基于海豚听觉系统模型的水下目标识别

周 卓; 梁 红; 杨长生; 赵国贵

doi:10.11993/j.issn.2096-3920.2021.02.003

基于海豚听觉系统模型的水下目标识别

doi: 10.11993/j.issn.2096-3920.2021.02.003

西北工业大学航海学院, 陕西西安, 710072

基金项目: 国家自然基金项目资助(61971354, 61771398).

详细信息

作者简介:
周卓(1996-), 男, 在读硕士, 主要研究方向为水下信号处理.

中图分类号: TJ630 TN911.72 Q811.211
计量
- 文章访问数: 432
- HTML全文浏览量: 23
- PDF下载量: 167
- 被引次数: 0
出版历程
- 收稿日期: 2020-07-14
- 修回日期: 2020-07-24
- 刊出日期: 2021-04-30

Underwater Target Identification Based on Dolphin Auditory System Model

School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, China

摘要

摘要: 从目标的主动声呐回波中提取其特征信息是实现水下目标分类识别的有效手段。动物声呐在水下目标识别中表现出的优异性能为人工声呐提供了解决方法。文中以宽吻海豚喀啦信号作为主动声呐的发射信号, 分别利用小波变换和海豚听觉系统模型2种方法提取了目标回波特征并作为支持向量机的输入进行分类。将通过海豚听觉系统模型得到的时谱图作为卷积神经网络的输入, 对目标进行分类识别。研究表明, 相比于小波变换方法, 利用基于海豚听觉系统模型的特征提取方法进行目标分类识别的效果更好; 结合卷积神经网络, 采用海豚喀啦信号结合海豚听觉系统模型在水下目标识别中可以获得更好的结果。
- 海豚喀啦信号 /
- 海豚听觉系统 /
- 目标分类识别
Abstract: Extracting feature information from the active sonar echo of target is an effective method to realize underwater target classification and identification. The excellent performance of animal sonar in underwater target identification provides a solution for artificial sonar. In this study, the click signal of bottlenose dolphin is used as the transmitting signal of active sonar. The echo characteristics of the target are extracted by wavelet transform and model of dolphin auditory system, and are classified as the input of support vector machine. In addition, this paper proposes an idea that the time spectrum obtained by the model based on dolphin auditory system is used as the input of convolution neural network to classify and identify the target. The results show that compared with that of the wavelet transform method, the feature extraction method based on the computer model of dolphin auditory system is better for target classification and identification. Combining with convolution neural network, using dolphin click signal and model of dolphin auditory system can obtain better results in underwater target identification.
- dolphin click signal /
- dolphin auditory system /
- target classification and identification

HTML全文

参考文献(14)

[1]	Au W W L, Scheifele P M. The Sonar of Dolphins[J]. The Journal of the Acoustical Society of America, 1993, 95(1): 585-586.
[2]	Au W W L, Hastings M C. Principles of Marine Bio-acoustics[M]. New York : Springer US, 2008.
[3]	Au W W L, Pawloski D A. Cylinder Wall Thickness Difference Discrimination by an Echolocating Atlantic Bottlenose Dolphin[J]. Journal of Comparative Physiology. A: Neuroethology, Sensory, Neural and Behavioral Physiology, 1992, 170(1): 41-47.
[4]	Branstetter B K, Mercado E, Au W W L. Representing Multiple Discrimination Cues in a Computational Model of the Bottlenose Dolphin Auditory System[J]. The Journal of the Acoustical Society of America, 2007, 122(4): 2459.
[5]	牛富强, 杨燕明, 文洪涛, 等. 瓶鼻海豚的Click声信号特性[J]. 声学技术, 2011, 30(2): 148-152.
[6]	牛富强, 薛睿超, 周在明, 等. 印太瓶鼻海豚(Tursiops aduncus)通讯声信号分类及特征参数的环境差异性分析[J]. 声学学报, 2020, 45(2): 189-195. Niu Fu-qiang, Xue Rui-chao, Zhou Zai-ming, et al. Anal-ysis of Differences on Whistle Classification and Characteristics of Indo-Pacific Bottlenose Dolphins(Tursiops aduncus) in Different Environment[J]. Acta Acustica, 2020, 45(2): 189-195.
[7]	陈晟, 牛富强, 林长伦, 等. 不同环境下瓶鼻海豚click信号及仿真分析[J]. 声学技术, 2019, 38(4): 452-458.
[8]	景志宏, 林钧清, 钱建立, 等. 水下目标识别技术的研究[J]. 舰船科学技术, 1999, 21(4): 38-44.
[9]	Capus C, Pailhas Y, Brown K, et al. Bio-inspired Wideband Sonar Signals Based on Observations of the Bottlenose Dolphin(Tursiops Truncatus)[J]. The Journal of the Acoustical Society of America, 2007, 121(1): 594-604.
[10]	任超. 基于支持向量机的水下目标识别技术[D]. 西安: 西北工业大学, 2016.
[11]	Au W W L, Andersen L N, René Rasmussen A, et al. Neural Network Modeling of a Dolphin’s Sonar Discrimination Capabilities[J]. The Journal of the Acoustical Society of America, 1995, 98(1): 43-50.
[12]	Lecun Y, Bengio Y, Hinton G. Deep Learning[J]. Nature, 2015, 521(7553): 436.
[13]	Lecun Y, Bottou L. Gradient-based Learning Applied to Document Recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[14]	Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition[EB/OL]. ArXiv, (2014-09-04)[2020-07-14]. https://arxiv.org/abs/1409. 1556.