Real-time Vehicle Tracking Research Articles

Proposing an Efficient Deep Learning Algorithm Based on Segment Anything Model for Detection and Tracking of Vehicles through Uncalibrated Urban Traffic Surveillance Cameras

In this study, we present a novel approach leveraging the segment anything model (SAM) for the efficient detection and tracking of vehicles in urban traffic surveillance systems by utilizing uncalibrated low-resolution highway cameras. This research addresses the critical need for accurate vehicle monitoring in intelligent transportation systems (ITS) and smart city infrastructure. Traditional methods often struggle with the variability and complexity of urban environments, leading to suboptimal performance. Our approach harnesses the power of SAM, an advanced deep learning-based image segmentation algorithm, to significantly enhance the detection accuracy and tracking robustness. Through extensive testing and evaluation on two datasets of 511 highway cameras from Quebec, Canada and NVIDIA AI City Challenge Track 1, our algorithm achieved exceptional performance metrics including a precision of 89.68%, a recall of 97.87%, and an F1-score of 93.60%. These results represent a substantial improvement over existing state-of-the-art methods such as the YOLO version 8 algorithm, single shot detector (SSD), region-based convolutional neural network (RCNN). This advancement not only highlights the potential of SAM in real-time vehicle detection and tracking applications, but also underscores its capability to handle the diverse and dynamic conditions of urban traffic scenes. The implementation of this technology can lead to improved traffic management, reduced congestion, and enhanced urban mobility, making it a valuable tool for modern smart cities. The outcomes of this research pave the way for future advancements in remote sensing and photogrammetry, particularly in the realm of urban traffic surveillance and management.

VegaEdge: Edge AI confluence for real-time IoT-applications in highway safety

Traditional highway safety and monitoring solutions, reliant on surveillance cameras, face limitations due to their dependence on high-speed internet connectivity and the remote processing of Artificial Intelligence (AI) algorithms. This reliance introduces latency, undermining the real-time detection and analysis crucial for highway applications. The fusion of AI with the Internet of Things (IoT) opens new avenues for highway safety and surveillance innovation. Yet, most existing solutions are confined to vehicle detection and tracking, hindered by edge-IoT platforms’ limited power and processing capabilities. Addressing these limitations, this paper presents VegaEdge, an AI framework optimized for edge-IoT devices capable of real-time vehicle detection and tracking, trajectory forecasting, and identifying anomalous driving behaviors, such as road departures, sudden stops, and hazardous merges. A novel lightweight anomaly detection algorithm based on trajectory prediction is used for identifying hazardous driving on highways. VegaEdge demonstrates its versatility and efficiency across various traffic conditions and roadway configurations and has been evaluated on platforms like the Nvidia Jetson Orin and Xavier NX. The Nvidia Jetson Orin processes up to 738 trajectories per second and detects up to 140 vehicles in a single frame. Additionally, the Carolinas Anomaly Dataset (CAD) an extension of the Carolinas Highway Dataset (CHD) is introduced. While CHD consists of standard highway vehicle videos and trajectories, CAD includes video data of anomalous driving behaviors, providing a crucial resource for enhancing anomaly detection algorithms. CAD is available at https://github.com/TeCSAR-UNCC/Carolinas_Dataset#chd-anomaly-test-set.

Facial Recognition Technology in Policing and Security—Case Studies in Regulation

Technology-enabled state surveillance has evolved rapidly to allow real-time remote tracking and surveillance of people and vehicles and the aggregation of vast amounts of data on people and their movements, networks, and relationships. Facial recognition technology (FRT) comprises a suite of technologies that allows verification, identification, and categorisation by analysing a person’s facial image. Such technologies impact fundamental rights, such as privacy, freedom of expression, and freedom of assembly, but can also be used to detect, investigate, and deter serious crime and harm and to counter threats to security, thus promoting collective interests in security and public safety. These impacts have been considered in terms of scholarship and advocacy, but the shape of principled regulation is less well traversed. This contribution examines three contemporary case studies of the regulation of FRT in policing and security to analyse the challenges in regulating this technology.

