Robust Space-Time Adaptive Track-Before-Detect Algorithm Based on Persymmetry and Symmetric Spectrum

Underwater monopulse space-time adaptive track-before-detect method,which combines space-time adaptive detector(STAD)and the track-before-detect algorithm based on dynamic programming(DP-TBD),denoted as STAD-DP-TBD,can effectively detect low-speed weak targets.However,due to the complexity and variability of the underwater environment,it is difficult to obtain sufficient secondary data,resulting in a serious decline in the detection and tracking performance,and leading to poor robustness of the algorithm.In this paper,based on the adaptive matched filter(AMF)test and the RAO test,underwater monopulse AMF-DP-TBD algorithm and RAO-DP-TBD algorithm which incorporate persymmetry and symmetric spectrum,denoted as PSAMF-DP-TBD and PS-RAO-DP-TBD,are proposed and compared with the AMF-DP-TBD algorithm and RAO-DP-TBD algorithm based on persymmetry array,denoted as P-AMF-DP-TBD and P-RAO-DP-TBD.The simulation results show that the four methods can work normally with sufficient secondary data and slightly insufficient secondary data,but when the secondary data is severely insufficient,the P-AMF-DP-TBD and P-RAO-DP-TBD algorithms has failed while the PSAMF-DP-TBD and PS-RAO-DP-TBD algorithms still have good detection and tracking capabilities.

Research on Track Fastener Service Status Detection Based on Improved Yolov4 Model

As an important part of railway lines, the healthy service status of track fasteners was very important to ensure the safety of trains. The application of deep learning algorithms was becoming an important method to realize its state detection. However, there was often a deficiency that the detection accuracy and calculation speed of model were difficult to balance, when the traditional deep learning model is used to detect the service state of track fasteners. Targeting this issue, an improved Yolov4 model for detecting the service status of track fasteners was proposed. Firstly, the Mixup data augmentation technology was introduced into Yolov4 model to enhance the generalization ability of model. Secondly, the MobileNet-V2 lightweight network was employed in lieu of the CSPDarknet53 network as the backbone, thereby reducing the number of algorithm parameters and improving the model’s computational efficiency. Finally, the SE attention mechanism was incorporated to boost the importance of rail fastener identification by emphasizing relevant image features, ensuring that the network’s focus was primarily on the fasteners being inspected. The algorithm achieved both high precision and high speed operation of the rail fastener service state detection, while realizing the lightweight of model. The experimental results revealed that, the MAP value of the rail fastener service state detection algorithm based on the improved Yolov4 model reaches 83.2%, which is 2.83% higher than that of the traditional Yolov4 model, and the calculation speed was improved by 67.39%. Compared with the traditional Yolov4 model, the proposed method achieved the collaborative optimization of detection accuracy and calculation speed.

基于改进Detection Transformer的棉花幼苗与杂草检测模型研究

基于深度学习的目标检测技术在棉花幼苗与杂草检测领域已取得一定进展。论文提出了基于改进Detection Transformer的棉花幼苗与杂草检测模型,以提高杂草目标检测的准确率和效率。首先,引入了可变形注意力模块替代原始模型中的Transformer注意力模块,提高模型对特征图目标形变的处理能力。提出新的降噪训练机制,解决了二分图匹配不稳定问题。提出混合查询选择策略,提高解码器对目标类别和位置信息的利用效率。使用Swin Transformer作为网络主干,提高模型特征提取能力。通过对比原网络,论文提出的模型方法在训练过程中表现出更快的收敛速度,并且在准确率方面提高了6.7%。

基于改进Tracktor的行人多目标跟踪算法

在多目标视频跟踪中,针对受交互遮挡等影响导致检测偏差从而致使目标身份丢失的问题,提出一种基于改进Tracktor的行人多目标跟踪算法DUTracktor。在检测框回归中设计一个动态更新模块,利用孪生网络对建议框进一步检测定位;利用时序信息增强模块更新当前帧更适合的模板,建立全局上下文关系;并通过像素相关进行特征融合,从而增强目标边缘信息和尺度信息;利用相机运动补偿和融合相似矩阵构建二级关联跟踪机制,建立检测框和轨迹更强大的关联性,提高目标跟踪的鲁棒性。在公开的MOT16数据集上进行实验测试,并与当前主流算法相比,该算法跟踪精度表现较优,具有良好的鲁棒性,FPS稳定在24帧。

