Title :
Motion indexing of video
Author :
Sahouria, Emile ; Zakhor, Avideh
Author_Institution :
Dept. of Electr. Eng., California Univ., Berkeley, CA, USA
Abstract :
A system has been developed to analyze and index surveillance videos based on the motions of objects in the scene. A segmentation and tracking system extracts trajectories from compressed video, which are represented in a multiresolution manner and stored in a database. Hand-drawn queries can be submitted to the system for imprecise searches. The system was tested on real video footage with numerous moving objects; the success rates for tracking and recall in most cases exceeded 70 percent, a promising result
Keywords :
image representation; image resolution; image segmentation; indexing; motion estimation; optical tracking; surveillance; video signal processing; visual databases; compressed video; database; hand-drawn queries; imprecise searches; motion indexing; moving objects; multiresolution; representation; segmentation; surveillance video; tracking; trajectories; video footage; Databases; Image databases; Indexing; Layout; Motion analysis; Surveillance; System testing; Tracking; Trajectory; Video compression; Visual databases;
Conference_Titel :
Image Processing, 1997. Proceedings., International Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8183-7
DOI :
10.1109/ICIP.1997.638824
