Trajectons: Action Recognition Through the Motion Analysis of Tracked Features

Pyry Matikainen, Martial Hebert, and Rahul Sukthankar
Workshop on Video-Oriented Object and Event Classification, ICCV 2009, September, 2009.


Download
  • Adobe portable document format (pdf) (1MB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
The defining feature of video compared to still images is motion, and as such the selection of good motion features for action recognition is crucial, especially for bag of words techniques that rely heavily on their features. Existing motion techniques either assume that a difficult problem like background/foreground segmentation has already been solved (contour/silhouette based techniques) or are computationally expensive and prone to noise (optical flow). We present a technique for motion based on quantized trajectory snippets of tracked features. These quantized snippets, or trajectons, rely only on simple feature tracking and are computationally efficient. We demonstrate that within a bag of words framework trajectons can match state of the art results, slightly outperforming histogram of optical flow features on the Hollywood Actions dataset. Additionally, we present qualitative results in a video search task on a custom dataset of challenging YouTube videos.

Keywords
action recognition, motion

Notes

Text Reference
Pyry Matikainen, Martial Hebert, and Rahul Sukthankar, "Trajectons: Action Recognition Through the Motion Analysis of Tracked Features," Workshop on Video-Oriented Object and Event Classification, ICCV 2009, September, 2009.

BibTeX Reference
@inproceedings{Matikainen_2009_6466,
   author = "Pyry Matikainen and Martial Hebert and Rahul Sukthankar",
   title = "Trajectons: Action Recognition Through the Motion Analysis of Tracked Features",
   booktitle = "Workshop on Video-Oriented Object and Event Classification, ICCV 2009",
   month = "September",
   year = "2009",
}