References
- Dataset
- Mercoledì, 15 Maggio 2013 23:34
- Stefano Michieletto
- 2233
If you use the IAS-Lab Action Dataset, please cite the following works:
M. Munaro, G. Ballin, S. Michieletto, and E. Menegatti.
"3D Flow Estimation for Human Action Recognition from Colored Point Clouds."
In Biologically Inspired Cognitive Architectures (BICA), vol. 5, pp. 42-51, ISSN: 2212-683X, 2013
M. Munaro, S. Michieletto, and E. Menegatti.
"An evaluation of 3D motion flow and 3D pose estimation for human action recognition."
In RSS 2013 Workshop on RGB-D: Advanced Reasoning with Depth Cameras, Berlin (Germany), June 2013.
This dataset was used to test the action recognition algorithms in:
- M. Munaro, S. Michieletto, and E. Menegatti. "An evaluation of 3D motion flow and 3D pose estimation for human action recognition." In RSS 2013 Workshop on RGB-D: Advanced Reasoning with Depth Cameras, Berlin (Germany), June 2013.
- M. Munaro, G. Ballin, S. Michieletto, and E. Menegatti. "3D Flow Estimation for Human Action Recognition from Colored Point Clouds." Journal on Biologically Inspired Cognitive Architectures (BICA), vol. 5, pp. 42-51, ISSN: 2212-683X, 2013.
Downloads
- Dataset
- Mercoledì, 15 Maggio 2013 23:31
- Stefano Michieletto
- 5851
All the samples in the IAS-Lab Action Dataset are provided as ROS bags.
Any sample contains:
- point cloud (registered RGB and depth)
- rgb image (RGB images at 640x480 resolution)
- skeleton tracker joints (estimated by the NITE middleware)
Download the dataset in a compressed rar file: here.
Overview
- Dataset
- Venerdì, 03 Maggio 2013 14:36
- Stefano Michieletto
- 6929
The IAS-Lab Action Dataset contains 540 video samples:
- 15 different actions;
- 12 different people;
- 3 different attempts.
We asked the subjects to perform well defined actions:
1. check watch |
2. cross arms |
3. get up |
4. kick |
5. pick up |
6. point |
7. punch |
8. scratch head |
9. sit down |
10. standing |
11. throw from bottom up |
12. throw over head |
13. turn around |
14. walk |
15. wave |
For questions and remarks directly related to the IASLab Action Dataset please contact Questo indirizzo email è protetto dagli spambots. È necessario abilitare JavaScript per vederlo. or Questo indirizzo email è protetto dagli spambots. È necessario abilitare JavaScript per vederlo.