Color-based features for registering image time series

Prakash Duraisamy; Yassine Belkhouche; Stephen Jackson; Kamesh Namuduri; Bill Buckles

doi:10.1117/12.919632

2 May 2012 Color-based features for registering image time series

Prakash Duraisamy, Yassine Belkhouche, Stephen Jackson, Kamesh Namuduri, Bill Buckles

Proceedings Volume 8394, Algorithms for Synthetic Aperture Radar Imagery XIX; 83940U (2012) https://doi.org/10.1117/12.919632
Event: SPIE Defense, Security, and Sensing, 2012, Baltimore, Maryland, United States

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.

Citation Download Citation

Prakash Duraisamy, Yassine Belkhouche, Stephen Jackson, Kamesh Namuduri, and Bill Buckles "Color-based features for registering image time series", Proc. SPIE 8394, Algorithms for Synthetic Aperture Radar Imagery XIX, 83940U (2 May 2012); https://doi.org/10.1117/12.919632

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available