结合影像分区与尺度估计的耕地提取方法研究

doi:10.12082/dqxxkx.2018.180076

地球信息科学学报 ›› 2018, Vol. 20 ›› Issue (7): 1014-1025.doi: 10.12082/dqxxkx.2018.180076

结合影像分区与尺度估计的耕地提取方法研究

周文(), 明冬萍^*(), 闫鹏飞

中国地质大学（北京）信息工程学院,北京 100083

收稿日期:2018-01-09 修回日期:2018-04-09 出版日期:2018-07-20 发布日期:2018-07-13
通讯作者: 明冬萍 E-mail:zhouwenlc@163.com;mingdp@cugb.edu.cn
作者简介:
作者简介：周文（1993-）,女,硕士生,主要从事高空间分辨率遥感影像信息提取。E-mail: zhouwenlc@163.com
基金资助:
国家自然科学基金项目(41371347、41671369）;二十一世纪空间技术应用股份有限公司2016年开放基金（21AT-2016-07）;中央高校基本科研业务费专项资金

Cultivated Land Extraction Based on Image Region Division and Scale Estimation

ZHOU Wen(), MING Dongping^*(), YAN Pengfei

School of Information Engineering, China University of Geosciences (Beijing), Beijing 100083, China

Received:2018-01-09 Revised:2018-04-09 Online:2018-07-20 Published:2018-07-13
Contact: MING Dongping E-mail:zhouwenlc@163.com;mingdp@cugb.edu.cn
Supported by:
National Natural Science Foundation of China, No.41371347, 41671369;Open Fund of Twenty First Century Areospace Technology Company Limitied. No.21AT-2016-07;Fundamental Research Funds for Central Universities

摘要/Abstract

摘要：

尺度效应的存在使得不同地物的空间及属性尺度存在差异,不存在适合于影像中所有地物的唯一尺度。但通过影像分区,然后针对不同区域设置最优分割参数,可以有效地提高影像整体的分割精度。耕地地块分割中,对分割边界的要求较高,需要保证地块边界清晰连续,鉴于此,本文提出了一种结合影像分区及尺度估计的耕地地块提取方法。本文利用不同地物的温度反演影像来实现区域划分,根据温度数据将影像划分为不同地物类型、作物类型或作物长势不同的多个区域。接下来,分别对不同的区域影像进行分割,由于不同类型地物的固有空间空间尺度不同,所以不同区域影像的最佳分割参数也随之不同。空间统计的平均局部方差法可以用来预估各区域影像的分割参数,与分割参数优选的方法相比,该方法可快速准确定位,且效率较高。因此本文利用该方法进行参数估计,采用边缘约束分水岭分割算法进行耕地地块分割。此外,本文对现有影像分割评价指标进行了改进。实验结果显示,本文提出的耕地地块提取方法可针对影像的不同区域,快速准确地设置分割参数,且与其他分割方法相比,地块边界更清晰连续、多边界问题得到了极大改善。

关键词: 影像区域划分, 分割参数估计, 边缘约束分水岭, 耕地地块分割, 温度反演

Abstract:

Influenced by scale effect, different objects have different spatial and attribute scales, so there is no one set of segmentation parameters can suit all objects in the same image. However, classifying similar objects into same region, and then setting optimal segmentation parameters for different regions can improve the overall segmentation accuracy of the images effectively. In cultivated land extraction, it is critical to have clear and continuous boundary for the segmented plots. This paper presents a cultivated land extraction method combining image region division and segmentation parameters estimation. Temperature inversion was used to divide the image into different regions, of which the types of covered objects are different or the growths of crops are different. Next, regional image segmentation is performed for different regions. Since different object's inherent spatial scales are different, so different regional images' optimal segmentation parameters are also different. The optimal segmentation parameters of the image can be estimated to a certain level by analyzing the characteristics of the image space quantitatively. Compared with other segmentation parameter optimization selection methods, this method can be accurately and quickly positioned, and has a higher efficiency. Next, estimated segmentation parameters were used in the process of cultivated land segmentation by using edge restraint watershed segmentation algorithm. Edge restraint watershed segmentation algorithm uses the canny operator for the post-processing of the watershed segmentation algorithm. The boundary of the canny operator is used to constrain the consolidation process. The experimental result shows that the method proposed in this paper can set segmentation parameters for different regions quickly and accurately. Compared with other segmentation methods, this propose method has a quite clearer and more continuous block boundaries and the boundary fragmentation problem is greatly relieved.

