FFSSD: Feature Fusion SSD algorithm with SE on Traffic Sign Detection

Abstract

Traffic sign detection is of great importance to the development of intelligent vehicles. In this paper, we propose a modified SSD algorithm called FFSSD to the traffic environment. Firstly,we integrate low and high level features together in order to enhance the accuracy of tiny instances. Besides, we insert a feature enhancement module into it and the original SSD loss was altered by focal loss, which is designed to solve the problem of uneven sample distribution. We evaluate the algorithm on GTSDB (The German Traffic Sign Detection Benchmark dataset). The experimental result demonstrates that our algorithm has a great achievement. Compared with some up-of-date methods, it also achieves higher correctness in the traffic field.