一种利用结构特征的高分辨率遥感影像种植园自动提取方法

doi:10.11947/j.AGCS.2016.20150511

测绘学报 ›› 2016, Vol. 45 ›› Issue (9): 1065-1072.doi: 10.11947/j.AGCS.2016.20150511

一种利用结构特征的高分辨率遥感影像种植园自动提取方法

闫利, 江维薇

武汉大学测绘学院, 湖北武汉 430079

收稿日期:2015-10-16 修回日期:2016-06-12 出版日期:2016-09-20 发布日期:2016-09-29
通讯作者: 江维薇 E-mail:626834986@qq.com
作者简介:闫利(1966-),男,博士,教授,研究方向为摄影测量、遥感图像处理和三维激光成像扫描测量技术的研究.E-mail:lyan@sgg.whu.edu.cn
基金资助:
国家科技支撑计划（2012BAJ23B03）

A Structure Feature for Automatic Extraction of Plantation from High-resolution Remote Sensing Imagery

YAN Li, JIANG Weiwei

School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China

Received:2015-10-16 Revised:2016-06-12 Online:2016-09-20 Published:2016-09-29
Supported by:
The National Key Technology Research and Development Program of the Ministry of Science and Technology of China (No.2012BAJ23B03)

摘要/Abstract

摘要： 卫星遥感在土地监测中发挥了重要作用，而数据处理技术应具有良好的适用性和较高的精度水平以满足应用需求。针对目前种植园提取算法适用性较差、数据依赖性高、自动化程度低、算法复杂及特征冗余等问题，本文提出了一种新型种植园结构特征，多尺度多方向结构指数，通过对其进行阈值化并结合形态学处理实现了种植园的自动提取。对多种植模式、背景植被化程度和结构复杂度各不相同的全色和多光谱种植园影像分别设计了3组试验，结果证明，与传统方法相比，本文方法适用性更强，对多方向、多尺度、基元变形、种植线变形、种植模式规律性差、背景高度植被化等诸多复杂的种植园等均能进行有效提取，整体精度达到90%以上。此外，试验结果中，全色影像与多光谱影像精度相当，表明本文方法具有较低的光谱依赖性，因此在数据选择和应用上具有更大的灵活性。

关键词: 高分辨率, 多尺度多方向, 结构特征, 种植园, 自动提取

Abstract: Satellite remote sensing is an invaluable tool to manage land resources. However, data analysis procedures should satisfy the good adaptability, wide application prospects and high accuracy levels demanded by users. This study presented a novel multi-scale and multi-direction structure index (MMI) to describe the structure feature of plantation caused by cultivation. Plantation are extracted by performing a threshold on the MMI feature map, and combined with morphological operators to refine the extraction results. We designed three groups of experiments to test our method, each group used panchromatic and multispectral imagery respectively with various cultivation mode, different vegetated background and structure complexity. The results show our method is much more adaptive on plantation extraction than traditional methods. It is efficient for various complex plantations, e.g. multi-direction, multi-scale, highly vegetated backgrounds, low regularity of planting mode with deformation of textons and planting lines, the accuracy results exceed 90%. And panchromatic images achieve accuracies as high as multispectral images, which indicate our method has low dependence on spectrum, thus it is more flexible for data selection and application.

Key words: high resolution, multi-scale and multi-direction, structure feature, plantation, automatic extraction

中图分类号:

P237

闫利, 江维薇. 一种利用结构特征的高分辨率遥感影像种植园自动提取方法[J]. 测绘学报, 2016, 45(9): 1065-1072.

YAN Li, JIANG Weiwei. A Structure Feature for Automatic Extraction of Plantation from High-resolution Remote Sensing Imagery[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(9): 1065-1072.

参考文献

[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] 杨钊霞, 邹峥嵘, 陶超, 等. 空-谱信息与稀疏表示相结合的高光谱遥感影像分类[J]. 测绘学报, 2015, 44(7): 775-781. DOI: 10.11947/j.AGCS.2015.20140207. YANG Zhaoxia, ZOU Zhengrong, TAO Chao, et al. Hyperspectral Image Classification Based on the Combination of Spatial-spectral Feature and Sparse Representation[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(7): 775-781. DOI: 10.11947/j.AGCS.2015.20140207.
[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] 王馨爽, 陈尔学, 李增元, 等. 多时相双极化合成孔径雷达干涉测量土地覆盖分类方法[J]. 测绘学报, 2015, 44(5): 533-540. DOI: 10.11947/j.AGCS.2015.20130244. WANG Xinshuang, CHEN Erxue, LI Zengyuan, et al. Multi-temporal and Dual-polarization Interferometric SAR for Land Cover Type Classification[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(5): 533-540. DOI: 10.11947/j.AGCS.2015.20130244.
[5] 赵庚星, 余松烈. 冬小麦遥感估产研究进展[J]. 山东农业大学学报(自然科学版), 2001, 32(1): 107-111. ZHAO Gengxing, YU Songlie. Advance of Winter Wheat Yield Estimation by Remote Sensing[J]. Journal of Shandong Agricultural University (Natural Science), 2001, 32(1): 107-111.
[6] YU Qian, GONG Peng, CLINTON N, et al. Object-based Detailed Vegetation Classification with Airborne High Spatial Resolution Remote Sensing Imagery[J]. Photogrammetric Engineering & Remote Sensing, 2006, 72(7): 799-811.
[7] CHETVERIKOV D, HARALICK R M. Texture Anisotropy, Symmetry, Regularity: Recovering Structure and Orientation from Interaction Maps[C]//Proceedings of the 1995 6th British Conference on Machine Vision. Surrey, UK: BMVA Press, 1995, 1: 57-66.
[8] STAROVOITOV V V, JEONG S Y, PARK R H. Texture Periodicity Detection: Features, Properties, and Comparisons[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 1998, 28(6): 839-849.
[9] LIN H C, WANG Lingling, YANG S N. Extracting Periodicity of a Regular Texture Based on Autocorrelation Functions[J]. Pattern Recognition Letters, 1997, 18(5): 433-443.
[10] CHARALAMPIDIS D. Texture Synthesis: Textons Revisited[J]. IEEE Transactions on Image Processing, 2006, 15(3): 777-787.
[11] LÓPEZ J A, IZQUIERDO VERDIGUIER E, CHOVA L G, et al. Land Cover Classification of VHR Airborne Images for Citrus Grove Identification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(1): 115-123.
[12] 孙伟伟. 基于流形学习的高光谱影像降维理论与方法研究[J]. 测绘学报, 2014, 43(4): 439. DOI: 10.13485/J.CNKI.11-2089.2014.0066. SUN Weiwei. Theory and Methods of Dimensionality Reduction Using Manifold Learning for Hyperspectral Imagery[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(4): 439. DOI: 10.13485/J.CNKI.11-2089.2014.0066.
[13] 张喜旺, 秦耀辰, 秦奋. 综合季相节律和特征光谱的冬小麦种植面积遥感估算[J]. 农业工程学报, 2013, 29(8): 154-163. ZHANG Xiwang, QIN Yaochen, QIN Fen. Remote Sensing Estimation of Planting Area for Winter Wheat by Integrating Seasonal Rhythms and Spectral Characteristics[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(8): 154-163.
[14] DAI Xiaolong, KHORRAM S. The Effects of Image Misregistration on the Accuracy of Remotely Sensed Change Detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(5): 1566-1577.
[15] 曹森, 潘耀忠, 张锦水, 等. 土地覆盖图斑多时相遥感影像自动配准[J]. 测绘学报, 2014, 43(3): 290-297. DOI: 10.13485/j.cnki.11-2089.2014.0042. CAO Sen, PAN Yaozhong, ZHANG Jinshui, et al. Land Cover Patches Based Automatic Multi-temporal Remote Sensing Images Registration[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(3): 290-297. DOI: 10.13485/j.cnki.11-2089.2014.0042.
[16] MARR D, HILDRETH E. Theory of Edge Detection[J]. Proceedings of the Royal Society B: Biological Sciences, 1980, 207(1167): 187-217.
[17] YALNIZ I Z, AKSOY S. Unsupervised Detection and Localization of Structural Textures Using Projection Profiles[J]. Pattern Recognition, 2010, 43(10): 3324-3337.
[18] HAN Junwei, MCKENNA S J, WANG Ruixuan, Regular Texture Analysis as Statistical Model Selection[C]//Proceedings of the 10th European Conference on Computer Vision. Berlin: Springer, 2008: 242-255.
[19] LIU Yanxi, COLLINS R T, TSIN Y. A Computational Model for Periodic Pattern Perception Based on Frieze and Wallpaper Groups[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(3): 354-371.
[20] RUIZ L A, RECIO J A, HERMOSILLA T. Methods for Automatic Extraction of Regularity Patterns and Its Application to Object-oriented Image Classification[C]//Proceedings of Photogrammetric Image Analysis. Munich: [s.n.], 2007: 117-121.

