Translator Disclaimer
30 October 2009 Scale adaptive FLIR target detection method for complex background
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74953K (2009)
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
According to the FLIR image of complex ground fixed target have disordered gray difference between target and background, and no base image available, we propose a target detection algorithm in FLIR imagery using scale space theory. First the reference image been created depending on the satellite dates, 2D Forward-looking image sequences of target regions created by using VRMap software according to the flying route. After performing LoG filtering on these reference images, we obtain a series of characteristic scale, where each scale is related to the size of target. Using these scales, several blob-like candidate regions can be found with the same size with reference image. Then the result is obtained between candidate regions and the reference image using Hausdorff measure and centroid distance. A simulation experiment is developed for the proposed algorithm and results show that our method has high accuracy and quickly performance and it has strong practicability.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jing Liu, Jiyin Sun, and Bing Han "Scale adaptive FLIR target detection method for complex background", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74953K (30 October 2009);

Back to Top