|
|
论文:2024,Vol:42,Issue(3):417-425 |
|
|
引用本文： |
|
|
刘晓春, 杨云川, 胡友峰, 杨向锋, 李永胜, 肖霖. 基于水下运动目标亮点图像模型的数据增强[J]. 西北工业大学学报 |
|
|
LIU Xiaochun, YANG Yunchuan, HU Youfeng, YANG Xiangfeng, LI Yongsheng, XIAO Lin. Data augmentation based on highlight image models of underwater maneuvering target[J]. Journal of Northwestern Polytechnical University |
|
|
|
|
|
|
|
| 基于水下运动目标亮点图像模型的数据增强 |
|
| 刘晓春1, 杨云川1, 胡友峰2, 杨向锋1, 李永胜1, 肖霖1 |
|
1. 中国船舶集团公司 第705研究所, 陕西 西安 710077;
2. 中国船舶集团公司 第705研究所昆明分部, 云南 昆明 650102 |
| 摘要: |
| 随着水声对抗技术的发展,深度学习技术被应用于水下目标的回波几何特征识别,但面临着样本稀缺问题。改进水下目标亮点模型,建立主动声呐目标回波信息方程,结合二者并进行空间位置的有规律变化,构成水下运动目标的亮点图像模型。以水下航行体为例详细介绍了模型的构建过程,并建立4种典型尺度诱饵的亮点图像模型实例,生成5种目标的多空间状态数据样本。设计eHasNet-5卷积分类网络,利用生成数据进行网络训练、验证和测试。试验实测数据测试表明,目标亮点图像生成模型为深度学习在主动声呐目标识别领域的应用提供了一种新的数据增强方法,生成数据训练的网络具备二维尺度目标分类能力。 |
| 关键词:
亮点图像
数据增强
目标分类
深度学习
|
|
| Data augmentation based on highlight image models of underwater maneuvering target |
|
| LIU Xiaochun1, YANG Yunchuan1, HU Youfeng2, YANG Xiangfeng1, LI Yongsheng1, XIAO Lin1 |
|
1. The 705 Research Institute, China State Shipbuilding Corporation Limited, Xi'an 710077, China;
2. Kunming Branch of the 705 Research Institute, China State Shipbuilding Corporation Limited, Kunming 650102, China |
| Abstract: |
| With the development of underwater acoustic countermeasure technology, deep learning is applied to recognize echo geometry features of underwater targets, but it faces the problem of sample scarcity. In this paper, we improved the underwater target highlight model, and established the target echo information equation of active sonar. By changing the spatial positions of target and sonar regularly, we performed the highlight image models of underwater maneuvering targets. Taking an underwater vehicle as an example, the model construction process was introduced in detail, and highlight image models of four typical acoustic scale decoys were also established, and five multi-space state highlight image data samples were generated. The eHasNet-5 convolutional classification network was designed, and the network was trained, verified and tested with the generated data. Finally, the experimental data test shows that the target highlight image generation models provide a new data augmentation method for the application of deep learning in active sonar target recognition, and the trained network by generated data has the ability to classify two-dimensional objects. |
| Key words:
highlight image
data augmentation
target classification
deep learning
|
|
| 收稿日期: 2023-05-26
修回日期:
|
| DOI: 10.1051/jnwpu/20244230417 |
| 通讯作者: 杨云川(1972—),研究员 e-mail:yunchuanyang@163.com
Email：yunchuanyang@163.com |
| 作者简介: 刘晓春(1982—),博士研究生
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] SUN Tongjing, JIN Jiwei, LIU Tong, et al. Active sonar target classification method based on fisher's dictionary learning[J]. Applied Sciences, 2021, 11(22): 10635
[2] WANG Zirui, WU Jing, WANG Haitao, et al. A torpedo target recognition method based on the correlation between echo broadening and apparent angle[J]. Applied Sciences, 2022, 12(23): 12345
[3] WU Yushuang, LI Xiukun, WANG Yang. Extraction and classification of acoustic scattering from underwater target based on Wigner-Ville distribution[J]. Applied Acoustics, 2018, 138: 52-59
