Real-Time Multi-Camera Tracking for Vehicles in Congested, Low-Velocity Environments: A Case Study on Drive-Thru Scenarios

Software was developed in Python for the digital processing of object images before their detection using the You Only Look Once (YOLO) artificial neural network. Detection was carried out on object images, specifically vehicles and other road users. The preprocessing of images was performed through histogram equalization and local contrast enhancement. The original images were read from video cameras or graphic files. Image detection was performed using the medium-sized YOLO convolutional neural network model, YOLOv8m. As a result of detection, the studied objects, particularly cars, were highlighted with rectangular bounding boxes. To evaluate the accuracy of object detection, several metrics (parameters) were used: Precision, Recall, Intersection over Union (IoU), F1, and Average Precision (AP). The YOLO network was pre-trained on the Common Objects in Context dataset. The YOLO neural network returns the object recognition confidence, the coordinates of its center (x, y) on the image, and its width and height (w, h). The detected objects are marked with rectangular bounding boxes. The positioning of objects in the images was manually performed using the Roboflow tool, which allows for accurate spatial positioning of each object. The study of the impact of image preprocessing on the accuracy of object detection by the YOLO network was conducted using a typical traffic scene image. After histogram equalization, the histogram becomes more symmetrical and uniform, improving the visual quality of both dark and bright areas. This led to improved object detection accuracy across almost all metrics. The increase in detection accuracy by the IoU parameter is 0.169. The summary improvement in detection accuracy by the IoU, F1, AP parameters is 0.502. It was shown that after image preprocessing, detection accuracy increased, and all vehicles were correctly detected. The developed software can be used in various computer vision systems as well as in Internet of Things systems for remote monitoring and control.

Lesion segmentation in dermoscopic images significantly enhances the diagnostic performance of AI-based classification models. However, conventional methods often require pixel-level annotations, which are resource-intensive and prone to errors caused by external artifacts, such as hair and skin markings. We propose a hybrid framework called SAM-enhanced YOLO, which integrates the Segment Anything Model (SAM) with You Only Look Once (YOLO) for precise pixel-level segmentation. This method combines YOLO's efficient lesion localization with SAM's advanced zero-shot segmentation capabilities. To further validate the framework, we compared it against traditional methods, including GrabCut and Otsu's thresholding, as well as SAM used without YOLO (SAM-only). For SAM-only, lesion segmentation was initialized at the image center to simulate a typical dermoscopic imaging setup. SAM-enhanced YOLO demonstrated superior segmentation performance, achieving an Intersection over Union (IoU) of 0.738 and an F1-score (the harmonic mean of precision and recall) of 0.833, compared to 0.578 and 0.683 with SAM-only, respectively. This represents a 28% improvement in IoU and a 22% improvement in F1-score compared to SAM-only. The results were consistent across lesion shapes and contrast conditions, with SAM-enhanced YOLO exhibiting the lowest variability and highest robustness among the evaluated methods. By reducing the need for pixel-level annotations and outperforming both standalone SAM and traditional methods, SAM-enhanced YOLO provides a scalable and resource-efficient solution for dermoscopic lesion segmentation. This framework holds significant potential for improving diagnostic workflows in clinical and resource-limited settings.