BEVTrack:基于难例挖掘训练的端到端三维多目标跟踪方法

多目标跟踪已经成为自动驾驶系统中的一个关键组成部分,其目的是在连续的视频流与点云流中识别、定位并标识所有感兴趣的目标。目前三维多目标跟踪方法多依赖人工多阶段调参以保证整体跟踪性能,难以对复杂遮挡或运动进行有效建模。而现有的三维端到端多目标跟踪方法,如MUTR等,精度普遍较低。其核心原因为三维空间中的特征聚合和感知相对于二维图像更具挑战性,简单的网络难以实现复杂的三维特征聚合,并大量的噪声信息与难例信息干扰严重,影响模型的特征提取能力。针对以上问题,本文提出了一种基于难例挖掘训练的端到端多目标跟踪框架BEVTrack。针对三维特征关联问题,本文设计了基于鸟瞰图(BEV)位置编码的三维跟踪查询。通过基于BEV特征的三维跟踪查询,本文方法能够更好地将跟踪查询与实际三维特征进行有效关联,从而大幅度提升了跟踪精度。同时,模型依靠BEV数据进行特征关联,仅需轻量化的网络便可以实现快速有效的跟踪。针对数据噪声问题,本文提出了面向多目标跟踪的难例挖掘训练,通过针对检测难例与跟踪难例分别处理,训练模型去除检测错误噪声与跟踪匹配的能力,从而提升在真实场景下模型处理噪声信息与难例干扰的能力。在实验结果方面,基于Nuscenes数据集,我们进行了大量的对比实验与模型消融实验,实验结果证明本文的方法在该数据集上取得了领先的性能。

Vehicle Detection and Tracking in UAV Imagery via YOLOv3 and Kalman Filter

Unmanned aerial vehicles(UAVs)can be used to monitor traffic in a variety of settings,including security,traffic surveillance,and traffic control.Numerous academics have been drawn to this topic because of the challenges and the large variety of applications.This paper proposes a new and efficient vehicle detection and tracking system that is based on road extraction and identifying objects on it.It is inspired by existing detection systems that comprise stationary data collectors such as induction loops and stationary cameras that have a limited field of view and are not mobile.The goal of this study is to develop a method that first extracts the region of interest(ROI),then finds and tracks the items of interest.The suggested system is divided into six stages.The photos from the obtained dataset are appropriately georeferenced to their actual locations in the first phase,after which they are all co-registered.The ROI,or road and its objects,are retrieved using the GrabCut method in the second phase.The third phase entails data preparation.The segmented images’noise is eliminated using Gaussian blur,after which the images are changed to grayscale and forwarded to the following stage for additional morphological procedures.The YOLOv3 algorithm is used in the fourth step to find any automobiles in the photos.Following that,the Kalman filter and centroid tracking are used to perform the tracking of the detected cars.The Lucas-Kanade method is then used to perform the trajectory analysis on the vehicles.The suggested model is put to the test and assessed using the Vehicle Aerial Imaging from Drone(VAID)dataset.For detection and tracking,the model was able to attain accuracy levels of 96.7%and 91.6%,respectively.

Embedded System Development for Detection of Railway Track Surface Deformation Using Contour Feature Algorithm

Derailment of trains is not unusual all around the world,especially in developing countries,due to unidentified track or rolling stock faults that cause massive casualties each year.For this purpose,a proper condition monitoring system is essential to avoid accidents and heavy losses.Generally,the detection and classification of railway track surface faults in real-time requires massive computational processing and memory resources and is prone to a noisy environment.Therefore,in this paper,we present the development of a novel embedded system prototype for condition monitoring of railway track.The proposed prototype system works in real-time by acquiring railway track surface images and performing two tasks a)detect deformation(i.e.,faults)like squats,shelling,and spalling using the contour feature algorithm and b)the vibration signature on that faulty spot by synchronizing acceleration and image data.A new illumination scheme is also proposed to avoid the sunlight reflection that badly affects the image acquisition process.The contour detection algorithm is applied here to detect the uneven shapes and discontinuities in the geometrical structure of the railway track surface,which ultimately detects unhealthy regions.It works by converting Red,Green,and Blue(RGB)images into binary images,which distinguishes the unhealthy regions by making them white color while the healthy regions in black color.We have used the multiprocessing technique to overcome the massive processing and memory issues.This embedded system is developed on Raspberry Pi by interfacing a vision camera,an accelerometer,a proximity sensor,and a Global Positioning System(GPS)sensors(i.e.,multi-sensors).The developed embedded system prototype is tested in real-time onsite by installing it on a Railway Inspection Trolley(RIT),which runs at an average speed of 15 km/h.The functional verification of the proposed system is done successfully by detecting and recording the various railway track surface faults.An unhealthy frame’s onsite detection processing time was recorded at approximately 25.6ms.The proposed system can synchronize the acceleration data on specific railway track deformation.The proposed novel embedded system may be beneficial for detecting faults to overcome the conventional manual railway track condition monitoring,which is still being practiced in various developing or underdeveloped countries.

