A variety of traffic data, such as traffic counts and speed estimations, can be harvested from camera network systems installed along highways. This is possible through computer vision-based traffic monitoring processes that are mainly composed of vehicle detection and tracking, and field of view calibration. Several such processes have been proposed; however, they have not been fully validated on managing occlusion-based scenarios and generating reliable data over long periods of time and high volumes of traffic. This paper presents an effective, semi-automated method of detecting and tracking highway vehicles. The method integrates automated calibration of the field of view, detection and tracking. Trajectories, lanes, speeds and counts of tracked vehicles can be obtained from the videos using the proposed method. When a vehicle gets occluded by the other in adjacent lanes, the method identifies it based on the speed and acceleration, and terminates the tracking. When the vehicle reappears, it initiates a new tracking process. For validation, the framework is tested on videos recorded from CCTVs along the I-85 in GA, and evaluated on the accuracy of vehicle counting and speed. The tracked vehicles are counted when passing by pre-determined counting zones to avoid double counting. The speed results were compared with GPS data. The results indicate that the proposed system has a potential to minimize human intervention and provide reliable counting and speed data.
Unsupervised Framework for Traffic Counting: Speed Estimation Based on Camera Network Data
2014 International Conference on Computing in Civil and Building Engineering ; 2014 ; Orlando, Florida, United States
2014-06-17
Conference paper
Electronic Resource
English
Research on Vehicle Speed Estimation Algorithm with Traffic Camera
SAE Technical Papers | 2022
|Vehicle counting and traffic flow parameter estimation for dense traffic scenes
IET | 2020
|