基于变分水平集理论的水下图像分割方法

详细信息    查看全文 | 推荐本文 |

英文篇名：An underwater image segmentation method based on the variational level set theory 作者：席志红 ; 赵春梅 英文作者：XI Zhihong;ZHAO Chunmei;College of Information and Communication Engineering, Harbin Engineering University; 关键词：水下图像分割 ; 活动轮廓模型 ; 李纯明模型 ; C-V模型 ; 变分法 ; 水平集理论 ; 灰度图像 ; 水下图像 英文关键词：underwater image segmentation;;active contour model;;Lee's model;;C-V model;;variational method;;horizontal set theory;;grayscale image;;underwater images 中文刊名：YYKJ 英文刊名：Applied Science and Technology 机构：哈尔滨工程大学信息与通信工程学院; 出版日期：2018-10-23 15:20 出版单位：应用科技 年：2019 期：v.46;No.303 基金：国家自然科学基金项目(60875025) 语种：中文; 页：YYKJ201902010 页数：6 CN：02 ISSN：23-1191/U 分类号：57-62

摘要

为解决水下图像的分割问题,在李纯明模型(Li模型)和Chan-Vese模型(C-V模型)的基础上提出了指定目标的分割方法和多灰度目标的分割方法。对于指定灰度目标的分割方法,在C-V模型基础上加入了小范围的距离约束项,使其具有了局部性,可在多灰度目标中分割出预期目标;对于多灰度目标的分割方法,在李纯明方法的基础上加入了边缘定位函数作为其内部能量项,其对多灰度目标分割结果较好,且抗噪性较好。最后通过实验证明本文2种方法对水下多灰度目标图像的分割是有效的。
        In order to solve the problem of underwater image segmentation, the segmentation methods for a designated target and a multi-grayscale target are proposed respectively based on the Li Chunming model(Lee's model) and the Chan-Vese(C-V) model. For the segmentation method of a specified grayscale object, a small range of distance restriction item is added on the basis of the C-V model, making it have locality characteristic, and segment the desired target from the multi-gray target. The multi-gray target segmentation method is to join the edge detection function as the item of internal energy based on Li Chunming method. The results of multi-gray target segmentation are good, and the anti-noise characteristic is better. Finally, the effectiveness of the proposed two methods is verified.

引文

[1]李煊.基于单目视觉的水下图像分割及目标定位技术研究[D].哈尔滨:哈尔滨工程大学,2013.
    [2]刘松涛,殷福亮.基于图割的图像分割方法及其新进展[J].自动化学报,2012,38(6):911-922.
    [3]史言彬.基于单目视觉的水下目标识别和定位方法研究[D].哈尔滨:哈尔滨工程大学,2016.
    [4]FU K S,MUI J K.A survey on image segmentation[J].Pattern recognition,1981,13(1):3-16.
    [5]TEIMOURI N,OMID M,MOLLAZADE K,et al.A novel artificial neural networks assisted segmentation algorithm for discriminating almond nut and shell from background and shadow[J].Computers and electronics in agriculture,2014,105:34-43.
    [6]MATALAS L,BENJAMIN R,KITNEY R.An edge detection technique using the facet model and parameterized relaxation labeling[J].IEEE transactions on pattern analysis and machine intelligence,1997,19(4):328-341.
    [7]CHEN H H,CHUANG Wenning,WANG C C.Visionbased line detection for underwater inspection of breakwater construction using an ROV[J].Ocean engineering,2015,109:20-33.
    [8]LEE D,KIM G,KIM D,et al.Vision-based object detection and tracking for autonomous navigation of underwater robots[J].Ocean engineering,2012,48:59-68.
    [9]BARAT C,PHLYPO R.A fully automated method to detect and segment a manufactured object in an underwater color image[J].EURASIP journal on advances in signal processing,2010,2010:568092.
    [10]FU K S,MUI J K.A Survey on image segmentation[J].Pattern recognition,1981,13(1):3-16.
    [11]KASS M,WITKIN A,TERZOPOULOS D.Snakes:active contour models[J].International journal of computer vision,1988,1(4):321-331.
    [12]陈波.基于变分框架的图像分割和图像恢复研究[D].广州:中山大学,2007.
    [13]陈波,赖剑煌.用于图像分割的活动轮廓模型综述[J].中国图象图形学报,2007,12(1):11-20.
    [14]OSHER S,FEDKIW R.Level set methods and dynamic implicit surfaces[M].New York:Springer-Verlag,2002.
    [15]SETHIAN J A.Curvature and the evolution of fronts[J].Communications in mathematical physics,1985,101(4):487-499.
    [16]曹俊峰.基于水平集方法的图像分割研究[D].无锡:江南大学,2017.
    [17]谢小敏.水下图像分割和典型目标特征提取及识别技术研究[D].南京:南京理工大学,2015.