Pixel- and feature-level fusion of hyperspectral and lidar data for urban land-use classification

The complexity of urban areas makes it difficult for single-source remotely sensed data to meet all urban application requirements. Airborne light detection and ranging (lidar) can provide precise horizontal and vertical point cloud data, while hyperspectral images can provide hundreds of narrow spectral bands which are sensitive to subtle differences in surface materials. The main objectives of this study are to explore: (1) the performance of fused lidar and hyperspectral data for urban land-use classification, especially the contribution of lidar intensity and height information for land-use classification in shadow areas; and (2) the efficiency of combined pixel- and object-based classifiers for urban land-use classification. Support vector machine (SVM), maximum likelihood classification (MLC), and object-based classifiers were used to classify lidar, hyperspectral data and their derived features, such as the normalized digital surface model (nDSM), normalized difference vegetation index (NDVI), and texture measures, into 15 urban land-use classes. Spatial attributes and rules were used to minimize misclassification of the objects showing similar spectral properties, and accuracy assessments were carried out for the classification results. Compared with hyperspectral data alone, hyperspectral–lidar data fusion improved overall accuracy by 6.8% (from 81.7 to 88.5%) when the SVM classifier was used. Meanwhile, compared with SVM alone, the combined SVM and object-based method improved OA by 7.1% (from 87.6 to 94.7%). The results suggest that hyperspectral–lidar data fusion is effective for urban land-use classification, and the proposed combined pixel- and object-based classifiers are very efficient and flexible for the fusion of hyperspectral and lidar data.     

Detailed intra-urban mapping through transferable OBIA rule sets using WorldView-2 very-high-resolution satellite images

A detailed knowledge of the types and coverage of intra-urban features is helpful for different applications, such as roof run-off approximation and urban micro-climate studies. Previous studies have applied object-based image analysis (OBIA) to explore the detailed urban characterization on a single image of satellite sensors with very-high- resolution. The automated and transferable detection of intra-urban features is challenging because of variations of the spatial and spectral characteristics. This study utilizes the rule-based structure of OBIA to investigate the transferability of the OBIA rule sets on three subsets of a WorldView-2 (WV-2) image. Spatial, spectral, and textural features as well as several spectral indices are incorporated in these rule sets. The rule sets are developed on the first study site and reused in the second and third images. This OBIA framework provides a transferable process of detecting the intra-urban features without manually adjusting the rule set parameters and thresholds. Overall accuracies of 88%, 88%, and 86% are obtained for the first, second, and third images, respectively. The rule sets used in this study can be applied to other study areas or temporal WV-2 images for accurate detection of the intra-urban land-cover classes.     

A method for obtaining and applying classification parameters in object-based urban rooftop extraction from VHR multispectral images

Object-based methods of urban feature extraction from high spatial resolution remotely sensed data rely on semantic inference of spatial and contextual classification parameters in scenes of regular spatial or material composition. In this study, a supervised statistics-based method of determining and applying discretive parameters of rooftops in urban scenes of irregular composition is presented. After preprocessing to pansharpen IKONOS image data, the method includes the following steps: (1) image segmentation; (2) supervised object-based classification into broad spectral classes including impervious surfaces; (3) spectral, spatial, textural and contextual parameters are developed from statistical comparison of the sample rooftop and other impervious surface objects and (4) these parameters are implemented in a fuzzy logic rule base to separate rooftops from other impervious surfaces. Classification of a test scene results in 93% accuracy of rooftop identification, demonstrating the applicability of the method to the discrimination of spectrally similar but semantically variable classes.     

A comparison of pixel-based decision tree and object-based Support Vector Machine methods for land-cover classification based on aerial images and airborne lidar data

Precisely monitoring land cover/use is crucial for urban environmental assessment and management. Various classification techniques such as pixel-based and object-based approaches have advantages and disadvantages. In this article, based on our experiment data from an unmanned platform carried lidar scanner system and camera, we explored and compared classi?cation accuracies of pixel-based decision tree (DT) and object-based Support Vector Machine (SVM) approaches. Lidar height information can improve classification accuracy based on either object-based SVM or pixel-based DT. From total classification accuracy, object-based SVM was higher than that of pixel-based DT classification, and total accuracy and kappa coefficient of the former were 92.71% and 0.899, respectively. However, pixel-based DT outperformed object-based SVM when classifying small ‘scatter’ tree along roads. Additionally, in order to evaluate the accuracy of pixel-based DT and object-based SVM, we added benchmark data of ISPRS to compare the classification results of two methods. Object-based SVM classification methods by combining aerial imagery with lidar height information can achieve higher classification accuracy. And, accurately extracting tree class of different landscape pattern should select appropriate machine-learning algorithms. Comparison of the results on two methods will provide a reference for selecting a particular classification approaches according to local conditions.     

