Background pixels mutation detection and Hu invariant moments based traffic signs detection on autonomous vehicles

In this paper, background pixels mutation detection and Hu invariant moments based traffic signs segmentation are combined in traffic signs detection. Considering the gray histogram information in S space, it has good segmentation effects as a global threshold selection method, which can greatly reduce the processing time of the subsequent work. Then using moment invariant theory to extract standard images and seven Hu invariant moments of traffic signs, we contrast the eigenvalues with the suspected areas to establish a rapid and reliable traffic signs detection method.