Research on Video Abstraction

  • Linglin Wu
  • Xiaoyu Wu
  • Lei Yang
  • Linwan Liu
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 218)


This paper focuses on designing a system that is capable of abstracting useful video frames for archiving, cataloging, indexing, and editing purpose. Among the different features of video frames, statistics histogram is adopted to detect key frames because of its low sensitivity toward motion, low complexity of calculation, and robustness to noise. In addition, cumulative histogram is adopted to detect the edges of video frames due to its lower sensitivity to the motion of objects/camera and illumination variations than statistics histogram. Dynamic threshold-based sliding window is used to detect the shot boundaries and efficiently get the key frames in favor of its representativeness.


Video abstraction Histogram Shot boundary detection Key frame 


  1. 1.
    Wei-yu Y, Yan C, Sheng-li X (2008) Actuality and development of video summarization. Appl Res Comput 25(7):1948–1951Google Scholar
  2. 2.
    Yu-liang G, De X (2005) A unified framework for shot boundary detection. J Image Graph 10(5):650–655Google Scholar
  3. 3.
    Yu-jin Z (2003) Content-based visual information retrieval. Science Press, BeijingGoogle Scholar
  4. 4.
    Bradski G, Kaebler A (2008) Learning open CV: computer vision with the open CV library O’Reilly MediaGoogle Scholar
  5. 5.
    Hong-li D, Huai-xin C (2008) Video shot boundary detection method based on cumulative histogram. Telecommun Eng 48(3):66–69Google Scholar
  6. 6.
    Jian-yun C, Song-yang L, Ling-da W (2003) Video abstraction. J Image Graph 8A(7):721–725Google Scholar
  7. 7.
    Li-ping R (2011) Research on key frames extraction in videos. Lanzhou UniversityGoogle Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  1. 1.College of Information EngineeringCommunication University of ChinaBeijingChina

Personalised recommendations