A comparative study of the segmentation of weighted aggregation and multiresolution segmentation

Multiresolution segmentation (MRS) algorithm has been widely used to handle very-high-resolution (VHR) remote sensing images in the past decades. Unfortunately, segmentation quality is limited by the dependency of parameter selection on users’ experience and diverse images. Contrarily, the segmentation by weighted aggregation (SWA) can partly overcome the above limitations and produce an optimal segmentation for maximizing the homogeneity within segments and the heterogeneity across segments. However, SWA is solely tested and justified with digital photos in computer vision field instead of VHR images. This study aims at evaluating SWA performance on VHR imagery. First, multiscale spectral, shape, and texture features are defined to measure homogeneity of image objects for segmentation. Second, SWA is implemented to handle QuickBird, unmanned aerial vehicle (UAV), and GF-1 VHR images and further compared with MRS in eCognition software to demonstrate the applicability of SWA to diverse images in building, vegetation and water, forest stands, farmland, and mountain areas. Third, the results are fully evaluated with quantitative measurements on segmented objects and classification-based accuracy assessment on geographic information system vector data. The results indicate that SWA can produce higher quality segmentations, need fewer parameters and manual interventions, create fewer segmentation levels, incorporate more features, and obtain larger classification accuracy than MRS.     

遥感图像分区自动分类方法研究

对判读区域自然景观复杂,数据时相与质量差异较大的遥感图像用常规的分类方法难以达到令人满意的效果,为此,作者采用了一种通过定义图像判读区,分类管理器和改进监督分类算法等方法来实现遥感图像的分区自动分类,以不同时相的TM拼接图像进行分类试验,结果表明:该方法比传统的监督分类方法有明显改进:(1)与整幅图像用同一个标准进行分类的方案相比,其精度显著提高,(2)可在分类前灵活,任意生成所感兴趣的判读区域,(3)在每个分区内可以采取不同的分类方案进行分类,(4)每个分区的分类结果可以保存在同一个文件中,而不需要另外生成新的操作层.因此分类不受次数的限制,可保证分类结果的完整性,每个分区的分类结果也可以保存为单个分区的分类结果.     

Comparing object-based and pixel-based classifications for mapping savannas

The development of robust object-based classification methods suitable for medium to high resolution satellite imagery provides a valid alternative to ‘traditional’ pixel-based methods. This paper compares the results of an object-based classification to a supervised per-pixel classification for mapping land cover in the tropical north of the Northern Territory of Australia. The object-based approach involved segmentation of image data into objects at multiple scale levels. Objects were assigned classes using training objects and the Nearest Neighbour supervised and fuzzy classification algorithm. The supervised pixel-based classification involved the selection of training areas and a classification using the maximum likelihood classifier algorithm. Site-specific accuracy assessment using confusion matrices of both classifications were undertaken based on 256 reference sites. A comparison of the results shows a statistically significant higher overall accuracy of the object-based classification over the pixel-based classification. The incorporation of a digital elevation model (DEM) layer and associated class rules into the object-based classification produced slightly higher accuracies overall and for certain classes; however this was not statistically significant over the object-based using spectral information solely. The results indicate object-based analysis has good potential for extracting land cover information from satellite imagery captured over spatially heterogeneous land covers of tropical Australia.     

Optimizing multi-resolution segmentation scale using empirical methods: Exploring the sensitivity of the supervised discrepancy measure Euclidean distance 2 (ED2)

Multiresolution segmentation (MRS) has proven to be one of the most successful image segmentation algorithms in the geographic object-based image analysis (GEOBIA) framework. This algorithm is relatively complex and user-dependent; scale, shape, and compactness are the main parameters available to users for controlling the algorithm. Plurality of segmentation results is common because each parameter may take a range of values within its parameter space or different combinations of values among parameters. Finding optimal parameter values through a trial-and-error process is commonly practiced at the expense of time and labor, thus, several alternative supervised and unsupervised methods for supervised automatic parameter setting have been proposed and tested. In the case of supervised empirical assessments, discrepancy measures are employed for computing measures of dissimilarity between a reference polygon and an image object candidate. Evidently the reliability of the optimal-parameter prediction heavily relies on the sensitivity of the segmentation quality metric. The idea behind pursuing optimal parameter setting is that, for instance, a given scale setting provides image object candidates different from the other scale setting; thus, by design the supervised quality metric should capture this difference. In this exploratory study, we selected the Euclidean distance 2 (ED2) metric, a recently proposed supervised metric, whose main design goal is to optimize the geometrical discrepancy (potential segmentation error (PSE)) and arithmetic discrepancy between image objects and reference polygons (number-of segmentation ratio (NSR)) in two dimensional Euclidean space, as a candidate to investigate the validity and efficacy of empirical discrepancy measures for finding the optimal scale parameter setting of the MRS algorithm. We chose test image scenes from four different space-borne sensors with varying spatial resolutions and scene contents and systematically segmented them using the MRS algorithm at a series of parameter settings. The discriminative capacity of the ED2 metric across different scales groups was tested using non-parametric statistical methods. Our results showed that the ED2 metric significantly discriminates the quality of image object candidates at smaller scale values but it loses the sensitivity at larger scale values. This questions the meaningfulness of the ED2 metric in the MRS algorithm’s parameter optimization. Our contention is that the ED2 metric provides some notion of the optimal scale parameter at the expense of time. In this respect, especially in operational-level image processing, it is worth to re-think the trade-off between execution time of the processor-intensive MRS algorithm at series of parameter settings targeting a less-sensitive quality metric and an expert-lead trial-and-error approach.     

