3 October 1995 Target segmentation in IR imagery using a wavelet-based technique
Author Affiliations +
Segmentation of ground based targets embedded in clutter obtained by airborne Infrared (IR) imaging sensors is one of the challenging problems in automatic target recognition. In this paper a new texture based segmentation technique is presented that uses the statistics of 2D wavelet decomposition components of the local sections of the image. A measure of statistical similarity is then used to segment the image and separate the target from the background. This technique is applied on a set of real sequential IR imagery and has shown to produce a high degree of segmentation accuracy across varying ranges.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Firooz A. Sadjadi, Firooz A. Sadjadi, } "Target segmentation in IR imagery using a wavelet-based technique", Proc. SPIE 2588, Intelligent Robots and Computer Vision XIV: Algorithms, Techniques, Active Vision, and Materials Handling, (3 October 1995); doi: 10.1117/12.222669; https://doi.org/10.1117/12.222669


ATR System: An Air Force Perspective
Proceedings of SPIE (September 19 1987)
Machine recognition of objects using IR polarimetry
Proceedings of SPIE (May 23 1996)
Army's FLIR/ATR Evolution Path
Proceedings of SPIE (June 29 1989)
Wavelet-based technique for target segmentation
Proceedings of SPIE (July 04 1995)

Back to Top