Real-Time Vehicle Detection Based on Improved YOLO v5
Tongji University · Shandong University · +2 more institutions
Abstract
To reduce the false detection rate of vehicle targets caused by occlusion, an improved method of vehicle detection in different traffic scenarios based on an improved YOLO v5 network is proposed. The proposed method uses the Flip-Mosaic algorithm to enhance the network’s perception of small targets. A multi-type vehicle target dataset collected in different scenarios was set up. The detection model was trained based on the dataset. The experimental results showed that the Flip-Mosaic data enhancement algorithm can improve the accuracy of vehicle detection and reduce the false detection rate.
Citation impact
- FWCI
- 37.96
- Percentile
- 100%
- References
- 47
Authors
6- YZYu Zhang
Tongji University
- ZGZhongyin Guo
Tongji University
- JWJianqing Wu
Shandong University, Shandong Transportation Research Institute, Suzhou Research Institute
- YTYuan TianCorresponding
Shandong University, Shandong Transportation Research Institute, Suzhou Research Institute
- HTHaotian Tang
Shandong University, Shandong Transportation Research Institute
Topics & keywords
- Computer science
- Artificial intelligence
- Set (abstract data type)
- False positive rate
- Data set
- Object detection
- Pattern recognition (psychology)
- Computer vision