城市道路的多特征多核SVM提取方法

doi:10.13474/j.cnki.11-2246.2018.0047

测绘通报 ›› 2018, Vol. 0 ›› Issue (2): 72-77.doi: 10.13474/j.cnki.11-2246.2018.0047

城市道路的多特征多核SVM提取方法

李洪川¹, 楚恒^1,2,3, 霍英海¹

1. 重庆邮电大学光通信与网络重点实验室, 重庆 400065;
2. 西南大学地理科学学院, 重庆 400715;
3. 重庆市勘测院, 重庆 400020

收稿日期:2017-05-23 修回日期:2017-11-02 出版日期:2018-02-25 发布日期:2018-03-06
作者简介:李洪川(1991-),男,硕士生,主要研究方向为遥感影像融合与分类。E-mail:1007533013@qq.com
基金资助:
重庆市2013西南大学博士后科研项目（Rc201336）；重庆高校创新团队建设计划（CXTDX201601020）

Multi-feature Multiple Kernels SVM-based Urban Road Extraction

LI Hongchuan¹, CHU Heng^1,2,3, HUO Yinghai¹

1. School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
2. School of Geographical Sciences, Southwest University, Chongqing 400715, China;
3. Chongqing Survey Institute, Chongqing 400020, China

Received:2017-05-23 Revised:2017-11-02 Online:2018-02-25 Published:2018-03-06

摘要/Abstract

摘要：

针对高分辨率遥感影像中城市道路提取的复杂性及SVM的分类性能，提出了一种城市道路的多特征多核SVM提取方法。首先利用FCM算法将原始影像粗分为建成区和非建成区两类，剔除非建成区；然后根据分水岭分割算法分割建成区并提取分割对象的光谱特征与空间特征，以全局核函数和局部核函数加权组合的方式构建多核SVM对建成区进行二次分类，去除建成区中的建筑物等非道路信息；最后利用数学形态学处理，获得最终的道路提取结果。试验结果表明：文中所提方法能够较精确地提取城市道路信息，分类精度高于单核SVM提取及其他对比方法。

关键词: 高分辨率遥感影像, 城市道路提取, 多核SVM, 二次分类, 数学形态学

Abstract:

For the complex nature of urban road extraction in high-resolution remote sensing image and the classification performance of SVM,a new urban road extraction method of multi-feature multiple kernels SVM-based is proposed.Firstly,the FCM algorithm is utilized to classify the original image into the built-up areas and non-built-up areas,and the non-built-up areas are removed.Then this paper segments the built-up areas using watershed segmentation algorithm,and extracts the image objects spectral features and spatial features.This paper uses the weighted sum approach to achieve multiple kernels SVM (MKSVM) by the way of combining the global kernel function and the local kernel function.The secondary classification of built-up areas are achieved using MKSVM and remove the non-road information.Finally,the final road information is processed by using mathematics morphology.The result of experiment shows that the proposed method can fairly well extract the urban road information,and the accuracy of classification is much higher than SVM and other extraction methods.

Key words: high-resolution remote sensing imagery, urban road extraction, multiple kernels SVM, secondary classification, mathematics morphology

中图分类号:

P237

李洪川, 楚恒, 霍英海. 城市道路的多特征多核SVM提取方法[J]. 测绘通报, 2018, 0(2): 72-77.

LI Hongchuan, CHU Heng, HUO Yinghai. Multi-feature Multiple Kernels SVM-based Urban Road Extraction[J]. 测绘通报, 2018, 0(2): 72-77.