A systematic comparison of different object-based classification techniques using high spatial resolution imagery in agricultural environments

Geographic Object-Based Image Analysis (GEOBIA) is becoming more prevalent in remote sensing classification, especially for high-resolution imagery. Many supervised classification approaches are applied to objects rather than pixels, and several studies have been conducted to evaluate the performance of such supervised classification techniques in GEOBIA. However, these studies did not systematically investigate all relevant factors affecting the classification (segmentation scale, training set size, feature selection and mixed objects). In this study, statistical methods and visual inspection were used to compare these factors systematically in two agricultural case studies in China. The results indicate that Random Forest (RF) and Support Vector Machines (SVM) are highly suitable for GEOBIA classifications in agricultural areas and confirm the expected general tendency, namely that the overall accuracies decline with increasing segmentation scale. All other investigated methods except for RF and SVM are more prone to obtain a lower accuracy due to the broken objects at fine scales. In contrast to some previous studies, the RF classifiers yielded the best results and the k-nearest neighbor classifier were the worst results, in most cases. Likewise, the RF and Decision Tree classifiers are the most robust with or without feature selection. The results of training sample analyses indicated that the RF and adaboost. M1 possess a superior generalization capability, except when dealing with small training sample sizes. Furthermore, the classification accuracies were directly related to the homogeneity/heterogeneity of the segmented objects for all classifiers. Finally, it was suggested that RF should be considered in most cases for agricultural mapping.     

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.     

Mapping spiny aster infestations with QuickBird imagery

QuickBird satellite imagery acquired in June 2003 and September 2004 was evaluated for detecting the noxious weed spiny aster [Leucosyris spinosa (Benth.) Greene] on a south Texas, USA rangeland area. A subset of each of the satellite images representing a diversity of cover types was extracted and used as a study site. The satellite imagery had a spatial resolution of 2.8 m and contained 11-bit data. Unsupervised and supervised classification techniques were used to classify false colour composite (green, red, and near-infrared bands) images of the study site. Imagery acquired in June was superior to that obtained in September for distinguishing spiny aster infestations. This was attributed to differences in spiny aster phenology between the two dates. An unsupervised classification of the June image showed that spiny aster had producer's and user's accuracies of 90% and 93.1%, respectively, whereas a supervised classification of the June image had producer's and user's accuracies of 90% and 81.8%, respectively. These results indicate that high resolution satellite imagery coupled with image analysis techniques can be used successfully for detecting spiny aster infestations on rangelands.     

A comparison of unsupervised segmentation parameter optimization approaches using moderate- and high-resolution imagery

Unsupervised segmentation optimization methods have been proposed to aid in selecting an “optimal” set of scale parameters quickly and objectively for object-based image analysis. The goal of this study was to qualitatively assess three unsupervised approaches using both moderate-resolution Landsat and high-resolution Ikonos imagery from two study sites with different landscape characteristics to demonstrate the continued need for analyst intervention during the segmentation process. The results demonstrate that these methods selected parameters that were optimal for the scene which varied with method, image type, and site complexity. Several takeaways from this exercise are as follows: (1) some methods do not work as intended, (2) single-scale unsupervised optimization procedures cannot be expected to properly segment all the features of interest in the image every time, and (3) many multi-scale approaches require subjectively chosen weights or thresholds or additional testing to determine those values that meet the objective. Visual inspection of segmentation results is still required in order to assess over and under-segmentation as no method can be expected to select the best parameters for land cover classifications every time. These approaches should instead be used to narrow down parameter values in order to save time.     

