YOLOv4-A: Research on Traffic Sign Detection Based on Hybrid Attention Mechanism

YOLOv4-A: Research on Traffic Sign Detection Based on Hybrid Attention Mechanism

Aiming at the problem of false detection and missed detection in the traffic sign detection task, an improved YOLOv4 detection algorithm is proposed. Based on the YOLOv4 algorithm, the Efficient Channel Attention Module (ECA) and the Convolutional Block Attention Module (CBAM) are added to form YOLOv4-A algorithm. At the same time, the global K-means clustering algorithm is used to regenerate smaller anchors, which makes the network converge faster and reduces the error rate. The YOLOv4-A algorithm re-calibrates the detection branch features in the two dimensions of channel and space, so that the network can focus and enhance the effective features, and suppress the interference features, which improves the detection ability of the algorithm. Experiments on the TT100K traffic sign dataset show that the proposed algorithm has a particularly significant improvement in the performance of small target detection. Compared with the YOLOv4 algorithm, the precision and mAP@0.5 of the proposed algorithm are increased by 5.38% and 5.75%.