Development of a visual object localization module for mobile robots

Reports preliminary results from the design and implementation of a visual object localization module for mobile robots. The module takes an object-based approach to visual processing and relies on a preprocessing step that segments objects from the image. By tracking the size and the eccentricity of the objects in the image while the robot is moving, the visual object localization module can determine the position of objects relative to the robot using the displacement obtained from its odometry. In localizing the objects, the module is designed to combine the results of two different techniques. The visual looming technique measures the distance to an object using the change in the size of the object on the image plane. This technique is to be complemented by a variant of the triangulation technique that can locate an object using the eccentricity of the object when viewed from two different points. The module-with the preprocessing algorithm-is being implemented to run in real-time on a mobile robot. Evaluation of the visual localization module is being done in an integrated system introduced in the article. The integrated system creates an environment for real-time evaluation of the module as well as other mapping and navigation algorithms for mobile robots.