研究进展一人体关节点检测 ·从单张深度图中预测人体关节的3D位置，设计一种身体部位的中 间表示形式，将姿势估计问题映射为像素分类问题，然后采用随 机森林分类器识别身体部位，重新投影生成人体关节。 (I,x) tree 1 tree 7 ront ront depth image body parts 3D joint proposals [1]Shotton,J.,Fitzgibbon,A.,Cook,M.,Sharp,T.,Finocchio,M.,Moore,R.,...Blake,A.Real-time human pose recognition in parts from single depth images.In IEEE CVPR 2011‹¬nAG3š{uy • lôśï¸AșŚPzpƿŶ ^ƴOǑǍȣƊǦzǾ^ŶA ȉǃƇøóOÝȩŽ]ǍȈțijÜBjƤ~ƠȈțOŤ«ȀŰȏ Ļŋł~Ơ¶ǔƒǦzǾ^OȂĮčùůąPzpƿȳ [1] Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., ... & Blake, A. Real-time human pose recognition in parts from single depth images. In IEEE CVPR 2011.