Please wait a minute...
REMOTE SENSING FOR LAND & RESOURCES    2014, Vol. 26 Issue (4) : 51-55     DOI: 10.6046/gtzyyg.2014.04.09
Technology and Methodology |
Urban land use/cover classification of remote sensing using random forests under the framework of conditional random fields
YANG Yun1,2, XU Li3, YAN Peili4
1. College of Geological Engineering and Geomatics, Chang'an University, Xi'an 710054, China;
2. Key Laboratory for Western Mineral Resources and Engineering of Ministry of Education, Chang'an University, Xi'an 710054, China;
3. College of Information Engineering, Chang'an University, Xi'an 710061, China;
4. Xi'an Changqing Technology and Engineering Co., Ltd., Xi'an 710018, China
Download: PDF(994 KB)  
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    

The classification accuracy of superpixel-based conditional random fields(CRFs) model greatly depends on segmentation scale parameters, which constitutes a problem that should be solved. Therefore, to answer the question "whether a pixel-based CRFs model performs well in HSR image classification with m level spatial resolution or not",the authors proposed a pixel-based CRFs model with the association term defined as an output of random forests classifier and the interaction potential defined as Potts function weighted by contrast function, and the definition of association and interaction terms adopted multi-cue features such as histogram of gradient, multi- scale and multi-direction Texton filter and multi-spectral information from HSR imagery. Finally, the proposed model was trained using piecewise training method and inferred using α-expansion algorithm based on graph cut. Experiments on a typical urban scene from QuickBird multi-spectral satellite imagery have shown that the proposed RF-CRFs model shows the classification accuracy of over 82.52%. In addition, the classification accuracy of the model is higher than that of the RF classifier by 3.35% on average.

Keywords geological disasters      remote sensing interpretation      Nanping City of Fujian Province      China-Brazil Earth Resource Satellite(CBERS)     
:  TP751.1  
Issue Date: 17 September 2014
E-mail this article
E-mail Alert
Articles by authors
XU Yueren
HE Honglin
SHEN Xuhui
Cite this article:   
XU Yueren,HE Honglin,CHEN Lize, et al. Urban land use/cover classification of remote sensing using random forests under the framework of conditional random fields[J]. REMOTE SENSING FOR LAND & RESOURCES, 2014, 26(4): 51-55.
URL:     OR

[1] 杨红磊,彭军还.基于马尔可夫随机场的模糊c-均值遥感影像分类[J].测绘学报,2012,41(2):213-218. Yang H L,Peng J H.Remote sensing classification based on Markov random field and fuzzy c-means clustering[J].Acta Geodaetica et Cartographica Sinica,2012,41(2):213-218.

[2] Sutton C,Mccallum A.An introduction to conditional random fields[J].Machine Learning,2011,4(4):267-373.

[3] Shotton J,Winn J,Rother C,et al.Textonboost for image understanding:Multi-class object recognition and segmentation by jointly modeling texture,layout,and context[J].International Journal of Computer Vision,2009,81(1):2-23.

[4] Baloch S,Cheng E,Fang T.Shape based Conditional Random Fields for Segmenting Intracranial Aneurysms[M]//Image-based Geometric Modeling and Mesh Generation.Netherlands:Springer,2013:55-67.

[5] 高琳,唐鹏,盛鹏,等.复杂场景下基于条件随机场的视觉目标跟踪[J].光学学报,2010,30(6):1721-1728. Gao L,Tang P,Sheng P,et al.Visual object tracking based on conditional random fields under complex scene[J].Acta Optica Sinica,2010,30(6):1721-1728.

[6] 李玲玲,金泰松,李翠华.基于局部特征和隐条件随机场的场景分类方法[J].北京理工大学学报,2012,32(7):720-724. Li L L,Jin T S,Li C H.Scene classification based on local feature and hidden conditional random fields[J].Transactions of Beijing Institute of Technology,2012,32(7):720-724.

[7] Zhong P,Wang R.Modeling and classifying hyperspectral imagery by CRFs with sparse higher order potentials[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(2):688-705.

[8] Su X,He C,Feng Q,et al.A supervised classification method based on conditional random fields with multiscale region connection calculus model for SAR image[J].IEEE Geoscience and Remote Sensing Letters,2011,8(3):497-501.

[9] Hoberg T,Rottensteiner F,Heipke C.Context models for CRF-based classification of multitemporal remote sensing data[C]//ISPRS Annals of the Photogrammetry,Remote Sensing and Spatial Information Sciences.Melbourne,2012,1/7:129-134.

[10] 刘毅,杜培军,郑辉,等.基于随机森林的国产小卫星遥感影像分类研究[J].测绘科学,2012,37(4):194-196. Liu Y,Du P J,Zheng H,et al.Classification of China small satellite remote sensing image based on random forests[J].Science of Surveying and Mapping,2012,37(4):194-196.