[4] 施丹华, 胡必楠, 黄俊希. 水声对抗器材发展及其趋势分析[J]. 舰船科学技术, 2020, 42(9): 174-180 SHI Danhua, HU Binan, HUANG Junxi. State-of-the-art of foreign underwater acoustic countermeasures and their development trends[J]. Ship Science and Technology, 2020,42(9): 174-180(in Chinese)
[5] 张明洋, 刘雨东. 声诱饵反鱼雷水声对抗发展现状及趋势[J]. 数字海洋与水下攻防, 2023, 6(1): 111-117 ZHANG Mingyang, LIU Yudong. Development status and trend of acoustic decoy anti-torpedo underwater acoustic countermeasures[J]. Digital Ocean ＆ Underwater Warfare, 2023, 6(1): 111-117(in Chinese)
[6] 何文翔, 王海涛, 颜彬. 二维尺度目标模拟系统: 中国, CN201710862224.7[P]. 2018-04-06
[7] LI Junhao, YANG Honghui. The underwater acoustic target timbre perception and recognition based on the auditory inspired deep convolutional neural network[J]. Applied Acoustics, 2021, 182: 108210
[8] 金磊磊, 梁红, 杨长生. 基于卷积神经网络的水下目标声呐图像识别方法[J]. 西北工业大学学报, 2021,39(2): 285-291 JIN Leilei, LIANG Hong, YANG Changsheng. Sonar image recognition of underwater target based on convolutional neural network[J]. Journal of Northwestern Polytechnical University, 2021,39(2): 285-291(in Chinese)
[9] LIU Feng, SHEN Tangsheng, LUO Zailei, et al. Underwater target recognition using convolutional recurrent neural networks with 3-D Mel-spectrogram and data augmentation[J]. Applied Acoustics, 2021, 178: 107989
[10] WANG Zhong, LIU Liwen, WANG Chenyu, et al. Data enhancement of underwater high-speed vehicle echo signals based on improved generative adversarial networks[J]. Electronics, 2022, 11(15): 2310
[11] 曹文靖. 小样本水下目标识别的深层神经网络设计与加速[D]. 天津: 天津工业大学, 2021 CAO Wenjing. Design and acceleration of deep neural network for few-shot underwater target recognition[D]. Tianjin: Tiangong University, 2021(in Chinese)
[12] 汤渭霖. 声呐目标回波的亮点模型[J]. 声学学报, 1994, 19(2): 92-100 TANG Weilin. Highlight model of echoes from sonar targets[J]. Acta Acustica 1994, 19(2): 92-100(in Chinese)
[13] ZHAO Anbang, HE Cheng, HUI Juan, et al. Research of sonar echo highlights measurement[C]//OCEANS 2014-TAIPEI, Taipei, 2014: 1-9
[14] 刘文远, 赵金海. 基于修正亮点模型的水下体目标建模技术[J]. 鱼雷技术, 2010,18(5): 352-356 LIU Wenyuan, ZHAO Jinhai. Underwater target modeling technology based on modified highlight model[J]. Torpedo Technology, 2010,18(5): 352-356(in Chinese)
[15] 邓开, 向小梅, 顾颉. 尺度式声诱饵多亮点模型[J]. 声学技术, 2011, 30(2): 201-205 DENG Kai, XIANG Xiaomei, GU Jie. Multi-highlight model of scaling acoustic decoy[J]. Technical Acoustics, 2011, 30(2): 201-205(in Chinese)
[16] ZHAO Song, LI Lanrui, ZHANG Xinhua, et al. Simulation of backscatter signal of submarine target based on spatial distribution characteristics of target intensity[C]//2021 OES China Ocean Acoustics, Harbin, 2021: 234-239
[17] 邓伟. 潜艇精细回波特征在鱼雷自导中的应用[D]. 上海: 上海交通大学, 2014 DENG Wei. Application of fine echo characteristics of submarine in torpedo homing[D]. Shanghai: Shanghai Jiaotong University, 2014(in Chinese)
[18] 刘晓春, 董春凯. 基于目标空间尺度特征末程识别潜艇和诱饵的方法研究[J]. 鱼雷技术, 2008, 16(5): 46-50 LIU Xiaochun, DONG Chunkai. A method of distinguishing submarine and acoustic decoy based on features of target space dimension[J]. Torpedo Technology, 2008, 16(5): 46-50(in Chinese)
[19] LONG Yang, LIU Li, SHEN Fumin, et al. Zero-shot learning using synthesised unseen visual data with diffusion regularisation[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2018, 40(12): 2498-2512 |
|
|
|
|
|
|
|
