Electric Vehicle Traffic Flow Detection Algorithm based on Improved YOLOv5s
Main Article Content
Abstract
In the view of uneven distribution of electric vehicle charging piles in some areas, resulting in a shortage of charging resources. The flow of electric vehicles in the area can be detected, so that charging piles can be reasonably deployed according to the traffic flow. Therefore, we propose a traffic flow detection algorithm based on improved CAR-YOLOv5s algorithm. In terms of the backbone network, an improved MobileNetv3 architecture is used to balance the speed and precision of the model. A ghost lightweight module is introduced into the neck network to improve the detection speed of the model. After the model is trained and verified, it is combined with DeepSort to track, detect and count the driving electric vehicles and detect the traffic flow of electric vehicles. The improved CAR-YOLOv5s model parameters are reduced by 3.43M and the floating-point calculation is reduced by 10.2G. The tracking effect was tested on the GPU with an average speed of 20.8FPS, which is 27.18% faster than before the improvement. The experimental results show that the improved algorithm is suitable for real-time tracking and detection of electric vehicles on traffic roads.
Article Details
Issue
Section
Articles
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms: a. Authors retain copyright and grant the journal right of first publication, with the work two years after publication simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal. b. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal. c. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).