Improved YOLO v5 with balanced feature pyramid and attention module for traffic sign detection

Abstract

With the development of automatic driving technology, traffic sign detection has become a very important task. However, it is a challenging task because of the complex traffic sign scene and the small size of the target. In recent years, a number of convolutional neural network (CNN) based object detection methods have brought great progress to traffic sign detection. Considering the still high false detection rate, as well as the high time overhead and computational overhead, the effect is not satisfactory. Therefore, we employ lightweight network model YOLO v5 (You Only Look Once) as our work foundation. In this paper, we propose an improved YOLO v5 method by using balances feature pyramid structure and global context block to enhance the ability of feature fusion and feature extraction. To verify our proposed method, we have conducted a lot of comparative experiments on the challenging dataset Tsinghua-Tencent-100K (TT100K). The experimental results demonstrate that the mAP@.5 and mAP@.5:0.95 are improved by 1.9% and 2.1%, respectively.