Share Email Print
cover

Proceedings Paper

Non-cooperative stationary ground targets detection based on IRST
Author(s): Degui Yang; Xufeng Zhang; Hongqiang Wang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

There are many difficulties in detection for IRST as follows: (1) complex background and lack of target's motion information; (2) lack of prior information, the non-cooperative target is difficult to match; (3) there is big span of the imaging scene distance, and the image pixel gray cannot reflect the radiation of scene and target accurately. To overcome the difficulties, the paper presented an algorithm of non-cooperative stationary ground target detection based on feature set. Firstly, the spatial station model of imaging scene was founded to count the scene distance, and then we pretreat the IR image to get the apparent temperature image which can reflect the radiation of the scene truly. Secondly, the feature set was extracted in the sliding window of the pixel neighborhood, and the hypothesis test was used to detect the stationary targets. Lastly the sliding window was adjusted adaptively according to the target size. Simulation results demonstrate that the proposed algorithm has better detection performance to the ground non-cooperative stationary targets.

Paper Details

Date Published:
PDF: 8 pages
Proc. SPIE 8295, Image Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II, 82951C; doi: 10.1117/12.907329
Show Author Affiliations
Degui Yang, National Univ. of Defense Technology (China)
Xufeng Zhang, National Univ. of Defense Technology (China)
Hongqiang Wang, National Univ. of Defense Technology (China)


Published in SPIE Proceedings Vol. 8295:
Image Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II
Karen O. Egiazarian; Sos S. Agaian; Atanas P. Gotchev; John Recker; Guijin Wang, Editor(s)

© SPIE. Terms of Use
Back to Top