• Data Set

    Data Set

    Frames from (a) the left camera for concrete surface, (b) the right camera for concrete surface, (c) the left camera for grass surface, and (d) the right camera for grass surface.

  • Sample Silhouette Frames

    Silhouette frames of subject ID: 02539, walking on concrete floor, with shoe type ‘A’, with right viewpoint (R), with no briefcase (NB).

  • Sample Silhouette Errors

    Sample Silhouette Errors

    The bottom row ((f)-(j)) shows sample silhouette frames with a variety of segmentation errors. The raw image corresponding to each silhouette is shown on the top row ((a)-(e)).

  • Gait Cloud Readme

    In order to submit your code to the gait cloud, you need to follow few protocols.

    This Screencast will help you to setup a local development environment to write your gait algorithm and upload it to the gait cloud for evaluation on the entire HumanID dataset.

  • Gait Cloud Results

    Gait Cloud Results

    View your results in the form of ROC and CMC curves

  • Publication


    Ravi Panchumarthy, Ravi Subramanian, Sudeep Sarkar, “Biometric Evaluation on the Cloud: A Case Study with HumanID Gait Challenge,” UCC, pp.219-222, 2012 IEEE Fifth International Conference on Utility and Cloud Computing, 2012 .


1.2 TB Gait Dataset

1.2 TB Gait Dataset

This is a large (1.2 Tera Bytes) dataset of video of gait from 122 subjects in up to 32 possible combinations of variations in factors. See more details and how to get it HERE

Evaluate in 2 Easy Steps

Evaluate in 2 Easy Steps

Yes, using Gait Cloud, you can evaluate in 2 easy steps
1. Upload your code.
2. Trigger the job.

And Once the evaluation is complete, results will be available.