirichlet Allocation topic model-based framework for real-time network Intrusion Detection(LDA-ID),consisting of static and online LDA-ID.The problem of feature overlap is transformed into static LDA-ID topic number optimization and topic selection.Thus,the detection is based on the latent topic features.To achieve efficient real-time detection,we design an online computing mode for static LDA-ID,in which a parameter iteration method based on momentum is proposed to balance the contribution of prior knowledge and new information.Furthermore,we design two matching mechanisms to accommodate the static and online LDA-ID,respectively.Experimental results on the public NSL-KDD and UNSW-NB15 datasets show that our framework gets higher accuracy than the others.

Portable FBAR based E-nose for cold chain real-time bananas shelf time detection

Being cheap,nondestructive,and easy to use,gas sensors play important roles in the food industry.However,most gas sensors are suitable more for laboratory-quality fast testing rather than for cold-chain continuous and cumulative testing.Also,an ideal electronic nose(E-nose)in a cold chain should be stable to its surroundings and remain highly accurate and portable.In this work,a portable film bulk acoustic resonator(FBAR)-based E-nose was built for real-time measurement of banana shelf time.The sensor chamber to contain the portable circuit of the E-nose is as small as a smartphone,and by introducing an air-tight FBAR as a reference,the E-nose can avoid most of the drift caused by surroundings.With the help of porous layer by layer(LBL)coating of the FBAR,the sensitivity of the E-nose is 5 ppm to ethylene and 0.5 ppm to isoamyl acetate and isoamyl butyrate,while the detection range is large enough to cover a relative humidity of 0.8.In this regard,the E-nose can easily discriminate between yellow bananas with green necks and entirely yellow bananas while allowing the bananas to maintain their biological activities in their normal storage state,thereby showing the possibility of real-time shelf time detection.This portable FBAR-based E-nose has a large testing scale,high sensitivity,good humidity tolerance,and low frequency drift to its surroundings,thereby meeting the needs of cold-chain usage.

Force Sensitive Resistors-Based Real-Time Posture Detection System Using Machine Learning Algorithms

To detect the improper sitting posture of a person sitting on a chair,a posture detection system using machine learning classification has been proposed in this work.The addressed problem correlates to the third Sustainable Development Goal(SDG),ensuring healthy lives and promoting well-being for all ages,as specified by the World Health Organization(WHO).An improper sitting position can be fatal if one sits for a long time in the wrong position,and it can be dangerous for ulcers and lower spine discomfort.This novel study includes a practical implementation of a cushion consisting of a grid of 3×3 force-sensitive resistors(FSR)embedded to read the pressure of the person sitting on it.Additionally,the Body Mass Index(BMI)has been included to increase the resilience of the system across individual physical variances and to identify the incorrect postures(backward,front,left,and right-leaning)based on the five machine learning algorithms:ensemble boosted trees,ensemble bagged trees,ensemble subspace K-Nearest Neighbors(KNN),ensemble subspace discriminant,and ensemble RUSBoosted trees.The proposed arrangement is novel as existing works have only provided simulations without practical implementation,whereas we have implemented the proposed design in Simulink.The results validate the proposed sensor placements,and the machine learning(ML)model reaches a maximum accuracy of 99.99%,which considerably outperforms the existing works.The proposed concept is valuable as it makes it easier for people in workplaces or even at individual household levels to work for long periods without suffering from severe harmful effects from poor posture.

Towards Cache-Assisted Hierarchical Detection for Real-Time Health Data Monitoring in IoHT

