地貌形态多尺度综合分类方法

doi:10.13866/j.azr.2022.02.30

摘要/Abstract

摘要：

地貌形态对象往往大小悬殊,跨越特定的空间尺度。现有的地貌形态自动分类方法尚未充分顾及该特点,分类精度受到制约。利用地貌形态的大小为尺度,提出1种涉及尺度跨越性的地貌形态多尺度综合分类方法,该方法由多尺度分割、按尺度顺序筛选和多尺度合并3个步骤构成。其中,按尺度顺序筛选是1个以多尺度特征提取和监督分类为基础、以小尺度（小尺寸）优先和概率最大化为准则的被分类对象迭代确认过程。以黄土高原为例的试验结果表明,该方法简便可靠（总体精度可以达到75.16%,Kappa系数可以达到0.71）,可用于地貌形态精细化分类。

关键词: 地貌形态, 分类, 多尺度, 黄土高原

Abstract:

Landform objects span a broad range of sizes. Existing automatic landform classification methods do not fully consider size, however, which restricts classification accuracy. This study proposes a multi-scale integrated classification method for landform that considers the size of different features. The method consists of three steps: multi-scale segmentation, screening according to scale order, and multi-scale merging. The screening according to scale order is an iterative confirmation process of classified objects based on multi-scale feature extraction and supervised classification, with small scale (small size) priority and probability maximization as criteria. According to experimental results from the Loess Plateau, the method is simple and reliable (overall accuracy reached 75.16% and the Kappa coefficient reached 0.71) and can be used for detailed classification of landform.

Key words: landforms, classification, multi-scale, Loess Plateau

杨维涛,孙建国,马恒利,黄卓. 地貌形态多尺度综合分类方法[J]. 干旱区研究, 2022, 39(2): 638-645.

YANG Weitao,SUN Jianguo,MA Hengli,HUANG Zhuo. A multi-scale integrated classification method for landforms[J]. Arid Zone Research, 2022, 39(2): 638-645.