Mapping canopy gaps in an indigenous subtropical coastal forest using high-resolution WorldView-2 data

Invasive species usually colonize canopy gaps in tropical and subtropical forests, which results in a loss of native species. Therefore, an understanding of the location and distribution of canopy gaps will assist in predicting the occurrence of invasive species in such canopy gaps. We tested the utility of WorldView-2 (WV-2) with eight spectral bands at 2 m spatial resolution to delineate forest canopy gaps in a subtropical Dukuduku coastal forest in South Africa. We compared the four conventional visible-near-infrared bands with the eight-band WV-2 image. The eight-band WV-2 image yielded a higher overall accuracy of 86.90% (kappa coefficient = 0.82) than the resampled conventional four-band image that yielded an overall accuracy of 74.64% (kappa coefficient = 0.63) in pixel-based classification. We further compared the vegetation indices that were derived from four conventional bands with those derived from WV-2 bands. The enhanced vegetation index yielded the highest overall accuracy in the category of conventional indices (85.59% at kappa coefficient = 0.79), while the modified plant senescence reflectance index involving the red-edge band showed the highest overall accuracy (93.69%) in the category of indices derived from eight-band WV-2 imagery in object-based classification. Overall, the study shows that the unique high-resolution WV-2 data can improve the delineation of canopy gaps as compared to the conventional multispectral bands.     

Improvement of land-cover classification over frequently cloud-covered areas using Landsat 8 time-series composites and an ensemble of supervised classifiers

Recent abundance of moderate-to-high spatial resolution satellite imagery has facilitated land-cover map production. However, in cloud-prone areas, building high-resolution land-cover maps is still challenging due to infrequent satellite revisits and lack of cloud-free data. We propose a classification method for cloud-persistent areas with high temporal dynamics of land-cover types. First, compositing techniques are employed to create dense time-series composite images from all available Landsat 8 images. Then, spectral–temporal features are extracted to train an ensemble of five supervised classifiers. The resulting composite images are clear with at least 99.78% cloud-free pixels and are 20.47% better than their original images on average. We classify seven land classes, including paddy rice, cropland, grass/shrub, trees, bare land, impervious area, and waterbody over Hanoi, Vietnam, in 2016. Using a time series of composites significantly improves the classification performance with 10.03% higher overall accuracy (OA) compared to single composite classifications. Additionally, using time series of composites and the ensemble technique, which combines the best of five experimented classifiers (eXtreme Gradient Boosting, logistic regression, Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel – SVM–RBF and Linear kernel – SVM–Linear, multilayer perceptron), performed best with 84% OA and 0.79 kappa coefficient.     

New semi-automated mapping of asbestos cement roofs using rule-based object-based image analysis and Taguchi optimization technique from WorldView-2 images

The use of asbestos cement (AC) roofing materials is a significant concern because of their deleterious effects on human health and the environment. The main objective of this study was to map AC roofs from WorldView-2 (WV-2) images using object-based image analysis (OBIA). A robust Taguchi optimization technique was used to optimize segmentation parameters for WV-2 images in heterogeneous urban areas. In this research, two subsets of WV-2 satellite image sets were utilized to map AC roofs. Rule-based OBIA framework was developed on the first study area. Different supervised OBIA classifiers, such as Bayes, k-nearest neighbour (k-NN), support vector machine (SVM), and random forest (RF), were tested on the first image of the study areas to evaluate the performance of a rule-based classifier. Results of the supervised classifiers showed confusion between AC roof class and some urban features, with overall accuracies of 72.21%, 77%, 81.75%, and 82.02% for Bayes, k-NN, SVM, and RF, respectively. To assess the transferability of the proposed method, the adopted classification framework was applied to larger subsets of WV-2 of the second study area. The results of the proposed approach showed outstanding performance, with overall accuracies of 93.10% and 90.74% for the first and second classified images, respectively. The McNemar test emphasized the statistical reliability of rule-based result (in the first site) compared with supervised classification results. Therefore, the proposed framework of using rule-based classification and Taguchi optimization technique provide an efficient and expeditious approach to mapping and monitoring the presence of AC roofs and help local authorities in their decision-making strategies and policies.     

Building detection in an urban area using lidar data and QuickBird imagery

This article presents a hierarchical approach to detect buildings in an urban area through the combined usage of lidar data and QuickBird imagery. A normalized digital surface model (nDSM) was first generated on the basis of the difference between a digital surface model and the corresponding digital terrain model. Then, ground objects were removed according to a height threshold. In consideration of the relief displacement effect in very high resolution remote-sensing imagery, we segmented the nDSM by the region-growing method and used the overlap ratio to avoid over-removing building objects. Finally, the region size and spatial relation of trees and buildings were used to filter out trees occluded by buildings based on an object-based classification. Compared with previous methods directly using the normalized difference vegetation index (NDVI), our method improved the completeness from 85.94% to 90.20%. The overall accuracy of the buildings detected using the proposed method can be up to 94.31%, indicating the practical applicability of the method.     

Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery

In using traditional digital classification algorithms, a researcher typically encounters serious issues in identifying urban land cover classes employing high resolution data. A normal approach is to use spectral information alone and ignore spatial information and a group of pixels that need to be considered together as an object. We used QuickBird image data over a central region in the city of Phoenix, Arizona to examine if an object-based classifier can accurately identify urban classes. To demonstrate if spectral information alone is practical in urban classification, we used spectra of the selected classes from randomly selected points to examine if they can be effectively discriminated. The overall accuracy based on spectral information alone reached only about 63.33%. We employed five different classification procedures with the object-based paradigm that separates spatially and spectrally similar pixels at different scales. The classifiers to assign land covers to segmented objects used in the study include membership functions and the nearest neighbor classifier. The object-based classifier achieved a high overall accuracy (90.40%), whereas the most commonly used decision rule, namely maximum likelihood classifier, produced a lower overall accuracy (67.60%). This study demonstrates that the object-based classifier is a significantly better approach than the classical per-pixel classifiers. Further, this study reviews application of different parameters for segmentation and classification, combined use of composite and original bands, selection of different scale levels, and choice of classifiers. Strengths and weaknesses of the object-based prototype are presented and we provide suggestions to avoid or minimize uncertainties and limitations associated with the approach.     

Object-based land cover classification of shaded areas in high spatial resolution imagery of urban areas: A comparison study

A significant proportion of high spatial resolution imagery in urban areas can be affected by shadows. Considerable research has been conducted to investigate shadow detection and removal in remotely sensed imagery. Few studies, however, have evaluated how applications of these shadow detection and restoration methods can help eliminate the shadow problem in land cover classification of high spatial resolution images in urban settings. This paper presents a comparison study of three methods for land cover classification of shaded areas from high spatial resolution imagery in an urban environment. Method 1 combines spectral information in shaded areas with spatial information for shadow classification. Method 2 applies a shadow restoration technique, the linear-correlation correction method to create a “shadow-free” image before the classification. Method 3 uses multisource data fusion to aid in classification of shadows. The results indicated that Method 3 achieved the best accuracy, with overall accuracy of 88%. It provides a significantly better means for shadow classification than the other two methods. The overall accuracy for Method 1 was 81.5%, slightly but not significantly higher than the 80.5% from Method 2. All of the three methods applied an object-based classification procedure, which was critical as it provides an effective way to address the problems of radiometric difference and spatial misregistration associated with multisource data fusion (Method 3), and to incorporate thematic spatial information (Method 1).     

Wetland classification using Radarsat-2 SAR quad-polarization and Landsat-8 OLI spectral response data: a case study in the Hudson Bay Lowlands Ecoregion

Circumboreal Canadian bogs and fens distinguished by differences in soils, hydrology, vegetation and morphological features were classified using combinations of Radarsat-2 synthetic aperture radar (SAR) quad-polarization data and Landsat-8 Operational Land Imager (OLI) spectral response patterns. Separate classifications were conducted using a traditional pixel-based maximum likelihood classifer and a machine learning algorithm following an object-based image analysis (OBIA). This study focused on two wetland classes with extensive coverage in the area (bog and fen). In the pixel-based maximum likelihood classification, accuracy increased from approximately 69% user’s accuracy and 79% producer’s accuracy using Radarsat-2 SAR data alone to approximately 80% user’s accuracy and 87% producer’s accuracy using Landsat-8 OLI data alone. Use of the Radarsat-2 SAR and Landsat-8 OLI data following principal components analysis (PCA) data fusion did not result in higher pixel-based maximum likelihood classification accuracy. In the object-based machine learning classification, higher bog and fen class accuracies were obtained when using Radarsat-2 and Landsat OLI data individually compared to the equivalent pixel-based classification. Subsequently, a PCA-data fusion product outperformed the individual bands of the Radarsat-2 and Landsat-8 imagery in object-based classification. Greater than 90% producer’s accuracy was obtained. The margin of error (MOE) was less than 5% in all classifications reported here. Further research will examine alternative data fusion techniques and the addition of Radarsat-2 SAR interferometric digital elevation model (DEM)-based geomorphometrics in object-based classification of different morphological types of bogs and fens.     

