计算机科学 ›› 2022, Vol. 49 ›› Issue (11A): 211200100-6.doi: 10.11896/jsjkx.211200100

• 图像处理&多媒体技术 • 上一篇    下一篇

基于改进的SLIC和聚类算法结合的高分辨率遥感海冰图像分割

祁颖, 柴艳妹   

  1. 中央财经大学信息学院 北京 100081
  • 出版日期:2022-11-10 发布日期:2022-11-21
  • 通讯作者: 柴艳妹(chai-4@163.com)
  • 作者简介:(qiying77jdt@163.com)
  • 基金资助:
    中央财经大学科研创新团队支持计划;中央高校基本科研业务费专项资金;中央财经大学通识核心课程建设项目

High-resolution Remote Sensing Sea Ice Image Segmentation Based on Combination of ImprovedSLIC Algorithm and Clustering Algorithm

QI Ying, CHAI Yan-mei   

  1. School of Information,Central University of Finance and Economics,Beijing 100081,China
  • Online:2022-11-10 Published:2022-11-21
  • About author:QI Ying,born in 1994,postgraduate.Her main research interests include ima-ge processing and so on.
    CHAI Yan-mei,born in 1978,Ph.D,assistant professor,master supervisor,is a member of China Computer Federation.Her main research interests include image processing,pattern recognition and smarter learning.
  • Supported by:
    Program for Innovation Research in Central University of Finance and Economics,Fundamental Research Funds for the Central Universities and General Core Curriculum Construction Project in Central University of Finance and Economics.

摘要: 海冰分割是遥感图像处理领域的重要研究方向之一。由于高分辨率遥感海冰图像较大,采用SLIC构建超像素块,可为后续的再分割节省时间。SLIC虽能产生形状规则均匀的超像素块,但该算法的初始种子点对噪声敏感、分割精度与运行速度欠佳。因此,提出了一种基于改进的SLIC与聚类算法相结合的高分辨率遥感海冰图像分割算法。针对噪声敏感问题,首先采用各向异性扩散滤波进行图像的预处理,在保证图像完整性的同时有效降噪;其次,用L-p范数对传统SLIC算法中的欧氏距离度量进行扩展,以获取更优分割效果;最后,在SLIC超像素块的基础上分别采用DBSCAN和K-Means聚类算法进行精确分割,通过性能对比得到最优结果。实验结果表明,改进后的SLIC结合K-Means的分割方法的性能优于MRF算法及SLIC与DBSCAN相结合的算法,取得了较为理想的分割结果。

关键词: 图像分割, 各向异性扩散滤波, K-Means聚类, DBSCAN聚类, L-p范数, MRF算法

Abstract: Sea ice floe segmentation is an import topic in remote sensing.Due to the large high-resolution remotely sensed sea ice image,the simple linear iterative clustering(SLIC) algorithm is used to construct superpixel blocks,which can capture image redundancy and greatly reduce the complexity of subsequent image processing tasks.Although SLIC can generate super-pixel blocks with regular and uniform shapes,but there are still some problems to be used in sea ice floe segmentation.For example,the initial seed points of the algorithm are sensitive to noise,the segmentation accuracy is not high and the running speed is not very quick.Therefore,an improved SLIC combining clustering algorithm is proposed to segment high-resolution remote sensing sea ice image.Aiming at the problem of noise sensitivity,anisotropic diffusion filtering is used to preprocess the image to ensure the integrity of the image while removing noise.Then the L-p norm is used to substitute and expand the traditional Euclidean distance in the SLIC algorithm.Finally,on the basis of SLIC superpixel block,DBSCAN and K-Means clustering algorithms are separately used to precisely segment the sea ice images,and the optimal result is obtained through performance comparison.Experiments show that the improved SLIC combined with K-Means segmentation method is better than Markov tandom field(MRF) algorithm and the improved SLIC combined with DBSCAN.It can obtain quite good segmentation results.

