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.
Funder
Science and Technology Project of Shandong Provincial Department of Transportation
major scientific and technological innovation project of Shandong Province
Subject
Management, Monitoring, Policy and Law,Renewable Energy, Sustainability and the Environment,Geography, Planning and Development,Building and Construction
Reference53 articles.
1. Ministry of Transport of the People’s Republic of China, Statistical Bulletin of Transport Industry Development 2020
2. Jiangsu Provincial Department of Transport, Framework Agreement on Regional Cooperation of Expressway
3. Erratum to: Highway traffic accident prediction using VDS big data analysis
4. Handbook of Mathematical Models in Computer Vision;Paragios,2006
5. An end-to-end convolutional network for joint detecting and denoising adversarial perturbations in vehicle classification
Cited by
126 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献