基于偏振度特征图的水下裂缝图像分割算法

计算机与现代化 ›› 2022, Vol. 0 ›› Issue (03): 64-69.

基于偏振度特征图的水下裂缝图像分割算法

(河海大学物联网工程学院,江苏常州213022)

出版日期:2022-04-29 发布日期:2022-04-29
作者简介:邹杰(1996—),男,江苏泰州人,硕士研究生,研究方向:图像处理,E-mail: jayzoumeet@163.com; 宋轲(1998—),男,硕士研究生,研究方向:图像处理,E-mail: 948937774@qq.com; 王张帆(1997—),男,硕士研究生,研究方向:图像处理,E-mail: 1398062119@qq.com; 侯一兴(1996—),男,硕士研究生,研究方向;图像处理,E-mail: 876098921@qq.com; 张学武(1973—),男,教授,研究方向:信息获取与处理,E-mail: Lab_112@126.com。
基金资助:
国家重点研发计划项目(2018YFC0407101); 国家自然科学基金资助项目(61671202)

Underwater Crack Segmentation Algorithm Based on Polarization Characteristic Map

(College of Internet of Things Engineering, Hohai University, Changzhou 213022, China)

Online:2022-04-29 Published:2022-04-29

摘要/Abstract

摘要： 由于水体侵蚀、自然老化等问题，水库大坝等水下结构物在长期运行过程中存在表面损伤缺陷，与青苔、贝壳等附着物形成的凹陷，在颜色、纹理等方面具有极高的相似性。当凹陷距离裂缝较近时，极易引起裂缝图像分割误判。为解决该问题，本文引入偏振信息，提出一种基于偏振度特征图的裂缝图像分割算法，以超像素块为单元进行偏振度特征图提取，利用偏振度设定区域生长规则，以种子区域为基础进行区域生长合并，最后根据图像深度图确定裂缝区域。实验结果表明该算法能够有效减少分割误判，裂缝分割结果的特异性和准确度指标均能达到0.9以上，高于现有算法。

关键词: 偏振图像, SLIC算法, 区域生长, 裂缝分割

Abstract: Due to water erosion, natural aging and other problems, underwater structures such as reservoirs have surface damage defects during long-term operation. The depressions formed by attachments such as moss and shells on the surface of underwater structures are highly similar to cracks in terms of color and texture. When the depressions are close to cracks, it is easy to cause misjudgment in crack image segmentation. In order to solve this problem, the polarization information is introduced in this paper, and a crack image segmentation algorithm based on polarization degree feature map is proposed. The feature map is extracted by superpixel block, the region growth rule is set by polarization degree, and the region growth is combined based on seed region. Finally, the crack region is determined according to the image depth map. The experimental results show that this algorithm can effectively reduce the segmentation misjudgment, and the specificity and accuracy index of crack segmentation results can reach more than 0.9, which is much higher than other algorithms.

Key words: polarized image, SLIC algorithm, region growth, crack segmentation

邹杰, 宋轲, 王张帆, 侯一兴, 张学武. 基于偏振度特征图的水下裂缝图像分割算法[J]. 计算机与现代化, 2022, 0(03): 64-69.

ZOU Jie, SONG Ke, WANG Zhang-fan, HOU Yi-xing, ZHANG Xue-wu. Underwater Crack Segmentation Algorithm Based on Polarization Characteristic Map[J]. Computer and Modernization, 2022, 0(03): 64-69.