Real-time health data monitoring is pivotal for bolstering road services’safety,intelligence,and efficiency within the Internet of Health Things(IoHT)framework.Yet,delays in data retrieval can markedly hinder the efficacy of big data awareness detection systems.We advocate for a collaborative caching approach involving edge devices and cloud networks to combat this.This strategy is devised to streamline the data retrieval path,subsequently diminishing network strain.Crafting an adept cache processing scheme poses its own set of challenges,especially given the transient nature of monitoring data and the imperative for swift data transmission,intertwined with resource allocation tactics.This paper unveils a novel mobile healthcare solution that harnesses the power of our collaborative caching approach,facilitating nuanced health monitoring via edge devices.The system capitalizes on cloud computing for intricate health data analytics,especially in pinpointing health anomalies.Given the dynamic locational shifts and possible connection disruptions,we have architected a hierarchical detection system,particularly during crises.This system caches data efficiently and incorporates a detection utility to assess data freshness and potential lag in response times.Furthermore,we introduce the Cache-Assisted Real-Time Detection(CARD)model,crafted to optimize utility.Addressing the inherent complexity of the NP-hard CARD model,we have championed a greedy algorithm as a solution.Simulations reveal that our collaborative caching technique markedly elevates the Cache Hit Ratio(CHR)and data freshness,outshining its contemporaneous benchmark algorithms.The empirical results underscore the strength and efficiency of our innovative IoHT-based health monitoring solution.To encapsulate,this paper tackles the nuances of real-time health data monitoring in the IoHT landscape,presenting a joint edge-cloud caching strategy paired with a hierarchical detection system.Our methodology yields enhanced cache efficiency and data freshness.The corroborative numerical data accentuates the feasibility and relevance of our model,casting a beacon for the future trajectory of real-time health data monitoring systems.

Real-time moving object detection for video monitoring systems

Moving object detection is one of the challenging problems in video monitoring systems, especially when the illumination changes and shadow exists. Amethod for real-time moving object detection is described. Anew background model is proposed to handle the illumination varition problem. With optical flow technology and background subtraction, a moving object is extracted quickly and accurately. An effective shadow elimination algorithm based on color features is used to refine the moving obj ects. Experimental results demonstrate that the proposed method can update the background exactly and quickly along with the varition of illumination, and the shadow can be eliminated effectively. The proposed algorithm is a real-time one which the foundation for further object recognition and understanding of video mum＇toting systems.

Real-time detection of moving objects in video sequences

An approach to detection of moving objects in video sequences, with application to video surveillance is presented. The algorithm combines two kinds of change points, which are detected from the region-based frame difference and adjusted background subtraction. An adaptive threshold technique is employed to automatically choose the threshold value to segment the moving objects from the still background. And experiment results show that the algorithm is effective and efficient in practical situations. Furthermore, the algorithm is robust to the effects of the changing of lighting condition and can be applied for video surveillance system.

Enhancing Fire Detection Performance Based on Fine-Tuned YOLOv10

In recent years,early detection and warning of fires have posed a significant challenge to environmental protection and human safety.Deep learning models such as Faster R-CNN(Faster Region based Convolutional Neural Network),YOLO(You Only Look Once),and their variants have demonstrated superiority in quickly detecting objects from images and videos,creating new opportunities to enhance automatic and efficient fire detection.The YOLO model,especially newer versions like YOLOv10,stands out for its fast processing capability,making it suitable for low-latency applications.However,when applied to real-world datasets,the accuracy of fire prediction is still not high.This study improves the accuracy of YOLOv10 for real-time applications through model fine-tuning techniques and data augmentation.The core work of the research involves creating a diverse fire image dataset specifically suited for fire detection applications in buildings and factories,freezing the initial layers of the model to retain general features learned from the dataset by applying the Squeeze and Excitation attention mechanism and employing the Stochastic Gradient Descent(SGD)with a momentum optimization algorithm to enhance accuracy while ensuring real-time fire detection.Experimental results demonstrate the effectiveness of the proposed fire prediction approach,where the YOLOv10 small model exhibits the best balance compared to other YOLO family models such as nano,medium,and balanced.Additionally,the study provides an experimental evaluation to highlight the effectiveness of model fine-tuning compared to the YOLOv10 baseline,YOLOv8 and Faster R-CNN based on two criteria:accuracy and prediction time.

NFA:A neural factorization autoencoder based online telephony fraud detection

The proliferation of internet communication channels has increased telecom fraud,causing billions of euros in losses for customers and the industry each year.Fraudsters constantly find new ways to engage in illegal activity on the network.To reduce these losses,a new fraud detection approach is required.Telecom fraud detection involves identifying a small number of fraudulent calls from a vast amount of call traffic.Developing an effective strategy to combat fraud has become challenging.Although much effort has been made to detect fraud,most existing methods are designed for batch processing,not real-time detection.To solve this problem,we propose an online fraud detection model using a Neural Factorization Autoencoder(NFA),which analyzes customer calling patterns to detect fraudulent calls.The model employs Neural Factorization Machines(NFM)and an Autoencoder(AE)to model calling patterns and a memory module to adapt to changing customer behaviour.We evaluate our approach on a large dataset of real-world call detail records and compare it with several state-of-the-art methods.Our results show that our approach outperforms the baselines,with an AUC of 91.06%,a TPR of 91.89%,an FPR of 14.76%,and an F1-score of 95.45%.These results demonstrate the effectiveness of our approach in detecting fraud in real-time and suggest that it can be a valuable tool for preventing fraud in telecommunications networks.