Key words: Image segmentation, Anisotropic diffusion filter, K-Means clustering, DBSCAN clustering, L-P norm, MRF algorithm

中图分类号: 

  • TP39
[1]ZHAO Q P,YU L G,ZHU F.Research on SAR sea ice image segmentation [J].Journal of Tangshan Normal University,2017,39(2):49-52.
[2]ZHAO Z H.Research on wide observation band SAR ice water automatic segmentation based on incident angle perception [D].Anhui:Hefei University of Technology,2019.
[3]LI Q L.Study on separation method of large contact floating ice in polarimetric SAR drift ice area [D].Dalian:Dalian Maritime University,2017.
[4]CLAUSI D A,YANG X.Evaluating SAR Sea Ice Image Segmentation Using Edge-Preserving Region-Based MRFs[J].IEEE Journal of Selected Topics in Applied Earth Observations &Remote Sensing,2012,5(5):1383-1393.
[5]ACHANTA R,SHAJI A,SMITH K,et al.SLIC superpixels.Technical Report[C]//IVRG CVLAB.2010.
[6]LIU A Q,LIU H Y,WANG H B.Improved SLIC super-pixel image segmentation and merging algorithm [J].Journal of Anhui Architecture University,2020,28(4):39-46.
[7]CHEN Y Y,KANG Y,LI W F,et al.SLIC super-pixel segmentation algorithm based on comprehensive identification information [J].High Tech Communication,2021,31(8):816-823.
[8]SUN W J,YANG J.research on remote sensing image segmentation based on improved simple non iterative clustering [J].Computer Engineering and Application,2021,57(13):8.
[9]ULLAH S,BHATTI N,ZIA M.Adaptive tuning of SLIC parameter K[J].Multimedia Tools and Applications,2021,80(17):25649-25672.
[10]KONG X YG,XU B G.Research on denoising effect of mean filter and its improved algorithm [J].Journal of Shangqiu Normal University,2016,32(6):5.
[11]GAO H,TANG N,CHEN Y T.Remote sensing image denoi-sing algorithm based on the combination of linear filtering and wavelet threshold [C]//Proceedings of the 2018 Academic Exchange of Guangxi Society of Surveying and Mapping.2018:101-106.
[12]BAO G B,YANG X P,KANG H.Research on tooth image segmentation based on Improved Gaussian mixture model [J].Journal of Lanzhou University of Technology,2020,46(3):100-104.
[13]COMANICIU D,MEER P.Mean shift:a robust approach toward feature space analysis[J].IEEE Trans.on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[14]HAO L.Analysis and Research on seismic data noise suppression method based on anisotropic diffusion filtering [J].Petrochemical Applications,2021,40(3):86-88,93.
[15]ACHANTA R,SHAJI A,SMITH K,et al.SLIC superpixels.Technical Report[C]//IVRG CVLAB.2010.
[16]CHEN X T,ZHANG R Y,QU X X,et al.Application of SLIC super-pixel segmentation in medical image processing [J].Mo-dern Computer(Popular Version),2015(12):52-56.
[17]XU S T,LI Y J,ZHU Y.Optimization algorithm of SLIC super-pixel segmentation [J].Fujian Quality Management,2019(1):233.
[18]ZHANG Y,MA Y C,YANG X F,et al.Based on L_ Clustering algorithm for constrained similarity matrix of(2,1)-norm distance [J].Computer Engineering and Design,2021,42(3):726-733.
[19]WIORA J.Least Lp-norm low-pass filter[J].Automatica,2021,133:109854-109864.
[20]LIU M D,PAN X,GAO S S,et al.Indoor scene segmentation combined with DBSCAN clustering [J].Journal of Computer Aided Design and Graphics,2019,31(7):11.