参考文献

［1］ HAN J F, YANG K C, XIA M, et al. Resolution enhancement in active underwater polarization imaging with modulation transfer function analysis［J］. Applied Optics, 2015,54(11):3294-3302.
［2］ JAFFE J S. Underwater optical imaging: The past, the present, and the prospects［J］. IEEE Journal of Oceanic Engineering, 2015,40(3):683-700.
［3］全向前,陈祥子. 深海光学照明与成像系统分析及进展［J］. 中国光学, 2018,11(2):153-165.
［4］范新南,吴晶晶,史朋飞,等. 基于劳伦茨信息值的水下大坝裂缝提取算法［J］. 计算机与现代化, 2018(3):73-77.
［5］石为人,方莉,陈舒涵. 基于改进Otsu和Niblack的图像二值化方法［J］. 世界科技研究与发展, 2013,35(3):395-398.
［6］王千,王成,冯振元,等. K-means聚类算法研究综述［J］. 电子设计工程, 2012,20(7):21-24.
［7］ BHATTACHARYYA S, DAS S, DE S, et al. Color MRI image segmentation using QIMfGA based FCM［C］// The lst International Symposium on Signal and Image Processing. 2017:151-164.
［8］ CHEN M, LUDWIG S A. Color image segmentation using fuzzy C-regression model［J］. Advances in Fuzzy Systems, 2017(2):1-15.
［9］孔显,马晓珂. 基于非归一化直方图的GrabCut图像分割算法改进［J］. 计算机应用研究, 2020,37(5):1549-1552.
［10］温佩芝,陈晓,吴晓军,等. 基于三次样条插值的GrabCut自动目标分割算法［J］. 计算机应用研究, 2014,31(7):2187-2190.
［11］王燕妮,校曼. 偏振光在浑浊介质中的传输特性研究［J］. 激光与光电子学进展, 2020,57(14):308-315.
［12］刘飞,孙少杰,韩平丽,等. 水下偏振成像技术研究及进展［J］. 激光与光电子学进展, 2021,58(6):9-26.
［13］王春瑶,陈俊周,李炜. 超像素分割算法研究综述［J］. 计算机应用研究, 2014(1):6-12.
［14］杨艳,许道云. 优化加权核K-means聚类初始中心点的SLIC算法［J］. 计算机科学与探索, 2018,12(3):494-501.
［15］DE A, HORWITZ G D. Spatial receptive field structure of double-opponent and simple cells in macaque primary visual cortex［J］. Journal of Neurophysiology, 2020,123(3):DOI:10.1101/2020.01.20.913111.
［16］徐蔚波,刘颖,章浩伟. 基于区域生长的图像分割研究进展［J］. 北京生物医学工程, 2017,36(3):317-322.
［17］周浦城,张洪坤,薛模根. 基于颜色迁移和聚类分割的偏振图像融合方法［J］. 光子学报, 2016,40(1):149-153.
［18］WANG Y Y. Otsu image threshold segmentation method based on seagull optimization algorithm［J］. Journal of Physics: Conference Series, 2020,1650(3):1-7.
［19］UNNIKRISHNAN R, PANTOFARU C, HEBERT M. Toward objective evaluation of image segmentation algorithms［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2007,29(6):929-944.
［20］GOFERMAN S, ZELNIK-MANOR L, TAL A. Context-aware saliency detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011,34(10):1915-1926.
［21］JIANG M, SONG S M, HERRMANN J M, et al. Underwater loop-closure detection for mechanical scanning imaging sonar by filtering the similarity matrix with probab-ility hypothesis density filter［J］. IEEE Access, 2019,7:166614-166628.
［22］LI M D, LIU J Y, YANG W H, et al. Structure-revealing low-light image enhancement via robust retinex model［J］. IEEE Transactions on Image Processing, 2018,27(6):2828-2841.
［23］范新南,陈建跃,张学武,等. 结构相似性的水下偏振图像复原［J］. 中国图象图形学报, 2018,23(7):1033-1041.

[1]	张永梅1,2,3，杜国平1,4，邢阔1. 一种快速火灾识别方法[J]. 计算机与现代化, 2016, 0(3): 58-63.
[2]	罗玉皓;邹远文;夏勋. 运用OpenCV实现红外图像的瞳孔参数实时检测 [J]. 计算机与现代化, 2013, 1(6): 71-75.
[3]	吴玉荣. 基于小波变换和颜色传递的水下图像融合方法[J]. 计算机与现代化, 2013, 1(5): 77-79.
[4]	刘晏丽;赵卫东;陈宇飞;王志成;孟齐文;. 基于Hessian矩阵和区域生长的肝血管树的分割算法研究[J]. 计算机与现代化, 2011, 1(1): 113-4.