Abstract
Abstract. In intelligent transportation systems (ITS), it is essential to obtain reliable statistics of the vehicular flow in order to create urban traffic management strategies. These systems have benefited from the increase in computational resources and the improvement of image processing methods, especially in object detection based on deep learning. This paper proposes a method for vehicle counting composed of three stages: object detection, tracking and trajectory processing. In order to select the detection model with the best trade-off between accuracy and speed, the following one-stage detection models were compared: SSD512, CenterNet, Efficiedet-D0 and YOLO family models (v2, v3 and v4). Experimental results conducted on the benchmark dataset show that the best rates among the detection models were obtained using YOLOv4 with mAP = 87% and a processing speed of 18 FPS. On the other hand, the accuracy obtained in the proposed counting method was 94% with a real-time processing rate lower than 1.9.
Highlights
Through vehicle detection and counting, it is possible to establish traffic conditions, lane occupancy and congestion levels on highways
To select the detection model that was used in the framework, seven one-stage detection models were compared in order to determine the model with the best trade-off between accuracy and speed in a new dataset
YOLOv4 achieved the best trade-off with mAP= 87.0% and a processing speed of 18 FPS
Summary
Through vehicle detection and counting, it is possible to establish traffic conditions, lane occupancy and congestion levels on highways. This information is a fundamental pillar in Intelligent Transportation Systems (ITS). Most of the methods for vehicle detection and counting in ITS are based on hardware or software systems. Hardware solutions have a higher counting precision than software solutions, these sensors have limitations to obtain detailed information on the behavior of the vehicular flow, in addition to being intrusive and presenting high costs of installation and maintenance. Software-based systems, especially video-based methods that perform image processing (computer vision) have started to stand out because it is an inexpensive, non-intrusive approach that have proven to be successful (Song et al, 2019)
Sign-in/Register to view highlights & summary 
Published Version (
Free)
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 callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: 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.
