Object Tracking Technology Research Articles

FQTrack:Object Tracking Method Based on a Feature-Enhanced Memory Network and Memory Quality Selection Mechanism

Visual object tracking technology is widely used in intelligent security, automatic driving and other fields, and also plays an important role in frontier fields such as human–computer interactions and virtual reality. The memory network improves the stability and accuracy of tracking by using historical frame information to assist in the positioning of the current frame in object tracking. However, the memory network is still insufficient in feature mining and the accuracy and robustness of the model may be reduced when using noisy observation samples to update it. In view of the above problems, we propose a new tracking framework, which uses the attention mechanism to establish a feature-enhanced memory network and combines cross-attention to aggregate the spatial and temporal context information of the target. The former introduces spatio-temporal adaptive attention and cross-spatial attention, embeds spatial location information into channels, realizes multi-scale feature fusion, dynamically emphasizes target location information, and obtains richer feature maps. The latter guides the tracker to focus on the area with the largest amount of information in the current frame to better distinguish the foreground and background. In addition, through the memory quality selection mechanism, the accuracy and richness of the feature samples are improved, thereby enhancing the adaptability and discrimination ability of the tracking model. Experiments on benchmark test sets such as OTB2015, TrackingNet, GOT-10k, LaSOT and UAV 123 show that this method achieves comparable performance with advanced trackers.

Application of Modern Object Tracking Technologies to the Task of Aortography Key Point Detection in Transcatheter Aortic Valve Implantation

Object detection, as one of the most fundamental and challenging problems in computer vision, has attracted much attention in recent years. Over the past two decades, we have witnessed the rapid technological evolution of object detection and its profound impact on the whole field of computer vision. In this paper, aortography key point detection approaches for transcatheter aortic valve implantation based on machine learning tools are discussed. The paper provides a description and analytical comparison of such popular methods as "object detection", "pose estimation". As a result of this study, a visual assessment system is proposed to facilitate the performance of the intervention procedure. The final accuracy of the proposed system reaches 79.3% with an analysis speed of 12 ms per image.

Time-dependent synchronization factor of crowd rhythmic motion and its application on intelligent structural monitoring

The synchronization factor is an index to evaluate the level of consistency for crowd motion under rhythmic guidance, which is important for crowd load modeling as well as structural vibration monitoring. Most of the existing synchronization factors were defined based on the time history of the crowd movement over a long period of time, failing to consider the time-dependent characteristics of intra-subject variability. Moreover, these factors were generally based on the data that can only be measured under laboratory conditions, making them difficult to be applied on the monitoring of structures subjected to crowd excitation in real engineering practice. In this regard, this paper proposed a novel time-dependent synchronization factor for a crowd in rhythmic motion. By using multiple object tracking technology, the head movements of each person in the crowd were measured as the basis for calculating the newly proposed time-dependent synchronization factor, which is defined as the ratio between a representative value of the crowd movement time history and the average of the same values for each person in the crowd. A series of experiments were organized to study the characteristics and the applicability of the synchronization factor, whose relation with structural responses was clearly observed in the laboratory experiments as well as in a real structure. The results demonstrated that the newly proposed time-dependent synchronization factor is effective when applied on the intelligent operation and maintenance of the engineering structures.

A Liquidity Analysis System for Large-scale Video Streams in the Oilfield

This article introduces LinkStream, a liquidity analysis system based on multiple video streams designed and implemented for oilfield. LinkStream combines a variety of technologies to solve several problems in computing power and network latency. First, the system adopts an edge-central architecture and tailoring based on spatio-temporal correlation, which greatly reduces computing power requirements and network costs, and enables real-time analysis of large-scale video stream on limited edge devices. Second, it designed a set of liquidity information to describe the liquidity status in the oilfield. Finally, it uses object tracking technology to design a counting algorithm for the unique tubing object in the oilfield. We have deployed LinkStream in an oilfield in Iraq. LinkStream can perform real-time inference on over 200 video streams with acceptable resource overhead.

