Exploring Weak Stabilization for Motion Feature Extraction

June 2013

Exploring Weak Stabilization for Motion Feature Extraction

Authors:

Dennis Park, C. Lawrence Zitnick, Deva Ramanan, and Piotr Dollár
Conference Paper
Proceedings of (CVPR) Computer Vision and Pattern Recognition

Abstract:

We describe novel but simple motion features for the problem of detecting objects in video sequences. Previous approaches either compute optical flow or temporal differences on video frame pairs with various assumptions about stabilization. We describe a combined approach that uses coarse-scale flow and fine-scale temporal difference features. Our approach performs weak motion stabilization by factoring out camera motion and coarse object motion while preserving nonrigid motions that serve as useful cues for recognition. We show results for pedestrian detection and human pose estimation in video sequences, achieving state-of-the-art results in both. In particular, given a fixed detection rate our method achieves a five-fold reduction in false positives over prior art on the Caltech Pedestrian benchmark. Finally, we perform extensive diagnostic experiments to reveal what aspects of our system are crucial for good performance. Proper stabilization, long time-scale features, and proper normalization are all critical.
@conference{Park-2013-121198,
author = {Dennis Park And C. Lawrence Zitnick And Deva Ramanan And Piotr Dollár},
title = {Exploring Weak Stabilization for Motion Feature Extraction},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2013},
month = {June},
pages = {2882 - 2889},
}
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.