Video Processing Based Tracking and Vehicle Identification

Video surveillance and analysis have become integral components of various domains such as security, traffic management, and urban planning. However, effective tracking and identification of vehicles in video streams remain challenging due to environmental factors, occlusions, and complex motion patterns. This research proposes a novel approach leveraging YOLOv5, a state-of-the-art object detection algorithm, for real-time vehicle tracking and identification. By integrating YOLOv5 with advanced video processing techniques, including preprocessing for enhancing video quality and Kalman filtering for object tracking, the proposed system achieves improved accuracy and robustness in diverse scenarios. Experimental results demonstrate the effectiveness of the approach, showcasing high accuracy in vehicle tracking and reliable identification performance. The findings suggest significant potential for practical applications in enhancing video surveillance systems for better security and traffic management. Additionally, avenues for future research are discussed to further enhance the capabilities of video-based vehicle tracking and identification systems

Intelligent Traffic System for Urban Condition using Real-time Vehicle Tracking

Intelligent Traffic System for Urban Condition using Real-time Vehicle Tracking

Intelligent Traffic System for Urban Conditions Using Real-time Vehicle Tracking

Intelligent Traffic System for Urban Conditions Using Real-time Vehicle Tracking

Sybil Attacks Detection and Traceability Mechanism Based on Beacon Packets in Connected Automobile Vehicles.

Connected Automobile Vehicles (CAVs) enable cooperative driving and traffic management by sharing traffic information between them and other vehicles and infrastructures. However, malicious vehicles create Sybil vehicles by forging multiple identities and sharing false location information with CAVs, misleading their decisions and behaviors. The existing work on defending against Sybil attacks has almost exclusively focused on detecting Sybil vehicles, ignoring the traceability of malicious vehicles. As a result, they cannot fundamentally alleviate Sybil attacks. In this work, we focus on tracking the attack source of malicious vehicles by using a novel detection mechanism that relies on vehicle broadcast beacon packets. Firstly, the roadside units (RSUs) randomly instruct vehicles to perform customized key broadcasting and listening within communication range. This allows the vehicle to prove its physical presence by broadcasting. Then, RSU analyzes the beacon packets listened to by the vehicle and constructs a neighbor graph between the vehicles based on the customized particular fields in the beacon packets. Finally, the vehicle's credibility is determined by calculating the edge success probability of vehicles in the neighbor graph, ultimately achieving the detection of Sybil vehicles and tracing malicious vehicles. The experimental results demonstrate that our scheme achieves the real-time detection and tracking of Sybil vehicles, with precision and recall rates of 98.53% and 95.93%, respectively, solving the challenge of existing detection schemes failing to combat Sybil attacks from the root.

Enhanced D-CNN architecture and centroid-based algorithm for real-time vehicle tracking and accident detection from surveillance videos

In this new era of intelligence and automation, it is important to develop intelligent software to analyse traffic data and detect abnormal activities occurring in the public. Information from GPS, Surveillance cameras, traffic management systems etc will be helpful for the researchers to develop such algorithms. In this research work, we propose a method to detect traffic accidents and used a deep convolutional neural network (D-CNN) and Centroid based vehicle tracking algorithm for vehicle detection. Overlapping bounding boxes and speed of the vehicle are considered for collision detection. The vehicle is tracked using a centroid tracking algorithm to find acceleration, speed and trajectory values of each vehicle in the continuous frames. The trajectory and angle change after the collision can be used to classify the accidents. The result shows a detection accuracy of 99% in such a way outperforms the other latest methods. The results from the proposed method can be used in several accident reconstruction softwares like PC crash, ARPro etc.

Vehicle Tracking System for Small Scale Areas Using Wireless Sensor Network

A real-time vehicle tracking system is designed for specific covering zones based on wireless sensor network (WSN) technology. In this designed WSN infrastructure the location of the vehicles is tracked using a Neo-6MV2 UBLOX GPS module which is placed on the vehicles. Furthermore, the Enhanced ShockBurst protocol is employed to transmit wirelessly acquired location data to a master/center (destination) node using the NRF24101+PA LNA modules. The location information of the vehicle is graphically represented for a security center using an ADO.net-based desktop application. It is used to record the vehicle location information at certain time intervals (minutes) in the MSSQL database. This system intimates the system administrator about the long ques/waiting time of vehicles outside the premeditated area. After the successful deployment of the proposed WSN system, it has been substantiated that the proposed system can be used as an alternative to other wireless network infrastructures like WIFI or GSM for the small-scale areas vehicle tracking.