图/表 8

图1

图2

图3

图4

表1

图5

表2

表3

参考文献 25

[1]	田丹, 刘爱利, 丁浒, 等. 地貌形态类型面向对象分类法的改进[J]. 地理与地理信息科学, 2016, 32(2):46-50.
	[ Tian Dan, Liu Aili, Ding Hu, et al. Improvement of object-oriented classification method for landform types[J]. Geography and Geo-Information Science, 2016, 32(2):46-50. ]
[2]	李炳元, 潘保田, 程维明, 等. 中国地貌区划新论[J]. 地理学报, 2013, 68(3):291-306.
	[ Li Bingyuan, Pan Baotian, Cheng Weiming, et al. Research on geomorphological regionalization of China[J]. Acta Geographica Sinica, 2013, 68(3):291-306. ]
[3]	Deniz G, Toprak V, Strobl J. Object-based classification of landforms based on their local geometry and geomorphometric context[J]. International Journal of Geographical Information Science, 2011, 25(6):1011-1023. doi: 10.1080/13658816.2011.558845
[4]	Macmillan R A, Moon D E, Ray A. et al. Automated predictive ecological mapping in a Forest Region of B. C. Canada, 2001-2005[J]. Geoderma, 2007, 140(4):353-373. doi: 10.1016/j.geoderma.2007.04.027
[5]	秦承志, 卢岩君, 邱维理, 等. 模糊坡位信息在精细土壤属性空间推测中的应用[J]. 地理研究, 2010, 29(9):1706-1714. doi: 10.11821/yj2010090016
	[ Qin Chengzhi, Lu Yanjun, Qiu Weili, et al. Application of fuzzy slope positions in predicting spatial distribution of soil property at finer scale[J]. Geographical Research, 2010, 29(9):1706-1714. ] doi: 10.11821/yj2010090016
[6]	邱海军, 崔鹏, 胡胜, 等. 陕北黄土高原不同地貌类型区黄土滑坡频率分布[J]. 地球科学, 2016, 41(2):343-350.
	[ Qiu Haijun, Cui Peng, Hu Sheng, et al. Size-frequency distribution of landslides in different landforms on the Loess Plateau of Northern Shaanxi[J]. Earth Science, 2016, 41(2):343-350. ]
[7]	汤国安, 那嘉明, 程维明. 我国区域地貌数字地形分析研究进展[J]. 测绘学报, 2017, 46(10):1570-1591.
	[ Tang Guo’an, Na Jiaming, Cheng Weiming. Progress of digital terrain analysis on regional geomorphology in China[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10):1570-1591. ]
[8]	程维明, 周成虎, 申元村, 等. 中国近40年来地貌学研究的回顾与展望[J]. 地理学报, 2017, 72(5):755-775. doi: 10.11821/dlxb201705001
	[ Cheng Weiming, Zhou Chenghu, Shen Yuancun, et al. Retrospect and perspective of geomorphology researches in China over the past 40 years[J]. Acta Geographica Sinica, 2017, 72(5):755-775. ] doi: 10.11821/dlxb201705001
[9]	王彦文, 秦承志. 地貌形态类型的自动分类方法综述[J]. 地理与地理信息科学, 2017, 33(4):16-21.
	[ Wang Yanwen, Qin Chengzhi. Review of methods for landform automatic classification[J]. Geography and Geo-Information Science, 2017, 33(4):16-21. ]
[10]	Gonzalo-Martin C, Lillo-Saavedra M, Menasalvas E, et al. Local optimal scale in a hierarchical segmentation method for satellite images An OBIA approach for the agricultural landscape[J]. Journal of Intelligent Information Systems, 2016, 46(3):517-529. doi: 10.1007/s10844-015-0365-4
[11]	王晓峰, 延雨, 李月皓, 等. 银川市湿地景观演变及其驱动因素[J]. 干旱区研究, 2021, 38(3):855-866.
	[ Wang Xiaofeng, Yan Yu, Li Yuehao, et al. Wetland landscape evolution and its driving factors in Yinchuan[J]. Arid Zone Research, 2021, 38(3):855-866. ]
[12]	周成虎, 程维明, 钱金凯. 数字地貌遥感解析与制图[M]. 北京: 科学出版社, 2009: 4-9.
	[ Zhou Chenghu, Cheng Weiming, Qian Jinkai. Digital Geomorphological Interpretation and Mapping from Remote Sensing[M]. Beijing: Science Press, 2009: 4-9. ]
[13]	王乐, 周毅, 李阳. 面向子流域单元的典型黄土地貌分类研究[J]. 干旱区研究, 2019, 36(6):1592-1598.
	[ Wang Le, Zhou Yi, Li Yang. Classification of typical loess landforms in subcatchments[J]. Arid Zone Research, 2019, 36(6):1592-1598. ]
[14]	Maria Dekavalla, Demetre Argialas. Evaluation of a spatially adaptive approach for land surface classification from digital elevation models[J]. Taylor & Francis, 2017, 31(10):1-23.
[15]	常直杨, 孙伟红, 王建, 等. 青藏高原及其邻近地区地貌类型划分[J]. 山地学报, 2017, 35(1):1-8.
	[ Chang Zhiyang, Sun Weihong, Wang Jian, et al. Object-oriented method based on classification of geomorphic type in the Tibet Plateau and adjacent regions[J]. Mounta in Research, 2017, 35(1):1-8. ]
[16]	曹泽涛, 方子东, 姚瑾, 等. 基于随机森林的黄土地貌分类研究[J]. 地球信息科学学报, 2020, 22(3):452-463. doi: 10.12082/dqxxkx.2020.190247
	[ Cao Zetao, Fang Zidong, Yao Jin, et al. Loess Landform classification based on random forest[J]. Journal of GeoInformation Science, 2020, 22(3):452-463. ] doi: 10.12082/dqxxkx.2020.190247
[17]	陈春秀, 陈蜀江, 徐世薇, 等. 多特征辅助下的GF-6 WFV影像准噶尔山楂识别研究[J]. 干旱区研究, 2021, 38(2):553-561.
	[ Chen Chunxiu, Chen Shujiang, Xu Shiwei, et al. Crataegus songarica recognition using Gaofen-6 wide-field-view data assisted by multiple features[J]. Arid Zone Research, 2021, 38(2):553-561. ]
[18]	曹伟超, 陶和平, 孔博, 等. 利用最佳地形特征空间进行地貌形态自动识别——以西南地区为例[J]. 武汉大学学报(信息科学版), 2011, 36(11):1376-1380.
	[ Cao Weichao, Tao Heping, Kong Bo, et al. Topographic automatic recognition based on optimal topography feature space: Taking Southwest China as an Example[J]. Geomatics and Information Science of wuhan University, 2011, 36(11):1376-1380. ]
[19]	王丽娜, 丁文广, 许丹阳. 基于DEM的甘肃省地貌形态特征分类[J]. 水土保持通报, 2019, 39(1):264-269.
	[ Wang Lina, Ding Wenguang, Xu Danyang. DEM-Based geomorphological features of Gansu Province[J]. Bulletin of Soild and Water Conservation, 2019, 39(1):264-269. ]
[20]	Jasiewicz J, Stepinski T F. Geomorphons: A pattern recognition approach to classification and mapping of landforms[J]. Geomorphology, 2013, 182:147-156. doi: 10.1016/j.geomorph.2012.11.005
[21]	康鑫, 王彦文, 秦承志, 等. 多分析尺度下综合判别的地形元素分类方法[J]. 地理研究, 2016, 35(9):1637-1646. doi: 10.11821/dlyj201609004
	[ Kang Xin, Wang Yanwen, Qin Chengzhi, et al. A new method of landform element classificationbased on multi-scale morphology[J]. Eographical Research, 2016, 35(9):1637-1646. ] doi: 10.11821/dlyj201609004
[22]	张宗祜. 中国黄土高原地貌类型图[M]. 北京: 地质出版社, 1985.
	[ Zhang Zonghu. Geomorphic Types of Loess Plateau in China[M]. Beijing: Geological Publishing House, 1985. ]
[23]	Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1973,SMC- 3(6):610-621.
[24]	Jasiewicz J, Netzel P, Stepinski T. GeoPAT: A toolbox for pattern-based information retrieval from large geospatial databases[J]. Computers & Geosciences, 2015, 80:62-73. doi: 10.1016/j.cageo.2015.04.002
[25]	Xiong Liyang, Zhu Axing, Zhang Lei, et al. Drainage basin object-based method for regional-scale landform classification: A case study of loess area in China[J]. Physical Geography, 2018, 39(6):1-19. doi: 10.1080/02723646.2017.1354416

