Abstract

This paper presents a framework that recognizes the small human group and to detect the event in the video. This framework is utilized for robotized little human gathering occasion discovery inside of social or open spot environment furthermore serves to recognize a fording wrong doings, for example, Railway station, Traffic, collages, office etc. The proposed framework aims to automatically extract foreground human group without any user interaction or the use of any training data and identifies the event in the group. In the proposed method, the coarse foreground extraction is obtained by using the motion and the edge information of an object. Then, the human group is extracted by using the horizontal/ vertical filling scheme based on the coarse foreground extraction. If group is formed, features are extracted using features extraction algorithms from particular frame. Finally, event in particular frame is classified using unsupervised classifiers. The proposed method can be applied to video object segmentation and further video editing and retrieval applications.