Real Time Motion Changes for New Event

An original approach for real time detection of changes in 5 motion is presented, for detecting and recognizing events. Current video 6 change detection focuses on shot changes, based on appearance, not mo7 tion. Changes in motion are detected in pixels that are found to be active, 8 and this motion is input to sequential change detection, which detects 9 changes in real time. Statistical modeling of the motion data shows that 10 the Laplace provides the most accurate fit. This leads to reliable de11 tection of changes in motion for videos where shot change detection is 12 shown to fail. Once a change is detected, the event is recognized based on 13 motion statistics, size, density of active pixels. Experiments show that 14 the proposed method finds meaningful changes, and reliable recognition. 15