Acta Geodaetica et Cartographica Sinica >

2016 , Vol. 45 >Issue 7: 825 - 833

DOI: https://doi.org/10.11947/j.AGCS.2016.20150520

Applying Spatial Statistics into Remote Sensing Pattern Recognition: with Case Study of Cropland Extraction Based on GeOBIA

  • MING Dongping ,
  • QIU Yufang ,
  • ZHOU Wen
Expand
  • School of Information Engineering, China University of Geosciences(Beijing), Beijing 100083, China

Received date: 2015-10-14

  Revised date: 2016-02-24

  Online published: 2016-07-28

Supported by

The National Natural Science Foundation of China(No.41371347);Fundamental Research Funds for the Central Universities(No.2652013084)

Fold

Abstract

Information extraction from remote sensing image is the key to remote sensing applications and scale selection is one of the key factors influencing the information extraction accuracy. This paper discusses the theoretical foundation of applying spatial statistical methods to resolve the scale related issues involved in remote sensing pattern classification. Aiming at geo-object-based image analysis (GeOBIA), scale parameters involved in multi-scale segmentation for GeOBIA are generalized into three ones, and they are spatial parameter, attribute parameter and merging threshold. Further, the pre-estimation method of the optimal scale parameters is proposed based on spatial statistics. Taking GeOBIA based cropland extraction from SPOT-5 image as an example, this paper proposes a cropland extraction method combining spatial statistics based adaptive scale parameter pre-estimation and object-oriented classification. This paper employs mean-shift segmentation and series Rof object based classification on different scales to verify the validity of this method. Experimental results support the object based cropland extraction method based on the data-driven scale pre-estimation. The cropland extraction result by using the pre-estimated segmentation parameters can guarantee the accuracy of GeOBIA classification and the cropland extraction based on GeOBIA and adaptive scale pre-estimation avoids the time-consuming trial-and-error practice and speeds up the object-oriented classification procedure.

Key words： geo-object-based image analysis; image segmentation; scale pre-estimation; spatial statistics; cropland extraction

Cite this article

MING Dongping , QIU Yufang , ZHOU Wen . Applying Spatial Statistics into Remote Sensing Pattern Recognition: with Case Study of Cropland Extraction Based on GeOBIA[J]. Acta Geodaetica et Cartographica Sinica, 2016 , 45(7) : 825 -833 . DOI: 10.11947/j.AGCS.2016.20150520