A review of object tracking methods: From general field to autonomous vehicles

Object tracking is a key technology in the field of intelligent vehicle environmental perception. Accurate and efficient object tracking technologies provide autonomous vehicles with real-time information of moving objects, helping judge the behavioral intention of the objects and predict the trajectories. With the rapid development of artificial intelligence and vehicular sensors, object tracking algorithms have made great progress. Recently however, only a few studies focus on object tracking technology for autonomous vehicles, especially involving multi-source sensors and information fusion algorithms. This study systematically and comprehensively reviews over 230 studies, therein noting the recent research achievements in object tracking are generalized. First, the single object tracking (SOT) and multiple object tracking (MOT) algorithms based on vision sensor are introduced respectively, including 2D, 3D, and intelligent vehicle object tracking algorithms, while the pros and cons of the classical algorithms and latest algorithms are summarized. Then, the object tracking methods based on point cloud and multimodal fusion are discussed and analyzed, and a variety of object tracking datasets are displayed. Finally, on the basis of the research status of intelligent vehicle object tracking algorithms, the challenges and opportunities of future research are presented.

Development of Smart Video Surveillance Systems: Technical and Security Challenges in Urban Environments

Video surveillance schemes have become a critical tool for safeguarding urban and industrial services, thanks to the rapid advancement in object recognition, tracking, and human activity analysis technologies. The achievement of these systems relies on background analysis, motion detection, and innovative solutions for real-time data processing and storage. These schemes have transitioned from analog setups to IP-based systems, offering more flexibility and remote control capabilities. However, they face important cybersecurity challenges, such as data breaches, bandwidth consumption, and high processing demands. This research explores the technological advancements in video surveillance systems, focusing on the security challenges and analytics in urban environments. Furthermore, it discourses strategies for optimizing system efficiency through modern compression algorithms and real-time human activity analysis.

The identification of minor impact collisions in a long video for detecting property damages caused by fleeing vehicles using three-dimensional convolutional neural network

Abstract A parked vehicle damaged by a hit-and-run can only be repaired at the expense of the owner, unless the fleeing vehicle is identified and the driver apprehended. Identifying the fleeing vehicle involves using a video investigation method that searches for perpetrators through CCTV footage of the crime scene. When the length of the recorded video is long, the investigation may require an extended amount of time from the investigator, resulting in an added burden on their daily work. Some commercial companies are using object recognition and tracking technology to detect hit-and-run incidents; however, detecting small movements of a vehicle during a minor collision still remains a challenge. Therefore, there is a need for a system that can detect small movement in a vehicle in a lengthy video. Automatic recognition and tracking require a sufficient amount of training dataset. However, such a dataset for hit-and-run incidents is not publicly available. One of the reasons behind this scarcity is that it may violate personal information protection acts. On the other hand, instead of using real accident videos, we could use actors to simulate such accident scenes. Although this may be feasible, creating such a dataset would require substantial costs. In this paper, we describe a new dataset for hit-and-run incidents. We collected 833 hit-and-run videos by recreating a parking lot using miniaturized cars. This dataset has been made publicly available through Kaggle. We used three-dimensional convolution neural network, which is frequently used in the field of action recognition, to detect small movements of vehicles during hit-and-run incidents. In addition, the proportion of the area that surrounds the target vehicle to the min-max box of the vehicle itself and the length of the input frame are varied to compare the accuracy. As a result, we were able to achieve better accuracy by using the lowest proportion and the shortest input frame.

A Survey of Integrating Deep Learning-Based Missing Person Detection Model into CCTV Systems for Enhanced Identification

This study looks at the possibility of increasing identification abilities in closed-circuit video (CCTV) systems using a deep learning-based missing person detection model. Missing individuals are becoming increasingly common, necessitating the development of novel search tactics. This study uses deep learning to augment traditional CCTV systems by using an improved model that can reliably identify and track persons who go missing. Taking a detailed look at current techniques to missing person identification, the literature review shows the shortcomings of existing systems and the potential for improving them through the use of deep learning. The paper examines past methodologies, including facial recognition accuracy, tracking robustness, and system scalability.The integration of computer vision with missing person identification, object tracking technologies, and facial recognition algorithms are among the main topics. The research also investigates privacy, moral, and legal implications of deploying such technology in public.

Surveillance video synopsis framework base on tube set

Video synopsis technology can shorten the length of the video, which has attracted wide attention. However, due to the limitation of object extraction technology and the difficulty of preserving interactivity, synopsis videos will lose the semantic information of the original video. To address the above problems, we propose a video synopsis framework based on tube sets. Firstly, we propose a video tracking algorithm based on Yolov4 and Kalman Filter, which can effectively alleviate the problem that it is difficult for object tracking technology to extract occluded objects. Secondly, we propose a method that combines moving direction and dynamic threshold to judge interactivity. Accurately judging interactivity can ensure that the interactive objects are not separated in the synopsis video. Finally, we propose a tube set mapping model (TSMM) that can rearrange with the tube set as the basic unit. Experimental results demonstrate that our method can achieve superior performance than other state-of-the-art methods.

