KY 4D Gait Database B (Curve)

Introduction

Kyushu University 4D Gait Database B (Curve) is composed of image sequences of people walking along curved trajectories. This database comprises 42 subjects with two sequences for each subject. All people walked along curved trajectories, as indicated by dashed line 1 in the figure. The radius r varies either 1.5 [m] or 3.0 [m]. Multiple 3D models were reconstructed by the visual hull technique with 16 cameras placed in the studio. This dataset was first introduced in a paper published in Pattern Recognition Letter 2014, Identification of people walking along curved trajectories" [1].

Dataset

The KY 4D Gait Database B consists of sequential 3D models of forty two walking people, silhouette images taken by 16 cameras, and camera parameters of each camera. For more details, please refer to [1].

Download

Each video is temporally segmented to contain a single activity. You can download segmented videos from anonymous FTP server (ftp://robotics-ftp.ait.kyushu-u.ac.jp). The videos are in "gait" folder.

Citation

If you make use of the KY 4D Gait Database B in any form, please do cite the following paper [1]:

[1] Y. Iwashita, K. Ogawara, and R. Kurazume, "Identification of people walking along curved trajectories", Pattern Recognition Letters, to appear, 2014.

@inproceedings{yumi2014gait,
title={Identification of people walking along curved trajectories},
author={Y. Iwashita and K. Ogawara and R. Kurazume},
booktitle={Pattern Recognition Letters},
year={2014},
}

List of performance

Here is a list of performance presented in papers. If you have new results and want to show them here, please email me (yumi@ieee.org) with your paper information.

1. Following methods assume that the gallery dataset contains 3D models (i.e. multiple viewpoint images), but the probe dataset contains single viewpoint images.

Year	Information about targets and methodology	Performance [%]	Paper information

2013	21 people, walking on curved path, 2D image-based method	- 83.3 (Curve 1, smaller circle)	Expanding gait identification methods from straight to curved trajectories, Yumi Iwashita, Koichi Ogawara, Ryo Kurazume, IEEE Winter Conference on Applications of Computer Vision, pp.193-199, Jan 17-18. 2013.

2014	42 people, walking on curved path, 2D image-based method	- 61.9 (Curve 1, smaller circle) - 71.4 (Curve 2, larger circle)	Identification of people walking along curved trajectories, Yumi Iwashita, Koichi Ogawara, Ryo Kurazume, Pattern Recognition Letters, Vol. 46, pp. 60-69, 2014. (DOI: 10.1016/j.patrec.2014.04.004)

2017	42 people, walking on curved path, 2D image-based method	- 79.5 (Curve 1, smaller circle) - 86.0 (Curve 2, larger circle)	Robust Arbitrary-View Gait Recognition Based on 3D Partial Similarity Matching, Jin Tang, Jian Luo, Tardi Tjahjadi, Fan Guo, IEEE Transactions on Image Processing, Volume 26, Issue 1, pp 7-22, 2017.

2. Following methods assume that both gallery and probe datasets contain 3D models (i.e. multiple viewpoint images).

Year	Information about targets and methodology	Performance [%]	Paper information

2015	42 people, walking on curved path, 3D model-based method	- 55.3 (Curve 1, smaller circle) - 87.3 (Curve 2, larger circle)	Entropy volumes for viewpoint-independent gait recognition, D. Lopez-Fernandez. J. Madrid-Cuevas. Carmona-Poyato. Munoz-Salinas. Medina-Carnicer, Machine Vision and Applications, Volume 26, Issue 7, pp 1079-1094, 2015.

2016	42 people, walking on curved path, 3D model-based method	- 100.0 (Curve 1, smaller circle) - 100.0 (Curve 2, larger circle)	A new approach for multi-view gait recognition on unconstrained paths, D. Lopez-Fernandez, F.J. Madrid-Cuevas, A. Carmona-Poyato, R. Munoz-Salinas, R. Medina-Carnicer, Journal of Visual Communication and Image Representation Volume 38, July 2016, Pages 396-406, 2016.

Updated 11/16/2016