Advanced Driver Assistance Systems (ADAS) and Collision Avoidance Systems (CAS) are the primary modules of modern human-centric and autonomous driving applications, such as forward and rear-end collision warnings. To enhance the performance of ADAS and CAS systems in foggy weather, an Efficient and Cost-Effective Vehicle Detection and Tracking with Driver Assistance (ECE-VDTDA) system is proposed. The proposed ECE-VDTDA system comprises vehicle detection, tracking, and driver assistance modules. An optimized SimYOLO-V5s_WIOU vehicle detection algorithm is proposed, based on the SimSPPF module, the baseline You Only Look Once (YOLO) algorithm (YOLO-V5s), and the Wise Intersection Over Union (WIOU) localization loss function. State-of-the-art Deep-SORT, Strong-SORT, and optimized Deep-SORT algorithms are utilized for vehicle tracking. The vehicle detection and tracking performance of the ECE-VDTDA system is rigorously evaluated on DAWN, foggy driving, foggy cityscapes, BDD100K, web-collected, and self-collected foggy weather datasets. Optimized SimYOLO-V5s_WIOU algorithm outperformed on the foggy driving dataset with a 17.45% increase in mAP50, and foggy cityscapes dataset with a 0.32%, 1.05%, 1.58%, 2%, 0.54% increase in the multiclass mAP50, mAP50-95, F1 score, precision, and recall scores, respectively, compared to the baseline YOLO-V5s. Furthermore, the SimYOLO-V5s_WIOU algorithm also outperformed the state-of-the-art methods and enables Deep-SORT, Strong-SORT, and optimized Deep-SORT vehicle tracking algorithms to track vehicles with high confidence. The driver assistance module of the ECE-VDTDA system helps prevent imminent road collisions in foggy weather by estimating distance, speed, and time-to-collision and by issuing timely collision warnings. The experimental results demonstrate the robustness and computational efficiency of the proposed ECE-VDTDA system.

YOLO-YCbCr based smoke segmentation method for fire detection was proposed in this study to enhance smoke segmentation performance with reduction in computational cost. The proposed method consists of the deep learning object detection model, You Only Look Once (YOLO), and the color space-based segmentation model, rule-based YCbCr. YOLO is used to detect smoke objects in the input fire images through bounding boxes. The images in the bounding boxes are characterized based on YCbCr color space and the proposed YCbCr rules derived by considering smoke image characteristics segment smoke region. In order to evaluate the smoke segmentation performance, six different fire incident video data were used. The mean intersection over union (IoU) value of the proposed method was improved by approximately 31.3% and 24.5% respectively when compared to the reference models: YOLO-RGB model and YOLO-CIELAB model. It was found that YOLO significantly reduced the erroneous smoke segmentation and YCbCr rules derived from the smoke color features were effective in the smoke segmentation.

Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions. This paper describes our solution to the Track 3 multi-camera vehicle tracking task in 2021 AI City Challenge (AICITY21). This paper proposes a multi-target multi-camera vehicle tracking framework guided by the crossroad zones. The framework includes: (1) Use mature detection and vehicle re-identification models to extract targets and appearance features. (2) Use modified JDE-Tracker (without detection module) to track single-camera vehicles and generate single-camera tracklets. (3) According to the characteristics of the crossroad, the Tracklet Filter Strategy and the Direction Based Temporal Mask are proposed. (4) Propose Sub-clustering in Adjacent Cameras for multi-camera tracklets matching. Through the above techniques, our method obtained an IDF1 score of 0.8095, ranking first on the leaderboard <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> . The code will be released later.

&lt;div class="section abstract"&gt;&lt;div class="htmlview paragraph"&gt;As a basic link of driving behavior in urban roads, vehicle lane changing has a significant impact on traffic flow characteristics and traffic safety, and the automation of lane change is also a key issue to be solved in the field of intelligent driving. In this paper, the research on the automatic lane change control for intelligent vehicles is carried out. The main work is to build the overall structure of the vehicle's automatic lane change behavior, of which the planning and tracking are focused. The strategy of Constant Time Headway (CTH) is used in the lane change decision. The lane change trajectory adopts the model of constant velocity offset plus sine function, and the longitudinal displacement is determined by the vehicle speed when changing lanes. Model Predictive Control (MPC) theory is used to track the trajectory, which optimizes tracking accuracy and vehicle stability and constrains the range and rate of change of vehicle speed and steering angle. By using weighted quadratic cost function, linearity matrix inequality constraints and upper and lower bound constraints, the multi-objective trajectory tracking problem is eventually transformed into a constrained online convex quadratic programming problem. The results of simulation and HIL test show that the scheme of automatic lane change can make the vehicle smoothly complete the lane changing behavior, and the errors can meet the error requirements of lane change. Compared with other controller, the method shows smaller lateral acceleration, stronger robustness and higher control precision during the test. Moreover, the computational time of the proposed MPC controller, implemented using the PXI, is 47.994ms during one sampling period, which can satisfy the real-time requirement.&lt;/div&gt;&lt;/div&gt;