An ultra-fast and energy-efficient CNTFET-based image corner detection hardware for real-time image processing applications

In image processing and machine vision, corner detection is pivotal in diverse applications, including computer vision, 3D reconstruction, face detection, object tracking, and video technologies. Despite the wide usage, the real-time and energy-efficient hardware implementation of corner detection algorithms remains a critical challenge because of the computational resource limitations. On the other hand, owing to the complicated nature of corner detection algorithms, their hardware implementation has been limited to the graphics processing unit (GPU) and field programmable gate arrays (FPGA) platforms. In this regard, this work aims to propose a novel and ultra-efficient carbon nanotube field-effect transistor (CNTFET)-based hardware for image corner detection. Thanks to the proposed corner detection algorithm, the designed hardware has been realized using 2742 transistors with competitive accuracy. The proposed corner detection hardware indicated a remarkable salt-and-pepper noise immunity without using any noise reduction circuit. Our comprehensive simulations demonstrate 78%, 87%, and 94.5% total average improvements in delay, power, and energy compared to the other related corner detection hardware. Moreover, the proposed CNTFET-based corner detection hardware shows a 43 ps propagation delay, demonstrating its real-time operation. The proposed corner detection algorithm at the system level shows suitable accuracy metrics such as Recall, Precision, and error of detection (EoD) compared to the other well-known corner detectors. Our method has established a new pathway for real-time circuit-level hardware design for image processing and machine vision applications.

Low-cost system for real-time verification of personal protective equipment in industrial facilities using edge computing devices

Ensure worker safety in the industry is crucial. Despite efforts to improve safety, statistics show a plateau in the reduction of these accidents in recent years. To decrease the number of accidents, compliance with established industrial safety standards and regulations by competent authorities must be ensured, including the use of Personal Protective Equipment (PPE). PPE usage is of paramount importance, as it is essential to prevent accidents from occurring. This work aims to improve worker safety by verifying PPE usage. Technology plays a key role here. A cost-effective solution is proposed to monitor PPE usage in real time. Most existing safety control systems are costly and require considerable maintenance. A low-cost computer vision system is proposed to supervise safety in industrial facilities. This system uses object detection and tracking technology in low-cost embedded devices and can generate alarms in real time if PPE is not used. Unlike other works, temporal information is used to generate the alarms. Safety managers receive this information to take necessary actions. Emphasis has been placed on cost, scalability, and ease of use to facilitate system implementation in industrial plants. The result is an effective system that improves worker safety by verifying established safety measures at a reduced cost. The methodology used improves the Average Precision of PPE detection by 6%. In addition, unlike other studies, the problem of application deployment is addressed, which has an impact on its cost.

High-Speed Tracking with Mutual Assistance of Feature Filters and Detectors.

Object detection and tracking in camera images is a fundamental technology for computer vision and is used in various applications. In particular, object tracking using high-speed cameras is expected to be applied to real-time control in robotics. Therefore, it is required to increase tracking speed and detection accuracy. Currently, however, it is difficult to achieve both of those things simultaneously. In this paper, we propose a tracking method that combines multiple methods: correlation filter-based object tracking, deep learning-based object detection, and motion detection with background subtraction. The algorithms work in parallel and assist each other's processing to improve the overall performance of the system. We named it the "Mutual Assist tracker of feature Filters and Detectors (MAFiD method)". This method aims to achieve both high-speed tracking of moving objects and high detection accuracy. Experiments were conducted to verify the detection performance and processing speed by tracking a transparent capsule moving at high speed. The results show that the tracking speed was 618 frames per second (FPS) and the accuracy was 86% for Intersection over Union (IoU). The detection latency was 3.48 ms. These experimental scores are higher than those of conventional methods, indicating that the MAFiD method achieved fast object tracking while maintaining high detection performance. This proposal will contribute to the improvement of object-tracking technology.

Survey of AR Object Tracking Technology Based on Deep Learning

Augmented reality (AR) is the process of "augmenting" computer information into the real or physical world. This helps us better understand the process and has numerous application-level AR has an almost unlimited range of applications in today's world, and if implemented, will help solve many complex problems in a simple way. This paper presents a comprehensive survey of the different types of tracking technique. As used to develop object tracking algorithms for AR applications. This paper compares and analyses different types of sensor-based and vision-based tracking technologies, and finally draws conclusions. The mixed use of different types of tracking technologies is one of the best solutions to achieve accurate and powerful tracking to meet the strict requirements of AR applications.

