Title :
Image-Based 3D Human Pose Recovery with Locality Sensitive Sparse Retrieval
Author :
Chaoqun Hong ; Jun Yu ; Xuhui Chen
Author_Institution :
Dept. of Comput. Sci., Xiamen Univ. of Technol., Xiamen, China
Abstract :
Image-based 3D human pose recovery is usually conducted by retrieving relevant poses with image features. However, it suffers from high dimensionality of image features and low efficiency of retrieving process. In this paper, we propose a novel approach to recover 3D human poses from silhouettes. This approach improves traditional methods by adopting locality sensitive sparse coding in the retrieving process. It incorporates a local similarity preserving term into the objective of sparse coding, which groups similar silhouettes to alleviate the instability of sparse codes. The experimental results demonstrate the effectiveness of the proposed method.
Keywords :
computer vision; feature extraction; pose estimation; computer vision; image feature dimensionality; image-based 3D human pose recovery; local similarity preserving term; locality sensitive sparse coding; locality sensitive sparse retrieval; silhouette; sparse code instability; Context; Encoding; Laplace equations; Shape; Testing; Three-dimensional displays; Training; 3D human pose recovery; dimensionality reduction; locality sensitiveness; sparse coding;
Conference_Titel :
Systems, Man, and Cybernetics (SMC), 2013 IEEE International Conference on
Conference_Location :
Manchester
DOI :
10.1109/SMC.2013.360