Gesture Reco & Ditiop from video

Abstract

Recognizing Human Actions from video is a challenging problem which has received much attention during the recent years due to its many applications in different fields. A reliable system capable of recognizing various human actions has many important applications such an human computer interaction,content-based video retrieval, visual surveillance, analysis of sports events and more. The problem of human action recognition from video sequence was addressed in this project. The aim is to develop an algorithm which can recognize low-level-actions from the input video sequences. For the purpose of evaluation we introduce a new video database of such low- level five human actions (walking,running jogging, boxing and hand clapping )performed by 25 people in four different dimensions. The presented results of action recognition justify the proposed method and demonstrate its advantage compared to other relative approaches for action reorganization.