Comparing supervised and unsupervised multiresolution segmentation approaches for extracting buildings from very high resolution imagery

Although multiresolution segmentation (MRS) is a powerful technique for dealing with very high resolution imagery, some of the image objects that it generates do not match the geometries of the target objects, which reduces the classification accuracy. MRS can, however, be guided to produce results that approach the desired object geometry using either supervised or unsupervised approaches. Although some studies have suggested that a supervised approach is preferable, there has been no comparative evaluation of these two approaches. Therefore, in this study, we have compared supervised and unsupervised approaches to MRS. One supervised and two unsupervised segmentation methods were tested on three areas using QuickBird and WorldView-2 satellite imagery. The results were assessed using both segmentation evaluation methods and an accuracy assessment of the resulting building classifications. Thus, differences in the geometries of the image objects and in the potential to achieve satisfactory thematic accuracies were evaluated. The two approaches yielded remarkably similar classification results, with overall accuracies ranging from 82% to 86%. The performance of one of the unsupervised methods was unexpectedly similar to that of the supervised method; they identified almost identical scale parameters as being optimal for segmenting buildings, resulting in very similar geometries for the resulting image objects. The second unsupervised method produced very different image objects from the supervised method, but their classification accuracies were still very similar. The latter result was unexpected because, contrary to previously published findings, it suggests a high degree of independence between the segmentation results and classification accuracy. The results of this study have two important implications. The first is that object-based image analysis can be automated without sacrificing classification accuracy, and the second is that the previously accepted idea that classification is dependent on segmentation is challenged by our unexpected results, casting doubt on the value of pursuing ‘optimal segmentation’. Our results rather suggest that as long as under-segmentation remains at acceptable levels, imperfections in segmentation can be ruled out, so that a high level of classification accuracy can still be achieved.     

Mapping fractional landscape soils and vegetation components from Hyperion satellite imagery using an unsupervised machine-learning workflow

An unsupervised machine-learning workflow is proposed for estimating fractional landscape soils and vegetation components from remotely sensed hyperspectral imagery. The workflow is applied to EO-1 Hyperion satellite imagery collected near Ibirací, Minas Gerais, Brazil. The proposed workflow includes subset feature selection, learning, and estimation algorithms. Network training with landscape feature class realizations provide a hypersurface from which to estimate mixtures of soil (e.g. 0.5 exceedance for pixels: 75% clay-rich Nitisols, 15% iron-rich Latosols, and 1% quartz-rich Arenosols) and vegetation (e.g. 0.5 exceedance for pixels: 4% Aspen-like trees, 7% Blackberry-like trees, 0% live grass, and 2% dead grass). The process correctly maps forests and iron-rich Latosols as being coincident with existing drainages, and correctly classifies the clay-rich Nitisols and grasses on the intervening hills. These classifications are independently corroborated visually (Google Earth) and quantitatively (random soil samples and crossplots of field spectra). Some mapping challenges are the underestimation of forest fractions and overestimation of soil fractions where steep valley shadows exist, and the under representation of classified grass in some dry areas of the Hyperion image. These preliminary results provide impetus for future hyperspectral studies involving airborne and satellite sensors with higher signal-to-noise and smaller footprints.     

A multi-band approach to unsupervised scale parameter selection for multi-scale image segmentation

Image segmentation is one of key steps in object based image analysis of very high resolution images. Selecting the appropriate scale parameter becomes a particularly important task in image segmentation. In this study, an unsupervised multi-band approach is proposed for scale parameter selection in the multi-scale image segmentation process, which uses spectral angle to measure the spectral homogeneity of segments. With the increasing scale parameter, spectral homogeneity of segments decreases until they match the objects in the real world. The index of spectral homogeneity is thus used to determine multiple appropriate scale parameters. The performance of the proposed method is compared to a single-band based method through qualitative visual interpretation and quantitative discrepancy measures. Both methods are applied for segmenting two images: a QuickBird scene of an urban area within Beijing, China and a Woldview-2 scene of a suburban area in Kashiwa, Japan. The proposed multi-band based segmentation scale parameter selection method outperforms the single-band based method with the better recognition for diverse land cover objects in different urban landscapes.     