[21]LI Y G.Improvement of K-means clustering algorithm and its application in color image segmentation [D].Anhui:Anhui University,2018.
[22]Chukchi sea image source chukchi_20130531_2[OL].https://lta.cr.usgs.gov/gfl/?img:672:125&PTAGNAME=ArcticSea.
[1] 杨旭华, 王磊, 叶蕾, 张端, 周艳波, 龙海霞.
基于节点相似性和网络嵌入的复杂网络社区发现算法
Complex Network Community Detection Algorithm Based on Node Similarity and Network Embedding
计算机科学, 2022, 49(3): 121-128. https://doi.org/10.11896/jsjkx.210200009
[2] 张福昌, 仲国强, 毛玉旭.
面向轻量化医学图像分割网络的神经结构搜索
Neural Architecture Search for Light-weight Medical Image Segmentation Network
计算机科学, 2022, 49(10): 183-190. https://doi.org/10.11896/jsjkx.210800052
[3] 祝一帆, 王海涛, 李可, 吴贺俊.
一种高精度路面裂缝检测网络结构:Crack U-Net
Crack U-Net:Towards High Quality Pavement Crack Detection
计算机科学, 2022, 49(1): 204-211. https://doi.org/10.11896/jsjkx.210100128
[4] 金海燕, 彭晶, 周挺, 肖照林.
基于Graph Cuts多特征选择的双目图像分割方法
Binocular Image Segmentation Based on Graph Cuts Multi-feature Selection
计算机科学, 2021, 48(8): 150-156. https://doi.org/10.11896/jsjkx.200800221
[5] 许华杰, 张晨强, 苏国韶.
基于深层卷积残差网络的航拍图建筑物精确分割方法
Accurate Segmentation Method of Aerial Photography Buildings Based on Deep Convolutional Residual Network
计算机科学, 2021, 48(8): 169-174. https://doi.org/10.11896/jsjkx.200500096
[6] 叶中玉, 吴梦麟.
融合时序监督和注意力机制的脉络膜新生血管分割
Choroidal Neovascularization Segmentation Combining Temporal Supervision and Attention Mechanism
计算机科学, 2021, 48(8): 118-124. https://doi.org/10.11896/jsjkx.200600150
[7] 杨秀璋, 武帅, 夏换, 于小民.
基于自适应图像增强技术的水族文字提取与识别研究
Research on Shui Characters Extraction and Recognition Based on Adaptive Image Enhancement Technology
计算机科学, 2021, 48(6A): 74-79. https://doi.org/10.11896/jsjkx.200900070
[8] 曹林, 于威威.
基于图像分割的自适应窗口双目立体匹配算法研究
Adaptive Window Binocular Stereo Matching Algorithm Based on Image Segmentation
计算机科学, 2021, 48(11A): 314-318. https://doi.org/10.11896/jsjkx.201200264
[9] 顾兴健, 朱剑峰, 任守纲, 熊迎军, 徐焕良.
多尺度U网络实现番茄叶部病斑分割与识别
Multi-scale U Network Realizes Segmentation and Recognition of Tomato Leaf Disease
计算机科学, 2021, 48(11A): 360-366. https://doi.org/10.11896/jsjkx.201000166
[10] 金雨芳, 吴祥, 董辉, 俞立, 张文安.
基于改进YOLO v4的安全帽佩戴检测算法
Improved YOLO v4 Algorithm for Safety Helmet Wearing Detection
计算机科学, 2021, 48(11): 268-275. https://doi.org/10.11896/jsjkx.200900098
[11] 杨志伟, 戴铭, 周智恒.
基于直方图差异的工业产品表面缺陷检测方法
Surface Defect Detection Method of Industrial Products Based on Histogram Difference
计算机科学, 2020, 47(6A): 247-249. https://doi.org/10.11896/JsJkx.191000049
[12] 罗晋楠, 张济民.
基于扩展Haar特征和DBSCAN的钢轨识别算法
Rail Area Extraction Using Extended Haar-like Features and DBSCAN Clustering
计算机科学, 2020, 47(6A): 153-156. https://doi.org/10.11896/JsJkx.200100008
[13] 曹义亲, 段也钰, 武丹.
基于WFSOA的2D-Otsu钢轨缺陷图像分割方法
2D-Otsu Rail Defect Image Segmentation Method Based on WFSOA
计算机科学, 2020, 47(5): 154-160. https://doi.org/10.11896/jsjkx.190200295
[14] 饶梦,苗夺谦,罗晟.
一种粗糙不确定的图像分割方法
Rough Uncertain Image Segmentation Method
计算机科学, 2020, 47(2): 72-75. https://doi.org/10.11896/jsjkx.190500177
[15] 雷涛,连倩,加小红,刘鹏.
基于快速SLIC的图像超像素算法
Fast Simple Linear Iterative Clustering for Image Superpixel Algorithm
计算机科学, 2020, 47(2): 143-149. https://doi.org/10.11896/jsjkx.190400121
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!