Traffic Light Recognition for Real Scenes Based on Image Processing and Deep Learning

Authors

  • Mingliang Che School of Geographic Science, Nantong University, 226019 Nantong, China
  • Mingjun Che Wuxianshenghuo (Hangzhou) Info Tech Ltd., 311100 Hangzhou, China
  • Zhenhua Chao School of Geographic Science, Nantong University, 226019 Nantong, China
  • Xinliang Cao School of Geographic Science, Nantong University, 226019 Nantong, China

DOI:

https://doi.org/10.31577/cai_2020_3_439

Keywords:

Traffic light recognition, color features, perspective relationship, fractal dimension, SqueezeNet

Abstract

Traffic light recognition in urban environments is crucial for vehicle control. Many studies have been devoted to recognizing traffic lights. However, existing recognition methods still face many challenges in terms of accuracy, runtime and size. This paper presents a novel robust traffic light recognition approach that takes into account these three aspects based on image processing and deep learning. The proposed approach adopts a two-stage architecture, first performing detection and then classification. In the detection, the perspective relationship and the fractal dimension are both considered to dramatically reduce the number of invalid candidate boxes, i.e. region proposals. In the classification, the candidate boxes are classified by SqueezeNet. Finally, the recognized traffic light boxes are reshaped by postprocessing. Compared with several reference models, this approach is significantly competitive in terms of accuracy and runtime. We show that our approach is lightweight, easy to implement, and applicable to smart terminals, mobile devices or embedded devices in practice.

Downloads

Download data is not yet available.

Downloads

Published

2020-12-16

How to Cite

Che, M., Che, M., Chao, Z., & Cao, X. (2020). Traffic Light Recognition for Real Scenes Based on Image Processing and Deep Learning. Computing and Informatics, 39(3), 439–463. https://doi.org/10.31577/cai_2020_3_439