高分辨率影像分类的最优分割尺度计算

针对高分辨率遥感影像分类与信息提取中存在的难点,基于不同目标地物在高分辨率影像上具有对应最优分割尺度的基本思想,该文在分析现有最优分割尺度确定方法的基础上,提出了加权均值法结合最大面积的最优分割尺度的确定方法;利用该方法,进行了高分辨率影像分割实验,获取了对应典型地物的最优分割尺度数值范围,实现了典型地物的信息提取;并运用样本点检验的方法,计算并分析了分类的精度结果。结果表明:基于加权均值与最大面积相结合的最优分割尺度计算方法,应用于面向对象高分辨率影像信息的提取具有较为理想的精度。     

Unsupervised evaluation-based region merging for high resolution remote sensing image segmentation

Image segmentation has a remarkable influence on the classification accuracy of object-based image analysis. Accordingly, how to raise the performance of remote sensing image segmentation is a key issue. However, this is challenging, primarily because it is difficult to avoid over-segmentation errors (OSE) and under-segmentation errors (USE). To solve this problem, this article presents a new segmentation technique by fusing a region merging method with an unsupervised segmentation evaluation technique called under- and over-segmentation aware (UOA), which is improved by using edge information. Edge information is also used to construct the merging criterion of the proposed approach. To validate the new segmentation scheme, five scenes of high resolution images acquired by Gaofen-2 and Ziyuan-3 multispectral sensors are chosen for the experiment. Quantitative evaluation metrics are employed in the experiment. Results indicate that the proposed algorithm obtains the lowest total error (TE) values for all test images (0.3791, 0.1434, 0.7601, 0.7569, 0.3169 for the first, second, third, fourth, fifth image, respectively; these values are averagely 0.1139 lower than the counterparts of the other methods), as compared to six state-of-the-art region merging-based segmentation approaches, including hybrid region merging, hierarchical segmentation, scale-variable region merging, size-constrained region merging with edge penalty, region merging guided by priority, and region merging combined with the original UOA. Moreover, the performance of the proposed method is better for artificial-object-dominant scenes than the ones mainly covering natural geo-objects.     

高分辨率遥感影像分割方法研究

在遥感应用分析中,遥感影像分割是低层影像处理和中高层影像分析和理解的桥梁,是实现遥感影像信息自动提取的关键步骤,具有重要的意义。随着大量高分辨率遥感影像的出现,传统基于像素的影像处理方法已不能适应高分辨率遥感影像。近年来,国内外研究者们提出了面向对象影像的分析方法,而面向对象影像分析方法的关键就是影像分割,影像分割精度直接影响着高分辨率遥感信息提取和目标识别的精度。首先给出一般图像分割方法的综述;然后分析和总结了当前主要的高分辨率遥感影像分割方法,着重阐述了均值漂移、分形网络进化、马尔科夫随机场等分割方法的特点和研究现状;最后,对高分辨率遥感应用分析中影像分割方法的发展趋势进行了讨论与展望。     

激光雷达点云辅助的高分影像分水岭分割方法

针对分水岭分割方法用于高分辨率遥感影像分割时过分割现象严重,且分割精度会受"同谱异物"现象的影响等问题,该文提出了一种激光雷达(LiDAR)点云辅助的高分影像分水岭分割方法,该方法利用高分影像和LiDAR点云两种数据源指导分割的进行:首先根据点云滤波结果将高分影像分为地物、地面两幅分影像进行分割合并,保证地物与非地物的正确划分;然后对过分割现象,提出了分形网格演化算法结合点云高程特征的合并准则,得到整体分割结果。实验证明该方法能有效改善"同谱异物"地类的混淆现象,可为复杂城区提供更精确的地类分割结果。     

Parameter evaluation and optimization for multi-resolution segmentation in object-based shadow detection using very high resolution imagery

Object-based shadow detection in urban areas is an important topic in very high resolution remote sensing image processing. Multi-resolution segmentation (MRS) is an effective segmentation method, and is used for object-based shadow detection. However, several input parameters within MRS may result in unstable performance for final shadow detection; thus, the evaluation and optimization for the parameters upon the final shadow detection accuracy cannot be overlooked. In this paper, the three parameters in MRS (scale s, weight of colour w_color and weight of compactness w_compact) upon the final result of a recently proposed method, object-based shadow detection with Dempster–Shafer theory, were evaluated and optimized by sensitivity analysis and Taguchi’s method with three experimental data. Experiments show that scale s is the most sensitive parameter among the three parameters within MRS. More importantly, according to the Taguchi’s method theory, there is a very significant interaction effect between s and w_color, which cannot be overlooked. The shadow detection accuracy yielded by the optimum parameter combination in consideration of the interaction effect is higher than that only optimized by covering the main effect of single parameter in most cases.     

