Video-based Generic Object Recognition by Combining Motion Features and BoF

It has been needed to recognize objects in videos and attach tags automatically so as to categorize and search a large amount of videos on the Web. Recently, generic object recognition has been studied for still images actively, but not almost for videos. As for the generic object recognition in a video, it is important to make use of the features from various frames involved in the video efficiently. In this paper, we propose a method of recognizing generic objects in videos by combining BoF of each frames and motion features of consecutive frames. Experimental results showed the effectiveness of integrated use of motion features.

[1]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[2]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[3]  S. H. Mirza,et al.  Using Video for Multiview Object Categorization in Security Systems , 2009 .

[4]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[5]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .