Road Traffic Sign Saliency Map Model
Woong-Jae Won, Sungmoon Jeong, Minho Lee · 2007
In this paper, we propose a new pre-processing method for detecting road traffic sign based on visual saliency map model. Since the road traffic sign boards have dominent color contrast against environment, we consider the color opponents information with center surround difference normalization as an input feature extraction, which is effective to reduce noise influence as well as intensify the sign board color characteristics. Also, the edge feature map is considered to reflect the shape characteristics of the traffic sign boards. The weighted sum of the color feature map and edge feature map finally constructs road traffic sign saliency map. Computational experiment results show that the proposed method can successfully reinforce a road traffic sign board and inhibit the complex background traffic environment.