Hybrid region merging method for segmentation of high-resolution remote sensing images

Image segmentation remains a challenging problem for object-based image analysis. In this paper, a hybrid region merging (HRM) method is proposed to segment high-resolution remote sensing images. HRM integrates the advantages of global-oriented and local-oriented region merging strategies into a unified framework. The globally most-similar pair of regions is used to determine the starting point of a growing region, which provides an elegant way to avoid the problem of starting point assignment and to enhance the optimization ability for local-oriented region merging. During the region growing procedure, the merging iterations are constrained within the local vicinity, so that the segmentation is accelerated and can reflect the local context, as compared with the global-oriented method. A set of high-resolution remote sensing images is used to test the effectiveness of the HRM method, and three region-based remote sensing image segmentation methods are adopted for comparison, including the hierarchical stepwise optimization (HSWO) method, the local-mutual best region merging (LMM) method, and the multiresolution segmentation (MRS) method embedded in eCognition Developer software. Both the supervised evaluation and visual assessment show that HRM performs better than HSWO and LMM by combining both their advantages. The segmentation results of HRM and MRS are visually comparable, but HRM can describe objects as single regions better than MRS, and the supervised and unsupervised evaluation results further prove the superiority of HRM.     

融入超像素分割的高分辨率影像面向对象分类

针对高分辨率遥感影像面向对象分类中容易受分割参数的影响、分类精度不稳定的问题,本文提出了一种融入超像素分割的高分辨率影像面向对象分类方法.该方法通过简单线性迭代聚类(SLIC)算法对原始影像进行聚类生成超像素影像,并在此基础上采用分形网络演化方法(FNEA)进行多尺度分割生成同质性对象,最后利用最邻近分类方法进行地物分...     

集成改进Mean Shift和区域合并两种算法的图像分割

Mean Shift算法分割图像时,带宽的大小直接影响分割效果.带宽分为空间带宽和值域带宽.本文根据待分割遥感图像的空间分辨率参考选定空间带宽,基于渐近积分均方差最小原则计算每一波段值域带宽;针对MS算法分割图像时存在过分割问题,提出基于区域面积加权的区域相似度准则和基于区域熵的合并停止准则来合并分割后区域.MATLAB软件3组实验结果表明:本文方法相比EDISON软件能得到更好的分割效果,且能在一定程度上提高遥感影像分割的自动化.     

五种分割算法在高分辨率遥感图像中的适用性分析

本文将5种图像分割算法应用在高分辨率遥感图像分割上,并利用图像分割评价指标,对5种分割算法进行了对比分析,评价了各种方法的优缺点,讨论了它们在高分辨率遥感图像分割中的适用性,明确了不同分割方法的适用条件。实验结果表明,改进的分水岭分割法与JSEG分割法在高分辨率遥感图像分割中的适用性比较强,对大小斑块分割结果都比较好,而其他3种方法不能兼顾不同等级的斑块。     

Road condition assessment by OBIA and feature selection techniques using very high-resolution WorldView-2 imagery

Accurate information on the conditions of road asphalt is necessary for economic development and transportation management. In this study, object-based image analysis (OBIA) rule-sets are proposed based on feature selection technique to extract road asphalt conditions (good and poor) using WorldView-2 (WV-2) satellite data. Different feature selection techniques, including support vector machine (SVM), random forest (RF) and chi-square (CHI) are evaluated to indicate the most effective algorithm to identify the best set of OBIA attributes (spatial, spectral, textural and colour). The chi-square algorithm outperformed SVM and RF techniques. The classification result based on CHI algorithm achieved an overall accuracy of 83.19% for the training image (first site). Furthermore, the proposed model was used to examine its performance in different areas; and it achieved accuracy levels of 83.44, 87.80 and 80.26% for the different selected areas. Therefore, the selected method can be potentially useful for detecting road conditions based on WV-2 images.     

Approximate approaches to geometric corrections of high resolution satellite imagery

The exploitation of different non-rigorous mathematical models as opposed to the satellite rigorous models is discussed for geometric corrections and topographic/thematic maps production of high-resolution satellite imagery (HRSI). Furthermore, this paper focuses on the effects of the number of GCPs and the terrain elevation difference within the area covered by the images on the obtained ground points accuracy. From the research, it is obviously found that non-rigorous orientation and triangulation models can be used successfully in most cases for 2D rectification and 3D ground points determination without a camera model or the satellite ephemeris data. In addition, the accuracy up to the sub-pixel level in plane and about one pixel in elevation can be achieved with a modest number of GCPs.     

