Please wait a minute...
img

官方微信

遥感技术与应用  2020, Vol. 35 Issue (4): 873-881    DOI: 10.11873/j.issn.1004-0323.2020.4.0873
甘肃遥感学会专栏     
面向对象的天然绿洲与人工绿洲区分
李汝嫣1(),颉耀文1,2(),姜转芳1
1.兰州大学资源环境学院,甘肃 兰州 730000
2.兰州大学西部环境教育部重点实验室,甘肃 兰州 730000
Object-oriented Natural and Artificial Oasis Distinguishing in Landsat Imagery: Taking Minqin Oasis as an Example
Ruyan Li1(),Yaowen Xie1,2(),Zhuanfang Jiang1
1.The collage of Earth and Environment, Lanzhou University, Lanzhou 730000, China
2.Key Laboratory of Western China's Environmental System (Ministry of Education), Lanzhou University, Lanzhou 730000, China
 全文: PDF(4550 KB)   HTML
摘要:

以地处河西走廊东端、石羊河下游的民勤县湖区绿洲为例,以Landsat 8 OLI影像为数据源,从天然绿洲和人工绿洲的基本概念出发,在影像数据预处理、多尺度分割的基础上,综合考虑光谱、纹理、形状、上下文等信息,引入NDVI、最大化差异、紧致度、形状指数和空间邻接关系等多个特征,构建规则集进行天然绿洲和人工绿洲的区分,并将区分结果与基于最大似然法监督分类的绿洲区分结果进行比较分析。结果表明:使用面向对象的影像分析方法区分天然绿洲和人工绿洲的总体精度达到了91.75%,Kappa系数为0.65;较之面向像元的最大似然法监督分类结果,总体精度提高了10.40%,Kappa系数提高了0.13,其中人工绿洲条件Kappa系数提高了0.19,天然绿洲条件Kappa系数提高了0.30。面向对象的影像分析方法能够在一定程度上克服单一光谱特征分类方法的局限性,避免“异物同谱”和“同物异谱”现象带来的混淆,提高天然绿洲和人工绿洲区分的精度。

关键词: NDVI最大化差异紧致度形状指数规则集绿洲区分    
Abstract:

Taking Minqin Oasis in the downstream area of the Shiyang River Basin which is located in the east of Hexi Corridor as an example, the Landsat 8 OLI image was chosen as the data source. Under the consideration of the basic concept of the artificial oasis and natural oasis in this paper, combining with the information of the spectrum, texture, shape and context basing on the image data preprocessing and multi-scale segmentation, we introduce a series of indexes such as NDVI、maximum difference, compactness, shape index, the space adjacency relation and so on to construct a rule set for distinguish between natural oasis and artificial oasis. The obtained results were further compared with the results based on the maximum likelihood method. As a result, the total accuracy of using the object-oriented image analysis method to distinguishing between natural oasis and artificial oasis is 91.75%, and the Kappa coefficient is 0.65 by using the rule set established in this paper. Compared with the results based on the maximum likelihood method, the overall accuracy is improved by 10.40% and the Kappa coefficient is 0.13. The Kappa coefficient of the artificial oasis is increased by 0.19, and the Kappa coefficient of the natural oasis condition is increased by 0.30. The results showed that the object-oriented image analysis method can overcome the limitations of the classification method that only using spectral feature to a certain extent, avoid the confusion caused by the phenomenon of “same object with different spectrums” and “same spectrum with different objects”, and increase the accuracy of distinguishing between the artificial oasis and natural oasis.

Key words: NDVI    Maximum difference    Compactness    Shape index    Rule set    Oasis distinguish
收稿日期: 2019-09-12 出版日期: 2020-09-15
ZTFLH:  K90-06  
基金资助: 兰州大学中央高校基本科研业务费专项资金项目(lzujbky?2017?it105);国家自然科学基金项目(41471163)
通讯作者: 颉耀文     E-mail: 1753129463@qq.com;xieyw@lzu.edu.cn
作者简介: 李汝嫣(1993-),女,江苏连云港人,硕士,主要从事地图学与地理信息系统研究。E?mail:1753129463@qq.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
李汝嫣
颉耀文
姜转芳

引用本文:

李汝嫣,颉耀文,姜转芳. 面向对象的天然绿洲与人工绿洲区分[J]. 遥感技术与应用, 2020, 35(4): 873-881.

