A Novel Approach for Shot Boundary Detection in Videos
This is an incremental improvement for video analysis tasks, specifically targeting shot boundary detection in videos like cricket footage.
The paper tackles video shot boundary detection by introducing a split-and-merge method using Fisher linear discriminant and spectral clustering, achieving highly cohesive and loosely coupled shots as validated on a cricket video.
This paper presents a novel approach for video shot boundary detection. The proposed approach is based on split and merge concept. A fisher linear discriminant criterion is used to guide the process of both splitting and merging. For the purpose of capturing the between class and within class scatter we employ 2D2 FLD method which works on texture feature of regions in each frame of a video. Further to reduce the complexity of the process we propose to employ spectral clustering to group related regions together to a single there by achieving reduction in dimension. The proposed method is experimentally also validated on a cricket video. It is revealed that shots obtained by the proposed approach are highly cohesive and loosely coupled