Digital Tracks: Investigating the Integration of IoT in Modern Public Transport

The use of the Internet of Things in public transportation has fundamentally changed how we engage with and utilize transportation systems. IoT incorporates sensors, communication devices, and data analytics into vehicles and infrastructure to improve the effectiveness, safety, and convenience of public transport for passengers and service providers. This overview discusses the different uses of IoT in public transport such as real-time vehicle tracking, predictive maintenance, intelligent ticketing systems, and passenger safety features. It also evaluates the difficulties and possibilities linked with the widespread implementation of IoT in this sector while providing perspectives on the future development of connected urban mobility.

Integrating YOLOv8 with Fuzzy Logic System: A Novel Hybrid Approach for Efficient Parking Slot Availability Management

In urban areas, the challenge of finding parking spaces has become a significant concern, leading to congestion, wasted time, and increased pollution. Traditional parking management systems often lack the efficiency needed to address this issue adequately. In this paper, a novel approach was proposed to smart parking management that integrates the YOLOv8 model and fuzzy logic system. YOLOv8, a state-of-the-art object detection algorithm, enables real-time detection and tracking of vehicles within parking lots. By utilizing YOLOv8, the system can accurately identify vacant parking spaces in a timely manner. Furthermore, fuzzy logic was employed to enhance decision-making in selecting the optimal parking slot for users. Fuzzy logic enables the system to consider various factors such as proximity to the destination, parking space size, and distance from the entrance. By incorporating fuzzy logic into the decision-making process, the system can provide personalized recommendations tailored to individual user preferences and parking requirements. Based on the fuzzy inputs namely distance from entrance, proximity to exit and space, the system analyzes the best parking slot and assigns “rank” which is also fuzzy output. The decision can be made based on the rank provided to every slot of the parking lot. Slots with the highest rank should be preferred for parking because they are more suitable as they provide ease to parking the cars and can be suitable to customized needs of the users. The model can be deployed with LCD screens at various parking lots in order to save fuel and time of the commuters.

Real-time vehicle detection system on the highway

Locating and classifying different types of vehicles is a vital element in numerous applications of automation and intelligent systems ranging from traffic surveillance to vehicle identification, with deep learning models now dominating the field of vehicle detection. However, vehicle detection in Bangladesh remains a relatively unexplored research lacuna. One of the main goals of vehicle detection is its real-time application, with “You Only Look Once” (YOLO) models proving to be the most effective. This paper compared real-time vehicle highway detection systems using YOLOv4, Faster R-CNN and SSD algorithms to determine the best performance. A vehicle detection and tracking system was also developed that improved highway safety. Vehicle trials compared the real-time performances of the YOLO, Faster R-CNN and SSD algorithms in detecting and tracking highway vehicles by measuring precision, recall, F1-score and operating speed. Models for each algorithm were constructed and each model was trained and tested, with performance measured using a confusion matrix. This statistical tool assessed the efficiency of the system using a prepared test dataset and evaluated the results using appropriate indicators such as real-time road lines, traffic signs and vehicle detection false positive rates. Results showed that the YOLOv4 algorithm outperformed Faster R-CNN and SSD in real-time vehicle detection and tracking on highways. YOLOv4 also processed the results more quickly and proved superior in detecting and tracking objects in real time. The Faster R-CNN algorithm gave high object detection, tracking accuracy and recall while reducing the number of locations needing detection, with the SSD algorithm providing high precision, recall and good image detection results.

Efficient Roundabout Supervision: Real-Time Vehicle Detection and Tracking on Nvidia Jetson Nano

In recent years, a significant number of people in Morocco have been commuting daily to Casablanca, the country’s economic capital. This heavy traffic flow has led to congestion and accidents during certain times of the day as the city’s roads cannot handle the high volume of vehicles passing through. To address this issue, it is essential to expand the infrastructure based on accurate traffic-flow data. In collaboration with the municipality of Bouskoura, a neighboring city of Casablanca, we proposed installing a smart camera on the primary route connecting the two cities. This camera would enable us to gather accurate statistics on the number and types of vehicles crossing the road, which can be used to adapt and redesign the existing infrastructure. We implemented our system using the YOLOv7-tiny object detection model to detect and classify the various types of vehicles (such as trucks, cars, motorcycles, and buses) crossing the main road. Additionally, we used the Deep SORT tracking method to track each vehicle appearing on the camera and to provide the total number of each class for each lane, as well as the number of vehicles passing from one lane to another. Furthermore, we deployed our solution on an embedded system, specifically the Nvidia Jetson Nano. This allowed us to create a compact and efficient system that is capable of a real-time processing of camera images, making it suitable for deployment in various scenarios where limited resources are required. Deploying our solution on the Nvidia Jetson Nano showed promising results, and we believe that this approach could be applied in similar traffic-surveillance projects to provide accurate and reliable data for better decision-making.

