Topological Localization Based on Salient Regions in Unknown Environments

This paper presents a new topological localization system for mobile robot navigation based on salient visual regions. These salient regions are obtained by computing the opponencies of color and texture among multi-scale image spaces. Then they are organized to construct the vertex of topological map using hidden Markov model. So localization problem can be transformed to the evaluation problem of HMM. In our system, the topological map of environment can be created online and the robot locates itself concurrently. Experiments show that higher ratio of vertex recognition, that is localization, is obtained. And our system can guarantee mobile robot navigation safely in unknown environments