S.H. Kim and R.-H. Park (Korea)
video indexing, scene change detection,brightness variation
To manipulate large video databases, effective video indexing and retrieval algorithms are required. In this paper, we propose a robust scene change detection algorithm for video sequences with abrupt luminance variations. To efficiently detect scene changes, we employ edge features as well as color histograms. To reduce a computational load, first we compute the color histogram difference and then perform edge matching to find candidate shot boundary frames. The conventional algorithm detects large luminance variations by post processing, whereas the proposed algorithm directly extracts the luminance variations. Experimental results show that the proposed algorithm using edge features and color histograms yields the high accuracy with low computational complexity compared with conventional algorithms.
Important Links:
Go Back