Visual tracking is a fundamental technology in computer vision, with wide-ranging applications in fields such as robotics, autonomous driving, augmented reality, and security systems. A key challenge in these domains is ensuring stable object tracking in dynamic and complex environments. Tracking objects in real-world settings presents difficulties like occlusion, lighting changes, and sudden object movements, all of which demand the development of robust algorithms that can handle such variability effectively. This research introduces a novel single object visual tracking technique that leverages the YOLO (You Only Look Once) object detection model, combined with an adaptive particle filter. By integrating YOLO's precise object detection capabilities with the continuous state estimation offered by particle filters, this approach achieves stable object tracking, even in challenging environments. At the heart of the proposed algorithm is a dynamic fusion of YOLO detection results with image feature-based particle weight updates. When YOLO successfully detects an object, the position and size data of the object are used to adjust the state and weights of the particles, resulting in improved tracking accuracy and quick recovery from events such as sudden movements or occlusions. Conversely, in situations where YOLO detection is unavailable, the algorithm seamlessly transitions to a pure particle filter mode. In this fallback mode, visual features, such as image color histograms, are used to update particle weights, ensuring continuous and robust tracking even during temporary detection failures. The object’s dynamic state is modeled using an 8-dimensional vector, which includes information about position, velocity, size, and size-change rate. This comprehensive state representation enables precise tracking of various object motions and size transformations. Additionally, a Bhattacharyya distance-based weight calculation method is employed to assess particle similarity more effectively. Experimental results demonstrate that the proposed method excels in various challenging scenarios, including those with sudden object movements, partial occlusions, and lighting variations. The algorithm consistently delivers stable tracking, underscoring its robustness and adaptability. The contributions of this research have potential applications in fields such as autonomous driving, SLAM (Simultaneous Localization and Mapping), and augmented reality. Specifically, this technique could enhance pedestrian and vehicle tracking in autonomous driving systems and improve the accuracy of dynamic object tracking and environmental mapping in SLAM. It is also likely to play a key role in real-world applications like person tracking in security systems, player motion analysis in sports, and focused tracking in medical imaging. Future research directions include expanding the method to handle multi-object tracking and optimizing its real-time performance, broadening its applicability. Additionally, further improvements in tracking accuracy and robustness may be achieved by incorporating deep learning-based feature extraction and integrating data from various sensors.

Multi-Target Multi-Camera Tracking (MTMC) has an immense domain of Intelligent Traffic Surveillance System applications. Multifarious tasks manage to apply MTMC trackings, such as crowd analysis and city-scale traffic management. This paper describes our framework using spatial constraints for the Task of the Track 1 multi-camera vehicle tracking in the 2022 AI City Challenge. The framework includes single-camera detection and tracking, vehicle re-identification, and multi-camera track matching. To improve the system&#x2019;s accuracy, we proposed Region-Aware for the precision of vehicle detection and tracking, leading to the effective service of vehicle re-identification models to extract targets and appearance features. We use Crossing-Aware for a tracker to utilize the rich feature to find the tracklets and operate trajectory matching for multi-camera tracklets connection. Finally, the Inter-Camera Matching generated the global IDs for vehicle trajectory. Our method acquired an IDF1 score of 0.8129 on the AI City 2022 Challenge Track 1 public leaderboard.

This paper outlines an FPGA-accelerated perception sub-system for real-time object detection employing the You Only Look Once (YOLO) v5 model. The system uses the Deep Learning Processing Unit (DPU) B4096 implemented on the Xilinx Kria KV260 platform for efficient deep learning inference. The implementation shows a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$7.5 \times$</tex> speedup over traditional CPU solutions, achieving up to 59.94 Frames Per Second (FPS) for the YOLOv5 Nano model and 17.4 FPS for the YOLOv5 Large model. The system further shows high detection accuracy with a mean Average Precision (mAP) of 0.76 and an average Intersection over Union (IoU) of 0.72 for the intelligent traffic perception system. The implementation incorporates optimized data pipelines, quantized models, and high-throughput inference methodologies within the Kria Docker environment, utilizing OpenCV, Xilinx Runtime(XRT), and Vitis AI Runtime (VART). The results highlight that an effective hardware-software co-design approach, combining high throughput, optimal resource utilization, and reliable inference accuracy, significantly enhances the performance of FPGA-based AI (Artificial intelligence) workloads in applications such as surveillance, industrial automation, and production line safety.

