Boosting object detection performance in videos

作者: Sharathchandra U. Pankanti , Rogerio S. Feris , Ankur Datta , Yun Zhai

DOI:

关键词:

摘要: A method and system for training a special object detector to distinguish foreground appearing in sequence of frames target domain. The depicts motion the non-uniform background. is detected high-confidence subwindow an initial frame sequence, which includes computing measure confidence that determining exceeds specified threshold. tracked respective positive subwindows subsequent after frame. are within short period time. used train detect include frames.

参考文章(18)
Jerome Friedman, Trevor Hastie, Robert Tibshirani, Special Invited Paper-Additive logistic regression: A statistical view of boosting Annals of Statistics. ,vol. 28, pp. 374- 376 ,(2000)
P.M. Roth, H. Grabner, H. Bischof, D. Skocaj, A. Leonardist, On-line Conservative Learning for Person Detection international conference on computer communications and networks. pp. 223- 230 ,(2005) , 10.1109/VSPETS.2005.1570919
Liang Liang, Ruben M. Velarde, Szepo R. Hung, Automatic backlight detection ,(2010)
Behjat Siddiquie, Rogerio S. Feris, Larry S. Davis, Ankur Datta, Unsupervised model selection for view-invariant object detection in surveillance environments international conference on pattern recognition. pp. 3252- 3255 ,(2012)
Rogerio Feris, Ankur Datta, Sharath Pankanti, Ming-Ting Sun, Boosting object detection performance in crowded surveillance videos workshop on applications of computer vision. pp. 427- 432 ,(2013) , 10.1109/WACV.2013.6475050
Paul Viola, Michael J. Jones, Daniel Snow, Detecting Pedestrians Using Patterns of Motion and Appearance international conference on computer vision. ,vol. 63, pp. 734- 741 ,(2003) , 10.1007/S11263-005-6644-8
Pedro F. Felzenszwalb, Ross B. Girshick, David McAllester, Cascade object detection with deformable part models computer vision and pattern recognition. pp. 2241- 2248 ,(2010) , 10.1109/CVPR.2010.5539906