Video Segmentation and Structuring for Indexing Applications

Abstract

This paper introduces a complete framework for temporal video segmentation. First, a computationally efficient shot extraction method is introduced, which adopts the normalized graph partition approach, enriched with a non-linear, multiresolution filtering of the similarity vectors involved. The shot boundary detection technique proposed yields high precision (90%) and recall (95%) rates, for all types of transitions, both abrupt and gradual. Next, for each detected shot, the authors construct a static storyboard by introducing a leap keyframe extraction method. The video abstraction algorithm is 23% faster than existing techniques for similar performances. Finally, the authors propose a shot grouping strategy that iteratively clusters visually similar shots under a set of temporal constraints. Two different types of visual features are exploited: HSV color histograms and interest points. In both cases, the precision and recall rates present average performances of 86%.

Fast Temporal Video Segmentation Based on Krawtchouk-Tchebichef Moments

“…Histograms are considered a substitution for algorithms based on pixel intensities because the former do not consider spatial information. Hence, histograms, partly, are considered constant to small local and global motions compared with pixelbased algorithms [4], [27], [28]. TVS algorithms based on histogram assumes that the histograms are comparable for two consecutive frames having stationary object and background.…”