Human action detection via boosted local motion histograms

This paper presents a novel learning method for human action detection in video sequences. The detecting problem is not limited in controlled settings like stationary background or invariant illumination, but studied in real scenarios. Spatio-temporal volume analysis for actions is adopted to solve the problem. To develop effective representation while remaining resistant to background motions, only motion information is exploited to define suitable descriptors for action volumes. On the other hand, action models are learned by using boosting techniques to select discriminative features for efficient classification. This paper also shows how the proposed method enables learning efficient action detectors, and validates them on publicly available datasets.

[1]  Ivan Laptev,et al.  On Space-Time Interest Points , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[2]  Cordelia Schmid,et al.  Human Detection Using Oriented Histograms of Flow and Appearance , 2006, ECCV.

[3]  Juan Carlos Niebles,et al.  Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words , 2006, BMVC.

[4]  Fatih Murat Porikli,et al.  Integral histogram: a fast way to extract histograms in Cartesian spaces , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[5]  Patrick Pérez,et al.  Retrieving actions in movies , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Dariu Gavrila,et al.  The Visual Analysis of Human Movement: A Survey , 1999, Comput. Vis. Image Underst..

[7]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[8]  Ivan Laptev,et al.  Improvements of Object Detection Using Boosted Histograms , 2006, BMVC.

[9]  Mubarak Shah,et al.  Recognizing human actions in videos acquired by uncalibrated moving cameras , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[10]  S. Negahdaripour,et al.  Relaxing the Brightness Constancy Assumption in Computing Optical Flow , 1987 .

[11]  David A. Forsyth,et al.  Automatic Annotation of Everyday Movements , 2003, NIPS.

[12]  Rainer Lienhart,et al.  Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection , 2003, DAGM-Symposium.

[13]  Serge J. Belongie,et al.  Behavior recognition via sparse spatio-temporal features , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[14]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[15]  Mubarak Shah,et al.  Motion-Based Recognition , 1997, Computational Imaging and Vision.

[16]  Luc Van Gool,et al.  Determination of Optical Flow and its Discontinuities using Non-Linear Diffusion , 1994, ECCV.

[17]  Tae-Kyun Kim,et al.  Tensor Canonical Correlation Analysis for Action Classification , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Barbara Caputo,et al.  Recognizing human actions: a local SVM approach , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[19]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[20]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[21]  Martial Hebert,et al.  Efficient visual event detection using volumetric features , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[22]  Tae-Kyun Kim,et al.  Learning Motion Categories using both Semantic and Structural Information , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.