Introduction
The OU-ISIR Gait Database is meant to aid research efforts in the general area of developing, testing and evaluating algorithms for gait-based human identification. The Institute of Scientific and Industrial Research (ISIR), Osaka University (OU) has copyright in the collection of gait video and associated data and serves as a distributor of the OU-ISIR Gait Database.
The data have been collected since March 2007 at the Institute of Scientific and Industrial Research (ISIR), Osaka University (OU). The approved informed consent was obtained from all the subjects in this dataset. The data set consists of persons walking on a treadmill surrounded by the 25 cameras at 60 fps, 640 by 480 pixels. We have several covariates as below. The datasets are basically distributed in a form of silhouette sequences registered and size-normalized to 88 by 128 pixels size.
Detailed descriptions are found in the following technical note.
- Y. Makihara, H. Mannami, A. Tsuji, M.A. Hossain, K. Sugiura, A. Mori, and Y. Yagi, ``The OU-ISIR Gait Database Comprising the Treadmill Dataset,'' IPSJ Trans. on Computer Vision and Applications, Vol. 4, pp. 53-62, Apr., 2012.[PDF] [Bib]
List of datasets
Treadmill dataset A -Speed variation-
The dataset A is composed of gait silhouette sequences of 34 subjects from side view with speed variation from 2 km/h to 10 km/h at 1 km/h interval. Samples of still images are shown below (left: 2 km/h, middle: 4 km/h, right: 7 km/h).
Treadmill dataset B -Clothes variation-
The dataset B is composed of gait silhouette sequences of 68 subjects from side view with clothes variation up to 32 combinations. Samples of still images are shown below (left: half shirt and medical doctor pants, middle: down jacket and baggy pants, right: parka and half pants).
Treadmill dataset C -view variation-
Under preparation.
Treadmill dataset D -Gait fluctuation-
The dataset D is composed of gait silhouette sequences of 185 subjects from side view with various gait fluctuations among periods. Gait fluctuations are measured by Normalized AutoCorrelation (NAC) for the temporal axis of size-normalized gait silhouette images. DBhigh contains 100 subjects with the highest NACs (small fluctuations) and DBhigh contains also 100 subjects with the lowest NACs (large fluctuations). Note that 15 subjects are overlapped both in DBhigh and DBlow.
How to get the dataset?
To advance the state-of-the-art in gait-based human identification, this dataset could be downloaded as a zip file with password protection and the password will be issued on a case-by-case basis. To receive the password, the requestor must send the release agreement signed by a legal representative of your institution (e.g., your supervisor if you are a student) to the database administrator by mail, e-mail, or FAX.
- Release agreement
- Silhouette sample (password: sample)
- Treadmill dataset A with Instruction
- Old-version treadmill dataset A is a subset of current treadmill dataset A. Please see old-version instruction.
- Treadmill dataset B with Instruction
- Treadmill dataset C (Under preparation)
- Treadmill dataset D with Instruction
Note
Treadmill dataset C -view variation-
Under preparation.
Treadmill dataset D -Gait fluctuation-
The dataset D is composed of gait silhouette sequences of 185 subjects from side view with various gait fluctuations among periods. Gait fluctuations are measured by Normalized AutoCorrelation (NAC) for the temporal axis of size-normalized gait silhouette images. DBhigh contains 100 subjects with the highest NACs (small fluctuations) and DBhigh contains also 100 subjects with the lowest NACs (large fluctuations). Note that 15 subjects are overlapped both in DBhigh and DBlow.
How to get the dataset?
To advance the state-of-the-art in gait-based human identification, this dataset could be downloaded as a zip file with password protection and the password will be issued on a case-by-case basis. To receive the password, the requestor must send the release agreement signed by a legal representative of your institution (e.g., your supervisor if you are a student) to the database administrator by mail, e-mail, or FAX.
- Release agreement
- Silhouette sample (password: sample)
- Treadmill dataset A with Instruction
- Old-version treadmill dataset A is a subset of current treadmill dataset A. Please see old-version instruction.
- Treadmill dataset B with Instruction
- Treadmill dataset C (Under preparation)
- Treadmill dataset D with Instruction
Note
How to get the dataset?
To advance the state-of-the-art in gait-based human identification, this dataset could be downloaded as a zip file with password protection and the password will be issued on a case-by-case basis. To receive the password, the requestor must send the release agreement signed by a legal representative of your institution (e.g., your supervisor if you are a student) to the database administrator by mail, e-mail, or FAX.- Release agreement
- Silhouette sample (password: sample)
- Treadmill dataset A with Instruction
- Old-version treadmill dataset A is a subset of current treadmill dataset A. Please see old-version instruction.
- Treadmill dataset B with Instruction
- Treadmill dataset C (Under preparation)
- Treadmill dataset D with Instruction
Note
It was often reported that Windows built-in zip did not work to extract all the files. Please try another unzip software if necessary.
The database administrator
Department of Intelligent Media, The Institute of Scientific and Industrial Research, Osaka UniversityAddress: 8-1 Mihogaoka, Ibaraki, Osaka, 567-0047, JAPAN
FAX: +81-6-6877-4375.