Human detection in crowded environments is essential for applications such as surveillance, autonomous navigation, and crowd management. This study examines the performance of various YOLO (You Only Look Once) models in detecting humans. We combined four public human detection datasets to create a comprehensive dataset for crowd detection. Experiments were conducted on YOLOv5, YOLOv8, and YOLOv11 models, employing different architectures and model sizes. Performance was evaluated using mean Average Precision (mAP) at Intersection over Union (IoU) thresholds of 50% (mAP@50) and across 50-95% (mAP@50-95). The results indicate that the YOLOv8m model achieved the highest mAP@50 of 0.944 and mAP@50-95 of 0.697, surpassing larger models such as YOLOv11x, which attained 0.90 and 0.632 respectively. Additionally, other YOLOv8 variants demonstrated superior or comparable performance to their YOLOv5 and YOLOv11 counterparts. These findings highlight the effectiveness of YOLOv8’s optimized structures in delivering accurate and efficient human detection in high-density settings.

This paper proposes a Contextual Action Recognition System for classroom monitoring that integrates spatial and temporal modeling with contextual analysis for enhanced robustness and interpretability. YOLO (You Only Look Once) is used for spatial feature extraction, while ConvLSTM and Temporal Convolutional Network (TCN) capture temporal patterns. An attention-based fusion mechanism adaptively weights their outputs. A hybrid proximity detection approach, combining overlap assessment with Intersection over Union (IoU) thresholding outperforms traditional IoU-based methods, especially in perspectivedistorted scenes. The model achieved strong results: precision of 0.90, recall of 0.87, F 1 -score of 0.86, and $\mathrm{mAP} \text{@} 0.5$ of 0.92. It outperformed baselines like SlowFast and ACRN on datasets including AVA, UCF101-24, and JHMDB-21, demonstrating superior spatial relationship detection.

The feather coverage of a laying hen is an important indicator of both its productivity and welfare. Conventional manual feather scoring procedures are laborious, subjective, and stressful for the hens. Thermography offers a modern alternative to addressing these problems. Thermal cameras capture radiative heat loss, which is comparatively greater Classification from featherless areas. Studies have been conducted to establish a standard temperature range that correlates to specific featherless areas. However, such temperature-based approaches have been inconsistent with each other. In contrast, this study used deep learning techniques to automatically assess dorsal feather scores using thermal images. Thermal images (n = 1575) of the dorsal body of cage-free laying hens with varying degrees of feather damage were captured. Manual feather scoring was performed, classifying the image into a feather score (0–2) according to the increasing severity of feather loss. A total of 1222 images were selected, filtering out images of lower quality. Two types of computer vision models, a classification model and an object detection model, were trained and evaluated. A custom convolutional neural network (CNN) was trained to classify thermal images into feather score categories. Additionally, we trained and optimized You Only Look Once (YOLO) object detection models to detect areas of feather damage and predict the feather score. The CNN model achieved an overall accuracy of 0.81, with high precision for severe feather loss. The YOLO-based object detection model was optimum using YOLO11n, which achieved a precision of 0.81, a recall of 0.73 and a mean average precision (mAP) at 0.5 intersection over union (IoU) of 0.84. Results show the potential of combining thermal imaging with deep learning techniques to perform objective, automatic, and scalable feather scoring procedures. Future studies should focus on data diversity, multiple part scoring, and semantic segmentation for robust performance.

