Abstract
Real-time vehicle monitoring in highways, roads, and streets may provide useful data both for infrastructure planning and for traffic management in general. Even though it is a classic research area in computer vision, advances in neural networks for object detection and classification, especially in the last years, made this area even more appealing due to the effectiveness of these methods. This study presents TrafficSensor, a system that employs deep learning techniques for automatic vehicle tracking and classification on highways using a calibrated and fixed camera. A new traffic image dataset was created to train the models, which includes real traffic images in poor lightning or weather conditions and low-resolution images. The proposed system consists mainly of two modules, first one responsible of vehicle detection and classification and a second one for vehicle tracking. For the first module, several neural models were tested and objectively compared, and finally, the YOLOv3 and YOLOv4-based network trained on the new traffic dataset were selected. The second module combines a simple spatial association algorithm with a more sophisticated KLT (Kanade–Lucas–Tomasi) tracker to follow the vehicles on the road. Several experiments have been conducted on challenging traffic videos in order to validate the system with real data. Experimental results show that the proposed system is able to successfully detect, track, and classify vehicles traveling on a highway on real time.
Highlights
Number of vehicles on earth is increasing rapidly
Luo et al proposed a Retinex-based image adaptive correction algorithm (RIAC), conducted neural architecture search (NAS) on the backbone network used for feature extraction of the faster RCNN, and used the object feature enrichment that combines the multilayer feature information and the context information of the last layer after crosslayer connection. eir model has been trained and tested on the UNDETRAC dataset
TrafficSensor system is a solution for vehicle surveillance using deep learning
Summary
Number of vehicles on earth is increasing rapidly. According to data provided by International Organization of Motor Vehicle Manufacturers (OICA, https://www.oica.net/), the number of vehicles produced in the last years is way more than 70 million vehicles per year. is number is increasing very quickly, the number of travel kilometers increases even more quickly. is explosion in the number of moving vehicles raises several challenges of different types: environmental, economical, and infrastructure management. E study presents a vision-based traffic monitoring system, named TrafficSensor, that includes a robust vehicle detection and classification algorithm and a new technique for dealing with occlusions [10,11,12] It is the evolution of a previous system [13] towards a higher reliability and good performance even in challenging lightning or weather conditions, and poor camera resolution while keeping realtime operation. Luo et al proposed a Retinex-based image adaptive correction algorithm (RIAC) (to reduce the influence of shadows and illumination), conducted neural architecture search (NAS) on the backbone network used for feature extraction of the faster RCNN (to generate the optimal cross-layer connection to extract multilayer features more effectively), and used the object feature enrichment that combines the multilayer feature information and the context information of the last layer after crosslayer connection (to enrich the information of vehicle targets and improve the robustness of the model for challenging targets such as small scale and severe occlusion). Each layer uses a rectified linear unit as a nonlinear transformation. ree of the convolutional layers have in addition max pooling
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