Key words: image region division, segmentation parameter estimation, edge constraint watershed, cultivated land plots segmentation, temperature inversion

周文, 明冬萍, 闫鹏飞. 结合影像分区与尺度估计的耕地提取方法研究[J]. 地球信息科学学报, 2018, 20(7): 1014-1025.DOI:10.12082/dqxxkx.2018.180076

ZHOU Wen,MING Dongping,YAN Pengfei. Cultivated Land Extraction Based on Image Region Division and Scale Estimation[J]. Journal of Geo-information Science, 2018, 20(7): 1014-1025.DOI:10.12082/dqxxkx.2018.180076

图/表 16

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

图14

表1

表2

参考文献 30

[1]	苏红旗,肖克炎.基于GIS的证据权重法矿产预测系(EWM)[J].地质与勘探,1999,35(1):44-46. doi: 10.3969/j.issn.0495-5331.1999.01.012
	[ Su H Q, Xiao K Y.A GIS-base mineral deposits prediction system by using evidence weight modeling[J]. Geology and Prospecting, 1999,35(1):44-46. ] doi: 10.3969/j.issn.0495-5331.1999.01.012
[2]	唐宾. GIS支持下的金属矿产成矿预测简介[J].广西地质,2000,13(1):69-72.
	[ Tang B.Ore-forming Prediction of metallic mineral under GIS[J]. Guangxi Geology, 2000,13(1):69-72. ]
[3]	胡潭高,朱文泉,阳小琼,等.高分辨率遥感图像耕地地块提取方法研究[J].光谱学与光谱分析,2009,29(10):2703-2707.
	[ Hu T G, Zhu W Q, Yang X Q, et al.Farmland parcel extraction based on high resolution remote sensing image].[J]. Spectroscopy & Spectral Analysis, 2009,29(10):2703-2707. ]
[4]	Zhang H, Fritts J E, Goldman S A.Image segmentation evaluation: A survey of unsupervised methods[J]. Computer Vision and Image Understanding, 2008,110(2):260-280. doi: 10.1016/j.cviu.2007.08.003
[5]	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.
	[ Chen C L,Wu G.Evaluation of optimal segmentation scale with object-oriented method in remote sensing[J]. Remote Sensding Technology and Application, 2011,26(1):96-102. ]
[6]	Tong H, Maxwell T, Zhang Y, et al.A supervised and fuzzy-based approach to determine optimal multi-resolution image segmentation parameters[J]. Photogrammetric Engineering and Remote Sensing, 2012,78(10):1029-1044. doi: 10.14358/PERS.78.10.1029
[7]	Liu Y, Bian L, Meng Y, et al.Discrepancy measures for selecting optimal combination of parameter values in object-based image analysis[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012,68(1):144-156. doi: 10.1016/j.isprsjprs.2012.01.007
[8]	于欢,张树清,孔博,等.面向对象遥感影像分类的最优分割尺度选择研究[J].中国图象图形学报,2010,15(2):352-360. doi: 10.11834/jig.20100226
	[ Yu Huan, Zhang S Q, Kong B, et al.Optimal segmentation scale selection for object-oriented remote sensing image classification[J]. Journal of Image and Graphics, 2010,15(2):352-360. ] doi: 10.11834/jig.20100226
[9]	T. Blaschke.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
[10]	Bouziani M, Goita K, He D C.Rule-based classification of a very high resolution image in an urban environment using multispectral segmentation guided by cartographic data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010,48(8):3198-3211. doi: 10.1109/TGRS.2010.2044508
[11]	Inglada J, Michel J.Qualitative spatial reasoning for high-resolution remote sensing image analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009,47(2):599-612. doi: 10.1109/TGRS.2008.2003435
[12]	Wu Z, Yi L, Zhang G.Uncertainty analysis of object location in multi-source remote sensing imagery classification[J]. International Journal of Remote Sensing, 2009,30(20):5473-5487. doi: 10.1080/01431160903130945
[13]	Bhandarkar K J, Suk M.Multiscale image segmentation using a hierarchical self-organizing map[J]. Neurocomputing, 1997,14(3):241-272. doi: 10.1016/S0925-2312(96)00048-3
[14]	Raffaele S G, P Giovanni. Hierarchical texture-based segmentation of multiresolution remote-sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009,47(7):2129-2140. doi: 10.1109/TGRS.2008.2010708
[15]	明冬萍,周文,汪闽.基于谱空间统计特征的高分辨率影像分割尺度估计[J].地球信息科学学报,2016,18(5):622-631. doi: 10.3724/SP.J.1047.2016.00622
	[ Ming D P, Zhou W, Wang M.Scale parameter estimation based on the spatial and spectral statistics in high spatial resolution image segmentation[J]. Journal of Geo-information Science, 2016,18(5):622-63.] doi: 10.3724/SP.J.1047.2016.00622
