Estimation of Human Orientation using Coaxial RGB-Depth Images

Fumito Shinmura, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

2015

Abstract

Estimation of human orientation contributes to improving the accuracy of human behavior recognition. However, estimation of human orientation is a challenging task because of the variable appearance of the human body. The wide variety of poses, sizes and clothes combined with a complicated background degrades the estimation accuracy. Therefore, we propose a method for estimating human orientation using coaxial RGB-Depth images. This paper proposes Depth Weighted Histogram of Oriented Gradients (DWHOG) feature calculated from RGB and depth images. By using a depth image, the outline of a human body and the texture of a background can be easily distinguished. In the proposed method, a region having a large depth gradient is given a large weight. Therefore, features at the outline of the human body are enhanced, allowing robust estimation even with complex backgrounds. In order to combine RGB and depth images, we utilize a newly available single-chip RGB-ToF camera, which can capture both RGB and depth images taken along the same optical axis. We experimentally confirmed that the proposed method can estimate human orientation robustly to complex backgrounds, compared to a method using conventional HOG features.

References

1. Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on Pattern Analysis and

Paper Citation

in Harvard Style

Shinmura F., Deguchi D., Ide I., Murase H. and Fujiyoshi H. (2015). Estimation of Human Orientation using Coaxial RGB-Depth Images . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 113-120. DOI: 10.5220/0005305301130120

in Bibtex Style

@conference{visapp15,
author={Fumito Shinmura and Daisuke Deguchi and Ichiro Ide and Hiroshi Murase and Hironobu Fujiyoshi},
title={Estimation of Human Orientation using Coaxial RGB-Depth Images},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={113-120},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005305301130120},
isbn={978-989-758-090-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Estimation of Human Orientation using Coaxial RGB-Depth Images
SN - 978-989-758-090-1
AU - Shinmura F.
AU - Deguchi D.
AU - Ide I.
AU - Murase H.
AU - Fujiyoshi H.
PY - 2015
SP - 113
EP - 120
DO - 10.5220/0005305301130120