Share Email Print
cover

Proceedings Paper

Knowledge-based automatic recognition technology of radome from infrared images
Author(s): Xiao-jian Wang; Ling Ma; Xiao Fang; Lei Chen; Hong-bin Lu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, a kind of knowledge-based automatic target recognition (ATR) technology of radome from infrared image is studied. The circular imaging of radome is used as the characteristic distinguished from background to realize target recognition. For the characteristic of low contrast of infrared image, brightness transformation is used to preliminarily enhance the contrast of the original image. In the light of the fact that target background outline statistically takes on vertical and horizontal directivity, a kind of revised Sobel operator with direction of 45°and 135°is adopted to detect edge feature so that background noise is effectively suppressed. To reduce the error ratio of target recognition from single frame image, the method to inspect the relativity of target recognition results of successive frames is adopted. The performance of the algorithm is tested using actually taken infrared radome images, and the right recognition ratio is around 90%, which turns out that this technology is feasible.

Paper Details

Date Published: 5 August 2009
PDF: 6 pages
Proc. SPIE 7383, International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications, 73834N (5 August 2009); doi: 10.1117/12.836626
Show Author Affiliations
Xiao-jian Wang, Beijing Information High-Tech Institute (China)
Ling Ma, Beijing Information High-Tech Institute (China)
Xiao Fang, Beijing Information High-Tech Institute (China)
Lei Chen, Beijing Information High-Tech Institute (China)
Hong-bin Lu, Beijing Information High-Tech Institute (China)


Published in SPIE Proceedings Vol. 7383:
International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications
Jeffery Puschell; Hai-mei Gong; Yi Cai; Jin Lu; Jin-dong Fei, Editor(s)

© SPIE. Terms of Use
Back to Top