Improve Detection and Tracking of Pedestrian Subclasses by Pre-Trained Models (original) (raw)
Related papers
Information ISSN:2078-2489, 2023
Pedestrian tracking and detection have become critical aspects of advanced driver assistance systems (ADASs), due to their academic and commercial potential. Their objective is to locate various pedestrians in videos and assign them unique identities. The data association task is problematic, particularly when dealing with inter-pedestrian occlusion. This occurs when multiple pedestrians cross paths or move too close together, making it difficult for the system to identify and track individual pedestrians. Inaccurate tracking can lead to false alarms, missed detections, and incorrect decisions. To overcome this challenge, our paper focuses on improving data association in our pedestrian detection system’s Deep-SORT tracking algorithm, which is solved as a linear optimization problem using a newly generated cost matrix. We introduce a set of new data association cost matrices that rely on metrics such as intersections, distances, and bounding boxes. To evaluate trackers in real-time, we use YOLOv5 to identify pedestrians in images. We also perform experimental evaluations on the Multiple Object Tracking 17 (MOT17) challenge dataset. The proposed cost matrices demonstrate promising results, showing an improvement in most MOT performance metrics compared to the default intersection over union (IOU) data association cost matrix.
OPTIMIZING PEDESTRIAN TRACKING FOR ROBUST PERCEPTION WITH YOLOv8 AND DEEPSORT
Applied Computer Science, 2024
Multi-object tracking is a crucial aspect of perception in the area of computer vision, widely used in autonomous driving, behavior recognition, and other areas. The complex and dynamic nature of environments, the ever-changing visual features of people, and the frequent appearance of occlusion interactions all impose limitations on the efficacy of existing pedestrian tracking algorithms. This results in suboptimal tracking precision and stability. As a solution, this article proposes an integrated detector-tracker framework for pedestrian tracking. The framework includes a pedestrian object detector that utilizes the YOLOv8 network, which is regarded as the latest state-of-the-art detector, that has been established. This detector provides an ideal detection base to address limitations. Through the combination of YOLOv8 and the DeepSort tracking algorithm, we have improved the ability to track pedestrians in dynamic scenarios. After conducting experiments on publicly available datasets such as MOT17 and MOT20, a clear improvement in accuracy and consistency was demonstrated, with MOTA scores of 63.82 and 58.95, and HOTA scores of 43.15 and 41.36, respectively. Our research highlights the significance of optimizing object detection to unleash the potential of tracking for critical applications like autonomous driving.
Real-Time Pedestrians Detection by YOLOv5
2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2021
Real-time detection of objects is receiving growing attention. The pedestrian is the most critical object that needs to be detecting and tracking by autonomous vehicles. The major challenges to this mission are caused by the difference in objects like pedestrians in age, gender, clothing, lighting, backgrounds, and occlusion. This paper starts with a brief introduction of problem-related to pedestrians, objects detection framework and Neural Networks Algorithms, and Real-Time Systems. And we focus on pedestrians as moving objects that need to detect, track, and solve problems related to computer vision. And based on our study we present a suggested solution for solving problems related to Pedestrians Detection in real-time particular. These techniques aim to be used in many applications such as Autonomous Vehicles, and Advanced Driver Assistance Systems (ADAS).
Pedestrian and Vehicle Detection System Based on Deep Learning
IJSES, 2024
This paper discusses the application of deep learning technology in the field of pedestrian and vehicle detection. Pedestrian and vehicle detection is an important problem in computer vision, which has a wide range of practical applications. We review YOLO algorithms and their applications in pedestrian and vehicle detection. The selection and labeling methods of data sets, model training and optimization strategies, and the application of evaluation indexes are discussed. Finally, we analyze current technology challenges and future directions, including improved detection accuracy, real-time performance, and further improvements in the generalization ability of complex scenarios.
