Share Email Print

Proceedings Paper

Color-based features for registering image time series
Author(s): Prakash Duraisamy; Yassine Belkhouche; Stephen Jackson; Kamesh Namuduri; Bill Buckles
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Change detection is a important problem which plays a crucial role in many applications like environmental monitoring and city planning. The goal of change detection is to detects changes in specific features within certain time intervals. In this paper, we develop an automated method for detecting changes in urban areas over a period of time using lines and colors as features. Our proposed algorithm consists of two steps. In the first step, we detect corresponding lines between two images taken over different periods of time and we match them using our search algorithm. To be specific, first we use the Hough transform to detect lines. In the second step, we use colors to detect the changes over static and dyanmic objects. In a test of the method using aerial images over the our university campus area, we obtained reasonably good pose recovery and detection of scene changes.

Paper Details

Date Published: 2 May 2012
PDF: 10 pages
Proc. SPIE 8394, Algorithms for Synthetic Aperture Radar Imagery XIX, 83940U (2 May 2012); doi: 10.1117/12.919632
Show Author Affiliations
Prakash Duraisamy, Univ. of North Texas (United States)
Yassine Belkhouche, Univ. of North Texas (United States)
Stephen Jackson, Univ. of North Texas (United States)
Kamesh Namuduri, Univ. of North Texas (United States)
Bill Buckles, Univ. of North Texas (United States)

Published in SPIE Proceedings Vol. 8394:
Algorithms for Synthetic Aperture Radar Imagery XIX
Edmund G. Zelnio; Frederick D. Garber, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?