{"title":"Specific target recognition and segmentation algorithm for real-time side scan sonar images","authors":"Lei Wang, M. Li, Xiufen Ye, Tian Wang","doi":"10.1109/ICMA.2015.7237905","DOIUrl":null,"url":null,"abstract":"We propose a specific target recognition and segmentation algorithm to address the segmentation problem in real-time side scan sonar images. Using auxiliary information, shape, size and position relationship, we can improve the efficiency and effectiveness of sonar image segmentation. First, we give the method of segment isolated target, combine with this method, we address the segmentation problem of special size target and give the shape relationships of objects and shadows. Then, we propose an area judgment method to recognition different objects using these relationships. Experimental results show that the segmentation and recognition algorithm is good and effective.","PeriodicalId":286366,"journal":{"name":"2015 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 IEEE International Conference on Mechatronics and Automation (ICMA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMA.2015.7237905","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
We propose a specific target recognition and segmentation algorithm to address the segmentation problem in real-time side scan sonar images. Using auxiliary information, shape, size and position relationship, we can improve the efficiency and effectiveness of sonar image segmentation. First, we give the method of segment isolated target, combine with this method, we address the segmentation problem of special size target and give the shape relationships of objects and shadows. Then, we propose an area judgment method to recognition different objects using these relationships. Experimental results show that the segmentation and recognition algorithm is good and effective.