Abstract
Shot segmentation is an important technology in video analysis. Traditional shot segmentation methods usually need to set thresholds in advance. Due to the diversity of shot types, it is usually difficult to set appropriate thresholds for these segmentation. In this paper, a new shot segmentation method is proposed, which combines feature fusion with Bayesian online changepoint detection. Firstly, the HSV quantitative color features of video frames are extracted and a new feature MEP is constructed. The comprehensive similarity of MEP features of two adjacent frames is calculated. Then, Bayesian online changepoint detection algorithm is applied to detect the comprehensive similarity. The location of the changepoint detected is the position of shot segmentation in the video. The experimental results show that Bayesian online changepoint detection has the ability to distinguish different shots. The average Recall and Precision of our method are over 0.90, which is more accurate than the results of the methods which used to compare with our method.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