参考文献

[1] 刘纯,洪亮,陈杰,等.融合像素-多尺度区域特征的高分辨率遥感影像分类算法[J].遥感学报,2015,19(2):228-239.
[2] 孙可,张钧萍.局部自适应方向模板匹配的高分辨率遥感影像道路提取[C]//2015年光学精密工程论坛论文集.长春:《光学精密工程》编辑部,2015:509-515.
[3] ZHAO L,WANG X.Road Extraction in High Resolution Remote Sensing Images Based on Mathematic Morphology and Snake Model[C]//International Congress on Image and Signal Processing.[S.l.]:IEEE,2010:1436-1440.
[4] ZHAO W Z,LUO L Q,GUO Z,et al.Road Extraction in Remote Sensing Images Based on Spectral and Edge Analysis[J].Spectroscopy and Spectral Analysis,2015,35(10):2814-2819.
[5] 林鹏,阮仁宗,王玉强.一种基于面向对象的城镇道路自动提取方法研究[J].地理与地理信息科学,2016,32(1):49-54.
[6] ZHU E,SONG W,DAI J,et al.Road Extraction of High-resolution Remote Sensing Images Based on Improved SVM[J].Science of Surveying and Mapping,2016,41(12):224-228.
[7] MIAO Z,SHI W,GAMBA P,et al.An Object-based Method for Road Network Extraction in VHR Satellite Images[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2016,8(10):4853-4862.
[8] JIA S,LI X,GUO F,et al.A Fast and Robust FCM Algorithm with Local Information for Image Segmentation[J].Icic Express Letters,2015,9(3):869-874.
[9] 贾永红,冯在梅,沈庭乐.基于标记分水岭分割的高分辨率影像水体信息提取[J].测绘通报,2014(9):31-33.
[10] CHU S,HONG L,LIU C,et al.A New Regional Shape Index for Classification of High Resolution Remote Sensing Images[C]//Third International Workshop on Earth Observation and Remote Sensing Applications.Changsha:IEEE,2014.
[11] 陈杰,邵权斌,梅小明,等.结合尺度空间的面向对象高分辨率影像城市道路提取[J].测绘工程,2016,25(12):5-11.
[12] SHI W,MIAO Z,WANG Q,et al.Spectral-spatial Classification and Shape Features for Urban Road Centerline Extraction[J].IEEE Geoscience and Remote Sensing Letters,2014,11(4):788-792.
[13] ZHENG W,TANG H,HUANG T S.Emotion Recognition from Non-frontal Facial Images[M]//Emotion Recogn-ition:A Pattern Analysis Approach.Hoboken:John Wiley and Sons,Inc.,2015:183-213.
[14] CUSANO C,NAPOLETANO P,SCHETTINI R.Remote Sensing Image Classification Exploiting Multiple Kernel Learning[J].IEEE Geoscience and Remote Sensing Letters,2015,12(11):2331-2335.
[15] 晁拴社,楚恒,王兴.高光谱图像数据的多尺度多核SVM分类[J].计算机与现代化,2016(2):11-14.
[16] 吴一全,殷骏,戴一冕,等.基于蜂群优化多核支持向量机的淡水鱼种类识别[J].农业工程学报,2014,30(16):312-319.
[17] GONZALEZ R C,WOODS R E,EDDINS S L.数字图像处理[M].阮秋琦,译.北京:电子工业出版社,2014.
[18] 赵时英.遥感应用分析原理与方法[M].北京:科学出版社,2003.

城市道路的多特征多核SVM提取方法

Multi-feature Multiple Kernels SVM-based Urban Road Extraction

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	潘建平, 付占宝, 程卫华, 陆世安, 李鑫, 孙博文, 黄桂萍. 基于地表类型的山地海绵城市生态建设评估[J]. 测绘通报, 2022, 0(5): 84-88.
[2]	陈智朗, 付振华, 朱紫阳, 王慧慧, 刘沁雯, 杨钰灵, 许耿然. 基于HRNet的高分辨率遥感影像建筑物变化信息提取[J]. 测绘通报, 2022, 0(5): 126-132.
[3]	杨素妨, 杜林. 多特征流形鉴别嵌入的高分辨率遥感影像分类[J]. 测绘通报, 2021, 0(9): 37-42.
[4]	耿万轩, 周维勋, 金双根. 基于LDCNN特征提取的多核SVM高分辨率遥感影像场景分类[J]. 测绘通报, 2021, 0(8): 14-21.
[5]	聂倩, 七珂珂, 赵艳福. 融入超像素分割的高分辨率影像面向对象分类[J]. 测绘通报, 2021, 0(6): 44-49.
[6]	陈利燕, 林鸿, 吴健华. 融合随机森林和超像素分割的建筑物自动提取[J]. 测绘通报, 2021, 0(2): 49-53.
[7]	王媛, 杜明义, 杨柳忠, 蔡国印, 张宁. 多源遥感数据支持下的城市生态状况评价[J]. 测绘通报, 2021, 0(11): 16-20.
[8]	迪里胡玛尔·阿汗木江, 玉素甫江·如素力. 新疆焉耆盆地土壤湿度时空分布特征[J]. 测绘通报, 2021, 0(11): 36-41.
[9]	常京新, 高贤君, 杨元维, 王双喜. 融合多时相高分影像的建筑物轮廓优化方法[J]. 测绘通报, 2020, 0(7): 112-115.
[10]	谢梦, 刘伟, 李二珠, 杨梦圆, 王晓檀. 深度卷积神经网络支持下的遥感影像语义分割[J]. 测绘通报, 2020, 0(5): 36-42.
[11]	乔婷婷, 李鲁群. 结合数据增广和迁移学习的高分辨率遥感影像场景分类[J]. 测绘通报, 2020, 0(2): 37-42.
[12]	陈辉, 张卡, 宿东, 王蓬勃. 建筑物侧面轮廓线约束的高分辨率遥感影像建筑物高度估算方法[J]. 测绘通报, 2019, 0(9): 34-37,72.
[13]	孟庆祥, 吴玄. 基于深度卷积神经网络的高分辨率遥感影像场景分类[J]. 测绘通报, 2019, 0(7): 17-22.
[14]	郝怀旭, 万太礼, 罗年学. 利用OpenStreetMap数据进行高空间分辨率遥感影像分类[J]. 测绘通报, 2019, 0(7): 69-72,126.
[15]	方鑫, 陈善雄. 密集城区高分辨率遥感影像建筑物提取[J]. 测绘通报, 2019, 0(4): 79-83.