基于改进YOLOv7-ByteTrack的干制哈密大枣缺陷检测与计数系统

针对目前无法同时对随机多列排布干制哈密大枣进行快速缺陷检测和统计计数问题,该研究设计了一款干制哈密大枣在线检测与计数系统。以干制哈密大枣为研究对象,利用工业相机拍摄传送带上随机排列的多类别缺陷干制哈密大枣视频为数据源,采用改进的YOLOv7模型进行干制哈密大枣多类别缺陷检测并将检测结果作为后续多目标跟踪算法的输入;考虑到传送带上干制哈密大枣的外观相似性高以及排列密集等特点,该研究结合ByteTrack多目标跟踪算法的思想,设计了一种多类别干制哈密大枣的画线计数方法,实现了随机排布多类别干制哈密大枣的缺陷检测、准确定位及计数。试验结果表明:1)改进的YOLOv7模型浮点计算量为64.6 G,在干制哈密大枣目标检测数据的测试集上的平均检测精度、召回率、F_(1)平衡分数分别达到了98.03%、93.43%和95.00%,相比YOLOv7模型分别提高了4.40、6.88和7.00个百分点,浮点计算量下降了38.6%;2)基于改进YOLOv7为目标检测器开发的ByteTrack算法计数模型对干制哈密大枣计数的准确率为90.12%。该研究可为干制哈密大枣检测计数和分选分级提供技术支持。

改进YOLOv7+Bytetrack的小目标检测与追踪

近年来,目标检测技术已经相当成熟,但小目标检测一直是目标检测领域的一大挑战。为了解决这一问题,设计一种名为MFF-YOLOv7的小目标检测算法,该算法旨在提高小目标检测的准确率。设计级联双向特征金字塔KBiFPN,以及联合提出的多级感受野特征聚合模块MFA,来聚合浅层特征并增强特征的信息表达能力。为了解决小目标漏检问题,设计了新的解耦头和新的注意力机制。新的解耦头对小目标的检测能力更强,新的注意力机制可以重点关注感兴趣的小目标区域。引入了一种新的损失函数ECIOU,旨在加快模型的收敛速度。为了验证模型的性能,分别在三个小目标数据集上进行了实验。实验结果表明,MFF-YOLOv7算法提高了检测精度。同时,使用多目标追踪Bytetrack算法在MOT17和VisDrone2019-MOT两个多目标追踪数据集上对新模型进行了验证,进一步证明了其有效性。此外,MFF-YOLOv7算法在动态视频追踪中表现出了良好的性能。

基于改进CStrack关联策略的多目标跟踪算法

针对复杂场景下目标外观变化明显、运动不规律易导致轨迹中断和身份切换频繁等问题,从重识别(Re-Identification,Re-ID)特征、数据关联和插值等方面对跟踪器进行改进,提出基于改进CStrack关联策略的多目标跟踪算法。使用外观特征更新模块,减小因视角改变、目标移动导致特征剧烈变化而产生的影响,增强特征间的关联。提出二次关联方法,根据高低置信度检测结果的特点,使用不同的度量方式进行二次关联:第一次关联使用IoU距离融合外观特征作为关联的代价矩阵,第二次使用扩展IoU关联,缓解运动估计偏差、外观不可区分导致度量失效的问题;采用高斯回归算法,考虑运动信息,通过插值补偿漏检。在MOT17、MOT20数据集上进行测试,跟踪精度分别达到73.9%、64.2%。实验结果表明,该方法在跟踪精度上有明显优势,能够较好地适应复杂场景。

End-to-End Joint Multi-Object Detection and Tracking for Intelligent Transportation Systems

Environment perception is one of the most critical technology of intelligent transportation systems(ITS).Motion interaction between multiple vehicles in ITS makes it important to perform multi-object tracking(MOT).However,most existing MOT algorithms follow the tracking-by-detection framework,which separates detection and tracking into two independent segments and limit the global efciency.Recently,a few algorithms have combined feature extraction into one network;however,the tracking portion continues to rely on data association,and requires com‑plex post-processing for life cycle management.Those methods do not combine detection and tracking efciently.This paper presents a novel network to realize joint multi-object detection and tracking in an end-to-end manner for ITS,named as global correlation network(GCNet).Unlike most object detection methods,GCNet introduces a global correlation layer for regression of absolute size and coordinates of bounding boxes,instead of ofsetting predictions.The pipeline of detection and tracking in GCNet is conceptually simple,and does not require compli‑cated tracking strategies such as non-maximum suppression and data association.GCNet was evaluated on a multivehicle tracking dataset,UA-DETRAC,demonstrating promising performance compared to state-of-the-art detectors and trackers.

