Journal of Jilin University(Information Science Ed ›› 2015, Vol. 33 ›› Issue (1): 39-44.

Previous Articles     Next Articles

News Video Shot Detection Based on Weighted Color

ZHANG Jing, WANG Xuejun, JIANG Enyuan   

  1. College of Communication Engineering, Jilin University, Changchun 130012, China
  • Received:2014-04-21 Online:2015-01-24 Published:2015-03-20

Abstract:

Aiming at the change of color characteristics when news video shot transit, a method based on the weighted color histogram is proposed. The weighted color histogram is used to calculate the difference in the two adjacent frames. Then compare the difference with the adaptive threshold to determine the potential shot boundaries. In addition, in order to filter out the impact of flashlight scenes which is often appears in the video and determine the final shot boundary, the method of secondary detection is used which is based on an improved method of sliding window, and the method reduces the impact of rapid motions in videos effectively. The experimental results show that the method is easy to implement and it performs better result and lower complexity.

Key words: shot detection, weighted color, adaptive threshold, sliding window

CLC Number: 

  •