Image-based 3D Human Pose Recovery by Multi-view Locality Sensitive Sparse Retrieval

Image-based 3-D human pose recovery is usually conducted by retrieving relevant poses with image features. However, it suffers from the high dimensionality of image features and the low efficiency of the retrieving process. Particularly for multiview data, the integration of different types of features is difficult. In this paper, a novel approach is proposed to recover 3-D human poses from silhouettes. This approach improves traditional methods by adopting multiview locality-sensitive sparse coding in the retrieving process. First, it incorporates a local similarity preserving term into the objective of sparse coding, which groups similar silhouettes to alleviate the instability of sparse codes. Second, the objective function of sparse coding is improved by integrating multiview data. The experimental results show that the retrieval error has been reduced by 20% to 50%, which demonstrate the effectiveness of the proposed method.