One important task for autonomous driving is the precise detection and recognition of road traffic signs. This research focuses on a comprehensive set of 72 distinct traffic signs that are prevalent on urban roads in China, with the goal of developing an enhanced You Only Look Once (YOLO) network model tailored for this specific task. The modifications include the omission of the terminal convolution module and Conv3 (C3) module within the backbone network. Additionally, the 32-fold downsampling is replaced with a 16-fold downsampling, and a feature fusion module with dimensions of 152 × 152 is introduced in the feature layer. To capture a more encompassing context, a novel hybrid space pyramid pooling module, referred to as Hybrid Spatial Pyramid Pooling Fast (H-SPPF), is introduced. Furthermore, a channel attention mechanism is integrated into the framework, combined with three other improved methodologies. Upon evaluation, the enhanced algorithm demonstrates impressive results, achieving a precision rate of 91.72%, a recall rate of 91.77%, and a mean average precision (mAP) of 93.88% at an intersection over union (IoU) threshold of 0.5. Additionally, the method also achieves an mAP of 75.81% for a variety of IoU criteria between 0.5 and 0.95. These achievements are validated on an augmented dataset established for this study.

Abstract- With the rapid growth of urban populations and the increasing number of vehicles on the road, traffic congestion has become a significant problem in metropolitan areas. Conventional traffic control systems, which rely on pre-set signal timers, often fail to address real-time traffic conditions effectively, leading to inefficient traffic flow, increased fuel consumption, and environmental degradation. The paper “Smart Traffic Control System Based on Traffic Density Using YOLO” introduces a novel approach to address this issue by integrating artificial intelligence and computer vision into traffic management. The proposed system utilizes the YOLO (You Only Look Once) object detection algorithm to detect and classify vehicles in real-time from live video feeds captured at intersections. YOLO, known for its speed and accuracy in object detection tasks, calculates the vehicle density in each direction. Based on the detected density, the system dynamically adjusts the green light duration for each lane, ensuring that the direction with higher traffic receives longer green light periods. This method aims to optimize signal switching and minimize overall vehicle wait time. The paper outlines the complete architecture of the system, which includes modules for video input processing, vehicle detection using YOLO, traffic density computation, and adaptive signal timing control. By leveraging deep learning, the system enhances decision-making capabilities without relying on costly hardware like inductive loops or infrared sensors. This review evaluates the effectiveness and innovation of the proposed system, comparing it with traditional and sensor-based models. It highlights the advantages of using YOLO, such as real-time processing, high accuracy, and scalability. Additionally, the review discusses the system’s limitations, such as dependency on video clarity and environmental conditions, and proposes areas for future enhancement, including integration with cloud computing and edge AI for broader deployment. Keywords- Smart Traffic Control System, YOLO Object Detection, Traffic Density Estimation, Real-Time Traffic Monitoring, Adaptive Traffic Signal Control, Vehicle Classification ( Cars, Bikes, Buses, Trucks, Rikshaws), Intelligent Transportation System.

To investigate highway vehicle lane-changing behavior, we utilized the publicly available naturalistic driving dataset, HighD, to extract the movement data of vehicles involved in lane changes and their proximate counterparts. We employed univariate and multivariate Cox proportional hazards models alongside random survival forest models to analyze the influence of various factors on lane change duration, assess their statistical significance, and compare the performance of multiple random survival forest models. Our findings indicate that several variables significantly impact lane change duration, including the standard deviation of lane-changing vehicles, lane-changing vehicle speed, distance to the following vehicle in the target lane, lane-changing vehicle length, and distance to the following vehicle in the current lane. Notably, the standard deviation and vehicle length act as protective factors, with increases in these variables correlating with longer lane change durations. Conversely, higher lane-changing vehicle speeds and shorter distances to following vehicles in both the current and target lanes are associated with shorter lane change durations, indicating their role as risk factors. Feature variable selection did not substantially improve the training performance of the random survival forest model based on our findings. However, validation set evaluation showed that careful feature variable selection can enhance model accuracy, leading to improved AUC values. These insights lay the groundwork for advancing research in predicting lane-changing behaviors, understanding lane-changing intentions, and developing pre-emptive safety measures against hazardous lane changes.