Share Email Print

Proceedings Paper

Global motion estimation and target detection with region search
Author(s): Lei Ma; Jennie Si; Glen P. Abousleman
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper proposes a global motion model estimation and target detection algorithm for surveillance and tracking applications. The proposed algorithm analyzes the foreground-background structure of a video frame, and detects objects with independent motions. Each video frame is first segmented into regions where image intensity and motion fields are homogeneous. Then global motion model fitting is accomplished using linear regression of motion vectors through iterations of region search. With the use of non-parametric estimation of motion field, the proposed methods is more efficient than direct estimation of motion parameter; and it is able to detect outliers where independent moving targets are located. The proposed algorithm is more computationally efficient than parametric motion estimation, and also more robust than a variety of background compensation based detection.

Paper Details

Date Published: 17 May 2006
PDF: 10 pages
Proc. SPIE 6235, Signal Processing, Sensor Fusion, and Target Recognition XV, 623506 (17 May 2006); doi: 10.1117/12.665801
Show Author Affiliations
Lei Ma, Arizona State Univ. (United States)
Jennie Si, Arizona State Univ. (United States)
Glen P. Abousleman, General Dynamic C4 Systems (United States)

Published in SPIE Proceedings Vol. 6235:
Signal Processing, Sensor Fusion, and Target Recognition XV
Ivan Kadar, Editor(s)

© SPIE. Terms of Use
Back to Top