首页 > 论文 > 光学学报 > 38卷 > 6期(pp:628002--1)

基于多特征融合和软投票的遥感图像河流检测

River Detection in Remote Sensing Images Based on Multi-Feature Fusion and Soft Voting

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

河流是遥感图像中一种非常典型且重要的地理目标,对河流的自动检测在水资源调查及水利规划等方面有重大意义。在此提出了一种基于多特征融合和软投票方法的河流目标检测算法,该算法首先将图像分割成胞元,提取胞元的局部熵、纹理、光谱和颜色等特征,利用随机森林训练和分类,并利用基于形态学运算结合多判据投票法优化机器学习的粗检测结果,对优化后的粗检测结果利用水平集活动轮廓逼近河岸线。实验表明,该算法检测效果良好,对测试集的检测准确率达97.44%,在复杂背景下可以有效检测出河流。

Abstract

River is a very typical and important geographical target in remote sensing images. The automatic detection of rivers is of great significance in water resources investigation and water conservancy planning. In this paper, a river target detection algorithm based on multi-feature fusion and soft voting method is proposed. The algorithm firstly divides the images into cells and then extracts the local entropy, texture, spectrum, and color feature of the cells. Random forest is used to train and classify. To optimize the rough detection result of machine learning, the morphology operation and the multi-criteria voting method is introduced. For optimized rough detection result, the level set active contour is used to approach the river shoreline. Experiments show that the proposed algorithm has a good detection effect, and the detection accuracy rate of test set reaches 97.44%. In addition, the river can be effectively detected in the complex background.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP75

DOI:10.3788/aos201838.0628002

所属栏目:遥感与传感器

基金项目:国家自然科学基金(61175031)、国家863计划 (2012AA041402)

收稿日期:2017-12-03

修改稿日期:2018-01-10

网络出版日期:--

作者单位    点击查看

张庆春:东北大学信息科学与工程学院, 辽宁 沈阳 110819
佟国峰:东北大学信息科学与工程学院, 辽宁 沈阳 110819
李勇:东北大学信息科学与工程学院, 辽宁 沈阳 110819
高丽伟:东北大学信息科学与工程学院, 辽宁 沈阳 110819
陈槐嵘:东北大学信息科学与工程学院, 辽宁 沈阳 110819

联系人作者:佟国峰(tongguofeng@ise.neu.edu.cn)

备注:张庆春(1991-),男,硕士研究生,主要从事计算机视觉方面的研究。E-mail: 547116373@qq.com

【1】Guan W J, Cao B, Wang X Y, et al. Comparison of river information extraction methods[J]. Yellow River, 2017, 39(2): 52-55.
管伟瑾, 曹泊, 王晓艳, 等. 遥感信息提取方法比较[J]. 人民黄河, 2017, 39(2): 52-55.

【2】Fan L H, Lü J W, Deng J S.Classification of hyperspectral remote sensing images based on bands grouping and classification ensembles[J]. Acta Optica Sinica, 2014, 34(9): 0910002.
樊利恒, 吕俊伟, 邓江生. 基于分类器集成的高光谱遥感图像分类方法[J]. 光学学报, 2014, 34(9): 0910002.

【3】Wen J.Research on extraction of roads and rivers from high-resolution SAR image[D]. Changsha: Changsha University of Science & Technology, 2015: 1-5.
文俊. 基于高分辨率SAR图像的道路和河流提取方法研究[D]. 长沙: 长沙理工大学, 2015: 1-5.

【4】Zhu L N, Zhang J Q, Pa L. River change detection based on remote sensing image and vector[C]. Proceedings of the First International Multi-Symposiums on Computer and Computational Sciences (IMSCCS ''06), 2006: 188-191.
朱丽娜, 张建庆, 帕里. 基于遥感图像和矢量的河流变化检测[C]. 计算机和计算科学首届国际研讨会(IMSCCS ''06), 2006: 188-191.

【5】Hu Z L, Sun J P, Yuan Y N, et al. River detection in SAR images based on edge extraction in wavelet domain and ridge tracing technique[J]. Journal of Electronics & Information Technology, 2007, 29(3): 524-527.
胡正磊, 孙进平, 袁运能,等. 基于小波边缘提取和脊线跟踪技术的SAR图像河流检测算法[J]. 电子与信息学报, 2007, 29(3): 524-527.

【6】Chen A J. Rapid detection of large rivers in high resolution satellite images: volume 3[C]. Proceedings of 2010 International Conference on Remote Sensing (ICRS 2010), 2010: 322-325.
陈爱军. 高分辨率卫星图象中大型河流的快速检测: 卷3[C]. 2010遥感国际会议论文集(ICRS 2010), 2010: 322-325.

【7】Yu X S, Wu C D, Chen D Y, et al. River detection in remote sensing image based on multi-feature fusion [J]. Journal of Northeastern University Natural Science, 2012, 33(11): 1547-1550.
于晓升, 吴成东, 陈东岳,等. 基于多特征融合的遥感图像河流目标检测算法[J]. 东北大学学报: 自然科学版, 2012, 33(11): 1547-1550.

【8】Su L, Wu J J, Pang D. Panoramic sea-sky-line detection based on improved active contour model[J]. Acta Optica Sinica, 2016, 36(11): 1115003.
苏丽, 吴俊杰, 庞迪. 基于改进主动轮廓模型的全景海天线检测[J]. 光学学报, 2016, 36(11): 1115003.

【9】Zhou B Y, Zhao H W, Xiao Y, et al. Image feature description method based on local entropy[J]. Journal of Jilin University Engineering and Technology Edition, 2017, 47(2): 601-608.
周保余, 赵宏伟, 肖杨,等. 基于局部熵的图像特征描述方法[J]. 吉林大学学报(工学版), 2017, 47(2): 601-608.

【10】Tong G F, Li Y, Liu N, et al. Mixed feature extraction and matching for large affine scene[J]. Acta Optica Sinica, 2017, 37(11): 1115003.
佟国峰,李勇,刘楠,等. 大仿射场景的混合特征提取与匹配[J]. 光学学报, 2017, 37(11): 1115003.

【11】Qiao Z J.Texture image retrieval based on Gabor wavelet transform[D]. Changsha: Changsha University of Science & Technology, 2006: 25-31.
乔志杰. 基于Gabor小波变换的纹理图像检索[D]. 长沙: 长沙理工大学, 2006: 25-31.

【12】Liaw A, Wiener M, Wiener T C, et al. Classification and regression by random forest[J]. R News, 2002, 2(3):18-22.

【13】Zhang C C, Lin Z R . LIBSVM: a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 27.
张治中,林智仁. LIBSVM:一个支持向量机库[J]. ACM智能系统与技术,2011, 2(3): 27.

【14】Li C M, Xu C Y, Gui C F, et al. Level set evolution without re-initialization: a new variational formulation[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005: 8588904.

引用该论文

Zhang Qingchun,Tong Guofeng,Li Yong,Gao Liwei,Chen Huairong. River Detection in Remote Sensing Images Based on Multi-Feature Fusion and Soft Voting[J]. Acta Optica Sinica, 2018, 38(6): 0628002

张庆春,佟国峰,李勇,高丽伟,陈槐嵘. 基于多特征融合和软投票的遥感图像河流检测[J]. 光学学报, 2018, 38(6): 0628002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF