A Method for Background Suppression of Sonar Image Using Gaussian Mixture Model and Radon Transform
-
摘要: 水下运动小目标的声呐图像背景随着空间和时间起伏变化, 声呐图像的背景抑制处理是水下小目标检测的关键技术之一。文中采用混合高斯模型建立序列声呐图像背景的各个方位-距离单元幅度的统计模型, 抑制声呐图像中成片亮区、亮带干扰背景。针对混合高斯模型“剩余”噪声问题, 利用水下运动目标航迹的连续变化特征, 通过Radon变换和Radon逆变换提取历程累积声呐图像的线特征, 滤除混合高斯模型处理后的“剩余”噪声。对实测水下小目标直线运动和跨方位曲线运动2种情况下的多波束声呐数据进行了分析, 结果表明, 通过混合高斯模型和Radon变换滤波方法处理, 可以实现复杂声呐背景的去除, 获得“干净”的声呐背景, 有利于声呐对水下运动目标的自主检测。Abstract: The background of sonar image of small underwater moving target fluctuates with space and time. The background suppression is one of the key processes in sonar detection. In this paper, the Gaussian mixture model is used to model the amplitude variation of each azimuth-range resolution cell of sequential sonar image, so as to suppress the main background of highlight area and highlight band in the sonar image. In order to solve the problem of residual noise from the Gaussian mixture model, the continuous change characteristics of the track from an underwater moving target are considered, the line features of the history-accumulated sonar image are extracted, and the residual noise is filtered out by Radon transform and inverse Radon transform. The analysis of multi-beam sonar data from measurement under the conditions of small underwater target’s linear motion and cross-azimuth curvilinear motion shows that the complex sonar background can be removed and the clean sonar back-ground can be obtained by using the Gaussian mixture model and the filtering method via Radon transform, which can be used in sonar detection of underwater moving targets.
-
[1] 欧阳文, 朱卫国. 蛙人探测声纳系统研究进展[J]. 国防科技, 2012, 277(6): 53-57. [2] Fumitaka M, Akira A, Eric M, et.al. Automatic Signal Processing of Forward Looking Surveillance Sonar Data in Low Signal-to-noise Ratio Conditions[C]//2010 International Water Side Security Conference. Carrara, Italy: WSS, 2010: 1-7. [3] 李轲, 刘忠, 毛盾. 基于反蛙人声纳的小目标检测算法[J]. 舰船电子工程, 2010, 30(7): 173-176.Li Ke,?Liu Zhong,?Mao Dun. Algorithm for Detection of Small Targetin Sonar Image Based on Anti-diver Sonar[J]. Ship Electronic Engineering, 2010, 30(7): 173-176. [4] 赵海旭, 吴培荣, 王小雯, 等. 一种基于关联处理的声呐图像去噪技术[J]. 声学技术, 2016, 35(6): 571-574.Zhao Hai-xu, Wu Pei-rong, Wang Xiao-wen, et al. Sonar Image Denoising Technique Based on Relevancy Processing[J]. Technical Acoustics, 2016, 35(6): 571-574. [5] Yang T C, Schindall J, Huang C F, et al. Clutter Reduction Using Doppler Sonar in a Harbor Environment[J]. Journal of the Acoustical Society of America, 2012, 132(5): 3053-3067. [6] Ge Yu, Yang T C, Piao S C. Estimating the Delay-Doppler of Target Echo in a High Clutter Underwater Environment Using Wideband Linear Chirp Signals: Evaluation of Performance with Experimental Data[J]. Journal of the Acoustical Society of America, 2017, 142(4): 2047-2057. [7] 查宇飞, 毕笃彦, 杨源, 等. 视频目标跟踪方法[M]. 北京: 国防工业出版社, 2015. [8] 董佳佳. 基于声纳图像水下运动目标识别与跟踪技术研究[D]. 青岛: 中国海洋大学, 2011. [9] 董静. 基于图像声纳的动目标检测技术研究[D]. 哈尔滨: 哈尔滨工程大学, 2014. [10] Stauffer C, Grimson W E L. Adaptive Background Mixture Models for Real-time Tracking, Computer Vision and Pattern Recognition[C]//IEEE Computer Society Confer-ence on Computer Vision and Pattern Recognition. Fort Collins, CO, USA: IEEE, 1999: 246-252. [11] 陈允锋, 潘谢帆. 一种应用于慢速小目标探测的图像干扰抑制技术[J]. 声学技术, 2015, 34(2): 31-32.Chen Yun-feng, Pan Xie-fan. An Image Interference Suppression Technology Applied to Detecting the Slow and Small Target[J]. Technical Acoustics, 2015, 34(2): 31-32. [12] 何萌萌. 基于Radon变换的直线检测技术[D]. 哈尔滨: 哈尔滨工程大学, 2014. [13] Detect Lines Using the Radon Transform[EB/OL]. (2018- 08-09).https://www.mathworks.com/help/images/detect-lines-using-the-radon-transform.html.
点击查看大图
计量
- 文章访问数: 750
- HTML全文浏览量: 2
- PDF下载量: 483
- 被引次数: 0