[16]	林道庆,高智勇,陈心浩.基于改进分水岭算法和Canny算子的医学图像分割[J].中南民族大学学报(自然科学版),2007,26(3):66-70.
	[ Lin D Q, Gao Z Y, Chen X H.Medical images segmentation based on Improved watershed algorithm and canny operator[J]. Journal of South-Central University for Nationalities (Natural Science Edition), 2007,26(3):66-70. ]
[17]	刘荣,侯志强,谭洪波.结合分水岭变换的彩色图像边缘检测算法[J].微计算机信息,2010,26(26):189-191. doi: 10.3969/j.issn.2095-6835.2010.26.079
	[ Liu R, Hou Z Q, Tan H B.Color image edge detection using watershed transform[J]. Microcomputer Information, 2010,26(26):189-191.] doi: 10.3969/j.issn.2095-6835.2010.26.079
[18]	张翊涛,陈洋,王润生.结合自动分区与分层分析的多光谱遥感图像地物分类方法[J].遥感技术与应用,2005(3):332-337.
	[ Zhang Y T, Chen Y, Wang R S. Multispectral image classification based on subRegion and hierarchical theory[J]. Remote Sensing Technology and Application, 2005(3):332-337.]
[19]	竞霞,王锦地,王纪华,等.基于分区和多时相遥感数据的山区植被分类研究[J].遥感技术与应用,2008,23(4):394-397,360.
	[ Jing X, Wang J D, Wang J H, et al.Classifying forest vegetation using sub-region classification based on multi-temporal remote sensing images[J]. Remote Sensing Technology and Application, 2008,23(4):394-397,360. ]
[20]	师庆东,吕光辉,潘晓玲,等.遥感影像中分区分类法及在新疆北部植被分类中的应用[J].干旱区地理,2003(3): 264-268. doi: 10.3321/j.issn:1000-6060.2003.03.013
	[ Shi Q D, Lu G H, Pan X L, et al.Vegetation classification method of divided area and DEM at North Xinjiang[J]. Arid Land Geography, 2003,(3):264-268. ] doi: 10.3321/j.issn:1000-6060.2003.03.013
[21]	于菲菲,曾永年,徐艳艳,等.基于植被分区的多特征遥感智能分类[J].国土资源遥感,2014,26(1):63-70. doi: 10.6046/gtzyyg.2014.01.12
	[ Yu F F, Zeng Y N, Xu Y Y, et al.Intelligent remote sensing classification of multi - character data based on vegetation partition[J]. Remote Sensing for Land and Resources, 2014,26(1):63-70. ] doi: 10.6046/gtzyyg.2014.01.12
[22]	莫源富,周立新.分区分类法——针对山区遥感图象的一种有效的分类方法[J].中国岩溶,2000(4):70-75.
	[ Mo Y F, Zhou L X. Sub-region classification methodUB: An new classification method to remote sensing in mountain areas[J]. Carsologica Sinca, 2000(4):70-75. ]
[23]	李文莉,杨泽元,李瑛,等.基于分区和纹理特征的伊犁河谷遥感影像土地利用分类[J].测绘与空间地理信息,2013(8):68-71.
	[ Li W L, Yang Z Y, Li Y, et al. Ili valley land use classification of SPOT remote sensing image based on partition and texture information[J]. Geomatics ＆ Spatial Information Technology, 2013(8):68-71. ]
[24]	李石华,王金亮,陈姚.独龙江流域TM图像的分区分类方法探讨[J].遥感信息,2006(3):40-43,93.
	[ Li S H, Wang J L, Chen Y.An investigation on subr-egion classification method of TM image in Dulong River Basin[J]. Remote Sensing Information, 2006(3):40-43,93. ]
[25]	丁凤,徐涵秋.基于Landsat TM的3种地表温度反演算法比较分析[J]. 福建师大学报(自然科学版),2008,24(1):91-96.
	[ Ding F, Xu H Q.Comparison of three algorithms for retrieving land surface temperature from Landsat TM thermal infrared band[J]. Journal of Fujian Normal University, 2008,24(1):91-96. ]
[26]	徐涵秋. 新型Landsat8卫星影像的反射率和地表温度反演[J].地球物理学报,2015,58(3):741-747. doi: 10.6038/cjg20150304
	[ Xu H Q.Retrieval of the reflectance and land surface temperature of the newly-launched Landsat 8 satellite[J]. Chinese Journal of Geophysics, 2015,58(3):741-747. ] doi: 10.6038/cjg20150304
[27]	宋挺,段峥,刘军志,等. Landsat 8数据地表温度反演算法对比[J].遥感学报,2015,19(3):451-464. doi: 10.11834/jrs.20154180
	[ Song T, Zheng D, Liu J, et al.Comparison of four algorithms to retrieve land surface temperature using Landsat 8 satellite[J]. Journal of Remote Sensing, 2015,19(3):1993-2002. ] doi: 10.11834/jrs.20154180
[28]	Ming D, Li J, Wang J, 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. doi: 10.1016/j.isprsjprs.2015.04.010
[29]	Wang M, Ye P.Remote sensing image segmentation method based on hard boundary constraint and two-stage combination:, CN 103208121 A[P]. 2013.
[30]	张仙,明冬萍.面向地学应用的遥感影像分割评价[J].测绘学报,2015,44(b12):108-116. doi: 10.11947/j.AGCS.2015.F041
	[ Zhang X, Ming D P.Geo-application oriented evaluations of remote sensing image segmentation[J]. Acta Geodaetica et Cartographica Sinica, 2015,44(b12):108-116. ] doi: 10.11947/j.AGCS.2015.F041

