Fast Video Search Algorithm for Large Video Database Using Adjacent Pixel Intensity Difference Quantization Histogram Feature

†† Summary In this paper, we present a fast and robust video search algorithm for large video database using the histogram feature which is essentially different from conventional ones. This algorithm is based on the adjacent pixel intensity difference quantization (APIDQ) algorithm, which had been reliably applied to human face recognition previously. An APIDQ histogram is utilized as the feature vector of a frame image. Combined with active search [4], a temporal pruning algorithm, fast and robust video search can be achieved. The proposed search algorithm has been evaluated by 6 hours of video to search for given 200 video clips which having a each length of 15 seconds. Experimental results show the proposed algorithm can detect the similar video clip in merely 80ms, and is more accurate and robust against Gaussian noise than conventional fast video search algorithm.

[1]  Avideh Zakhor,et al.  Efficient video similarity measurement with video signature , 2002, Proceedings. International Conference on Image Processing.

[2]  Wei Xiong,et al.  Query by video clip , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[3]  Silvio Jamil Ferzoli Guimarães,et al.  Counting of Video Clip Repetitions using a Modified BMH Algorithm: Preliminary Results , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[4]  Sang Hyun Kim,et al.  An efficient algorithm for video sequence matching using the modified Hausdorff distance and the directed divergence , 2002, IEEE Trans. Circuits Syst. Video Technol..

[5]  Seth J. Teller,et al.  Video matching , 2004, Encyclopedia of Multimedia.

[6]  Rakesh Mohan,et al.  Video sequence matching , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[7]  Kunio Kashino,et al.  A quick AND/OR search for multimedia signals based on histogram features , 2003 .

[8]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[9]  Kunio Kashino,et al.  A quick search algorithm for acoustic signals using histogram features—time‐series active search , 2001 .

[10]  Cordelia Schmid,et al.  Segmenting, modeling, and matching video clips containing multiple moving objects , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[11]  J. David Schaffer,et al.  Evolvable visual commercial detector , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[12]  Wolfgang Effelsberg,et al.  On the detection and recognition of television commercials , 1997, Proceedings of IEEE International Conference on Multimedia Computing and Systems.

[13]  Hiroshi Murase,et al.  Focused color intersection with efficient searching for object extraction , 1997, Pattern Recognit..

[14]  Ruud M. Bolle,et al.  Comparison of sequence matching techniques for video copy detection , 2001, IS&T/SPIE Electronic Imaging.