Ruyan Li,Yaowen Xie,Zhuanfang Jiang. Object-oriented Natural and Artificial Oasis Distinguishing in Landsat Imagery: Taking Minqin Oasis as an Example. Remote Sensing Technology and Application, 2020, 35(4): 873-881.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2020.4.0873        http://www.rsta.ac.cn/CN/Y2020/V35/I4/873

图1  研究区地理位置(Landsat8-OLI 标准假彩色合成)
图2  技术路线图
人工草地天然草地人工植被建设用地稀疏灌丛荒漠
人工草地1.3212.0001.8241.2231.394
天然草地1.9821.7951.7391.777
人工植被1.9992.0002.000
建设用地1.9091.847
稀疏灌丛0.783
荒漠
表1  样本可分性表格(J-M距离)
编号尺度形状紧密度平滑度
I150.30.70.3
II250.30.70.3
III250.70.70.3
IV250.70.30.7
表2  多尺度分割算法的分割参数设置
图3  不同分割参数设置下的多尺度分割结果
图4  编号Ⅱ分割结果
指标计算公式参数说明
NDVINDVI=(NIR-Red)/(NIR+Red)NIR:近红外波段DN值,Red:红光波段DN值
Max diffMax?diff=MaxcLˉ-Min(cLˉ)/bMax(cLˉ)Min(cLˉ)分布为L通道该影像对象层均值的最大值和最小值,b是该影像对象的亮度值
CompactnessCompactness=l/ml为影像对象的边界长度,m为影像对象的像元数目;紧致度越小,表示区域边界形状越不平整
Shape indexShape?index=e/4Ae和A分别为影像对象的边界长度与面积;影像对象越不规则,形状指数越大
表3  各指标计算公式及其参数说明
图5  绿洲区分决策树
图6  基于规则集的绿洲区分结果
图7  最大似然法监督分类结果
图8  地理国情普查重分类结果
面向对象面向像元(最大似然法)
非绿洲人工绿洲天然绿洲非绿洲人工绿洲天然绿洲
生产者精度0.654 50.891 70.424 00.640 30.782 80.175 3
用户精度0.708 10.938 40.223 50.654 30.879 00.055 3
条件Kappa系数0.600.550.360.540.360.06
总体精度0.831 20.723 2
总体Kappa系数0.540.41
表4  绿洲区分结果精度评价
1 Hu Yinqiao, Zuo Hongchao. Forming Mechanism of Oasis Environment and Building Countermeasure of Ecological Environment in Arid Area[J]. Plateau Meteorology,2003,22(6):537-544.
1 胡隐樵,左洪超. 绿洲环境形成机制和干旱区生态环境建设对策[J]. 高原气象,2003,22(6):537-544.
2 Wang Yajun, Minire. Review of Oasis Research in China[J]. Journal of Arid Land Resources and Environment,2000,14(3):92-96.
2 王亚俊,米尼热. 中国绿洲研究回顾[J]. 干旱区资源与环境,2000,14(3):92-96.
3 Liu Chunyu, Zhao Jun, Liu Yingying,et al. Spatial-temporal Change of Landscape Pattern and LUCC in Ejin Natural Oasis over 25 Years[J].Journal of Arid Land Resources and Environment,2011,25(9):32-38.
3 刘春雨,赵军,刘英英,等. 25年来额济纳天然绿洲LUCC及景观格局时空变化[J]. 干旱区资源与环境,2011,25(9):32-38.
4 Wang Yajun, Zeng Fanjiang. Analysis and Progress of Oasis Research in China[J]. Arid Zone Resaerch,2010,27(4):501-506.
4 王亚俊,曾凡江. 中国绿洲研究文献分析及研究进展[J]. 干旱区研究,2010,27(4):501-506.
5 Jia Baoquan, Longjun Ci, Han Delin,et al. Review and Problem Analysis of Oasis Research in Arid Region[J]. Advance in Earth Sciences,2000,15(4):381-388.
5 贾宝全,慈龙骏,韩德林,等. 干旱区绿洲研究回顾与问题分析[J]. 地球科学进展,2000,15(4):381-388.
6 Sun Tao, Wang Jihe, Liu Hujun, et al. The Present Situation of Ecological Environment and Its Recovery Strategy on the Minqin Oasis[J]. Chinese Agricultural Science Bulletin,2010,26(7):245-251.
6 孙涛,王继和,刘虎俊,等. 民勤绿洲生态环境现状及恢复对策[J]. 中国农学通报,2010,26(7):245-251.
7 Bai Jie, Wang Xuegong, Zhao Chengzhang. Evaluation on the Coordinated Development Ability of Eco-economic System in Hexi Corridor Oases[J]. Arid Land Geography,2010,33(1):130-135.
7 白洁,王学恭,赵成章. 河西走廊绿洲生态经济系统协调发展能力评价[J]. 干旱区地理,2010,33(1):130-135.