[11] 雷震.随机森林及其在遥感影像处理中应用研究[D].上海:上海交通大学,2012. Lei Z.The research on random forests and its application to remote sensing image processing[D].Shanghai:Shanghai Jiaotong University,2012.

[12] Breiman L.Random forests[J].Machine Learning,2001,45(1):5-32.

[13] 王东广,肖鹏峰,宋晓群,等.结合纹理信息的高分辨率遥感图像变化检测方法[J].国土资源遥感,2012,24(4):76-81. Wang D G,Xiao P F,Song X Q,et al.Change detection method for high resolution remote sensing image in association with textural and spectral information[J].Remote Sensing for Land and Resources,2012,24(4):76-81.

[14] Kontschieder P,Bulò S R,Bischof H,et al.Structured class-labels in random forests for semantic image labelling[C]//International Conference on Computer Vision.Barcelona:IEEE,2011:2190-2197.

[15] Gould S.Darwin:A framework for machine learning and computer vision research and development[J].Journal of Machine Learning Research,2012,13:3533-3537.

[1] Dingjian JIN, Jianchao WANG, Fang WU, Zihong GAO, Yachao HAN, Qi LI. Aerial remote sensing technology and its applications in geological survey[J]. Remote Sensing for Land & Resources, 2019, 31(4): 1-10.
[2] Xiaoping XIE, Maowei BAI, Zhicong CHEN, Weibo LIU, Shuna XI. Remote sensing image interpretation and tectonic activity study of the active faults along the northeastern segment of the Longmenshan fault[J]. Remote Sensing for Land & Resources, 2019, 31(1): 237-246.
[3] Xinxin SUI, Suwen SUI. Design and implementation of remote sensing interpretation map database based on MapGIS and ArcGIS[J]. Remote Sensing for Land & Resources, 2018, 30(4): 218-224.
[4] Xinxin SUI, Suwen SUI, Kun LIU. Research and construction of interpretation result data management system toward remote sensing application[J]. Remote Sensing for Land & Resources, 2018, 30(3): 238-243.
[5] Ruijun WANG, Bokun YAN, Mingsong LI, Shuangfa DONG, Yongbin SUN, Bing WANG. Remote sensing interpretation of important ore-controlling geological units in Hongshan Region of Gansu Province using GF-1 image and its application[J]. Remote Sensing for Land & Resources, 2018, 30(2): 162-170.
[6] LI Haiying. Application of domestic high resolution remote sensing data to environmental geological survey[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(s1): 46-51.
[7] YANG Jinzhong, NIE Hongfeng, JING Qingqing. Preliminary analysis of mine geo-environment status and existing problems in China[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(2): 1-7.
[8] LI Xiaomin, ZHANG Kun, LI Dongling, LI Delin, LI Zongren, ZHANG Xing. Remote sensing technology delineation method and its application to permafrost of Zhada area in the Tibetan Plateau[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(1): 57-64.
[9] LI Xiaomin, YAN Yunpeng, LIU Gang, LI Dongling, ZHANG Xing, ZHUANG Yongcheng. Application of ZY-1 02C satellite data to hydrogeological investigation in Zanda area, Tibet[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(4): 141-148.
[10] ZHANG Kun, LI Xiaomin, MA Shibin, LIU Shiying, LI Shenghui. Application of GF-1 image to geological disaster survey in Cosibsumgy village on Sino-India border area[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(2): 139-148.
[11] JIN Dingjian, ZHI Xiaodong, WANG Jianchao, ZHANG Dandan, SHANG Boxuan. Comparison of UAV remote sensing image processing software for geological disasters monitoring[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(1): 183-189.
[12] SU Yuanyuan, ZHANG Jingfa, HE Zhongtai, JIANG Wenliang, JIANG Hongbo, LI Qiang. Assessment of applying ZY-3 DEM data to quantitative study of active structures[J]. REMOTE SENSING FOR LAND & RESOURCES, 2015, 27(4): 122-130.
[13] LIU Dechang, TONG Qinlong, LIN Ziyu, YANG Guofang. Remote sensing geological interpretation and strategy area selection for mineral exploration in Europe[J]. REMOTE SENSING FOR LAND & RESOURCES, 2015, 27(3): 136-143.
[14] WEI Yongming, WEI Xianhu, CHEN Yu. Analysis of distribution regularity and development tendency of earthquake secondary geohazards in Yingxiu-Maoxian section along the Minjiang River[J]. REMOTE SENSING FOR LAND & RESOURCES, 2014, 26(4): 179-186.
[15] XU Bing, FANG Chen. Data fusion methods of ZY-1 02C and ETM+ images and effect evaluation[J]. REMOTE SENSING FOR LAND & RESOURCES, 2014, 26(3): 80-85.
Full text



Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech