Space-Time Behavior Based Correlation

We introduce a behavior-based similarity measure which tells us whether two different space-time intensity patterns of two different video segments could have resulted from a similar underlying motion field. This is done directly from the intensity information, without explicitly computing the underlying motions. Such a measure allows us to detect similarity between video segments of differently dressed people performing the same type of activity. It requires no foreground/background segmentation, no prior learning of activities, and no motion estimation or tracking. Using this behavior-based similarity measure, we extend the notion of 2-dimensional image correlation into the 3dimensional space-time volume, thus allowing to correlate dynamic behaviors and actions. Small space-time video segments (small video clips) are "correlated" against entire video sequences in all three dimensions (x,y, and t). Peak correlation values correspond to video locations with similar dynamic b...

• Type: Conference
• Year: 2005
• Where: CVPR
• Authors: Eli Shechtman, Michal Irani
• Keywords: 3dimensional Space-time Volume, Behavior-based Similarity Measure, Computer Vision, CVPR 2005, Entire Video Sequences, Similar Dynamic Behaviors, Space-time Video Segments