Validation of real-time inside-out tracking and depth realization technologies for augmented reality-based neuronavigation.

Concomitant with the significant advances in computing technology, the utilization of augmented reality-based navigation in clinical applications is being actively researched. In this light, we developed novel object tracking and depth realization technologies to apply augmented reality-based neuronavigation to brain surgery. We developed real-time inside-out tracking based on visual inertial odometry and a visual inertial simultaneous localization and mapping algorithm. The cube quick response marker and depth data obtained from light detection and ranging sensors are used for continuous tracking. For depth realization, order-independent transparency, clipping, and annotation and measurement functions were developed. In this study, the augmented reality model of a brain tumor patient was applied to its life-size three-dimensional (3D) printed model. Using real-time inside-out tracking, we confirmed that the augmented reality model remained consistent with the 3D printed patient model without flutter, regardless of the movement of the visualization device. The coordination accuracy during real-time inside-out tracking was also validated. The average movement error of the X and Y axes was 0.34 ± 0.21 and 0.04 ± 0.08mm, respectively. Further, the application of order-independent transparency with multilayer alpha blending and filtered alpha compositing improved the perception of overlapping internal brain structures. Clipping, and annotation and measurement functions were also developed to aid depth perception and worked perfectly during real-time coordination. We named this system METAMEDIP navigation. The results validate the efficacy of the real-time inside-out tracking and depth realization technology. With these novel technologies developed for continuous tracking and depth perception in augmented reality environments, we are able to overcome the critical obstacles in the development of clinically applicable augmented reality neuronavigation.

Adversarial Examples in Visual Object Tracking in Satellite Videos: Cross-Frame Momentum Accumulation for Adversarial Examples Generation

The visual object tracking technology of remote sensing images has important applications in areas with high safety performance such as national defense, homeland security, and intelligent transportation in smart cities. However, previous research demonstrates that adversarial examples pose a significant threat to remote sensing imagery. This article first explores the impact of adversarial examples in the field of visual object tracking in remote sensing imagery. We design a classification- and regression-based loss function for the popular Siamese RPN series of visual object tracking models and use the PGD gradient-based attack method to generate adversarial examples. Additionally, we consider the temporal consistency of video frames and design an adversarial examples attack method based on momentum continuation. We evaluate our method on the remote sensing visual object tracking datasets SatSOT and VISO and the traditional datasets OTB100 and UAV123. The experimental results show that our approach can effectively reduce the performance of the tracker.

AI 공격용 드론 개발 방향 및 시사점

The role of attack drones in the ongoing war between Ukraine and Russia is drawing worldwide attention. In order to prepare for changes in the defense security environment and rapid decline in military resources, the Ministry of National Defense announced the National Defense Innovation 4.0 Basic Plan in March 2023, and established the concept of joint operation by reflecting the operation of AI-based manned and unmanned complex systems and new concept weapon systems. did Drones are the most important force in building manned and unmanned complex systems, and the dronebot combat system will be the basis for promoting Defense Innovation 4.0. Drones are a system that can be operated for multiple purposes that change their use according to mission equipment, and it is key to have advanced technology that is suitable for the future battlefield environment and efficient. If the existing attack drone is an operating system in which combatants remotely control the ground control device while watching the ground control device, the future direction of the development of attack drones for the Korean military to apply to dronebots is an AI attack drone in which the drone detects the target by itself and directly strikes and self-destructs. will develop into In order to develop AI attack drones, not only the performance of the drone system, but also AI-based cutting-edge technology for object tracking technology, object identification technology and shape recognition technology of reconnaissance equipment (EO/IR), which is mission equipment, as well as attack ammunition or Small, high-performance warhead design technology, ultra-small fuze design technology, shock absorption and launch control device technology, etc. must be developed to mount the projectile. In addition, as the amount of image information acquired through mission equipment increases, high-speed data transmission technology development to improve the transmission rate between the aircraft and the ground control equipment in real time must be simultaneously developed. It is necessary to quickly overcome drone and AI technologies, which are currently very poor compared to advanced countries, and take the lead in developing intelligent AI attack drones with excellent autonomy based on Korea's excellent ICT technology. Therefore, this study aims to find out the technological trends of domestic and foreign attack drones and to consider the development plans and tasks of AI attack drones.

Open-source software for automated rodent behavioral analysis.

