Extraction of Mine Characteristics
The key to the settlement of the target recognition lies in exact characteristics of targets. which possess lower dimension. An acoustic scatter can be described in the time domain by its impulse response function, or in the frequency domain by its form function. None of functions is fully separable in either the time or frequency domain. In this paper, a new method-FDWT method for extracting elastic component from mine is given. which is the discrete wavelet transform of the form function. Its advantage is simpler structure of algorithm and fewer dimensions of characteristics. This method is used to extract the acoustic components from the experiment data on the lake and identify three targets by trained BP neural network. A higher ratio of identification is obtained.
Underwater target Extraction of Characteristics Wavelet Transform
Li Xiukun Yang Shi-e Huang Yiwang
Underwater Acoustical Engineering Institute, Harbin Engineering University, Harbin 150001, China
国际会议
北京
英文
174-180
2007-10-01（万方平台首次上网日期，不代表论文的发表时间）