Multiple Pedestrian Detection and Tracking in Night Vision Surveillance Systems

Pedestrian detection and tracking are vital elements of today’s surveillance systems,which make daily life safe for humans.Thus,human detection and visualization have become essential inventions in the field of computer vision.Hence,developing a surveillance system with multiple object recognition and tracking,especially in low light and night-time,is still challenging.Therefore,we propose a novel system based on machine learning and image processing to provide an efficient surveillance system for pedestrian detection and tracking at night.In particular,we propose a system that tackles a two-fold problem by detecting multiple pedestrians in infrared(IR)images using machine learning and tracking them using particle filters.Moreover,a random forest classifier is adopted for image segmentation to identify pedestrians in an image.The result of detection is investigated by particle filter to solve pedestrian tracking.Through the extensive experiment,our system shows 93%segmentation accuracy using a random forest algorithm that demonstrates high accuracy for background and roof classes.Moreover,the system achieved a detection accuracy of 90%usingmultiple templatematching techniques and 81%accuracy for pedestrian tracking.Furthermore,our system can identify that the detected object is a human.Hence,our system provided the best results compared to the state-ofart systems,which proves the effectiveness of the techniques used for image segmentation,classification,and tracking.The presented method is applicable for human detection/tracking,crowd analysis,and monitoring pedestrians in IR video surveillance.

基于状态向量增强ByteTrack的新生羔羊活动量自动计算方法

为评价母羊繁殖性能并及时发现分娩栏中的弱活力羔羊,该研究提出一种基于状态向量增强ByteTrack的新生羔羊活动量自动计算方法。针对传统ByteTrack算法在跟踪目标被遮挡时易发生身份切换的问题,引入置信度信息增强的状态向量,提高跟踪算法区分遮挡与被遮挡羔羊的能力。针对跟踪目标丢失导致轨迹预测不准确的问题,构建目标丢失期间的虚拟轨迹并重更新轨迹状态向量,以纠正轨迹误差。在获取各羔羊活动轨迹后,计算各羔羊帧间移动距离统计羔羊活动量。在江苏海门山羊研发中心采集的新生羔羊活动视频数据集上,测试状态向量增强的ByteTrack多目标跟踪算法性能。测试结果表明,研究提出的多目标跟踪方法在高阶跟踪精度、多目标跟踪精度、多目标跟踪准确度、IDF1得分上分别达到80.8%、86.1%、84.5%和92.2%,相较于现有算法的最高精度,分别提高2.7、0.2、2.3和3.9个百分点。该研究所提方法能够实现同窝多只新生羔羊的稳定跟踪,为新生羔羊活动量的自动计算、母羊繁殖性能的自动评估提供技术支撑。

基于Bytetrack的多目标跟踪算法在斑马鱼毒性行为识别中的应用

利用计算机视觉技术识别斑马鱼(Danio rerio)在不同污染物暴露下的行为变化是水质毒性评价的常用方法之一,但传统方法存在效率低、面对遮挡和复杂环境时性能差等缺陷。针对这些问题,本研究使用基于Bytetrack的多目标跟踪算法追踪斑马鱼在4种污染物(Zn、Pb、Cr和苯酚)暴露2 h后的行为变化,对斑马鱼在4种浓度梯度中的平均速度、最大速度、最低速度、平均碰撞次数和行为轨迹等指标进行分析。结果显示,算法的追踪精度、漏检率和检测时间(每300帧)分别能达到90.26%、16.33%和0.19 min,检测时间和精度相比于传统目标检测方法有较大提升。同时,根据污染物不同,该方法能准确识别特定污染物环境中斑马鱼相应的运动状态及轨迹变化,可实现精确识别和实时响应,在鱼类毒性行为识别领域具有重要参考意义。

Segmentation Based Real Time Anomaly Detection and Tracking Model for Pedestrian Walkways

