With the rapid growth of people’s living standards and national economic levels, the increase of per capita vehicles leads to the exponential boost in urban traffic congestion. To solve the existing problems of traffic congestion, a deep learning architecture based on yolov4 was proposed to realize monitoring of vehicles, which is used for the real-time detection and statistics of traffic stream information. The result shows that the mean average precision (mAP) of vehicle detection can reach 85% under different occasions of light, traffic flow and vehicle speed. The method has strong environmental adaptability and broad applicability.
Real-Time Vehicle Detection Based on YOLOv4 Neutral Network
Lecture Notes on Data Engineering and Communications Technologies
International conference on Smart Technologies and Systems for Internet of Things ; 2021 December 19, 2021 - December 19, 2021
The 2021 International Conference on Smart Technologies and Systems for Internet of Things ; Chapter : 42 ; 342-347
2022-07-03
6 pages
Article/Chapter (Book)
Electronic Resource
English
Accurate Real-time Ship Target detection Using Yolov4
IEEE | 2021
|Vehicle Detection System using YOLOv4
IEEE | 2022
|Application of lightweight YOLOv4 in vehicle detection
British Library Conference Proceedings | 2022
|