Title :
Object recognition and tracking for remote video surveillance
Author :
Foresti, Gian Luca
Author_Institution :
Dipt. di Matematica e Inf., Udine Univ., Italy
fDate :
10/1/1999 12:00:00 AM
Abstract :
A system for real-time object recognition and tracking for remote video surveillance is presented. In order to meet real-time requirements, a unique feature, i.e., the statistical morphological skeleton, which achieves low computational complexity, accuracy of localization, and noise robustness has been considered for both object recognition and tracking. Recognition is obtained by comparing an analytical approximation of the skeleton function extracted from the analyzed image with that obtained from model objects stored into a database. Tracking is performed by applying an extended Kalman filter to a set of observable quantities derived from the detected skeleton and other geometric characteristics of the moving object. Several experiments are shown to illustrate the validity of the proposed method and to demonstrate its usefulness in video-based applications
Keywords :
Kalman filters; computational complexity; feature extraction; image sequences; image thinning; mathematical morphology; nonlinear filters; object recognition; statistical analysis; surveillance; video signal processing; analytical approximation; database; experiments; extended Kalman filter; feature extraction; geometric characteristics; image sequences; localization accuracy; low computational complexity; model objects; noise robustness; real-time object recognition; real-time object tracking; remote video surveillance; skeleton function; statistical morphological skeleton; video-based applications; Computational complexity; Image analysis; Image databases; Image recognition; Noise robustness; Object recognition; Real time systems; Skeleton; Spatial databases; Video surveillance;
Journal_Title :
Circuits and Systems for Video Technology, IEEE Transactions on
