Active Object Segmentation for Mobile Robots

The goal of active vision is to change intrinsic or extrinsic properties of the sensor in order to get new and improved information. In the case of 3-D object modeling from vision, this can mean moving the camera to view the scene from a new angle or to get a close-up view of an object that has been localized and is being modeled. We discuss using active vision to improve the speed and utility of map completion and object segmentation. Importantly, in order to be able to process untextured surfaces, we avoid relying on the existence of distinctive visual point features.