Computer vision and deep learning techniques for pedestrian detection and tracking: A survey
Neurocomputing, 2018
Pedestrian detection and tracking have become an important field in the computer vision research area. This growing interest, started in the last decades, might be explained by the multitude of potential applications that could use the results of this research field, e.g. robotics, entertainment, surveillance, care for the elderly and disabled, and content-based indexing. In this survey paper, vision-based pedestrian detection systems are analysed based on their field of application, acquisition technology, computer vision techniques and classification strategies. Three main application fields have been individuated and discussed: video surveillance, human-machine interaction and analysis. Due to the large variety of acquisition technologies, this paper discusses both the differences between 2D and 3D vision systems, and indoor and outdoor systems. The authors reserved a dedicated section for the analysis of the Deep Learning methodologies, including the Convolutional Neural Networks in pedestrian detection and tracking, considering their recent exploding adoption for such a kind systems. Finally, focusing on the classification point of view, different Machine Learning techniques have been analysed, basing the discussion on the classification performances on different benchmark datasets. The reported results highlight the importance of testing pedestrian detection systems on different datasets to evaluate the robustness of the computed groups of features used as input to classifiers.
Pedestrian detection system based on deep learning
International Journal of Advances in Applied Sciences (IJAAS), 2022
Pedestrian detection is a rapidly growing field of computer vision with applications in smart cars, surveillance, automotive safety, and advanced robotics. Most of the success of the last few years has been driven by the rapid growth of deep learning, more efficient tools capable of learning semantic, high-level, deeper features of images are proposed. In this article, we investigated the task of pedestrian detection on roads using models based on convolutional neural networks. We compared the performance of standard state-of-the-art object detectors like Faster region-based convolutional network (R-CNN), single shot detector (SSD), and you only look once, version 3 (YOLOv3). Results show that YOLOv3 is the best object detection model than others for pedestrians in terms of detection and time prediction. This is an open access article under the CC BY-SA license.
Comparison and study of Pedestrian Tracking using Deep SORT and state of the art detectors
2021
Object Tracking is becoming very popular these days in the computer vision field. It is the process of tracking an object across a sequence of frames. Deep Sort is a very fast and powerful tracking algorithm. It has a practical way of approaching multiple object tracking problems. It uses the appearance information to track objects through occlusions and thereby reducing the identity switches. Performance evaluation and comparison have been performed on pedestrian tracking using the Deep Sort algorithm in conjunction with the various state-of-the-art object detectors: YOLO, SSD and FasterRCNN. Criteria for Evaluation, datasets used for evaluation, along with the quantitative results have been described and discussed in this work.
Advances in Artificial Intelligence and Machine Learning
The World Health Organization estimates that well in excess of one million of lives are lost each year due to road traffic accidents. Since the human factor is the preeminent cause behind the traffic accidents, the development of reliable Advanced Driver Assistance Systems (ADASs) and Autonomous Vehicles (AVs) is seen by many as a possible solution to improve road safety. ADASs rely on the car perception system input that consists of camera(s), LIDAR and/or radar to detect pedestrians and other objects on the road. Hardware improvements as well as advances done in employing Deep Learning techniques for object detection popularized the Convolutional Neural Networks in the area of autonomous driving research and applications. However, the availability of quality and large datasets continues to be a most important contributor to the Deep Learning based model’s performance. With this in mind, this work analyses how a YOLO-based object detection architecture responded to limited data ava...
Autonomous Pedestrian Detection model for Crowd Surveillance using Deep Learning Framework
Pedestrian detection is a key ability required by most computer visions and crowd surveillance applications, with several applications such as person identification, person count and tracking. The number of techniques to identifying pedestrians in images has gradually increased in recent years, even with the significant advances in the state-of-the-art D based framework for object detection model. The research in the field of object detection and image classification has made a stride in the level of accuracy greater than 99% and the level of granularity. A powerful Object Detector, specifically designed for high-end surveillance applications, is needed that will not only position the bounding box and label it, but will also return their relative positions. The size of these bounding boxes can vary depending on the object and how it interacts with the physical world. To address these requirements, an extensive evaluation of the state-of-the-art algorithms has been presented in this ...
Pedestrian Detection Based on Deep Learning
International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2022
Pedestrian detection is most commonly employed in autonomous driving circumstances that necessitate rapid detection. It is also very useful for the purpose of video surveillance and other similar purpose. The primary goal of this project is to create a system that recognises pedestrians from video, or a stream of video sent to the system in the form of previously recorded video or real-time camera input. Bounding boxes will be drawn around the things that the system has spotted along with the confidence score of prediction. This project employs Python programming and the YOLO machine learning technology.