类别	UA/%	PA/%	类别	UA/%	PA/%
基岩山地	79.70	70.23	残塬沟谷	74.12	89.47
狭梁沟谷	71.01	76.96	宽塬沟谷	73.05	68.67
宽梁沟谷	72.5	84.41	低丘缓谷	72.28	74.12
平梁沟谷	70.38	86.25	河谷阶地	65.74	76.47
缓梁沟谷	69.56	58.94	盆地	76.53	66.58
缓峁沟谷	73.55	87.72	塬	51.6	45.14
总体精度	75.16%		Kappa系数	0.71

	总体精度/%	Kappa系数
尺度100	42.30	0.36
尺度200	48.91	0.45
尺度400	47.84	0.42
尺度800	48.66	0.43
尺度1200	32.19	0.25
尺度2000	24.98	0.16
本文方法	75.16	0.71

	G1		G2		G3
	PA/%	UA/%	PA/%	UA/%	PA/%	UA/%
100	59.43	58	70.61	75.75	80.16	87.95
200	58.95	65.73	71.7	77.68	75.74	73.09
400	61.88	71.57	77.72	75.81	72.8	75.99
800	65.64	65.84	75.03	81.93	60.71	68.14
1200	77.45	77.19	73.5	79.57	55.81	62.9
2000	79.56	77.86	67.25	68.43	46.25	55.54
MSIC	88.89	75.27	80.33	82.77	88.29	88.39