8 Xie Qiang, Fang Chuanglin. Analysis of the State of Affairs on the Regional Ecological Reconstruction and Economic and Social Sustainable Development in Hexi Corridor[J]. Arid Land Geography,2001,24(1):74-79.
8 谢强,方创琳. 河西走廊生态重建与经济可持续发展情势分析[J]. 干旱区地理,2001,24(1):74-79.
9 Liu Xinping, Han Tongkui. An Analysis on the Causes of Environmental Issues of Oasis Ecology in Xinjiang[J]. Journal of Arid Land Resources and Environment,2005,19(1):22-28.
9 刘新平,韩桐魁. 新疆绿洲生态环境问题分析[J]. 干旱区资源与环境,2005,19(1):22-28.
10 Wei huaidong, Zhou Lanping, Xu Xianying, et al. Monitoring of Dynamic Change of Land Desertification in the Minqin Oasis during the Period of 2003~2008[J]. Arid Zone Resaerch,2011,28(4):572-579.
10 魏怀东,周兰萍,徐先英,等. 2003~2008年甘肃民勤绿洲土地荒漠化动态监测[J]. 干旱区研究,2011,28(4):572-579.
11 Liu Xiujuan. Formation Mechanism and Classification System of Oasis[J]. Environmental Protection of Xinjiang,1995,17(1):1-6.
11 刘秀娟. 绿洲的形成机制和分类体系[J]. 新疆环境保护,1995,17(1):1-6.
12 Zhao Hong, Xie Yaowen. Combining Texture and Vegetation Index to Distinguish between Natural and Artificial Oases——Taking Jinta Oasis as an Example[J]. Journal of Ningxia University(Natural Science Edition),2013,34(1):88-92.
12 赵虹,颉耀文. 结合植被指数与纹理区分天然绿洲与人工绿洲——以甘肃省酒泉市金塔绿洲为例[J]. 宁夏大学学报(自然科学版),2013,34(1):88-92.
13 Li Jianlin, Wang Yan, Guo Qiaoling,et al. Fractal Study of the Distribution Proportion of the Oasis System in China[J]. Acta Prataculture Sinica,2010,19(3):63-69.
13 李建林,王燕,郭巧玲,等. 绿洲分布比例的分形研究[J]. 草业学报,2010,19(3):63-69.
14 Wang L, Sousa W P, Gong P. Integration of Object-based and Pixel-based Classification for Mapping Mangroves with IKONOS Imagery[J]. International Journal of Remote Sensing,2004,25(24):5655-5668. doi: 10.1080/01431160233 1291215.
doi: 10.1080/01431160233 1291215
15 Hussain M, Chen D M, Chen A, et al. Change Detection from Remotely Sensed Images: from Pixel-based to Object-based Approaches[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2013,80:91-106.doi:10.1016/j.isprsjprs. 2013.03.006.
doi: 10.1016/j.isprsjprs. 2013.03.006
16 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,2011,115:1301-1316. doi:10.1016/j.rse. 2011.01.009.
doi: 10.1016/j.rse. 2011.01.009
17 Myint S W, Gober P, Brazel A, et al. Per-pixel vs. Object-based Classification of Urban Land Cover Extraction Using High Spatial Resolution Imagery[J]. Remote Sensing of Environment,2011,115:1145-1161.doi:10.1016/j.rse.2010. 12.017.
doi: 10.1016/j.rse.2010. 12.017
18 Blaschke T. Object based Image Analysis for Remote Sensing[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2010,65(1):2-16. doi:10.1016/j.isprsjprs.2009.06.004.
doi: 10.1016/j.isprsjprs.2009.06.004
19 Yang Zhaohui, Bai Junnwu, Chen Zhihui, et al. Object-based Wetland Decision Tree Classification Method Using Sentinel-2A Image[J]. Journal of Geomatics Science and Technology,2019,36(3):262-268.
