A Novel Method for Plane Array Infrared Image to Detect Point Target

Author

Hong, Che ; Longhe, Sun

Author_Institution

No. 613 Inst., China Aviation Ind. Group I, Luoyang, China

Volume

2

fYear

2009

fDate

18-20 Aug. 2009

Firstpage

234

Lastpage

240

Abstract

Toward detection of moving point target in infrared images, a novel algorithm based on circular morphological filter and fuzzy fusion is built in this paper. Based on the real convex figure, morphological filter with circular structure is designed and the neural network is introduced to optimize the filter element. Based on minimum Bayesian risk criterion, the decision fusion is introduced and the sequential detection based on fuzzy decision fusion is built. Experimental results to real data show that the detection probability of images (SNRap2) can reach more than 98% with 1% false alarm with the novel algorithm so that it improves the detection performance.

Keywords

Bayes methods; image motion analysis; infrared imaging; neural nets; object detection; sensor fusion; circular morphological filter; fuzzy decision fusion; minimum Bayesian risk criterion; moving point target detection; neural network; plane array infrared image; Bayesian methods; Image sequences; Infrared detectors; Infrared imaging; Infrared surveillance; Matched filters; Neural networks; Object detection; Signal to noise ratio; Target tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Assurance and Security, 2009. IAS '09. Fifth International Conference on

Conference_Location

Xi´an

Print_ISBN

978-0-7695-3744-3

Type

conf

DOI

10.1109/IAS.2009.119

Filename

5283317