-
Color Balancing for Change Detection in Multitemporal Images,
Jim Thomas, Kevin W. Bowyer and Ahsan Kareem,
IEEE Workshop on Applications of Computer Vision,
January 2012, Colorado Springs, CO.
pdf of this paper.
... In this paper we address color balancing for the purpose of change detection.
... We evaluated the proposed method against other state-of-the-art ones using a
database consisting of aerial image pairs. The test image pairs were taken at
different times, under different lighting conditions, and with different scene
geometries and camera positions. On this database, our proposed approach
outperformed other state-of-the-art algorithms.
-
Towards a robust automated hurricane damage assessment from high-resolution images,
James Thomas, Ahsan Kareem, and Kevin W. Bowyer,
13th International Conference on Wind Engineering (ICWE 13), July 2011.
pdf of this paper.
In the event of a natural disaster such as hurricane or earthquake, estimating the extent of
damage is necessary for implementing fast and effective recovery measures. Images of affected
areas are easily obtained through satellite or aerial sensors. The key objects of interest
in such images are buildings, as damage directly impacts lives. This work aims to build a system
capable of fine-grained damage analysis by comparing before and after storm images. ...
-
Efficacy of Damage Detection Measures from Aerial Images,
Jim Thomas, Ahsan Kareem and Kevin W. Bowyer,
11-th Americas Conference on Wind Engineering, June 2009.
pdf of this paper.
Estimating the extent of damage caused by natural disasters is necessary for
implementing effective recovery measures. Aerial images of affected areas are
easily obtained through satellite or aerial sensors. A careful analysis of
images from before and after an event facilitates rapid detection and assessment
of damage. Significant previous research has been done on developing measures to
quantify the damage. In this study we evaluate the efficacy of existing change
measures used to estimate damage. Determining the efficacy of these damage measures
in definitive characterization of damage states is necessary for accurate automated
assessment of windstorm damage.
|