Real-time vehicle detection and tracking based on the combination of YOLOv7 and ByteTrack

Real-time tracking of vehicles is important for monitoring whether the roads are congested or not. How to achieve and maintain a high frame rate is a key problem to be solved in practical applications. In recent years, SORT, BOT-SORT [1] and other state-of-the-art target tracking algorithms have achieved fruitful results in target tracking tasks. The author combines YOLOv7(You Only Look Once v7) with bytetrack and compares the frame rate with some popular algorithms like Deepsort and bytetrack in real-time tracking to demonstrate that YOLOv7-bytetrack is more suitable for real-time detection, tracking of vehicles.

WatchDog: Real-time Vehicle Tracking on Geo-distributed Edge Nodes

Vehicle tracking, a core application to smart city video analytics, is becoming more widely deployed than ever before thanks to the increasing number of traffic cameras and recent advances in computer vision and machine-learning. Due to the constraints of bandwidth, latency, and privacy concerns, tracking tasks are more preferable to run on edge devices sitting close to the cameras. However, edge devices are provisioned with a fixed amount of computing budget, making them incompetent to adapt to time-varying and imbalanced tracking workloads caused by traffic dynamics. In coping with this challenge, we propose WatchDog, a real-time vehicle tracking system that fully utilizes edge nodes across the road network. WatchDog leverages computer vision tasks with different resource-accuracy tradeoffs, and decomposes and schedules tracking tasks judiciously across edge devices based on the current workload to maximize the number of tasks while ensuring a provable response time-bound at each edge device. Extensive evaluations have been conducted using real-world city-wide vehicle trajectory datasets, achieving exceptional tracking performance with a real-time guarantee.

A Novel Social Distancing Approach for Limiting the Number of Vehicles in Smart Buildings Using LiFi Hybrid-Network

The coronavirus (COVID-19) has arisen as one of the most severe problems due to its ongoing mutations as well as the absence of a suitable cure for this virus. The virus primarily spreads and replicates itself throughout huge groups of individuals through daily touch, which regretfully can happen in several unanticipated way. As a result, the sole viable attempts to constrain the spread of this new virus are to preserve social distance, perform contact tracing, utilize suitable safety gear, and enforce quarantine measures. In order to control the virus's proliferation, scientists and officials are considering using several social distancing models to detect possible diseased individuals as well as extremely risky areas to sustain separation and lockdown procedures. However, models and systems in the existing studies heavily depend on the human factor only and reveal serious privacy vulnerabilities. In addition, no social distancing model/technique was found for monitoring, tracking, and scheduling vehicles for smart buildings as a social distancing approach so far. In this study, a new system design that performs real-time monitoring, tracking, and scheduling of vehicles for smart buildings is proposed for the first time named the social distancing approach for limiting the number of vehicles (SDA-LNV). The proposed model employs LiFi technology as a wireless transmission medium for the first time in the social distance (SD) approach. The proposed work is considered as Vehicle-to-infrastructure (V2I) communication. It might aid authorities in counting the volume of likely affected people. In addition, the proposed system design is expected to help reduce the infection rate inside buildings in areas where traditional social distancing techniques are not used or applicable.

FRCNN-Based Reinforcement Learning for Real-Time Vehicle Detection, Tracking and Geolocation from UAS

