The Algorithm for Unstructured Road to Abstract Road Surface based on Color Feature

Visual navigation of mobile robots is an important issue in the field of computer vision research. For the characteristics of unstructured roads, in this paper, we use color feature and space information to solve this problem. First, compress color space of color image containing unstructured road to quantity color values. Second, automatically select the appropriate growing seed point by the space distribution of road area in the color images containing road, and then progress regional growth and obtain the boundary of unstructured road. The experiments show that this algorithm could identify a wide range of unstructured roads base on only part of the image color characteristics. Further more, its accurate recognition results and a small amount of computation could basically meet the real-time requirement of the mobile robot during outdoor industry. KeywordsUnstructured-Road; identification; Regional growth