|
|
论文:2021,Vol:39,Issue(2):285-291 |
|
|
引用本文： |
|
|
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 |
|
|
JIN Leilei, LIANG Hong, YANG Changsheng. Sonar image recognition of underwater target based on convolutional neural network[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于卷积神经网络的水下目标声呐图像识别方法 |
|
| 金磊磊, 梁红, 杨长生 |
|
| 西北工业大学 航海学院, 陕西 西安 710072 |
| 摘要: |
| 水下目标识别是水下无人探测的一项核心技术，为提高水下自动目标识别准确率，提出基于卷积神经网络的目标声呐图像识别方法，针对声呐图像特点，设计了融合图像显著区域分割和金字塔池化的水下目标识别模型。基于流形排序显著性检测方法分割和裁剪图像，减小输入数据维度并减少图像背景对目标特征提取过程的干扰；通过堆叠卷积层和池化层，从原始声呐图像中自动学习目标的高层语义信息，避免人工提取图像特征对有效信息的破坏；提出采用空间金字塔池化方法提取特征图中的多尺度信息，弥补声呐图像细节信息少的缺陷，同时解决输入图像尺寸不一致的问题。结果表明，设计的卷积神经网络模型在实测声呐图像数据集上能够比常规卷积神经网络更准确、更快速地识别水下目标。 |
| 关键词:
自动目标识别
声呐图像
卷积神经网络
显著性
金字塔池化
|
|
| Sonar image recognition of underwater target based on convolutional neural network |
|
| JIN Leilei, LIANG Hong, YANG Changsheng |
|
| School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China |
| Abstract: |
| Underwater target recognition is one core technology of underwater unmanned detection. To improve the accuracy of underwater automatic target recognition, a sonar image recognition method based on convolutional neural network was proposed and the underwater target recognition model was established according to the characteristics of sonar images. Firstly, the sonar image was segmented and clipped with a saliency detection method to reduce the dimension of input data, and to reduce the interference of image background to the feature extraction process. Secondly, by using stacked convolutional layers and pooling layers, the high-level semantic information of the target was automatically learned from the input sonar image, to avoid damaging the effective information caused by extracting image features manually. Finally, the spatial pyramid pooling method was used to extract the multi-scale information from the sonar feature maps, which was to make up for the lack of detailed information of sonar images and solve the problem caused by the inconsistent size of input images. On the collected sonar image dataset, the experimental results show that the target recognition accuracy of the present method can recognize underwater targets more accurately and efficiently than the conventional convolutional neural networks. |
| Key words:
automatic target recognition
sonar image
convolutional neural network
saliency detection
spatial pyramid pooling
|
|
| 收稿日期: 2020-08-05
修回日期:
|
| DOI: 10.1051/jnwpu/20213920285 |
| 基金项目: 国家自然科学基金（61971354，61771398）资助 |
| 通讯作者:
Email： |
| 作者简介: 金磊磊(1991-),西北工业大学博士研究生,主要从事水下目标识别研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 金磊磊 在本刊中的所有文章 |
| 梁红 在本刊中的所有文章 |
| 杨长生 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] KARRAS C, MARANTOS P, BECHLIOULIS C, et al. Unsupervised online system identification for underwater robotic vehicles[J]. IEEE Journal of Oceanic Engineering, 2018, 44(3):1-22
[2] KUMAR N, MITRA U, NARAYANAN S. Robust object classification in underwater sidescan sonar images by using reliability-aware fusion of shadow features[J]. Oceanic Engineering, 2015, 40(3):592-606
[3] MYERS V, FAWCETT J. A template matching procedure for automatic target recognition in synthetic aperture sonar imagery[J]. IEEE Signal Processing Letters, 2010, 17(7):683-686
[4] KAMAL S, MOHAMMED K, PILLAI S, et al. Deep learning architectures for underwater target recognition[C]//2013 Ocean Electronics(SYMPOL), 2013
[5] FERGUSON L, RAMAKRISHNAN R, WILLIAMS B, et al. Convolutional neural networks for passive monitoring of a shallow water environment using a single sensor[C]//2017 IEEE International Conference on Acoustics, Speech and Signal Processing, 2017
[6] WILLIAMS D. Underwater target classification in synthetic aperture sonar imagery using deep convolutional neural networks[C]//International Conference on Pattern Recognition, 2017:2497-2502
[7] 宋达. 基于深度学习的水下目标识别方法研究[D]. 成都:电子科技大学, 2018 SONG Da. Research on deep learning-based underwater target recognition method[D]. Chengdu:University of Electronic Science and Technology of China, 2018(in Chinese)
[8] 李琛, 黄兆琼, 徐及, 等. 使用深度学习的多通道水下目标识别[J]. 声学学报, 2020, 45(4):506-514 LI Chen, HUANG Zhaoqiong, XU Ji, et al. Multi-channel underwater target recognition using deep learning[J]. Acta Acustica, 2020, 45(4):506-514(in Chinese)
[9] ZEILER M, FERGUS R. Visualizing and understanding convolutional networks[C]//European Conference on Computer Rision Springes, Cham, 2014
[10] ZEILER M, TAYLOR G, FERGUS R. Adaptive deconvolutional networks for mid and high level feature learning[C]//2011 International Conference on Computer Vision, 2011:2018-2025
[11] 王靖宇. 基于视听觉信息的机器觉察与仿生智能感知方法研究[D]. 西安:西北工业大学, 2016 WANG Jingyu. The Research of machine awareness and bio-inspired perception based on audio-visual information[D]. Xi'an:Northwestern Polytechnical University, 2016(in Chinese)
[12] YANG C, ZHANG L, LU H, et al. Saliency detection via graph-based manifold ranking[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013
[13] HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Trans on Pattern Analysis & Machine Intelligence, 2014, 37(9):346-361
[14] HE K, ZHANG X, REN S, et al. Delving deep into rectifiers:surpassing human-level performance on imagenet classification[C]//2015 International Conference on Computer Vision, 2015
[15] KINGMA D, BA J. Adam:a method for stochastic optimization[C]//Proceedings of International Conference on Learning Representations, 2015 |
|
|
|
相关文献: |
|
|
1．金磊磊, 梁红, 杨长生.基于显著性检测的声呐图像快速降噪研究[J]. 西北工业大学学报, 2019,37(1): 80-86 |
|
|
|
|
|
|