Presently,video surveillance is commonly employed to ensure security in public places such as traffic signals,malls,railway stations,etc.A major chal-lenge in video surveillance is the identification of anomalies that exist in it such as crimes,thefts,and so on.Besides,the anomaly detection in pedestrian walkways has gained significant attention among the computer vision communities to enhance pedestrian safety.The recent advances of Deep Learning(DL)models have received considerable attention in different processes such as object detec-tion,image classification,etc.In this aspect,this article designs a new Panoptic Feature Pyramid Network based Anomaly Detection and Tracking(PFPN-ADT)model for pedestrian walkways.The proposed model majorly aims to the recognition and classification of different anomalies present in the pedestrian walkway like vehicles,skaters,etc.The proposed model involves panoptic seg-mentation model,called Panoptic Feature Pyramid Network(PFPN)is employed for the object recognition process.For object classification,Compact Bat Algo-rithm(CBA)with Stacked Auto Encoder(SAE)is applied for the classification of recognized objects.For ensuring the enhanced results better anomaly detection performance of the PFPN-ADT technique,a comparison study is made using Uni-versity of California San Diego(UCSD)Anomaly data and other benchmark data-sets(such as Cityscapes,ADE20K,COCO),and the outcomes are compared with the Mask Recurrent Convolutional Neural Network(RCNN)and Faster Convolu-tional Neural Network(CNN)models.The simulation outcome demonstrated the enhanced performance of the PFPN-ADT technique over the other methods.

Robust Deep Transfer Learning Based Object Detection and Tracking Approach

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.

Improved YOLOv8n Model for Detecting Helmets and License Plates on Electric Bicycles

Wearing helmetswhile riding electric bicycles can significantly reduce head injuries resulting fromtraffic accidents.To effectively monitor compliance,the utilization of target detection algorithms through traffic cameras plays a vital role in identifying helmet usage by electric bicycle riders and recognizing license plates on electric bicycles.However,manual enforcement by traffic police is time-consuming and labor-intensive.Traditional methods face challenges in accurately identifying small targets such as helmets and license plates using deep learning techniques.This paper proposes an enhanced model for detecting helmets and license plates on electric bicycles,addressing these challenges.The proposedmodel improves uponYOLOv8n by deepening the network structure,incorporating weighted connections,and introducing lightweight convolutional modules.These modifications aim to enhance the precision of small target recognition while reducing the model’s parameters,making it suitable for deployment on low-performance devices in real traffic scenarios.Experimental results demonstrate that the model achieves an mAP@0.5 of 91.8%,showing an 11.5%improvement over the baselinemodel,with a 16.2%reduction in parameters.Additionally,themodel achieves a frames per second(FPS)rate of 58,meeting the accuracy and speed requirements for detection in actual traffic scenarios.

Improvement of High-Speed Detection Algorithm for Nonwoven Material Defects Based on Machine Vision

Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.

A Hybrid Intrusion Detection Method Based on Convolutional Neural Network and AdaBoost

To solve the problem of poor detection and limited application range of current intrusion detection methods,this paper attempts to use deep learning neural network technology to study a new type of intrusion detection method.Hence,we proposed an intrusion detection algorithm based on convolutional neural network(CNN)and AdaBoost algorithm.This algorithm uses CNN to extract the characteristics of network traffic data,which is particularly suitable for the analysis of continuous and classified attack data.The AdaBoost algorithm is used to classify network attack data that improved the detection effect of unbalanced data classification.We adopt the UNSW-NB15 dataset to test of this algorithm in the PyCharm environment.The results show that the detection rate of algorithm is99.27%and the false positive rate is lower than 0.98%.Comparative analysis shows that this algorithm has advantages over existing methods in terms of detection rate and false positive rate for small proportion of attack data.

Moving Multi-Object Detection and Tracking Using MRNN and PS-KM Models

On grounds of the advent of real-time applications,like autonomous driving,visual surveillance,and sports analysis,there is an augmenting focus of attention towards Multiple-Object Tracking(MOT).The tracking-by-detection paradigm,a commonly utilized approach,connects the existing recognition hypotheses to the formerly assessed object trajectories by comparing the simila-rities of the appearance or the motion between them.For an efficient detection and tracking of the numerous objects in a complex environment,a Pearson Simi-larity-centred Kuhn-Munkres(PS-KM)algorithm was proposed in the present study.In this light,the input videos were,initially,gathered from the MOT dataset and converted into frames.The background subtraction occurred whichfiltered the inappropriate data concerning the frames after the frame conversion stage.Then,the extraction of features from the frames was executed.Afterwards,the higher dimensional features were transformed into lower-dimensional features,and feature reduction process was performed with the aid of Information Gain-centred Singular Value Decomposition(IG-SVD).Next,using the Modified Recurrent Neural Network(MRNN)method,classification was executed which identified the categories of the objects additionally.The PS-KM algorithm identi-fied that the recognized objects were tracked.Finally,the experimental outcomes exhibited that numerous targets were precisely tracked by the proposed system with 97%accuracy with a low false positive rate(FPR)of 2.3%.It was also proved that the present techniques viz.RNN,CNN,and KNN,were effective with regard to the existing models.