Detecting and Segmenting Objects for Mobile Manipulation
international conference on computer vision(2009)
摘要
This paper proposes a novel 3D scene interpretation ap- proach for robots in mobile manipulation scenarios using a set of 3D point features (Fast Point Feature Histograms) and probabilistic graphical methods (Conditional Random Fields). Our system uses real time stereo with textured light to obtain dense depth maps in the robot's manipulators working space. For the purposes of manipulation, we want to interpret the planar supporting surfaces of the scene, recognize and segment the object classes into their primi- tive parts in 6 degrees of freedom (6DOF) so that the robot knows what it is attempting to use and where it may be han- dled. The scene interpretation algorithm uses a two-layer classification scheme: i) we estimate Fast Point Feature Histograms (FPFH) as local 3D point features to segment the objects of interest into geometric primitives; and ii) we learn and categorize object classes using a novel Global Fast Point Feature Histogram (GFPFH) scheme which uses the previously estimated primitives at each point. To show the validity of our approach, we analyze the proposed sys- tem for the problem of recognizing the object class of 20 objects in 500 table settings scenarios. Our algorithm iden- tifies the planar surfaces, decomposes the scene and objects into geometric primitives with 98.27% accuracy and uses the geometric primitives to identify the object's class with an accuracy of 96.69%.
更多查看译文
关键词
image segmentation,manipulators,object detection,probability,robot vision,3D scene interpretation approach,conditional random fields,fast point feature histograms,manipulators,mobile manipulation,objects detection,objects segmention,probabilistic graphical methods,robots
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络