Rodent behavioral analysis is a major specialization in experimental psychology and behavioral neuroscience. Rodents display a wide range of species-specific behaviors, not only in their natural habitats but also under behavioral testing in controlled laboratory conditions. Detecting and categorizing these different kinds of behavior in a consistent way is a challenging task. Observing and analyzing rodent behaviors manually limits the reproducibility and replicability of the analyses due to potentially low inter-rater reliability. The advancement and accessibility of object tracking and pose estimation technologies led to several open-source artificial intelligence (AI) tools that utilize various algorithms for rodent behavioral analysis. These software provide high consistency compared to manual methods, and offer more flexibility than commercial systems by allowing custom-purpose modifications for specific research needs. Open-source software reviewed in this paper offer automated or semi-automated methods for detecting and categorizing rodent behaviors by using hand-coded heuristics, machine learning, or neural networks. The underlying algorithms show key differences in their internal dynamics, interfaces, user-friendliness, and the variety of their outputs. This work reviews the algorithms, capability, functionality, features and software properties of open-source behavioral analysis tools, and discusses how this emergent technology facilitates behavioral quantification in rodent research.

Deep Learning Derived Object Detection and Tracking Technology Based on Sensor Fusion of Millimeter-Wave Radar/Video and Its Application on Embedded Systems

This paper proposes a deep learning-based mmWave radar and RGB camera sensor early fusion method for object detection and tracking and its embedded system realization for ADAS applications. The proposed system can be used not only in ADAS systems but also to be applied to smart Road Side Units (RSU) in transportation systems to monitor real-time traffic flow and warn road users of probable dangerous situations. As the signals of mmWave radar are less affected by bad weather and lighting such as cloudy, sunny, snowy, night-light, and rainy days, it can work efficiently in both normal and adverse conditions. Compared to using an RGB camera alone for object detection and tracking, the early fusion of the mmWave radar and RGB camera technology can make up for the poor performance of the RGB camera when it fails due to bad weather and/or lighting conditions. The proposed method combines the features of radar and RGB cameras and directly outputs the results from an end-to-end trained deep neural network. Additionally, the complexity of the overall system is also reduced such that the proposed method can be implemented on PCs as well as on embedded systems like NVIDIA Jetson Xavier at 17.39 fps.

Multi-Stage Visual Tracking With Siamese Anchor-Free Proposal Network

The austere challenge of visual object tracking is to find the target to be tracked in various noise interference and obtain its accurate bounding box coordinates. Recently, the object tracking technology based on the Siamese network has made great breakthroughs, and more and more Siamese network trackers have been proposed with superior performance. They still have some shortcomings. To this end, a new Multi-Stage visual tracking algorithm with Siamese Anchor-Free Proposal Network (MS-SiamAFPN) is proposed in this paper. The algorithm is a three-stage Siamese network tracker composed of Feature Extraction and Fusion (FEF) sub-network, Classification and Regression (CR) sub-network, Validation and Regression (VR) sub-network in series. Firstly, the Anchor-Free Proposal Network (AFPN) module is designed in the CR stage, which can make full use of positive and negative samples for training while reducing neural network parameters. Secondly, aim to achieve better robustness and recognizability in the VR stage, on the one hand, a novel Feature Purification (FP) module is designed, which can automatically select the important channels, and extract the features of irregular regions on the input fusion features, so as to strengthen the representation ability of image features. On the other hand, the target recognition and position regression are regarded as different processing tasks, and the recognition score and position fine-tuning of candidate targets are obtained by newly designing the Dual-Branch Network (DBN) structure, thereby avoiding feature ambiguity. Due to the synergy of the above these innovations, MS-SiamAFPN has obtained a large performance improvement, and achieved SOTA performance in multiple public dataset benchmarks.

3-D Vehicle Detection Enhancement Using Tracking Feedback in Sparse Point Clouds Environments

In recent years, vehicle detection in intelligent transportation systems using 3D LIDAR point clouds based on deep neural networks has made substantial progress. However, when the point clouds are very sparse, the detection model cannot generate proposals efficiently, resulting in false negative results. Considering that the object tracking technology accurately predicts vehicles based on historical measurements and motion models, and these prediction results can become proposals for object detection. Therefore, this paper proposes a novel object detection paradigm based on tracking feedback to address the false negative problem based on sparse point clouds. According to the distribution of the state vector from the Kalman prediction, multiple proposals are sampled and fed back to the second stage of two-stage detection models. After regression and non-maximum suppression, the false negative results can be effectively reduced. This method enhances the vehicle detection capability of classical neural networks. Comparing the recall metric of multiple detection models at different distances in the public KITTI and nuSences datasets, the proposed method can promote up to 5.31% compared to the previous method, which reflects the effectiveness and versatility of the proposed method.