帮助 关于我们

返回检索结果

基于谱空间统计特征的高分辨率影像分割尺度估计
Scale Parameter Estimation Based on the Spatial and Spectral Statistics in High Spatial Resolution Image Segmentation

查看参考文献20篇

明冬萍 1 *   周文 1   汪闽 2  
文摘 多尺度分割是面向对象遥感影像分析的关键性基础步骤,影像分割过程中尺度参数的选择直接关系到面向对象影像分析的质量和精度。本文首先从理论层面将遥感影像分割的尺度界定为基于统计的原始影像全局或局部特征的一种定量化估计,并在算法层面上将多尺度分割算法的尺度参数概括为空间尺度分割参数(类别或斑块间的空间距离)、属性尺度分割参数(类别或斑块间的属性距离)和合并阈值参数(斑块大小或斑块像元数目);接着,提出了基于谱空间统计的高分辨率影像分割尺度估计方法;最后,以均值漂移多尺度分割算法为例,采用高空间分辨率的Ikonos、Quickbird和航空影像数据,对本文提出的基于谱空间统计的高分辨率影像分割尺度估计方法进行了验证。结果表明,该方法在一定程度上不仅避免了高分辨率遥感影像分割尺度参数选择的主观性和盲目性,还提高了面向对象影像分析的自动化程度,具有可行性和有效性。
其他语种文摘 Object-Based Image Analysis (OBIA) is becoming an important technology for the information extraction from high spatial resolution images. Multi-scale image segmentation is a key and fundamental procedure of OBIA, however, the scale selection within the multi-scale image segmentation is always difficult to achieve for the high-performance OBIA. This paper firstly generalizes the commonly used segmentation scale parameters into three aspects: the spatial parameter (the spatial distance between classes), the attribute parameter (the attribute distance or spectral difference between classes) and the merging threshold (the area or pixel number of the minimum useful object). Next, this paper proposes a spatial and spectral statistics-based scale parameter estimation method for OBIA. The main concept of this proposed method is to use the average local variogram (without considering the anisotropism of spatial distribution) or the semivariogram (considering the anisotropism of spatial distribution) to pre-estimate the optimal spatial parameter. Next, the selection of the optimal attribute parameter and the selection of the merging threshold are achieved based on the local variance histogram and the simple geometric computation, respectively. Taking the mean-shift segmentation as an example, this study uses Ikonos, Quickbird and aerial panchromatic images as the experimental data to verify the validity of the proposed scale parameter estimation method. Experiments based on the quantitative multi-scale segmentation evaluation could testify the validity of this method. This pre-estimation based scale parameter selection method is practically helpful and efficient in OBIA. The idea of this method can be further extended to be integrated into other segmentation algorithms and be adaptive to other sensor data.
来源 地球信息科学学报 ,2016,18(5):622-631 【核心库】
关键词 面向对象影像分析 ; 影像分割 ; 尺度估计 ; 空间统计 ; 光谱统计
地址

1. 中国地质大学(北京)信息工程学院, 北京, 100083  

2. 南京师范大学, 虚拟地理环境教育部重点实验室, 南京, 210023

语种 中文
文献类型 研究性论文
ISSN 1560-8999
学科 测绘学
基金 国家自然科学基金项目 ;  中央高校基本科研业务费专项资金 ;  国家高分辨率对地观测系统重大专项 ;  江苏省自然科学基金
文献收藏号 CSCD:5694334

参考文献 共 20 共1页

1.  Blaschke T. Geographic object-based image analysis-towards a new paradigm. ISPRS Journal of Photogrammetry and Remote Sensing,2014,87:180-191 被引 88 次    
2.  Blaschke T. Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing,2010,65(1):2-16 被引 202 次    
3.  Hay G J. An automated object-based approach for the multiscale image segmentation of forest scenes. International Journal of Applied Earth Observation and Geoinformation,2005,7(4):339-359 被引 21 次    
4.  Myint S W. Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery. Remote Sensing of Environment,2011,115(5):1145-1161 被引 66 次    
5.  Dronova I. Landscape analysis of wetland plant functional types: the effects of image segmentation scale, vegetation classes and classification methods. Remote Sensing of Environment,2012,127:357-369 被引 16 次    
6.  Claudio R J. Combining wavelets and watersheds for robust multiscale image segmentation. Image and Vision Computing,2007,25(1):24-33 被引 10 次    
7.  Kim M. Estimation of optimal image object size for the segmentation of forest stands with multispectral IKONOS imagery. Object-based image analysis-spatial concepts for knowledge driven remote sensing applications,2008:291-307 被引 1 次    
8.  Johnson B. Unsupervised image segmentation evaluation and refinement using a multi-scale approach. ISPRS Journal of Photogrammetry and Remote Sensing,2011,66:473-483 被引 51 次    
9.  Tian J. Optimization in multi-scale segmentation of high-resolution satellite images for artificial feature recognition. International Journal of Remote Sensing,2007,28(20):4625-4644 被引 11 次    
10.  Anders N S. Segmentation optimization and stratified object-based analysis for semi-automated geomorphological mapping. Remote Sensing of Environment,2011,115(12):2976-2985 被引 13 次    
11.  Clinton N. Accuracy assessment measures for object-based image segmentation goodness. Photogrammetric Engineering & Remote Sensing,2010,76(3):289-299 被引 23 次    
12.  Liu Y. Discrepancy measures for selecting optimal combination of parameter values inobject-based image analysis. ISPRS Journal of Photogrammetry and Remote Sensing,2012,68:144-156 被引 28 次    
13.  Dragut L. ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data. International Journal of Geographical Information Science,2010,24(6):859-871 被引 95 次    
14.  Eid M E. A proposed multi-scale approach with automatic scale selection for image change detection. The Egyptian Journal of Remote Sensing and Space Sciences,2010,13:1-10 被引 1 次    
15.  Goodchild M. Introduction: scale, multiscaling, remote sensing, and GIS. Scale in remote sensing and GIS,1997:1-12 被引 2 次    
16.  Definiens A G. Definiens developer 7 user guide (version 7.0.2.936),Definiens,2007:23 被引 1 次    
17.  Ming D. Scale parameter selection by spatial statistics for GeOBIA: using mean-shift based multi-scale segmentation as an example. ISPRS Journal of Photogrammetry and Remote Sensing,2015,106:28-41 被引 8 次    
18.  Ming D. Semivariogram-based spatial bandwidth selection for remote sensing image segmentation with mean-shift algorithm. IEEE Geoscience and Remote Sensing Letters,2012,9(5):813-817 被引 7 次    
19.  Comaniciu D. Mean shift: a robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619 被引 1752 次    
20.  Espindola G. Parameter selection for region growing image segmentation algorithms using spatial autocorrelation. International Journal of Remote Sensing,2006,27(14):3035-3040 被引 43 次    
引证文献 7 篇

1 马燕妮 面向对象影像多尺度分割最大异质性参数估计 遥感学报,2017,21(4):566-578
被引 21 次

2 闫鹏飞 尺度自适应的高分辨率遥感影像分水岭分割方法 遥感技术与应用,2018,33(2):321-330
被引 6 次

显示所有7篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号