19 杨朝辉,白俊武,陈志辉,等.利用Sentinel-2A影像的面向对象特征湿地决策树分类方法[J].测绘科学技术学报,2019,36(3):262-268.
20 Yao Bo, Zhang Huaiqing, Liu Yang, et al. Remote Sensing Classification of Wetlands based on Object-oriented and CART Decision Tree Method[J]. Forest Research,2019,32(5):91-98.
20 姚博,张怀清,刘洋,等.面向对象CART决策树方法的湿地遥感分类[J].林业科学研究,2019,32(5):91-98.
21 Jiang Decai, Li Wenji, Li Jingmin, et al. Extraction of the Forest Fire Region based on the Span of ALOS PALSAR by Object-oriented Analysis[J]. Remote Sensing for Land and Resources,2019,31(4):47-52.
21 姜德才,李文吉,李敬敏,等.ALOS PALSAR散射总功率的面向对象林火区提取[J].国土资源遥感,2019,31(4):47-52.
22 Chen Yanli, Mo Weihua, Mo Jianfei, et al. Object-oriented Classification for the Extraction of Rice Planting Area in South[J]. Remote Sensing Technology and Application,2011,26(2):163-168.
22 陈燕丽,莫伟华,莫建飞,等.基于面向对象分类的南方水稻种植面积提取方法[J].遥感技术与应用,2011,26(2):163-168.
23 Hao Rui,Li Zhaofu,Zhang Shuyu,et al.Integrating UAV and Object-based Image Analysis for Rural Residential Environment Information Extraction[J].Remote Sensing Technology and Application,2020,35(3):576-586.
23 郝睿,李兆富,张舒昱,等.整合无人机和面向对象的农村居住环境信息提取[J].遥感技术与应用,2020,35(3):576-586.
24 Song Minghui.Object-oriented Urban Land Classification with GF-2 Remote Sensing Image[J].Remote Sensing Technology and Application, 2020,34(3):547-553.
24 宋明辉.基于高分二号数据的面向对象城市土地利用分类研究[J].遥感技术与应用,2019,34(3):547-552, 629.
25 Hu Rongming, Wei Man, Yang Chengbin, et al. Taking SPOT5 Remote Sensing Data for Example to Compare Pixel-based and Object-oriented Classification[J]. Remote Sensing Technology and Application,2012,27(3):366-371.
25 胡荣明,魏曼,杨成斌,等.以SPOT5遥感数据为例比较基于像素与面向对象的分类方法[J].遥感技术与应用,2012,27(3):366-371.
26 Peng Haitao, Ke Changqing. Study on Object-oriented Remote Sensing Image Classification based on Multi-levels Segmentation[J]. Remote Sensing Technology and Application,2010,25(1):149-154.
26 彭海涛,柯长青.基于多层分割的面向对象遥感影像分类方法研究[J].遥感技术与应用,2010,25(1):149-154.
27 Yu Qian, Gong Peng, Nick Clinton, et al. Object-based Detailed Vegetation Classification with Airborne High Spatial Resolution Remote Sensing Imagery[J]. Photogrammetric Engineering and Remote Sensing,2006,72(7):799-811. doi:10.14358/PERS.72.7.799.
doi: 10.14358/PERS.72.7.799
28 Ma L, Li M C, Ma X X, et al. A Review of Supervised Object-based Land-cover Image Classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2017,130:277-293. doi:10.1016/j.isprsjprs.2017.06.001.
doi: 10.1016/j.isprsjprs.2017.06.001
29 Xie Yaowen, Yuan chunxia, Shi Jianyao. Dynamic Analysis of Landscape Changes in the Lake-area of Minqin, Gansu, in the past 15 Years[J]. Journal of Lanzhou University(Natural Sciences Edition),2008,44(1):11-16.
29 颉耀文,袁春霞,史建尧. 近15年甘肃民勤湖区景观格局动态变化分析[J]. 兰州大学学报(自然科学版),2008,44(1):11-16.
30 Zhang Kai, Feng Qi, Yongqing Lü, et al. Study on Spatial Heterogeneity of Soil Water Contents in Oasis-desert Belt of Minqin[J]. Journal of Desert Research,2011,31(5):1149-1155.
