Compressed domain video retrieval using object and global motion descriptors

Video content description has become an important task with the standardization effort of MPEG-7, which aims at easy and efficient access to visual information. In this paper we propose a system to extract object-based and global features from compressed MPEG video using the motion vector information for video retrieval. The reliability of the motion information is enhanced by a motion accumulation process. The global features like motion activity and camera motion parameters are extracted from the above enhanced motion information. The object features such as speed, area and trajectory are then obtained after the proposed object segmentation. The number of objects in a given video shot is determined by the proposed K-means clustering procedure. The object segmentation is done by applying EM algorithm.

[1]  Shih-Fu Chang,et al.  An integrated approach for content-based video object segmentation and retrieval , 1999, IEEE Trans. Circuits Syst. Video Technol..

[2]  David S. Doermann,et al.  Event detection from MPEG video in the compressed domain , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[3]  Dragutin Petkovic,et al.  Query by Image and Video Content: The QBIC System , 1995, Computer.

[4]  Ajay Divakaran,et al.  MPEG-7 visual motion descriptors , 2001, IEEE Trans. Circuits Syst. Video Technol..

[5]  Anne H. H. Ngu,et al.  Modeling and Retrieval of Moving Objects , 2004, Multimedia Tools and Applications.

[6]  Christos Faloutsos,et al.  Compressed-domain video indexing techniques using DCT and motion vector information in MPEG video , 1997, Electronic Imaging.

[7]  Patrick Bouthemy,et al.  Statistical Motion-Based Retrieval with Partial Query , 2000, VISUAL.

[8]  Forouzan Golshani,et al.  Motion recovery for video content classification , 1995, TOIS.

[9]  Sethuraman Panchanathan,et al.  A critical evaluation of image and video indexing techniques in the compressed domain , 1999, Image Vis. Comput..

[10]  Sanjeev R. Kulkarni,et al.  Rapid estimation of camera motion from compressed video with application to video annotation , 2000, IEEE Trans. Circuits Syst. Video Technol..

[11]  Alfred She,et al.  Motion descriptors for content-based video representation , 2000, Signal Process. Image Commun..

[12]  Edoardo Ardizzone,et al.  Video indexing using MPEG motion compensation vectors , 1999, Proceedings IEEE International Conference on Multimedia Computing and Systems.

[13]  John Chung-Mong Lee,et al.  Video Annotation by Motion Interpretation Using Optical Flow Streams , 1996, J. Vis. Commun. Image Represent..

[14]  David Doermann,et al.  Archiving, indexing, and retrieval of video in the compressed domain , 1996, Other Conferences.

[15]  Charles A. Bouman,et al.  A compressed video database structured for active browsing and search , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[16]  Shih-Fu Chang,et al.  A fully automated content-based video search engine supporting spatiotemporal queries , 1998, IEEE Trans. Circuits Syst. Video Technol..

[17]  R. Venkatesh Babu,et al.  Compressed domain action classification using HMM , 2002, Pattern Recognit. Lett..

[18]  Avideh Zakhor,et al.  A Trajectory Based Video Indexing System For Street Surveillance , 1999 .

[19]  B. S. Manjunath,et al.  NeTra-V: toward an object-based video representation , 1997, Electronic Imaging.

[20]  Jonathan D. Courtney.  Automatic video indexing via object motion analysis , 1997, Pattern Recognit..

[21]  Ames SteetCambridge.  Recognizing Movement Using Motion Histograms , 1999 .