Title :
Discriminative Human Pose Estimation Based on the Bandelet2 Image Descriptor
Author :
Han, Hong ; Tong, Minglei ; Gou, Jingxiang ; Wang, Rui ; Feng, Guangjie
Author_Institution :
Xidian Univ., Xi´´an, China
Abstract :
In this paper, we address the recovering from monocular images focusing on designing a novel image descriptor derived from the second generation Bandelet transformation, noted as Bandelet2, to tackle with estimation accuracy combined with state-of-art prediction methods. The proposed Bandelet2 image representation could boost the accuracy for the final 3D pose prediction in monocular video images by information from geometric flow to characterize image context, especially for human body shapes and motions. We have compared our image descriptor with classic ones as HOG, HMAX, laterally tested among different regression methods on standard Humaneva-I motion capture dataset and showed 3D reconstruction results. Final statistics verifies competitive discriminatory effectiveness and precision of Bandelet2 descriptor in estimating 3D human poses from monocular images.
Keywords :
image representation; pose estimation; regression analysis; wavelet transforms; Bandelet transformation; Bandelet2 image descriptor; Bandelet2 image representation; Humaneva-I motion capture dataset; discriminative human pose estimation; image context; monocular video image; regression method; Estimation; Geometry; Humans; Image representation; Legged locomotion; Three dimensional displays; Training; Bandelet discriminate approach; human pose estimation;
Conference_Titel :
Image and Graphics (ICIG), 2011 Sixth International Conference on
Conference_Location :
Hefei, Anhui
Print_ISBN :
978-1-4577-1560-0
Electronic_ISBN :
978-0-7695-4541-7
DOI :
10.1109/ICIG.2011.124