GF-2影像面向对象典型城区地物提取方法

国产高分遥感影像信息丰富,提供了精准的地物空间细节,深入研究高分数据处理及其提取城区地类目标信息的方法具有重要意义。本文以国产高分二号（GF-2）遥感影像为数据源,利用规则集的面向对象分类方法,通过ESP尺度分析工具选取得出最优分割尺度,建立各类地物的特征体系及分类规则,最终提取出研究区典型城区地物信息,并将之与传统基于像元的SVM监督分类结果作比较。结果表明：规则集的面向对象分类总体精度为92.23%,Kappa系数为0.9,比SVM监督分类有大幅度提高。对高分二号等高分辨率影像,面向对象的分类方法精度更高,图示效果更好,是城区地物提取的有效方法。     

Remote sensing-derived national land cover land use maps: a comparison for Malawi

Reliable land cover land use (LCLU) information, and change over time, is important for Green House Gas (GHG) reporting for climate change documentation. Four different organizations have independently created LCLU maps from 2010 satellite imagery for Malawi for GHG reporting. This analysis compares the procedures and results for those four activities. Four different classification methods were employed; traditional visual interpretation, segmentation and visual labelling, digital clustering with visual identification and supervised signature extraction with application of a decision rule followed by analyst editing. One effort did not report classification accuracy and the other three had very similar and excellent overall thematic accuracies ranging from 85 to 89%. However, despite these high thematic accuracies there were very significant differences in results. National percentages for forest ranged from 18.2 to 28.7% and cropland from 40.5 to 53.7%. These significant differences are concerns for both remote-sensing scientists and decision-makers in Malawi.     

基于TM影像的面向对象地表覆被信息提取

为验证基于TM影像的面向对象分类方法对复杂地区地表覆被信息提取的可行性,以地处西南地区的渝北为例进行实验。利用样本数据对各个波段的光谱特征进行分析,取得对各波段覆被探测能力的初步认识;基于光谱特征的多尺度分割,运用面向对象分类方法对其分类。面向对象的分类方法总精度和Kappa系数分别为88.42%和0.854 7,将其与监督、非监督分类结果对比分析。结果表明,该方法有效抑制了"椒盐"现象,取得较好的分类结果。     

结合空间分析的面向对象无人机影像土地利用分类

利用高分辨遥感影像进行土地利用分类,为农村土地利用动态监测及土地综合整治快速地提供基础地理空间数据。以高分辨无人机影像为数据源,研究利用面向对象多尺度分割技术结合GIS空间分析对影像进行土地利用分类。根据对象内同质性高、对象间异质性高的准则,引入加权局部方差与空间自相关指数构建全局最优分割非监督评价指数,然后利用最邻近分类器对影像进行分类。实验结果表明,该方法减少人工目视确定最优分割尺度的主观性,能够避免某些地物不能被有效归类的现象,在单一尺度下获得较高的分类精度。     

面向对象的多尺度加权联合稀疏表示的高空间分辨率遥感影像分类

针对高空间分辨率遥感影像中的地物具有多尺度特性,以及各个尺度的对象特征对地物分类精度的影响具有较强的尺度效性,并结合面向对象影像分析方法和多尺度联合稀疏表示方法在高空间分辨率遥感影像分类中的各自优点,提出了一种面向对象的多尺度加权稀疏表示的高空间分辨率遥感影像分类算法。首先,采用多尺度分割算法获得多尺度分割结果并提取对象的多尺度特征;然后,根据影像对象的多尺度分割质量测度计算各尺度的对象权重,构建面向对象的多尺度加权联合稀疏表示模型;最后,采用2个国产GF-2高空间分辨率遥感数据集和1个高光谱-高空间分辨率航空遥感数据集（WashingtonD.C.数据）验证该算法的有效性。试验结果表明,与SVM、像素级稀疏表示、单尺度和多尺度对象级稀疏表示和深度学习等算法相比较,本文算法获得了较高的OA和Kappa分类精度,提高了各个尺度地物的分类精度,有效抑止了地物分类结果中的椒盐噪声现象,同时保持大尺度地物的区域性和小尺度地物的细节信息。     

Evaluation of data fusion and image segmentation in earth observation based rapid mapping workflows

This paper is an exploratory study, which aimed to discover the synergies of data fusion and image segmentation in the context of EO-based rapid mapping workflows. Our approach pillared on the geographic object-based image analysis (GEOBIA) focusing on multiscale, internally-displaced persons’ (IDP) camp information extraction from very high spatial resolution (VHSR) images. We applied twelve pansharpening algorithms to two subsets of a GeoEye-1 image scene that was taken over a former war-induced ephemeral settlement in Sri Lanka. A multidimensional assessment was employed to benchmark pansharpening algorithms with respect to their spectral and spatial fidelity. The multiresolution segmentation (MRS) algorithm of the eCognition Developer software served as the key algorithm in the segmentation process. The first study site was used for comparing segmentation results produced from the twelve fused products at a series of scale, shape, and compactness settings of the MRS algorithm. The segmentation quality and optimum parameter settings of the MRS algorithm were estimated by using empirical discrepancy measures. Non-parametric statistical tests were used to compare the quality of image object candidates, which were derived from the twelve pansharpened products. A wall-to-wall classification was performed based on a support vector machine (SVM) classifier to classify image objects candidates of the fused images. The second site simulated a more realistic crisis information extraction scenario where the domain expertise is crucial in segmentation and classification. We compared segmentation and classification results of the original images (non-fused) and twelve fused images to understand the efficacy of data fusion. We have shown that the GEOBIA has the ability to create meaningful image objects during the segmentation process by compensating the fused image’s spectral distortions with the high-frequency information content that has been injected during fusion. Our findings further questioned the necessity of the data fusion step in rapid mapping context. Bypassing time-intensive data fusion helps to actuate EO-based rapid mapping workflows. We, however, emphasize the fact that data fusion is not limited to VHSR image data but expands over many different combinations of multi-date, multi-sensor EO-data. Thus, further research is needed to understand the synergies of data fusion and image segmentation with respect to multi-date, multi-sensor fusion scenarios and extrapolate our findings to other remote sensing application domains beyond EO-based crisis information retrieval.     

