We propose part-segment (PS) features for estimating an articulated pose in still images. The PS feature evaluates the image likelihood of each body part (e.g. head, torso, and arms) robustly to background clutter and nuisance textures on the body. While general gradient features (e.g. HOG) might include many nuisance responses, the PS feature represents only the region of the body part by iterative segmentation while updating the shape prior of each part. In contrast to similar segmentation features, part segmentation is improved by part-specific shape priors that are optimized by training images with fully-automatically obtained seeds. The shape priors are modeled efficiently based on clustering for fast extraction of PS features. The PS feature is fused complementarily with gradient features using discriminative training and adaptive weighting for robust and accurate evaluation of part similarity. Comparative experiments with public datasets demonstrate improvement in pose estimation by the PS features.
Norimichi UKITA
Nara Institute of Science and Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Norimichi UKITA, "Part-Segment Features with Optimized Shape Priors for Articulated Pose Estimation" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 1, pp. 248-256, January 2016, doi: 10.1587/transinf.2015EDP7228.
Abstract: We propose part-segment (PS) features for estimating an articulated pose in still images. The PS feature evaluates the image likelihood of each body part (e.g. head, torso, and arms) robustly to background clutter and nuisance textures on the body. While general gradient features (e.g. HOG) might include many nuisance responses, the PS feature represents only the region of the body part by iterative segmentation while updating the shape prior of each part. In contrast to similar segmentation features, part segmentation is improved by part-specific shape priors that are optimized by training images with fully-automatically obtained seeds. The shape priors are modeled efficiently based on clustering for fast extraction of PS features. The PS feature is fused complementarily with gradient features using discriminative training and adaptive weighting for robust and accurate evaluation of part similarity. Comparative experiments with public datasets demonstrate improvement in pose estimation by the PS features.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7228/_p
Copy
@ARTICLE{e99-d_1_248,
author={Norimichi UKITA, },
journal={IEICE TRANSACTIONS on Information},
title={Part-Segment Features with Optimized Shape Priors for Articulated Pose Estimation},
year={2016},
volume={E99-D},
number={1},
pages={248-256},
abstract={We propose part-segment (PS) features for estimating an articulated pose in still images. The PS feature evaluates the image likelihood of each body part (e.g. head, torso, and arms) robustly to background clutter and nuisance textures on the body. While general gradient features (e.g. HOG) might include many nuisance responses, the PS feature represents only the region of the body part by iterative segmentation while updating the shape prior of each part. In contrast to similar segmentation features, part segmentation is improved by part-specific shape priors that are optimized by training images with fully-automatically obtained seeds. The shape priors are modeled efficiently based on clustering for fast extraction of PS features. The PS feature is fused complementarily with gradient features using discriminative training and adaptive weighting for robust and accurate evaluation of part similarity. Comparative experiments with public datasets demonstrate improvement in pose estimation by the PS features.},
keywords={},
doi={10.1587/transinf.2015EDP7228},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Part-Segment Features with Optimized Shape Priors for Articulated Pose Estimation
T2 - IEICE TRANSACTIONS on Information
SP - 248
EP - 256
AU - Norimichi UKITA
PY - 2016
DO - 10.1587/transinf.2015EDP7228
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2016
AB - We propose part-segment (PS) features for estimating an articulated pose in still images. The PS feature evaluates the image likelihood of each body part (e.g. head, torso, and arms) robustly to background clutter and nuisance textures on the body. While general gradient features (e.g. HOG) might include many nuisance responses, the PS feature represents only the region of the body part by iterative segmentation while updating the shape prior of each part. In contrast to similar segmentation features, part segmentation is improved by part-specific shape priors that are optimized by training images with fully-automatically obtained seeds. The shape priors are modeled efficiently based on clustering for fast extraction of PS features. The PS feature is fused complementarily with gradient features using discriminative training and adaptive weighting for robust and accurate evaluation of part similarity. Comparative experiments with public datasets demonstrate improvement in pose estimation by the PS features.
ER -