Multi-Class Detection and Segmentation of Objects in Depth
This work addresses scene perception for autonomous humanoid robots in home environments, though it appears incremental as it extends existing methods with multi-class and depth components.
The paper tackles 3D multi-class object detection and segmentation for humanoid household robots by learning a minimal joint codebook and incorporating depth information from RGB-D imagery, resulting in improved detection efficiency across classes and more robust detection with natural 3D object localization.
The quality of life of many people could be improved by autonomous humanoid robots in the home. To function in the human world, a humanoid household robot must be able to locate itself and perceive the environment like a human; scene perception, object detection and segmentation, and object spatial localization in 3D are fundamental capabilities for such humanoid robots. This paper presents a 3D multi-class object detection and segmentation method. The contributions are twofold. Firstly, we present a multi-class detection method, where a minimal joint codebook is learned in a principled manner. Secondly, we incorporate depth information using RGB-D imagery, which increases the robustness of the method and gives the 3D location of objects -- necessary since the robot reasons in 3D space. Experiments show that the multi-class extension improves the detection efficiency with respect to the number of classes and the depth extension improves the detection robustness and give sufficient natural 3D location of the objects.