主动声呐B显图像中的疑似目标自动拾取算法  

Automatic picking up algorithm of suspected targets in the B-type image of active sonar

作　　者：余杰 蔡志明[1] 王平波[1] YU Jie;CAI Zhiming;WANG Pingbo(College of Electronic Engineering,Naval University of Engineering,Wuhan 430030,China;715th Research Institute,China State Shipbuilding Corporation,Hangzhou 310012,China)

机构地区：[1]海军工程大学电子工程学院,湖北武汉430030 [2]中国船舶集团公司第715研究所,浙江杭州310012

出　　处：《哈尔滨工程大学学报》2022年第10期1532-1538,共7页Journal of Harbin Engineering University

基　　金：国家自然科学基金项目(41976177)。

摘　　要：针对主动声呐B显图像呈“满天星”状从而导致人工提取目标困难的问题,本文在分析B显图像干扰分布特点和界定疑似目标概念的基础上,综合运用图像分割、图像形态学、统计拟合与检测等技术,提出一种疑似目标自动拾取算法。研讨了图像自动调亮与二值化、形态学闭运算与前景背景标定、双阈值检测与综合筛判等算法关键环节的设计与实现,并使用海试数据对算法性能进行了检验。结果表明:本文算法能自动区分B显图像的前景和背景区,从中稳定可靠地自动拾取疑似目标,漏报率低。To address the problems of the B-display image of active sonar being "all over the sky" and of the difficulty in picking up the targets manually, an automatic algorithm for picking up suspected targets is proposed based on the analysis of the interference distribution characteristics of B-type image and the definition of the concept of suspected targets by comprehensively applying image segmentation, image morphology, statistical fitting, and detection. The design and implementation of key links of the algorithm, such as automatic image brightening and binarization, morphological closed operation, foreground and background calibration, double threshold detection, and comprehensive screening, are discussed. The performance of the algorithm is tested by using sea trial data. Results show that this algorithm can automatically distinguish the foreground area from the background area of the B-type images and automatically pick up the suspected targets stably and reliably with a low level of miss alarm rate.

关 键 词：疑似目标 自动检测 声呐B显 双阈值检测 自动调亮 图像形态学 图像分割 视在信噪比 

分 类 号：TB566[交通运输工程—水声工程]