Title :
3-D Recovery of a Non-rigid Object from a Single Camera View Employing Multiple Coordinates Representation
Author :
Ishikawa, Seiichiro ; Joo Kooi Tan ; Hyoungseop Kim ; Ishikawa, Seiichiro
Author_Institution :
Kyushu Inst. of Technol., Kitakyushu, Japan
Abstract :
This paper proposes a novel technique for 3-D recovery of a non-rigid object, such as a human in motion, from a single camera view. To achieve the 3-D recovery, the proposed technique performs segmentation of an object under deformation into respective parts which are all regarded as rigid objects. For high accuracy segmentation, multi-stage learning and local subspace affinity are employed for the segmentation. Each part recovers its 3-D shape by applying the factorization method to it. Obviously the deformed portion containing twist or stretch motion cannot recover the 3-D shape by this procedure. The idea of the present paper is to recover such deformed portion by averaging the 3-D locations of a point on the portion described by the coordinates of respective parts. The experiments employing a synthetic non-rigid object and real human motion data show effectiveness of the proposed technique.
Keywords :
cameras; image capture; image motion analysis; image representation; image segmentation; matrix decomposition; deformed portion recovery; factorization method; local subspace affinity; multiple coordinates representation; multistage learning; nonrigid object 3D recovery; object segmentation; real human motion; single camera view; Accuracy; Cameras; Computer vision; Image segmentation; Joints; Motion segmentation; Shape; Factorization; Non-rigid Structure from Motion;
Conference_Titel :
Pattern Recognition (ACPR), 2013 2nd IAPR Asian Conference on
Conference_Location :
Naha
DOI :
10.1109/ACPR.2013.174