activity_detection icon indicating copy to clipboard operation
activity_detection copied to clipboard

Feature Extraction for Human Activity Detection from RGBD Images

This code is released as part of the Human Activity Detection project at Personal Robotics Lab at Cornell University.

Currently two codes are available:

  • Extracting features from sequence of human activity: Refer to [Sung et al. ICRA 2012] below.
  • Visualizing skeleton data for Cornell Activity Dataset

===== How to run it? =====

  1. Download Cornell Activity Dataset from http://pr.cs.cornell.edu/humanactivities/data.php

  2. Feature Extraction - Refer to README inside FeatureExtractor

===== Project Website =====

http://pr.cs.cornell.edu/humanactivities/

===== Any Questions about the code or CAD-60 dataset? =====

Contact: Jaeyong Sung - [email protected]

===== More details about this code available at =====

Unstructured Human Activity Detection from RGBD Images, Jaeyong Sung, Colin Ponce, Bart Selman, Ashutosh Saxena. International Conference on Robotics and Automation (ICRA), 2012.

(bibtex) @inproceedings{sung_rgbdactivity_2012, title={Unstructured Human Activity Detection from RGBD Images}, author={Jaeyong Sung and Colin Ponce and Bart Selman and Ashutosh Saxena}, booktitle={International Conference on Robotics and Automation (ICRA)}, year={2012} }