Learning action dictionaries from video

TitleLearning action dictionaries from video
Publication TypeConference Papers
Year of Publication2008
AuthorsTuraga P, Chellappa R
Conference NameImage Processing, 2008. ICIP 2008. 15th IEEE International Conference on
Date Published2008/10//
Keywords(artificial, action, action-phrases;learning, automated, decomposition;video, dictionaries;spatial, intelligence);video, segment, segmentation;learning, sequence;computer, Surveillance, surveillance;, systems;computer, transforms;video, vision;image, vision;independent

Summarizing the contents of a video containing human activities is an important problem in computer vision and has important applications in automated surveillance systems. Summarizing a video requires one to identify and learn a 'vocabulary' of action-phrases corresponding to specific events and actions occurring in the video. We propose a generative model for dynamic scenes containing human activities as a composition of independent action-phrases - each of which is derived from an underlying vocabulary. Given a long video sequence, we propose a completely unsupervised approach to learn the vocabulary. Once the vocabulary is learnt, a video segment can be decomposed into a collection of phrases for summarization. We then describe methods to learn the correlations between activities and sequentiality of events. We also propose a novel method for building invariances to spatial transforms in the summarization scheme.