结合随机森林面向对象的森林资源分类

doi:10.11947/j.AGCS.2020.20190272

测绘学报 ›› 2020, Vol. 49 ›› Issue (2): 235-244.doi: 10.11947/j.AGCS.2020.20190272

结合随机森林面向对象的森林资源分类

王猛¹, 张新长^1,3, 王家耀^2,3, 孙颖⁴, 箭鸽¹, 潘翠红¹

1. 广州大学地理科学学院, 广东广州 510006;
2. 河南省时空大数据产业技术研究院, 河南郑州 450018;
3. 河南大学环境与规划学院, 河南开封 475004;
4. 中山大学地理科学与规划学院, 广东广州 510275

收稿日期:2019-06-27 修回日期:2019-11-25 发布日期:2020-03-03
通讯作者: 张新长 E-mail:eeszxc@mail.sysu.edu.cn
作者简介:王猛(1994-),男,硕士生,研究方向为遥感信息提取、基础地理空间数据更新。E-mail:wangmcug@163.com
基金资助:
国家重点研发计划（2018YFB2100702）；国家自然科学基金重点项目（41431178）；广东省自然科学基金重点项目（2016A030311016）；智慧广州时空信息云平台建设项目（GZIT2016-A5-147）；河南省时空大数据产业技术研究院资助项目（2017DJA001）；中央高校基本科研业务费专项资金（19lgpy44）

Forest resource classification based on random forest and object oriented method

WANG Meng¹, ZHANG Xinchang^1,3, WANG Jiayao^2,3, SUN Ying⁴, JIAN Ge¹, PAN Cuihong¹

1. School of Geographical Sciences, Guangzhou University, Guangzhou 510006, China;
2. Research Institute of Henan Spatio-Temporal Big Data Industrial Technology, Zhengzhou 450018, China;
3. The College of Environment and Planning, Henan University, Kaifeng 475004, China;
4. Department of Geography and Planning, Sun Yat-Sen University, Guangzhou 510275, China

Received:2019-06-27 Revised:2019-11-25 Published:2020-03-03
Supported by:
The National Key R & D Program of China (No. 2018YFB2100702);The Key Program of the National Natural Science Foundation of China (No. 41431178);The Key Program of the Natural Science Foundation of Guangdong Province (No. 2016A030311016);The Smart Guangzhou Spatiotemporal Infomation Cloud Platform Project (No. GZIT2016-A5-147);Supported by the Research Institute of Henan Spatio-Temporal Big Data Industrial Technology(2017DJA001);The Fundamental Research Funds for the Central Universities (No. 19lgpy44)

摘要/Abstract

摘要： 针对森林资源分类研究较少且缺少相对简单有效的方法的情况，提出一种结合面向对象和随机森林的森林资源分类方法。面向对象分割技术可减少"椒盐效应"，随机森林分类算法具有高准确度、抗噪声能力强、性能稳定等优势。鉴于此，通过调整面向对象的分割参数，构造最优特征空间及估算随机森林中决策树的数量等，构建了最优的面向对象随机森林分类模型。另外，选择了SVM算法作对比试验。试验结果显示，本文分类算法的总体精度达到83.34%，Kappa系数为0.789 2，明显高于SVM，能够有效提高森林资源分类的精度。

关键词: 森林资源分类, 面向对象方法, 随机森林

Abstract: Given that there are few studies on forest resource classification with the lack of relatively simple and effective methods, a forest resource classification method integrating object-oriented segmentation and random forest is proposed in this paper. Object-oriented segmentation technology could efficiently reduce the "salt and pepper effect", and random forest classification algorithm has the advantages of high accuracy, strong anti-noise ability and satisfying stability. Therefore, we built the optimum random forest classification model by adjusting the object-oriented segmentation parameters, constructing the optimal feature space and estimating the number of decision trees in random forests. Besides, the SVM algorithm is taken into comparison. The results show that the overall accuracy of the classification algorithm in this study is 83.34%with the Kappa coefficient reaching 0.789 2, which are significantly higher than that of SVM algorithm. It proves that object-oriented random forest classification can effectively improve the accuracy of forest resource classification.

Key words: forest resource classification, object-oriented method, random forest

中图分类号:

P237

王猛, 张新长, 王家耀, 孙颖, 箭鸽, 潘翠红. 结合随机森林面向对象的森林资源分类[J]. 测绘学报, 2020, 49(2): 235-244.

WANG Meng, ZHANG Xinchang, WANG Jiayao, SUN Ying, JIAN Ge, PAN Cuihong. Forest resource classification based on random forest and object oriented method[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(2): 235-244.