Real-Time Tunable Gas Sensing Platform Based on SnO_(2) Nanoparticles Activated by Blue Micro-Light-Emitting Diodes

Micro-light-emitting diodes(μLEDs)have gained significant interest as an activation source for gas sensors owing to their advantages,including room temperature operation and low power consumption.However,despite these benefits,challenges still exist such as a limited range of detectable gases and slow response.In this study,we present a blueμLED-integrated light-activated gas sensor array based on SnO_(2)nanoparticles(NPs)that exhibit excellent sensitivity,tunable selectivity,and rapid detection with micro-watt level power consumption.The optimal power forμLED is observed at the highest gas response,supported by finite-difference time-domain simulation.Additionally,we first report the visible light-activated selective detection of reducing gases using noble metal-decorated SnO_(2)NPs.The noble metals induce catalytic interaction with reducing gases,clearly distinguishing NH3,H2,and C2H5OH.Real-time gas monitoring based on a fully hardwareimplemented light-activated sensing array was demonstrated,opening up new avenues for advancements in light-activated electronic nose technologies.

Virtual Assembly Collision Detection Algorithm Using Backpropagation Neural Network

As computer graphics technology continues to advance,Collision Detection(CD)has emerged as a critical element in fields such as virtual reality,computer graphics,and interactive simulations.CD is indispensable for ensuring the fidelity of physical interactions and the realism of virtual environments,particularly within complex scenarios like virtual assembly,where both high precision and real-time responsiveness are imperative.Despite ongoing developments,current CD techniques often fall short in meeting these stringent requirements,resulting in inefficiencies and inaccuracies that impede the overall performance of virtual assembly systems.To address these limitations,this study introduces a novel algorithm that leverages the capabilities of a Backpropagation Neural Network(BPNN)to optimize the structural composition of the Hybrid Bounding Volume Tree(HBVT).Through this optimization,the research proposes a refined Hybrid Hierarchical Bounding Box(HHBB)framework,which is specifically designed to enhance the computational efficiency and precision of CD processes.The HHBB framework strategically reduces the complexity of collision detection computations,thereby enabling more rapid and accurate responses to collision events.Extensive experimental validation within virtual assembly environments reveals that the proposed algorithm markedly improves the performance of CD,particularly in handling complex models.The optimized HBVT architecture not only accelerates the speed of collision detection but also significantly diminishes error rates,presenting a robust and scalable solution for real-time applications in intricate virtual systems.These findings suggest that the proposed approach offers a substantial advancement in CD technology,with broad implications for its application in virtual reality,computer graphics,and related fields.

CVTD: A Robust Car-Mounted Video Text Detector

Text perception is crucial for understanding the semantics of outdoor scenes,making it a key requirement for building intelligent systems for driver assistance or autonomous driving.Text information in car-mounted videos can assist drivers in making decisions.However,Car-mounted video text images pose challenges such as complex backgrounds,small fonts,and the need for real-time detection.We proposed a robust Car-mounted Video Text Detector(CVTD).It is a lightweight text detection model based on ResNet18 for feature extraction,capable of detecting text in arbitrary shapes.Our model efficiently extracted global text positions through the Coordinate Attention Threshold Activation(CATA)and enhanced the representation capability through stacking two Feature Pyramid Enhancement Fusion Modules(FPEFM),strengthening feature representation,and integrating text local features and global position information,reinforcing the representation capability of the CVTD model.The enhanced feature maps,when acted upon by Text Activation Maps(TAM),effectively distinguished text foreground from non-text regions.Additionally,we collected and annotated a dataset containing 2200 images of Car-mounted Video Text(CVT)under various road conditions for training and evaluating our model’s performance.We further tested our model on four other challenging public natural scene text detection benchmark datasets,demonstrating its strong generalization ability and real-time detection speed.This model holds potential for practical applications in real-world scenarios.