Effects of image restoration on automatic acquisition of moving objects in thermal video sequences degraded by the atmosphere

 

By: Oren Haik and Yitzhak Yitzhaky

Ben Gurion University, Department of Electro-Optics

itzik@ee.bgu.ac.il

 

Abstract

This work aims to determine the effect of image restoration (de-blurring) on the ability to acquire moving objects detected automatically from long-distance thermal video signals. This is done by first, restoring the videos using a blind-deconvolution method developed recently, and then examining its effect on the geometrical features of automatically detected moving objects. Results show that for modern (low-noise and high-resolution) thermal imaging devices the geometrical features obtained from the restored videos, better resemble the true properties of the objects. These results correspond to a previous study which demonstrated that image restoration can significantly improve the ability of human observers to acquire moving objects from long-range thermal videos.

 

 

The following table links to short video sequences comparing performances of target detection and tracking with and without image restoration*

 

Moving Targets

(At about 3km distance)

Recorded vs. Restored

Motion Detection

(in Recorded vs. Restored)

Target Detection & tracking

(in Recorded vs. Restored)

Bicycle rider

Fig. 3 (a), (b)

Fig. 5 (a), (b)

Fig. 6 (a), (b)

Person with a pole

Fig. 3 (c), (d)

Fig. 5 (c), (d)

Fig. 6 (c), (d)

Walking man + Dog

Fig. 3 (e), (f)

Fig. 5 (e), (f)

Fig. 6 (e), (f)

Man on a roof

Fig. 3 (g), (h)

Fig. 5 (g), (h)

Fig. 6 (g), (h)

 

*

§                    Frequently the videos should be downloaded first before they can be run.

§                    In order to run the compressed videos, the Indeo 5.x Video Codec should be installed in the computer.

§         This codec is available in the site:

http://cas.bellarmine.edu/tietjen/Resources/Indeo%20V5.0/indeo_5.htm

 

Beck to Home Page