In the last few years, uncrewed aerial systems (UASs) have been broadly employed for many applications including urban traffic monitoring. However, in the detection, tracking, and geolocation of moving vehicles using UAVs there are problems to be encountered such as low-accuracy sensors, complex scenes, small object sizes, and motion-induced noises. To address these problems, this study presents an intelligent, self-optimised, real-time framework for automated vehicle detection, tracking, and geolocation in UAV-acquired images which enlist detection, location, and tracking features to improve the final decision. The noise is initially reduced by applying the proposed adaptive filtering, which makes the detection algorithm more versatile. Thereafter, in the detection step, top-hat and bottom-hat transformations are used, assisted by the Overlapped Segmentation-Based Morphological Operation (OSBMO). Following the detection phase, the background regions are obliterated through an analysis of the motion feature points of the obtained object regions using a method that is a conjugation between the Kanade–Lucas–Tomasi (KLT) trackers and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering. The procured object features are clustered into separate objects on the basis of their motion characteristics. Finally, the vehicle labels are designated to their corresponding cluster trajectories by employing an efficient reinforcement connecting algorithm. The policy-making possibilities of the reinforcement connecting algorithm are evaluated. The Fast Regional Convolutional Neural Network (Fast-RCNN) is designed and trained on a small collection of samples, then utilised for removing the wrong targets. The proposed framework was tested on videos acquired through various scenarios. The methodology illustrates its capacity through the automatic supervision of target vehicles in real-world trials, which demonstrates its potential applications in intelligent transport systems and other surveillance applications.

Scale Invariant low frame rate tracking

The cameras used for road surveillance present low image quality and significant variability of objects’ scale, making real-time vehicle detection and tracking challenging. This paper proposes Scale Invariant Low Frame Rate Tracking, called SILFT, a new methodology to track vehicles in most surveillance systems whose frame rate and resolution are low. This architecture uses the fusion of a dense optical flow with object detection in a 6-step pipeline. The detections are masks for the optical flow that later will be used for finding the object correspondence between frames, making it effective in low frame rate sequences with large object scale variability. SILFT achieved average precision for detection of 65.97%, surpassing the YOLO and FASTER R-CNN models in the proposed database. For the tracking task, SILFT achieved a PR-MOTA of 0.45, whereas the YOLO model with intersection over union tracking achieved 0.13 in the proposed dataset.

Applying Ternion Stream DCNN for Real-Time Vehicle Re-Identification and Tracking across Multiple Non-Overlapping Cameras

The increase in security threats and a huge demand for smart transportation applications for vehicle identification and tracking with multiple non-overlapping cameras have gained a lot of attention. Moreover, extracting meaningful and semantic vehicle information has become an adventurous task, with frameworks deployed on different domains to scan features independently. Furthermore, approach identification and tracking processes have largely relied on one or two vehicle characteristics. They have managed to achieve a high detection quality rate and accuracy using Inception ResNet and pre-trained models but have had limitations on handling moving vehicle classes and were not suitable for real-time tracking. Additionally, the complexity and diverse characteristics of vehicles made the algorithms impossible to efficiently distinguish and match vehicle tracklets across non-overlapping cameras. Therefore, to disambiguate these features, we propose to implement a Ternion stream deep convolutional neural network (TSDCNN) over non-overlapping cameras and combine all key vehicle features such as shape, license plate number, and optical character recognition (OCR). Then jointly investigate the strategic analysis of visual vehicle information to find and identify vehicles in multiple non-overlapping views of algorithms. As a result, the proposed algorithm improved the recognition quality rate and recorded a remarkable overall performance, outperforming the current online state-of-the-art paradigm by 0.28% and 1.70%, respectively, on vehicle rear view (VRV) and Veri776 datasets.

Real-time vehicle identification and tracking during agricultural master-slave follow-up operation using improved YOLO v4 and binocular positioning

The identification and positioning of a master is essential for the master-slave cooperative operation of agricultural machinery. This study aimed to develop an agricultural vehicle dynamic identification and tracking method for agricultural master-slave follow-up operation using improved YOLO v4 and binocular positioning. The regular pruning algorithm was used to trim the original YOLO v4 channel to achieve a fast and accurate identification of master vehicle. The principle of binocular vision positioning was used to calculate the position of the master. The method (IYO-BPO) proposed in this study fused target detection and binocular vision positioning together, which was used to identify and track the master vehicle in real time. To evaluate the performance of the developed method, RTK-GPS and a gyroscope were installed on the master vehicle to obtain the reference position and heading angle. Identification and tracking experiments of both the linear and S-shaped movement of the master were conducted. The RMS errors were 0.067 m, 0.203 m, and 2.602° in terms of the longitudinal, lateral, and heading angle deviation, respectively, when the master moved along a straight line. The results show that the master vehicle could be identified and tracked by the IYO-BPO correctly and effectively.