Activity recognition using the velocity histories of tracked keypoints


We present an activity recognition feature inspired by human psychophysical performance. This feature is based on the velocity history of tracked keypoints. We present a generative mixture model for video sequences using this feature, and show that it performs comparably to local spatio-temporal features on the KTH activity recognition dataset. In addition, we contribute a new activity recognition dataset, focusing on activities of daily living, with high resolution video sequences of complex actions. We demonstrate the superiority of our velocity history feature on high resolution video sequences of complicated activities. Further, we show how the velocity history feature can be extended, both with a more sophisticated latent velocity model, and by combining the velocity history feature with other useful information, like appearance, position, and high level semantic information. Our approach performs comparably to established and state of the art methods on the KTH dataset, and significantly outperforms all other methods on our challenging new dataset.

DOI: 10.1109/ICCV.2009.5459154

Extracted Key Phrases

11 Figures and Tables

Citations per Year

467 Citations

Semantic Scholar estimates that this publication has 467 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Messing2009ActivityRU, title={Activity recognition using the velocity histories of tracked keypoints}, author={Ross Messing and Christopher Joseph Pal and Henry A. Kautz}, journal={2009 IEEE 12th International Conference on Computer Vision}, year={2009}, pages={104-111} }