A local approach to optimize the scale parameter in multiresolution segmentation for multispectral imagery

The results obtained using the object-based image analysis approach for remote sensing image analysis depend strongly on the quality of the segmentation step. In this paper, to optimize the scale parameter in a multiresolution segmentation, we analyse a high-resolution image of a large and heterogeneous agricultural area. This approach is based on using a set of agricultural plots extracted from official maps as uniform spatial units. The scale parameter is then optimized in each uniform spatial unit. Intra-object and inter-object heterogeneity measurements are used to evaluate each segmentation. To avoid subsegmentation, some oversegmentation is allowed, but is attenuated in a second step using the spectral difference segmentation algorithm. The statistical distribution of the scale parameter is not equal in all land uses, indicating the soundness of this local approach. A quantitative assessment of the results was also conducted for the different land covers. The results indicate that the spectral contrast between objects is larger with the local approach than with the global approach. These differences were statistically significant in all land uses except irrigated fruit trees and greenhouses. In the absence of subsegmentation, this suggests that the objects will be placed far apart in the space of variables, even if they are very close in the physical space. This is an obvious advantage in a subsequent classification of the objects.     

Individual tree crown segmentation in tropical peat swamp forest using airborne hyperspectral data

Abstract

Individual tree crown segmentation is important step for deriving various information for fine-scale analysis of ecological process. However, only several studies have applied tree crown segmentation in tropical forest ecosystems, especially in mixed peat swamp forests. In this study, hyperspectral data were used to detect changes in the biochemical and biophysical characteristics, which are important factors for tree crown segmentation. Principal Component Analysis method was performed to investigate its influence on crown segmentation. Visually Selected PCs, 160 PCs and 160 Spectral Bands image were used and two segmentation techniques; Watershed Transformation and Region Growing segmentation were applied on those images. The highest accuracy was achieved for the crown segmentation is using Region Growing segmentation, based on 1:1 measurement, D value and RMSE value. The results obtained from 160 PCs image using region growing algorithm shows better accuracy with D value of 0.2 (80% accuracy, 20% error) and RMSE of 9.9 m².     

大规模影像数据库的设计与实现

本文对现有遥感影像数据管理方法进行了讨论,针对其存在的不足,沿用传统数据库技术成果,如SQL技术、索引技术,并利用SQL Server 2005简单易用,且支持二进制大对象(BLOB),提出分幅分块存储管理方式,解决数据的物理存储问题,结合金字塔技术、索引技术、JPEG压缩技术,解决了数据的快速加载问题。工程应用实际表明,该方法能够满足海量遥感影像数据的管理需求。     

遥感影像并行分割的无缝拼接算法

针对影像数据分块并行处理造成的接边问题,该文基于构建缓冲区的方法提出了一种新的拼接算法。该算法只在每一个数据分块的右侧和下侧构建缓冲区,消除拼接线的原则是保证分割边界的准确性和拓扑关系的正确性。数据分块完成后采用并行的策略对第一个块进行分割,然后将每一块的分割结果与相邻的块进行拼接,在缓冲区内按一定规则判断各块分割对象是否保留并对拓扑关系进行检查,拼接完各块后并行输出对象矢量化后的结果。通过实验验证,该算法不仅保证了分割边界的准确性,而且能够处理大影像,提高了工作效率。     

基于Gabor纹理描述的遥感影像分割

本文引入了在不同影像层次上的Gabor纹理特征,采用分裂-合并加智能像素精致的方法,实现遥感影像的非监督分割。实验结果表明采用Gabor滤波器为基础的多分辨率分析来描述高分辨率遥感影像的纹理特征,可以明显地描述影像的高、低频特征,并且基于Gabor纹理特征进行遥感影像的分割是有效的;将本文方法的分割结果与经典的eCognition分割结果进行了对比试验,表明本文方法的分割结果较好。     

改进分数阶达尔文粒子群的多Renyi熵图像分割算法

针对智能优化图像分割算法易陷入局部最优、分割精度不高等问题,本文融合改进的分数阶达尔文粒子群算法和二维Renyi熵多阈值,提出了一种新的多阈值遥感图像分割算法。算法利用粒子自身进化信息来定义进化因子,结合进化因子并利用高斯图函数调整分数阶次a系数以实现精确计算和快速收敛;根据局部最优概率因子对局部最优位置进行Levy飞行随机扰动以提高算法跳出局部最优的能力;同时将二维Renyi熵单阈值扩展到多阈值分割上,并结合改进的分数阶达尔文粒子群算法,将二维Renyi熵多阈值应用于遥感图像分割中仿真结果表明,与其他2种智能优化分割算法相比,本文分割算法在细节处理和分割精度上均有明显优势,在PRI上至少提升7.27%、VOI至少降低6.5%、GCE至少降低10.4%.