DocumentCode :
1719909
Title :
Feature extraction of underwater target based on the time-frequency analysis
Author :
Guo-jun, Zhang ; Pan-pan, Wang ; Peng, Wang
Author_Institution :
Nat. Key Lab. for Electron. Meas. Technol., North Univ. of China, Taiyuan, China
Volume :
3
fYear :
2010
Abstract :
Target feature extraction is a prerequisite for the target recognition. This paper mainly researched on extracting the features of underwater targets based on the time-frequency analysis. The method of time-frequency analysis-S transform was introduced and applied in underwater signal processing. The single-frequency signal, pulse signal and two kinds of ship-radiated noises collected by hydrophone were processed by S transform. According to the time-frequency distribution, the phase information and the instantaneous-frequency estimation of signals were studied. Then singular value based on S transform was proposed as another feature of ships. The results proved that the features of underwater targets can be extracted effectively by S transform.
Keywords :
feature extraction; hydrophones; object detection; underwater acoustic communication; feature extraction; hydrophone; pulse signal; single-frequency signal; target recognition; time frequency analysis-S transform; time-frequency analysis; underwater signal processing; underwater target; Feature extraction; Marine vehicles; Matrix decomposition; Noise; Time frequency analysis; Transforms; S transform; ship-radiated noises; singular values; time-frequency analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing Systems (ICSPS), 2010 2nd International Conference on
Conference_Location :
Dalian
Print_ISBN :
978-1-4244-6892-8
Electronic_ISBN :
978-1-4244-6893-5
Type :
conf
DOI :
10.1109/ICSPS.2010.5555704
Filename :
5555704
Link To Document :
بازگشت