An integrated scheme for object-based video abstraction

ABSTRACT

In this paper, we present a novel scheme for object-based key-frame extraction facilitated by an efficient video object segmentation system. Key-frames are the subset of still images which best represent the content of a video sequence in an abstracted manner. Thus, key-frame based video abstraction transforms an entire video clip to a small number of representative images. The challenge is that the extraction of key-frames needs to be automated and context dependent so that they maintain the important contents of the video while remove all redundancy. Among various semantic primitives of video, objects of interest along with their actions and generated events can play an important role in some applications such as object-based video surveillance system. Furthermore, on-line processing combined with fast and robust video object segmentation is crucial for real-time applications to report unwanted action or event as soon as it happens. Experimental results on the proposed scheme for object-based video abstraction are presented.

REFERENCES

• 1: T. Sikora, "The MPEG-4 video standard verification model," IEEE Trans. Circuits Syst. Video Technology, vol. 7, pp.19-31, Feb. 1997.
• 2: William E. Grim.son, From Images to Surfaces, The MIT press, pp3-5, 1981.
• 3: Rafael C. Gonzales , Paul Wintz, Digital image processing (2nd ed.), Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1987
• 4: H.J.Zhang et al. "An Integrated system for Content-based Video Retrieval and Browing", Pattern recognition, vol. 30, No.4, pp.643-658, 1997.
• 5: Til Aach , André Kaup , Rudolf Mester, Statistical model-based change detection in moving video, Signal Processing, v.31 n.2, p.165-180, March 1993 [doi>10.1016/0165-1684(93)90063-G]
• 6: R. Mech , M. Wollborn, A Noise Robust Method for Segmentation of Moving Objects in Video Sequences, Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 4, p.2657, April 21-24, 1997
• 7: A.M.Ferman et al., "Object-Based Indexing of MPEG-4 Compressed Video", SPIE-3024, pp. 953-963, Feb. 1997, San Jose, CA.
• 8: J Canny, A computational approach to edge detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.8 n.6, p.679-698, Nov. 1986 [doi>10.1109/TPAMI.1986.4767851]
• 9: A. Neri , S. Colonnese , G. Russo , P. Talone, Automatic moving object and background separation, Signal Processing, v.66 n.2, p.219-232, April 1998 [doi>10.1016/S0165-1684(98)00007-3]
• 10: C. Gu and M-C Lee, "Semantic Segmentation and Tracking of Semantic Video objects," IEEE Trans. Orcuits Syst. Video Technology, vol. 8, pp.572-584, Sep. 1998.
• 11: L. Shapiro, "Computer Vision," Prentice Hall, to be published.
• 12: htto://students.washington.edu/cikim/cidil/mos/mos3.html
• 14: M.Wollborn and R. Mech, "Refined procedure for objective evaluation of video generation algorithms," Doc. ISO/IEC JTCl/SC29/WG11 M3448, March, 1998.
• 15: M. Hu, "Visual pattern recognition by moment invariants", IRE Trans. Information Theory, IT-8(2), pp. 179-182, Feb. 1962.
• 16: Ju Guo et al,, "Fast and accurate moving object extraction technique for MPEG-4 object-based video coding," SPIE, vol.3653, pp.1210-1221, January, 1999.
• 17: Changick Kim and Jenq-Neng Hwang, "Fast and Robust Moving Object Segmentation in Video Sequences," IEEE international conference on Image Processing (ICIP'99), Kobe, Japan, Oct. 1999.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.1 Multimedia Information Systems
          Subjects: Video (e.g., tape, disk, DVI)

  I. Computing Methodologies
  I.6 SIMULATION AND MODELING

  K. Computing Milieux
  K.1 THE COMPUTER INDUSTRY
      Subjects: Standards

General Terms:
Algorithms, Design, Experimentation, Measurement, Performance, Standardization, Theory

Keywords:
MPEG-4/MPEG-7, object-based key frame extraction, video abstraction, video object segmentation