Abstract: Semantic video retrieval which deals with unstructured information traditionally relies on shot boundary detection and key frames extraction. For content interpretation and for similarity matching between shots, video segmentation, i.e. detection of similarity-based events, are closely related with multidimensional time series representing video in a feature space. Since video has a high degree of frame-to-frame-correlation, semantic gap search is quite difficult as it requires high-level knowledge and often depends on a particular domain application. Based on principal components analysis a method of video disharmony authentication has been proposed. Regions features induced by traditional frame segmentations have been used to detect video shots. Results of experiments with endoscopic video are discussed.

Keywords: Video Data, Frames, Time series segmentation, Principal component

ACM Classification Keywords: I.2.10 Vision and Scene Understanding (Video analysis), G.3 Probability and Statistics (Time series analysis).

Link:

NEURAL NETWORK SEGMENTATION OF VIDEO VIA TIME SERIES ANALYSIS

Dmitry Kinoshenko, Sergey Mashtalir, Andreas Stephan, Vladimir Vinarski

http://www.foibg.com/ijita/vol18/ijita18-3-p04.pdf