综合聚类和上下文特征的高光谱影像分类

常规高光谱影像逐像素分类往往没有考虑空间相关性,分类结果未体现地物的空间关联和分布特征。为了在分类中充分利用空间特征,利用聚类信息并结合隐马尔可夫随机场模型讨论了高光谱遥感影像光谱-空间分类方法。首先,在不同特征提取方法（最小噪声分离、独立成分分析和主成分分析）下,使用不同聚类方法（k-均值、迭代自组织分析算法和模糊c-均值算法）借助隐马尔可夫随机场获取优化的分割图;然后,采用4连通区域标记法对分割区域标记生成图像对象,并根据支持向量机的逐像素分类结果采用多数投票法对图像对象进行分类;最后,借助凹槽窗口邻域滤波技术改进分类结果,削弱“椒盐”现象。该方法综合了监督分类和非监督分类的优势,通过聚类引入地物空间相关性信息,通过隐马尔可夫随机场引入上下文特征,较好地弥补了单纯基于光谱信息分类的不足。     

高分辨率影像城市绿地快速提取技术与应用

高分辨率遥感影像是城市绿地信息快速提取的主要数据源 ,文中以多尺度影像分割与面向对象影像分析方法为主要技术 ,利用样本多边形对象的成员函数建立训练区 ,自动提取大庆市城市绿地覆盖信息 ,达到清查城市绿地的目的。该方法信息获取周期短、精度高、成本低 ,实现了城市绿地信息精确获取与快速更新。     

粗糙集高分辨率遥感影像面向对象分类

面向对象的高分辨率遥感影像分类已受到研究者们的广泛关注。本文提出一种基于粗糙集理论的面向对象分类方法以区分高分辨率遥感影像上的不同地物。首先,利用基于相位一致梯度与前景标记的分水岭变换进行影像分割,提取图像斑块;然后,利用Gabor小波提取斑块的纹理特征,进而根据粗糙集理论提取纹理分类规则;最后,在对象光谱特征的初步分类结果,根据纹理分类规则得到最终结果基础上。依据粗糙集理论只能处理离散属性数据,本文重点提出一种适用于面向对象分类的连续区间属性离散化方法。实验表明本文方法可取得较好分类结果与较高分类精度。     

European forest cover mapping with high resolution satellite data: The Carpathians case study

The aim of the study was to elaborate a methodology for forest mapping based on high resolution satellite data, relevant for reporting on forest cover and spatial pattern changes in Europe. The Carpathians were selected as a case study area and mapped using 24 Landsat scenes, processed independently with a supervised approach combining image segmentation, knowledge-based rules to extract a training set and the maximum likelihood decision rule. Validation was done with available very high resolution imagery. Overall accuracies per scene ranged from 93 to 96%. The labelling disagreement in overlapping areas of adjacent scenes was 6.8% on average.     

VHR GeoEye-1 imagery reveals an ancient water landscape at the Longcheng site,northern Chaohu Lake Basin (China)

ABSTRACT

This study mainly focuses on revealing an ancient water landscape at the Longcheng site in the northern Chaohu Lake Basin using very high-resolution (VHR) GeoEye-1 imagery. First, prior to classification, the GeoEye-1 image was processed following atmospheric and geometric correction. The supervised classification was carried out in order to show the land-cover situation in the Longcheng area. The overall classification accuracy was 89.98%, with a kappa coefficient of 0.87. The moat system around the city walls was discovered by using rule-based object-oriented segmentation of the postclassified image, and the other walls of ancient Longcheng were manually identified from the pansharpened VHR GeoEye-1 image. Finally, a map of the ancient water landscape containing the ancient city, wall and moat at the Longcheng site was produced. This paper demonstrates that VHR remote sensing has the ability to uncover an ancient water landscape and provide new insights for archaeological and paleoenvironmental studies.