一种利用结构特征的高分辨率遥感影像种植园自动提取方法

A Structure Feature for Automatic Extraction of Plantation from High-resolution Remote Sensing Imagery

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	何直蒙, 丁海勇, 安炳琪. 高分辨率遥感影像建筑物提取的空洞卷积E-Unet算法[J]. 测绘学报, 2022, 51(3): 457-467.
[2]	张玉鑫, 颜青松, 邓非. 高分辨率遥感影像建筑物提取多路径RSU网络法[J]. 测绘学报, 2022, 51(1): 135-144.
[3]	叶沅鑫, 孙苗苗, 王蒙蒙, 谭鑫. 结合邻域信息和结构特征的遥感影像变化检测[J]. 测绘学报, 2021, 50(10): 1349-1357.
[4]	张涛, 丁乐乐, 史芙蓉. 高分辨率遥感影像城中村提取的景观语义指数方法[J]. 测绘学报, 2021, 50(1): 97-104.
[5]	戴激光, 朱婷婷, 张依蕾, 王杨, 方鑫鑫. 高分辨率光学卫星影像线段融合方法[J]. 测绘学报, 2020, 49(4): 489-498.
[6]	于莉楠, 宁晓刚, 王浩, 刘纪平. 拓扑插值与光谱特征结合的复杂城区边界提取[J]. 测绘学报, 2019, 48(8): 1004-1013.
[7]	左宗成, 张文, 张东映. 融合可变形卷积与条件随机场的遥感影像语义分割方法[J]. 测绘学报, 2019, 48(6): 718-726.
[8]	董志鹏, 王密, 李德仁, 王艳丽, 张致齐. 遥感影像目标的尺度特征卷积神经网络识别法[J]. 测绘学报, 2019, 48(10): 1285-1295.
[9]	范荣双, 陈洋, 徐启恒, 王竞雪. 基于深度学习的高分辨率遥感影像建筑物提取方法[J]. 测绘学报, 2019, 48(1): 34-41.
[10]	董志鹏, 王密, 李德仁, 王艳丽, 张致齐. 利用对象光谱与纹理实现高分辨率遥感影像云检测方法[J]. 测绘学报, 2018, 47(7): 996-1006.
[11]	Yun ZHANG. 智能摄影测量和图像处理在高分辨率光学遥感影像处理中的应用——CRC-AGIP实验室的案例[J]. 测绘学报, 2018, 47(6): 722-729.
[12]	郑卓, 方芳, 刘袁缘, 龚希, 郭明强, 罗忠文. 高分辨率遥感影像场景的多尺度神经网络分类法[J]. 测绘学报, 2018, 47(5): 620-630.
[13]	李成名, 殷勇, 吴伟, 武鹏达. Stroke特征约束的树状河系层次关系构建及简化方法[J]. 测绘学报, 2018, 47(4): 537-546.
[14]	黄博华, 钟巍, 翟仁健, 周青. 城市道路网匹配的层次化面域剖分模型[J]. 测绘学报, 2018, 47(11): 1526-1536.
[15]	杨幸彬, 吕京国, 江珊, 张丹璐. 高分辨率遥感影像DSM的改进半全局匹配生成方法[J]. 测绘学报, 2018, 47(10): 1372-1384.