In this paper we present a new descriptor for spatial distribution of motion activity in video sequences. We construct a histogram of areas of distinct regions (or "blobs") of "motion active" regions over the entire video shot. We carry out another thresholding process on the histogram to get our descriptor, which is a histogram normalized with respect to the average size of the blobs, and thus normalized with respect to frame size. We get similar precision-recall performance to the spatial activity descriptor in the current MPEG-7 experimental model. We are also able to successfully capture the effects of camera motion as well as the effects of non-camera motion in distinct uncorrelated parts of our descriptor. Since the feature extraction is in the compressed domain and simple, it is extremely fast. We find that our descriptor enables fast and accurate indexing of video.
Ajay Divakaran, Kadir A. Peker, Huifang Sun