DocumentCode :
2085873
Title :
The image processing and target identification of laser imaging fuze
Author :
Chengtian, Song ; Keyong, Wang ; Lian, Zheng
Author_Institution :
Sch. of Aerosp. Sci. & Eng., Beijing Inst. of Technol., Beijing, China
Volume :
1
fYear :
2008
fDate :
17-19 Nov. 2008
Firstpage :
1117
Lastpage :
1120
Abstract :
Imaging detection can get the geometric shape and exterior features of target in very close distance, and supply the information for target recognition. But because of the large amount of the information and the real-time requirement, the image of target is always distorted and incomplete.To solve this probolem,the image proecessing and target identification method of laser imaging fuze are introduced. Firstly,a thinning algorithm for binary image is proposed to get the target skeleton. Secondly, the feature of the target is extracted, this kind of feature is very helpful on the hardware design of system. Finally ,the FMW (Feature Mapping Wave) network is developed from M-P network and ART theory to recognitize target status. This kind of image processing system including plane target identification and the engagement of missile and plane identification. The validity of the system has been validated.
Keywords :
feature extraction; image recognition; image thinning; object detection; feature mapping wave network; image processing; imaging detection; laser imaging fuze; target identification; target recognition; target skeleton; Bismuth; Data mining; Feature extraction; Image processing; Image recognition; Knowledge engineering; Laser noise; Missiles; Skeleton; Target recognition; FMW network; area feature; edge extraction; laser imaging fuze; target recognition; thinning processing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent System and Knowledge Engineering, 2008. ISKE 2008. 3rd International Conference on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4244-2196-1
Electronic_ISBN :
978-1-4244-2197-8
Type :
conf
DOI :
10.1109/ISKE.2008.4731097
Filename :
4731097
Link To Document :
بازگشت