Effective algorithm for detecting various wipe patterns and discriminating wipe from object and camera motion

Abstract

Wipe transition detection in video segmentation is more difficult to detect than abrupt and other gradual transitions, because of diversity in patterns, and difficulty in distinguishing wipe from camera and object motion. In this study, the authors propose an algorithm for wipe transition detection. In the proposed algorithm, first the moving strip due to wipe is obtained, which eliminate most of the edges due to object boundaries and retain true wipe boundaries, and then Hough transform is applied on these moving lines to detect and categorise various wipe types. In order to decrease the computational load of the proposed algorithm, the authors propose a preprocessing step as a first stage of the algorithm. The preprocessing step consists of calculation of statistical image difference between the consecutive frames to obtain the potential wipe frames, which are input to their proposed algorithm. The proposed algorithm detects and identifies various types of wipes and also distinguishes wipes from object and camera motion. The performance comparison of the proposed algorithm, with and without preprocessing, with other existing techniques clearly exhibit its effectiveness in terms of better recall, precision, F1 measure and detection rate.