面向对象的无人机影像地物分类

doi:10.3969/j.issn.0255-8297.2021.02.013

摘要/Abstract

摘要： 为了对农村用地进行有效分类，本文选取面向对象的分类方法，利用某农村的无人机航摄影像提取其土地类别信息。首先对无人机获取的原始影像进行预处理；然后对研究区反复进行分割实验，选取最优的分割尺度，在不同层次进行最优尺度地物分割；最后根据地物矢量、光谱、形状等特征差异，对最优分割尺度层上的地物进行最适宜的分类规则的建立，进而在每一层提取土地利用信息。利用单一尺度分割分类进行对比实验，选取734个样本进行精度验证，研究结果表明：多尺度多层次分割分类的总体分类精度可达84.20%，kappa系数为0.806 2；单一尺度分割分类总体精度仅为77.11%，kappa系数为0.721 4。由此可见，本文研究所采用的数据和区域内的类别的分类精度更高。

关键词: 面向对象分类, 无人机影像, 多尺度分割, 土地利用

Abstract: In order to effectively classify the rural land, an object-oriented classification method is selected to extract the land classification information of drone aerial photography images. First, original drone-taking images are preprocessed, then by repeatedly performing segmentation tests on the study area, the optimal segmentation scale of each feature is selected, with which the images are segmented at different levels. And based on feature differences in feature vector, spectrum, shape, etc., the most suitable classification rules are established for the features on the optimal segmentation scale layer. Accordingly, the land use information of each layer can be extracted. Experimental results with 734 samples for accuracy verification show that the overall classification accuracy of multi-scale and multi-level segmentation classification reaches 84.20%, and the kappa coefficient is 0.8062, whereas the overall accuracy of single-scale segmentation classification is only 77.11%, and the kappa coefficient is 0.7214. It shows that the data used in this study and the classification accuracy of the categories inside the region are higher.

Key words: object-oriented classification, unmanned aerial vehicle image, multi-scale segmentation, land use

中图分类号:

P237

马飞虎, 徐发东, 孙翠羽. 面向对象的无人机影像地物分类[J]. 应用科学学报, 2021, 39(2): 312-320.

MA Feihu, XU Fadong, SUN Cuiyu. Land-Use Information of Object-Oriented Classification by UAV Image[J]. Journal of Applied Sciences, 2021, 39(2): 312-320.

参考文献

[1] 程琳琳, 董雪梅, 詹佳琪, 等. 基于面向对象的GF-1遥感影像采煤沉陷区湿地分类[J]. 农业工程学报, 2018, 34(9):240-247. Cheng L L, Dong X M, Zhan J Q, et al. Classification of wetland based on object-oriented method in coal mining subsidence area using GF-1 remote sensing image[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(9):240-247. (in Chinese)
[2] 张华, 张改改, 吴睿. 基于GF-1卫星数据的面向对象的民勤绿洲植被分类研究[J]. 干旱区地理, 2017, 40(4):831-838. Zhang H, Zhang G G, Wu R. Object-based vegetable classification based on GF-1 imagery in minqin oasis[J]. Arid Land Geography, 2017, 40(4):831-838. (in Chinese)
[3] 王柯, 付怡然, 彭向阳, 等. 无人机低空遥感技术进展及典型行业应用综述[J]. 测绘通报, 2017(S1):85-89. Wang K, Fu Y R, Peng X Y, et al. Overview of UAV low altitude remote sensing technology and application in typical industries[J]. Bulletin of Surveying and Mapping, 2017(S1):85-89. (in Chinese)
[4] 程琳琳, 赵云肖, 陈良. 高潜水位采煤沉陷区土地损毁程度评价[J]. 农业工程学报, 2017, 33(21):253-260. Cheng L L, Zhao Y X, Chen L. Evaluation of land damage degree of mining subsidence area with high groundwater level[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(21):253-260. (in Chinese)
[5] Baatz M, Schape A. Object-oriented and multi-scale image analysis in semantic networks[C]//Proceedings of the 2nd International Symposium on Operationalization of Remote Sensing. Enschede, Netherlands, 1999:16-20.
[6] 胡佳, 林辉, 孙华, 等. 湿地类型遥感影像分割最优尺度选择[J]. 中南林业科技大学学报, 2015, 35(11):32-37. Hu J, Lin H, Sun H, et al. Select optimal segmentation scale of wetlands using remote sensing data[J]. Journal of Central South University of Forestry & Technology, 2015, 35(11):32-37. (in Chinese)
[7] Khatami R, Mountrakis G, Stehman S V. A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes:general guidelines for practitioners and future research[J]. Remote Sensing of Environment, 2016, 177:89-100.
[8] 何少林, 徐京华, 张帅毅. 面向对象的多尺度无人机影像土地利用信息提取[J]. 国土资源遥感, 2013, 25(2):107-112. He S L, Xu J H, Zhang S Y. Land use classification of object-oriented multi-scale by UAV image[J]. Remote Sensing for Land and Resources, 2013, 25(2):107-112. (in Chinese)
[9] 马燕妮, 明冬萍, 杨海平. 面向对象影像多尺度分割最大异质性参数估计[J]. 遥感学报, 2017, 21(4):566-578. Ma Y N, Ming D P, Yang H P. Scale estimation of object-oriented image analysis based on spectral-spatial statistic[J]. Journal of Remote Sensing, 2017, 21(4):566-578. (in Chinese)
[10] 刘舒, 朱航. 基于超高空间分辨率无人机影像的面向对象土地利用分类方法[J]. 农业工程学报, 2020, 36(2):87-94. Liu S, Zhu H. Object-oriented land use classification based on ultra-high resolution images taken by unmanned aerial vehicle[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(2):87-94. (in Chinese)
[11] Ponttuset J, Arbelaez P, Barron J, et al. Multiscale combinatorial grouping for image segmentation and object proposal generation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(1):128-140.
[12] 陈冬梅, 冯策元, 周建民, 等. 面向对象的农村用地信息遥感提取技术应用——以宁夏西吉为例[J]. 城市发展研究, 2017, 24(9):127-132, 29. Chen D M, Feng C Y, Zhou J M, et al. Applications of object-oriented rural land use information extraction by remote sensing technology:——a case study of Xiji County, Ningxia Province[J]. Urban Development Studies, 2017, 24(9):127-132, 29. (in Chinese)
[13] 朱俊杰, 范湘涛, 杜小平. 几何特征表达及基于几何特征的建筑物提取[J]. 应用科学学报, 2015, 33(1):9-20. Zhu J J, Fan X T, Du X P. Geometric feature representation and building extraction based on geometric features[J]. Journal of Applied Sciences, 2015, 33(1):9-20. (in Chinese)
[14] 鲁恒, 李永树, 林先成. 无人机高分辨率影像分类研究[J]. 测绘科学, 2011, 36(6):108-110. Lu H, Li Y S, Lin X C. Classification of high resolution imagery by unmanned aerial vehicle[J]. Science of Surveying and Mapping, 2011, 36(6):108-110. (in Chinese)
[15] 张磊, 宫兆宁, 王启为, 等. Sentinel-2影像多特征优选的黄河三角洲湿地信息提取[J]. 遥感学报, 2019, 23(2):313-326. Zhang L, Gong Z N, Wang Q W, et al. Wetland mapping of Yellow River Delta wetlands based on multi-feature optimization of Sentinel-2 image[J]. Journal of Remote Sensing, 2019, 23(2):313-326. (in Chinese)