Range image analysis for controlling an adaptive 3D camera

Abstract

Human vision is the reference when designing perception systems for cognitive service robots, especially its ability to quickly identify task-relevant regions in a scene and to foveate on these regions. An adaptive 3D camera currently under development aims at mimicking these properties for endowing service robots with a higher level of perception and interaction capabilities with respect to everyday objects and environments. A scene is coarsely scanned and analyzed. Based on the result of analysis and the task, relevant regions within the scene are identified and data acquisition is concentrated on details of interest allowing for higher resolution 3D sampling of these details. To set the stage we first briefly describe the sensor hardware and focus then on the analysis of range images captured by the hardware. Two approaches - one based on saliency maps and the other on range image segmentation - and preliminary results are presented.