30 张凯,冯起,吕永清,等. 民勤绿洲荒漠带土壤水分的空间分异研究[J]. 中国沙漠,2011,31(5):1149-1155.
31 Tang Wanping. Never Let Minqin Become the Second Lop Nur——An Investigation on Ecological Environment Governance and Poverty Alleviation and Development in Minqin Lake District, Gansu[J]. China Today Forum,2005(9):29-34.唐万平. 决不能让民勤成为第二个罗布泊——关于甘肃民勤湖区生态环境治理和扶贫开发的调查[J]. 今日中国论坛,2005(9):29-34.
32 Ma Na, Hu Yunfeng, Zhuang Dafang, et al. Determination on the Optimum Band Combination of HJ-1A Hyperspectral Data in the Case Region of Dongguan based on Optimum Index Factor and J-M Distance[J]. Remote Sensing Technology and Application,2010,25(3):358-365.
32 马娜,胡云锋,庄大方,等. 基于最佳波段指数和J-M距离可分性的高光谱数据最佳波段组合选取研究——以环境小卫星高光谱数据在东莞市的应用为例[J]. 遥感技术与应用,2010,25(3):358-365.
33 Qi La, Liu Liangyun, Zhao Chunjiang, et al. Selection of Optimum Periods for Extracting Winter Wheat based on Multi-temporal Remote Sensing Images[J]. Remote Sensing Technology and Application,2008,23(2):154-160.
33 齐腊,刘良云,赵春江,等. 基于遥感影像时间序列的冬小麦种植监测最佳时相选择研究[J]. 遥感技术与应用,2008,23(2):154-160.
34 Blaschke T, Hay G J, Kelly M, et al. Geographic Object-based Image Analysis - Towards a New Paradigm[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014,87:180-191. doi:10.1016/j.isprsjprs.2013.09.014.
doi: 10.1016/j.isprsjprs.2013.09.014
35 Chen Chunlei, Wu Gang. Evaluation of Optimal Segmentation Scale with Object-oriented Method in Remote Sensing[J]. Remote Sensing Technology and Application,2011,26(1):96-102.
35 陈春雷,武刚. 面向对象的遥感影像最优分割尺度评价[J]. 遥感技术与应用,2011,26(1):96-102.
[1] 焦雪敏,张赫林,徐富宝,王岩,彭代亮,李存军,徐希燕,范海生,黄运新. 青藏高原1982~2015年FPAR时空变化分析[J]. 遥感技术与应用, 2020, 35(4): 950-961.
[2] 岳昂,曾庆伟,王怀警. 于桥水库蓝藻水华遥感长时序监测研究[J]. 遥感技术与应用, 2020, 35(3): 694-701.
[3] 纪甫江,蒙继华,方慧婷. 基于CASA-WOFOST耦合模型的大豆单产遥感估算研究[J]. 遥感技术与应用, 2020, 35(2): 406-415.
[4] 李嘉玲, 董东林, 林刚, 汪箫悦, 王健, 吴朝阳. 基于NDVI数据的江苏省植被物候变化及其影响因子分析[J]. 遥感技术与应用, 2019, 34(2): 367-376.
[5] 茹皮亚·西拉尔, 杨辽. 新疆棉花物候时空变化遥感监测及气温影响分析[J]. 遥感技术与应用, 2018, 33(5): 923-931.
[6] 张滔,唐宏. 基于Google Earth Engine的京津冀2001~2015年植被覆盖变化与城镇扩张研究[J]. 遥感技术与应用, 2018, 33(4): 593-599.
[7] 施佩荣,陈永富,刘华,吴云华. 基于分割评价函数的多尺度分割参数的选择[J]. 遥感技术与应用, 2018, 33(4): 628-637.
[8] 汪航,师茁. 基于MODIS时间序列数据的春尺蠖虫害遥感监测方法研究—以新疆巴楚胡杨为例[J]. 遥感技术与应用, 2018, 33(4): 686-695.
[9] 苗茜,王昭生,王荣,黄玫,孙佳丽. 基于NDVI数据评估O3污染对华北地区夏季植被生长的影响[J]. 遥感技术与应用, 2018, 33(4): 696-702.
[10] 周玉科,刘建文. 基于MODIS NDVI和多方法的青藏高原植被物候时空特征分析[J]. 遥感技术与应用, 2018, 33(3): 486-498.
[11] 王佳鹏,施润和,张超,刘浦东,曾毓燕. 基于光谱分析的长江口湿地互花米草叶片叶绿素含量反演研究[J]. 遥感技术与应用, 2017, 32(6): 1056-1063.
[12] 杨涛,黄法融,李倩,白磊,李兰海. 新疆北部植被生长季NDVI时空变化及其与冬季降雪的关系[J]. 遥感技术与应用, 2017, 32(6): 1132-1140.
[13] 孙晓,吴孟泉,何福红,张安定,赵德恒,李勃 . 2015年黄海海域浒苔时空分布及台风“灿鸿”影响研究[J]. 遥感技术与应用, 2017, 32(5): 921-930.
[14] 林齐根,邹振华,祝瑛琦,王瑛. 基于光谱、空间和形态特征的面向对象滑坡识别[J]. 遥感技术与应用, 2017, 32(5): 931-937.
[15] 周金霖,马明国,肖青,闻建光. 西南地区植被覆盖动态及其与气候因子的关系[J]. 遥感技术与应用, 2017, 32(5): 966-972.