Real-Time Vehicle Detection Based on Improved YOLO v5

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.

Automated summary

This paper proposes an improved method for vehicle detection in different traffic scenarios based on an improved YOLO v5 network to reduce the false detection rate caused by occlusion. The proposed method enhances the network's perception of small targets through the Flip-Mosaic algorithm. A multi-type vehicle target dataset collected in different scenarios is used for training the detection model. Experimental results demonstrate that the Flip-Mosaic data enhancement algorithm can improve the accuracy of vehicle detection and reduce the false detection rate.