References

[1] 温奇,李苓苓,刘庆杰, 等. 基于视觉显著性和图分割的高分辨率遥感影像中人工目标区域提取[J]. 测绘学报, 2013, 42(6):831-837. WEN Qi, LI Lingling, LIU Qingjie, et al. A Man-made Object Area Extraction Method Based on Visual Saliency Detection and Graph-cut Segmentation for High Resolution Remote Sensing Imagery[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(6):831-837.
[2] 李亮, 舒宁, 王凯, 等. 融合多特征的遥感影像变化检测方法[J]. 测绘学报, 2014, 43(9):945-953, 959.DOI:10.13485/j.cnki.11-2089.2014.0138. LI Liang, SHU Ning, WANG Kai, et al. Change Detection Method for Remote Sensing Images Based on Multi-features Fusion[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(9):945-953, 959. DOI:10.13485/j.cnki.11-2089.2014.0138.
[3] 冯文卿, 张永军. 利用多尺度融合进行面向对象的遥感影像变化检测[J]. 测绘学报, 2015, 44(10):1142-1151.DOI:10.11947/j.AGCS.2015.20140260. FENG Wenqing,ZHANG Yongjun.Object-oriented Change Detection for Remote Sensing Images Based on Multi-scale Fusion[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(10):1142-1151. DOI:10.11947/j.AGCS.2015.20140260.
[4] 李慧, 唐韵玮, 刘庆杰, 等. 一种改进的基于最小生成树的遥感影像多尺度分割方法[J]. 测绘学报, 2015, 44(7):791-796.DOI:10.11947/j.AGCS.2015.20140060. LI Hui, TANG Yunwei, LIU Qingjie, et al.An Improved Algorithm Based on Minimum Spanning Tree for Multi-scale Segmentation of Remote Sensing Imagery[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(7):791-796. DOI:10.11947/j.AGCS.2015.20140060.
[5] 慎利, 唐宏, 王世东, 等. 结合空间像素模板和Adaboost算法的高分辨率遥感影像河流提取[J]. 测绘学报, 2013, 42(3):344-350. SHEN Li, TANG Hong, WANG Shidong, et al. River Extraction from the High Resolution Remote Sensing Image Based on Spatially Correlated Pixels Template and Adboost Algorithm[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(3):344-350.
[6] CHEN D, STOW D A, GONG P. Examining the Effect of Spatial Resolution and Texture Window Size on Classification Accuracy:An Urban Environmental Case[J]. International Journal of Remote Sensing, 2004, 25(11):2177-2192.
[7] MING Dongping,DU Jinyang,ZHANG Xiyu, et al. Modified Average Local Variance for Pixel-level Scale Selection of Multi-band Remote Sensing Images and Its Scale Effect on Image Classification Accuracy[J]. Journal of Applied Remote Sensing, 2013, 7(1):073565-1-18. DOI:10.1117/1.JRS.7.073565.
[8] MING Dongping, YANG Jianyu, LI Longxiang, et al. Modified ALV for Selecting the Optimal Spatial Resolution and Its Scale Effect on Image Classification Accuracy[J]. Mathematical and Computer Modelling, 2011, 54(3-4):1061-1068.
[9] BELGIU M, DRĂGUT L. Comparing Supervised and Unsupervised Multiresolution Segmentation Approaches for Extracting Buildings from Very High Resolution Imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 96:67-75.
[10] CASTILLA G, HERNANDO A,ZHANG Chunhua,et al. The Impact of Object Size on the Thematic Accuracy of Landcover Maps[J]. International Journal of Remote Sensing, 2014, 35(3):1029-1037.
[11] GOODCHILD M, QUATTROCHI DA. Introduction:Scale, Multiscaling, Remote Sensing, and GIS[M]//QUATTROCHI D A, GOODCHILD M F. Scale in Remote Sensing and GIS.Boca Raton:Lewis Publishers, 1997:1-12.
[12] LAM N S N, QUATTROCHI DA. On the Issues of Scale, Resolution, and Fractal Analysis in the Mapping Sciences[J]. The Professional Geographer, 1992, 44(1):88-98.
[13] CAO C, LAM N S N. Understanding the Scale and Resolution Effects in Remote Sensing and GIS[M]//QUATTROCHI D A, GOODCHILD M F. Scale in Remote Sensing and GIS.Boca Raton:Lewis Publishers, 1997:57-72.
[14] 明冬萍, 王群, 杨建宇. 遥感影像空间尺度特性与最佳空间分辨率选择[J]. 遥感学报, 2008, 12(4):529-537. MING Dongping, WANG Qun, YANG Jianyu. Spatial Scale of Remote Sensing Image and Selection of Optimal Spatial Resolution[J]. Journal of Remote Sensing, 2008, 12(4):529-537.
[15] MING Dongping, LI J, WANG Junyi, et al. Scale Parameter Selection by Spatial Statistics for GeOBIA:Using Mean-shift Based Multi-scale Segmentation as an Example[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 106:28-41.
[16] MING Dongping, CI Tianyu, CAI Hongyue, et al. Semivariogram-based Spatial Bandwidth Selection for Remote Sensing Image Segmentation with Mean-shift Algorithm[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(5):813-817.
[17] WOODCOCKCE, STRAHLERA H. The Factor of Scale in Remote Sensing[J]. Remote Sensing of Environment, 1987, 21(3):311-332.
[18] LLOYD CD, ATKINSON PM. Scale and the Spatial Structure of Landform:Optimizing Sampling Strategies with Geostatistics[C]//Proceedings of the 3rd International Conference on GeoComputation. Bristol:University of Bristol, 1998.
[19] MATHERON G. Principles of Geostatistics[J]. Economic Geology,1963, 58(8):1246-1266.
[20] GARDNER R H. Pattern, Process, and the Analysis of Spatial Scales[M]//PETERSON D L, PARKER V T. Ecological Scale:Theory and Applications. New York:Columbia University Press,1998:17-34.
[21] O'NEILL R V, TURNER S J, CULLINAN V I, et al. Multiple Landscape Scales:An Intersite Comparison[J]. Landscape Ecology, 1991, 5(3):137-144.
[22] COMANICIU D, RAMESH V, MEER P. The Variable Bandwidth Mean Shift and Data-driven Scale Selection[C]//Proceedings of the 8th IEEE International Conference on Computer Vision, 2001. Vancouver:IEEE, 2001:438-445.
[23] LI Xiangru, HU Zhanyi, WU Fuchao. A Note on the Convergence of the Mean Shift[J]. Pattern Recognition, 2007, 40(6):1756-1762.
[24] LI Xiangru, WU Fuchao, HU Zhanyi. Convergence of a Mean Shift Algorithm[J]. Journal of Software, 2005, 16(3):365-374.
[25] CAO Feng, GE Yong, WANG Jinfeng. Optimal Discretization for Geographical Detectors-based Risk Assessment[J]. GIScience & Remote Sensing, 2013, 50(1):78-92.
[26] CAO Feng, GE Yong, WANG Jinfeng. Spatial Data Discretization Methods for GeoComputation[J]. International Journal of Applied Earth Observation and Geoinformation, 2014, 26:432-440.
[27] PEÑA-BARRAGÁN J M,NGUGI M K,PLANT R E, et al. Object-based Crop Identification Using Multiple Vegetation Indices, Textural Features and Crop Phenology[J]. Remote Sensing of Environment, 2011, 115(6):1301-1316.
Options
Outlines

/

〈 〉