|
|
论文:2023,Vol:41,Issue(1):153-159 |
|
|
引用本文： |
|
|
曹禹, 刘光宇, 穆琳琳, 曾志勇, 赵恩铭, 邢传玺. 基于多区域最优选择策略的声呐图像目标检测[J]. 西北工业大学学报 |
|
|
CAO Yu, LIU Guangyu, MU Linlin, ZENG Zhiyong, ZHAO Enming, XING Chuanxi. Sonar image target detection based on multi-region optimal selection strategy[J]. Journal of Northwestern Polytechnical University |
|
|
|
|
|
|
|
| 基于多区域最优选择策略的声呐图像目标检测 |
|
| 曹禹1, 刘光宇1, 穆琳琳2, 曾志勇1, 赵恩铭1, 邢传玺3 |
|
1. 大理大学 工程学院, 云南 大理 671003;
2. 哈尔滨工程大学 未来技术学院, 黑龙江 哈尔滨 150001;
3. 云南民族大学 电气信息工程学院, 云南 昆明 650504 |
| 摘要: |
| 为了解决侧扫声呐图像目标检测受噪声和阴影区域影响,难以准确检测目标的问题,提出一种谱聚类结合熵权法的多区域最优选择策略的目标检测方法。根据先验知识提前设定谱聚类的聚类数,将声呐图像的像素聚类为多个不同的区域;提取每个区域具有的平移、旋转和缩放的不变性特征,用于构建多区域的特征准则矩阵;利用熵权法对该特征准则矩阵计算各特征的权重以及每个区域的综合加权分数,即可得到最终的目标区域。实验结果表明,所提方法不仅能够有效地克服侧扫声呐图像中的噪声和阴影区域带来的不利影响,还可以在图像聚类后的多个区域中实现最优目标区域的选择,验证了所提方法的可行性和有效性。 |
| 关键词:
声呐图像
目标
图像分割
谱聚类
特征选择
熵权法
|
|
| Sonar image target detection based on multi-region optimal selection strategy |
|
| CAO Yu1, LIU Guangyu1, MU Linlin2, ZENG Zhiyong1, ZHAO Enming1, XING Chuanxi3 |
|
1. School of Engineering, Dali University, Dali 671003, China;
2. School of Future Technology, Harbin Engineering University, Harbin 150001, China;
3. School of Electrical and Information Technology, Yunnan Minzu University, Kunming 650504, China |
| Abstract: |
| To overcome the adverse effects of noise and shadow regions on target detection in side-scan sonar images, more precisely, it is difficult to accurately detect targets, a target detection technology based on a multi-region optimal selection strategy of spectral clustering combined with the entropy weight method is proposed in this study. First, the cluster numbers for spectral clustering are set in advance based on prior knowledge, and the pixels of the sonar image are clustered into several different regions. Second, the invariable features of translation, rotation and scaling up that each region is extracted and used to construct the feature criterion matrix for the multiple regions. Last, the entropy weight method is used to calculate the weights of each feature and the comprehensive weighted score of each region for this feature criterion matrix to obtain the final target region. Experimental results show that the proposed method can effectively overcome the adverse effects of noise and shadow regions in side-scan sonar images, but also achieve the selection of optimal target region among multiple regions after image clustering, thus verifying the feasibility and effectiveness of the proposed method in this study. |
| Key words:
sonar image
objective
image segmentation
spectral clustering
feature selection
entropy weight method
|
|
| 收稿日期: 2022-05-03
修回日期:
|
| DOI: 10.1051/jnwpu/20234110153 |
| 基金项目: 国家自然科学基金(62065001,61761048)与云南省地方本科高校基础研究联合专项资金[2019FH001(-066)]资助 |
| 通讯作者: 刘光宇(1982-),大理大学副研究员,主要从事水下声呐图像处理研究。e-mail:dlu_cy@163.com
Email：dlu_cy@163.com |
| 作者简介: 曹禹(1994-),大理大学硕士研究生,主要从事水下声呐图像处理研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] WANG H, GAO N, XIAO Y, et al. Image feature extraction based on improved FCN for UUV side-scan sonar[J]. Marine Geophysical Research, 2020, 41(4):1-17
[2] 赵建虎, 尚晓东, 张红梅. 水深数据约束下的声呐图像海底地形恢复方法[J]. 中国矿业大学学报, 2017, 46(2):443-448 ZHAO Jianhu, SHANG Xiaodong, ZHANG Hongmei. Recovering seabed topography from sonar image with constraint of sounding data[J]. Journal of China University of Mining & Technology, 2017, 46(2):443-448 (in Chinese)
[3] 罗俊杰, 迟骋, 张春华, 等. 时域压缩合成孔径超分辨水声成像算法[J]. 声学学报, 2021, 46(6):1144-1152 LUO Junjie, CHI Cheng, ZHANG Chunhua, et al. A time-domain compression synthetic aperture super-resolution underwater acoustic imaging algorithm[J]. Acta Acustica, 2021, 46(6):1144-1152 (in Chinese)
[4] DIVAS K, HELGE R, DAVID S, et al. Object detection in sonar images[J]. Electronics, 2020, 9(7):1180
[5] GRABEK J, CYGANEK B. Speckle noise filtering in side-scan sonar images based on the tucker tensor decomposition[J]. Sensors, 2019, 19(13):2903
[6] ZHAO J, MAI D, ZHANG H, et al. Automatic detection and segmentation on gas plumes from multibeam water column images[J]. Remote Sensing, 2020, 12(18):3085
[7] HUO G, WU Z, LI J. Underwater object classification in side-scan sonar images using deep transfer learning and semisynthetic training data[J]. IEEE Access, 2020, 8:47407-47418
[8] SONG Y, LIU P. Segmentation of sonar images with intensity inhomogeneity based on improved MRF[J]. Applied Acoustics, 2020, 158:107051
[9] 高山, 许坚, 张鹏. 声呐图像水雷目标自动识别[J]. 水雷战与舰船防护, 2006(1):42-45 GAO Shan, XU Jian, ZHANG Peng. Automatic recognition of mine targets in sonar images[J]. Mine Warfare and Ship Protection, 2006(1):42-45 (in Chinese)
[10] WANG X, LI Q, YU Y, et al. Evaluation criterion of underwater object clustering segmentation with pulse-coupled neural network[J]. IET Image Processing, 2020, 14(16):4076-4085
[11] LI J, JIANG P, ZHU H. A local region-based level set method with Markov random field for side-scan sonar image multi-level segmentation[J]. IEEE Sensors Journal, 2020, 21(1):510-519
[12] LI K, LIU Z, LU J, et al. Detection algorithm of the shipwreck target based on residual contour information[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2021, 35(2):2150006
[13] FAN Z, XIA W, LIU X, et al. Detection and segmentation of underwater objects from forward-looking sonar based on a modified mask RCNN[J]. Signal, Image and Video Processing, 2021, 15(6):1135-1143
[14] WANG J, JIANG J. SA-net:a deep spectral analysis network for image clustering[J]. Neurocomputing, 2020, 383:10-23
[15] ZHANG C, ZHU G, LIAN B, et al. Image segmentation based on multiscale fast spectral clustering[J]. Multimedia Tools and Applications, 2021, 80(16):24969-24994
[16] 李鑫, 李哲民, 魏居辉, 等. 基于特征分离的跨域自适应学习模型[J]. 计算机研究与发展, 2022, 59(1):105-117 LI Xin, LI Zhemin, WEI Juhui, et al. Cross-domain adaptive learning model based on feature separation[J]. Journal of Computer Research and Development, 2022, 59(1):105-117 (in Chinese)
[17] LIU P, SONG Y. Segmentation of sonar imagery using convolutional neural networks and Markov random field[J]. Multidimensional Systems and Signal Processing, 2020, 31(1):1-27
[18] LI D W, CHEN J B, QIU M L, et al. The evaluation and analysis of the entropy weight method and the fractional grey model study on the development level of modern agriculture in huizhou[J]. Mathematical Problems in Engineering, 2021, 2021(10):1-8
[19] 郭海涛, 田坦, 张春田. 基于模糊聚类的声呐图像多区域分割[J]. 海洋技术, 2004(3):39-40 GUO Haitao, TIAN Tan, ZHANG Chuntian. Multi-region segmentation of sonar image based on fuzzy clustering[J]. Marine Technology, 2004(3):39-40 (in Chinese) |
|
|
|
相关文献: |
|
|
1．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 |
|
|
2．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 |
|
|
3．张君昌, 周艳玲, 万锦锦.融合超像素与动态图匹配的视频跟踪[J]. 西北工业大学学报, 2017,35(1): 133-137 |
|
|
4．黄伟, 杨文姬, 曾璟, 曾舒如, 陈光.基于谱聚类和增量学习的运动目标物体检测算法研究[J]. 西北工业大学学报, 2017,35(1): 170-176 |
|
|
5．申昇, 杨宏晖, 王芸, 潘悦, 唐建生.联合互信息水下目标特征选择算法[J]. 西北工业大学学报, 2015,33(4): 639-643 |
|
|
|
|
|
|