最佳评价结果	边缘约束分水岭分割	多分辨率分割
基元数	1900284	2388
Ui	2029.231	353.086
Vi	-0.042009	0.119191
A(i)	0.021250899	-0.058179414

最佳评价结果	边缘约束分水岭分割	多分辨率分割
基元数	1840250	9120
Ui	927.049	127.009
Vi	-0.048007	0.000182
A(i)	0.024542846	0.003845729

结合影像分区与尺度估计的耕地提取方法研究

Cultivated Land Extraction Based on Image Region Division and Scale Estimation

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 30

相关文章 4

Metrics

本文评价

推荐阅读 0

[1]	陈冰倩, 张友水, 程璟媛, 赵雪. 福州市地表温度热点及时空变化分析[J]. 地球信息科学学报, 2019, 21(5): 710-719.
[2]	高文升, 张雨泽, 房世峰, 杨锋杰, 吴骅. 基于Landsat-8 TIRS的大气参数快速估算方法[J]. 地球信息科学学报, 2017, 19(1): 110-116.
[3]	夏叡, 李云梅, 王桥, 王彦飞, 金鑫, 徐恩惠. 无锡市城市扩张与热岛响应的遥感分析[J]. 地球信息科学学报, 2009, 11(5): 677-683.
[4]	丁凤, 徐涵秋. TM热波段图像的地表温度反演算法与实验分析[J]. 地球信息科学学报, 2006, 8(3): 125-130,135.