参考文献

[1] 张海波, 汪长城, 朱建军, 等. 利用ESAR极化数据的复杂地形区森林地上生物量估算[J]. 测绘学报, 2018, 47(10):1353-1362. DOI:10.11947/j.AGCS.2018.20170120. ZHANG Haibo, WANG Changcheng, ZHU Jianjun, et al. Forest above-ground biomass estimation for rugged terrain by using ESAR polarization data[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(10):1353-1362. DOI:10.11947/j.AGCS.2018.20170120.
[2] 施拥军. 森林遥感分类技术研究——以浙西北山区为例[D]. 杭州:浙江大学, 2003. SHI Yongjun. Research on technologies of forest classification by remote sensing:a case study of northwest mountainous area in Zhejiang[D]. Hangzhou:Zhejiang University, 2003.
[3] 闫飞. 森林资源调查技术与方法研究[D]. 北京:北京林业大学, 2014. YAN Fei. Research of technology and method of forest resource inventory[D]. Beijing:Beijing Forestry University, 2014.
[4] ACHARD F, ESTREGUIL C. Forest classification of Southeast Asia using NOAA AVHRR data[J]. Remote Sensing of Environment, 1995, 54(3):198-208.
[5] MCDONALD A J, GEMMELL F M, LEWIS P E. Investigation of the utility of spectral vegetation indices for determining information on coniferous forests[J]. Remote Sensing of Environment, 1998, 66(3):250-272.
[6] VERSTRETE M M, PINTY B. Designing optimal spectral indexes for remote sensing applications[J]. IEEE Transactions on Geoscience & Remote Sensing, 1996, 34(5):1254-1265.
[7] MAYAUX P, DE GRANDI G, MALINGREAU J P. Central African forest cover revisited:a multisatellite analysis[J]. Remote Sensing of Environment, 2000, 71(2):183-196.
[8] MARTIN M E, NEWMAN S D, ABER J D, et al. Determining forest species composition using high spectral resolution remote sensing data[J]. Remote Sensing of Environment, 1998, 65(3):249-254.
[9] PASQUARELLA V J, HOLDEN C E, WOODCOCK C E. Improved mapping of forest type using spectral-temporal Landsat features[J]. Remote Sensing of Environment, 2018, 210:193-207.
[10] 韩涛. 用TM资料对祁连山部分地区进行针叶林、灌木林分类研究[J]. 遥感技术与应用, 2002, 17(6):317-321. HAN Tao. Study on classification between coniferous forest and shrubbery based on TM data in the part of QI Lian mountainous area[J]. Remote Sensing Technology and Application, 2002, 17(6):317-321.
[11] 严恩萍, 林辉, 莫登奎, 等. 基于ALOS数据的遥感植被分类研究[J]. 中南林业科技大学学报, 2010, 30(11):37-42. YANG Enping, LIN Hui, MO Dengkui, et al. Vegetation classification based on ALOS data[J]. Journal of Central South University of Forestry & Technology, 2010, 30(11):37-42
[12] SANTRA A, MITRA S S. A comparative study of tasselled cap transformation of DMC and ETM+ images and their application in forest classification[J]. Journal of the Indian Society of Remote Sensing, 2014, 42(2):373-381.
[13] RICHTER R, REU B, WIRTH C, et al. The use of airborne hyperspectral data for tree species classification in a species-rich central European forest area[J]. International Journal of Applied Earth Observation and Geoinformation, 2016, 52:464-474.
[14] GHEBREZGABHER M G, YANG Taibao, YANG Xuemei, et al. Extracting and analyzing forest and woodland cover change in Eritrea based on Landsat data using supervised classification[J]. The Egyptian Journal of Remote Sensing and Space Science, 2016, 19(1):37-47.
[15] PULETTI N, CHIANUCCI F, CASTALDI C. Use of Sentinel-2 for forest classification in Mediterranean environments[J]. Annals of Silvicultural Research, 2018, 42(1):32-38.
[16] CHEN Y, SHI P, FUNG T, et al. Object-oriented classification for urban land cover mapping with ASTER imagery[J]. International Journal of Remote Sensing, 2007, 28(20):4645-4651.
[17] 陶超, 谭毅华, 蔡华杰, 等. 面向对象的高分辨率遥感影像城区建筑物分级提取方法[J]. 测绘学报, 2010, 39(1):39-45. TAO Chao, TAN Yihua, CAI Huajie, et al. Object-oriented method of hierarchical urban building extraction from high-resolution remote-sensing imagery[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(1):39-45.
[18] SCHIEWE J, TUFTE L, EHLERS M. Potential and problems of multi-scale segmentation methods in remote sensing[J]. GeoBIT/GIS, 2001, 6(1):34-39.
