Title :
Weak Underwater Laser Image Target Detection Based on K-L Transform
Author :
Shu-bin, Yang ; Fu-yuan, Peng
Author_Institution :
Sch. of Electr. & Inf. Eng., Wuhan Inst. of Technol., Wuhan
Abstract :
In allusion to characteristics of low contrast, small dimension of target and complexity of background in underwater laser image, a method of detecting and describing underwater laser weak target using decorrelation trait of orthogonal transform is presented. K-L transform trace matrix that describes most image energy, shape distributing and also extrudes difference between target and background is used to detect the weak target. The results of computer simulation demonstrate that the proposed method can efficiently detect weak target in low signal-to-noise ratio underwater laser image.
Keywords :
Karhunen-Loeve transforms; decorrelation; laser ranging; object detection; optical correlation; underwater optics; K-L transform; background analysis; decorrelation; image energy; orthogonal transform; range gating; shape distribution; weak underwater laser image target detection; Delay effects; Image analysis; Laser modes; Laser noise; Laser theory; Object detection; Shape; Signal generators; Sonar detection; Underwater tracking; Background analysis; K-L transform; Range gating; Target detection; Underwater laser image;
Conference_Titel :
Computer Science and Software Engineering, 2008 International Conference on
Conference_Location :
Wuhan, Hubei
Print_ISBN :
978-0-7695-3336-0
DOI :
10.1109/CSSE.2008.244