Research on Shot Detection Algorithm of Self-adaptive Dual Thresholds Based on Multi-feature Fusion

详细信息    查看全文

• 关键词：Shot boundary detection ; Video retrieval ; Non ; uniform blocks ; Feature fusion ; Self ; adaptive dual thresholds
• 刊名：Lecture Notes in Computer Science
• 出版年：2017
• 出版时间：2017
• 年：2017
• 卷：10092
• 期：1
• 页码：247-261
• 参考文献：1.Wang, S., Jia, K., Wang, C., Liu, W.: Abrupt cut detection and key frame extraction based on motion information. Comput. Eng. 16, 5–8 (2012)
  2.Liu, G., Wen, X., Zheng, W., et al.: Shot boundary detection and keyframe extraction based on scale invariant feature transform. In: Eigth IEEE/ACIS International Conference on Computer and Information Science, pp. 1126–1130. IEEE Computer Society (2009)
  3.Wei, M.: The Research of the Key Frame Extraction Algorithm of Content-based Video Retrieval. Wuhan Polytechnic University (2010)
  4.Quandong, L.: Content-Based Video Retrieval Research on Shot Detection and Key Frame Extraction. North University of China (2011)
  5.Feng, H., Yuan, X., Wei, M., et al.: A shot boundary detection method based on color space. In: Proceedings of the International Conference on E-Business and E-Government, ICEE 2010, 7–9 May 2010, Guangzhou, China, pp. 1647–1650 (2010)
  6.Quanlei, H.: Research on Content-based Video Shot Segmentation and Retrieval Technology. Shandong University (2009)
  7.Quintyne, K.I., Walsh, L., Coate, L.: A self-adapting dual-threshold method for video shot transition detection. In: 2008 IEEE International Conference on Networking, Sensing and Control, ICNSC 2008, pp. 704–707 IEEE (2008)
  8.Zhao, N., Ning, L., Liu, H.Y.: Content-based cut shot detecting algorithm of news video. J. Jilin Univ. (2009)
  9.Zhang, M.: The Research on Key Frame Selection and Feature Matching Video Retrieval. Beijing University of Posts and Telecommunications (2012)
  10.Ekin, A., Tekalp, A.M.: Automatic soccer video analysis and summarization. IEEE Trans. Image Process. 12(7), 796–807 (2003)CrossRef
  11.Lu, Z.M., Shi, Y.: Fast video shot boundary detection based on SVD and pattern matching. IEEE Trans. Image Process. 22(12), 5136–5145 (2013). A Publication of the IEEE Signal Processing SocietyMathSciNet CrossRef
  12.Miao, P.: Research on Some Technologies Based on Video Retrieval. Nanjing University of Science and Technology (2010)
  13.Liu, X.: Research on Key Frame Extraction Algorithm Based on Multi-feature in Video Retrieval. China University of Mining and Technology (2015)
  14.Zhou, L.: Research of Shot Detection and Key Frame Extraction of Content-based Video Retrieval. Hebei University of Technology (2014)
  15.Tang, J., Xie, L., Yuan, Q., et al.: Shot boundary detection algorithm based on ORB. J. Commun. 11, 187–190 (2013)
  16.Li, D., Jin, L., Yang, W., Fei, M.: Shot boundary detection algorithm based on self-adaptive dual thresholds of accumulative frame. Comput. Sci. 39(6), 258–260+296 (2012)
  
• 作者单位：Jinlai Lv (17)
  Huiru Bai (17)
  
  17. College of Computer Science and Technology, Taiyuan University of Technology Shanxi, Taiyuan, China
  
• 丛书名：Transactions on Edutainment XIII
• ISBN：978-3-662-54395-5
• 卷排序：10092

文摘

The shot is basic physical unit of video sequence, which is a collection of several consecutive frames in time and space that is captured by a camera. Shot boundary detection is the structural basis of video retrieval, the performance of detection algorithm will directly affect the efficiency of video retrieval. By describing and analyzing advantages and disadvantages of existing algorithms, this paper proposes a shot detection algorithm of self-adaptive dual thresholds based on multi-feature fusion. Firstly, frame difference is calculated by combining HSV color feature and LBP texture feature in the image that is non-uniformly divided into several blocks. Secondly, frame difference is compared with two self-adaptive thresholds to detect shot boundary. Finally, video is segmented some independent shots. Experiment analysis shows that this algorithm can’t only extract features that reflect main contents of video images, but also effectively detect abrupt shots and gradual shots. It reduces the number of false detection and miss detection, therefore, it has higher recall and precision than existing shot boundary detection algorithms. To a certain extent, this algorithm improves the efficiency of shot boundary detection.