[19] 顾海燕, 闫利, 李海涛, 等. 基于随机森林的地理要素面向对象自动解译方法[J]. 武汉大学学报(信息科学版), 2016, 41(2):228-234. GU Haiyan, YAN Li, LI Haitao, et al. An object-based automatic interpretation method for geographic features based on random forest machine learning[J]. Geomatics and Information Science of Wuhan University, 2016, 41(2):228-234.
[20] BREIMAN L. Random forests[J]. Machine learning, 2001, 45(1):5-32.
[21] HE Xianjin, ZHANG Xinchang, XIN Qinchuan. Recognition of building group patterns in topographic maps based on graph partitioning and random forest[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 136:26-40.
[22] STUMPF A, KERLE N. Object-oriented mapping of landslides using random forests[J]. Remote Sensing of Environment, 2011, 115(10):2564-2577.
[23] PUISSANT A, ROUGIER S, STUMPF A. Object-oriented mapping of urban trees using Random Forest classifiers[J]. International Journal of Applied Earth Observation and Geoinformation, 2014, 26:235-245.
[24] WATTS J D, LAWRENCE R L. Merging random forest classification with an object-oriented approach for analysis of agricultural lands[C]//Proceedings of the International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Beijing:Chinese Society for Geodesy Photogrammetry and Cartography, 2008:579-582.
[25] 付春风. 基于GIS的流溪河森林公园景观分类与制图[J]. 华中农业大学学报, 2009, 28(2):233-237. FU Chunfeng. GIS-based forest landscape classification and mapping of Liuxihe National Forest Park[J]. Journal of Huazhong Agricultural University, 2009, 28(2):233-237.
[26] 李国元, 胡芬, 张重阳, 等. WorldView-3卫星成像模式介绍及数据质量初步评价[J]. 测绘通报, 2015(S1):11-16. DOI:10.13474/j.cnki.11-2246.2015.0675. LI Guoyuan, HU fen, ZHANG Chongyang, et al. Introduction to imaging mode of WorldView-3 satellite and image quality preliminary evaluation[J]. Bulletin of Surveying and Mapping, 2015(S1):11-16. DOI:10.13474/j.cnki.11-2246.2015.0675.
[27] RODRIGUEZ-GALIANO V F, GHIMIRE B, ROGAN J, et al. An assessment of the effectiveness of a random forest classifier for land-cover classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012(67):93-104.
[28] 张志强, 张新长, 辛秦川, 等. 结合像元级和目标级的高分辨率遥感影像建筑物变化检测[J]. 测绘学报, 2018, 47(1):102-112. DOI:10.11947/j.AGCS.2018.20170483. ZHANG Zhiqiang, ZHANG Xinchang, XIN Qinchuan, et al. Combining the pixel-based and object-based methods for building change detection using high-resolution remote sensing images[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(1):102-112. DOI:10.11947/j.AGCS.2018.20170483.
[29] 张雯, 刘爱利, 齐威, 等. 基于随机森林的月貌面向对象分类[J]. 遥感信息, 2018, 33(1):93-98. ZHANG Wen, LIU Aili, QI Wei, et al. Lunar terrain object-oriented classification based on random forest[J]. Remote Sensing Information, 2018, 33(1):93-98.
[30] BAATZ M, SCHAPE A. Multiresolution segmentation:an optimization approach for high quality multi-scale image segmentation[C]//Angewandte Geographische Informations Verarbeitung. Heidelberg:Wichmann-Verlag, 2000:12-23.
[31] 孙坤, 鲁铁定. 顾及多尺度分割参数的FNEA面向对象分类[J]. 测绘通报, 2018(3):43-48. SUN Kun, LU Tieding. Research on FNEA object-oriented classification based on multi-scale partition parameters[J]. Bulletin of Surveying and Mapping, 2018(3):43-48.
[32] GENUER R, POGGI J M, TULEAU-MALOT C. Variable selection using random forests[J]. Pattern Recognition Letters, 2010, 31(14):2225-2236.
[33] WEISS G M. Mining with rarity:a unifying framework[J]. ACM SIGKDD Explorations Newsletter, 2004, 6(1):7-19.
[34] STEHMAN S V. Selecting and interpreting measures of thematic classification accuracy[J]. Remote sensing of Environment, 1997, 62(1):77-89.

结合随机森林面向对象的森林资源分类

Forest resource classification based on random forest and object oriented method

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	王蓝星, 王群明, 童小华. 融合多光谱影像的高光谱影像厚云去除方法[J]. 测绘学报, 2022, 51(4): 612-621.
[2]	熊艳, 高仁强, 徐战亚. 机载LiDAR点云数据降维与分类的随机森林方法[J]. 测绘学报, 2018, 47(4): 508-518.
[3]	杨俊涛, 康志忠. 多尺度特征和马尔可夫随机场模型的电力线场景点云分类法[J]. 测绘学报, 2018, 47(2): 188-197.
[4]	张志强, 张新长, 辛秦川, 杨晓羚. 结合像元级和目标级的高分辨率遥感影像建筑物变化检测[J]. 测绘学报, 2018, 47(1): 102-112.
[5]	冯文卿, 眭海刚, 涂继辉, 孙开敏, 黄伟明. 高分辨率遥感影像的随机森林变化检测方法[J]. 测绘学报, 2017, 46(11): 1880-1890.