YOLOv5-TS: Detecting traffic signs in real-time

Traffic sign detection plays a vital role in assisted driving and automatic driving. YOLOv5, as a one-stage object detection solution, is very suitable for Traffic sign detection. However, it suffers from the problem of false detection and missed detection of small objects. To address this issue, we have made improvements to YOLOv5 and subsequently introduced YOLOv5-TS in this work. In YOLOv5-TS, a spatial pyramid with depth-wise convolution is proposed by replacing maximum pooling operations in spatial pyramid pooling with depth-wise convolutions. It is applied to the backbone to extract multi-scale features at the same time prevent feature loss. A Multiple Feature Fusion module is proposed to fuse multi-scale feature maps multiple times with the purpose of enhancing both the semantic expression ability and the detail expression ability of feature maps. To improve the accuracy in detecting small even extra small objects, a specialized detection layer is introduced by utilizing the highest-resolution feature map. Besides, a new method based on k-means++ is proposed to generate stable anchor boxes. The experiments on the data set verify the usefulness and effectiveness of our work.