Mapping the land-cover distribution in arid and semiarid urban landscapes with Landsat Thematic Mapper imagery

Mapping the land-cover distribution in arid and semiarid urban landscapes using medium spatial resolution imagery is especially difficult due to the mixed-pixel problem in remotely sensed data and the confusion of spectral signatures among bare soils, sparse density shrub lands, and impervious surface areas (ISAs hereafter). This article explores a hybrid method consisting of linear spectral mixture analysis (LSMA), decision tree classifier, and cluster analysis for mapping land-cover distribution in two arid and semiarid urban landscapes: Urumqi, China, and Phoenix, USA. The Landsat Thematic Mapper (TM) imagery was unmixed into four endmember fraction images (i.e. high-albedo object, low-albedo object, green vegetation (GV), and soil) using the LSMA approach. New variables from these fraction images and TM spectral bands were used to map seven land-cover classes (i.e. forest, shrub, grass, crop, bare soil, ISA, and water) using the decision tree classifier. The cluster analysis was further used to modify the classification results. QuickBird imagery in Urumqi and aerial photographs in Phoenix were used to assess classification accuracy. Overall classification accuracies of 86.0% for Urumqi and 88.7% for Phoenix were obtained, much higher accuracies than those utilizing the traditional maximum likelihood classifier (MLC). This research demonstrates the necessity of using new variables from fraction images to distinguish between ISA and bare soils and between shrub and other vegetation types. It also indicates the different effects of spatial patterns of land-cover composition in arid and semiarid landscapes on urban land-cover classification.     

Urban object extraction using Dempster Shafer feature-based image analysis from worldview-3 satellite imagery

A detailed and up-to-date land use of the urban environment is essentially required in many applications. Very high-resolution (VHR), Multispectral Scanner System (MSS) Worldview-3 (WV-3) satellite imagery provides detailed information on urban characteristics, which should be professionally mined. In this research, WV-3 was processed by machine learning (ML) methods to extract the most accurate urban features. Fuze-Go panchromatic sharpening in conjunction with atmospheric and topographic correction was initially utilized to increase the image quality and colour contrast. Three image analysis approaches including, current pixel-based image analysis (PBIA), object-based image analysis (OBIA) and new feature-based image analysis (FBIA) were implemented on WV-3 image. The k-nearest neighbour (k-NN), Naive Bayes (NB), support vector machine (SVM) classifiers were represented by PBIA, the Decision Tree (DT) classifier was examined as OBIA and the Dempster–Shafer (DS) fusion classifier was manifested for the first time as FBIA. In order to engage DS as FBIA, four types of Belief Masses, namely, Precision, Recall, Overall Accuracy, and kappa coefficient (?) were implemented and compared to assign the most likelihood urban features. All the applied classifiers were also trained on the first site and then tested on another site to examine the transferability. The accuracy, reliability, and computational time of all classifiers were examined by confusion matrix and McNemar assessment. Results show improvements on the detailed urban extraction obtained using the proposed FBIA with 92.2% overall accuracy in compared with PBIA and OBIA. The FBIA result of urban extraction is more consistent when transferred to another study area and consumes much lesser time than OBIA. Also, the precision mass belief measurement achieved highest efficiency regarding receiver operating characteristic (ROC) curve rate.     

Classification of impervious land-use features using object-based image analysis and data fusion

The proportion of impervious area within a watershed is a key indicator of the impacts of urbanization on water quality and stream health. Research has shown that object-based image analysis (OBIA) techniques are more effective for urban land-cover classification than pixel-based classifiers and are better suited to the increased complexity of high-resolution imagery. Focusing on five 2-km² study areas within the Black Creek sub-watershed of the Humber River, this research uses eCognition® software to develop a rule-based OBIA workflow for semi-automatic classification of impervious land-use features (e.g., roads, buildings, Parking Lots, driveways). The overall classification accuracy ranges from 88.7 to 94.3%, indicating the effectiveness of using an OBIA approach and developing a sequential system for data fusion and automated impervious feature extraction. Similar accuracy results between the calibrating and validating sites demonstrates the strong potential for the transferability of the rule-set from pilot study sites to a larger area.     

Quantifying high‐resolution impervious surfaces using spectral mixture analysis

Impervious surface distribution and its temporal changes are considered key urbanization indicators and are utilized for analysing urban growth and influences of urbanization on natural environments. Recently, urban impervious surface information was extracted from medium/coarse resolution remote sensing imagery (e.g. Landsat ETM+ and AVHRR) through spectral analytical methods (e.g. spectral mixture analysis (SMA), regression tree, etc.). Few studies, however, have attempted to generate impervious surface information from high resolution remotely sensed imagery (e.g. IKONOS and Quickbird). High resolution images provide detailed information about urban features and are, therefore, more valuable for urban analysis. The improved spatial resolution, however, also brings new challenges when existing spectral analytical methods are applied. In particular, a higher spatial resolution leads to reduced boundary effects and increased within‐class variability. Taking Grafton, Wisconsin, USA as a study site, this paper analyses the spectral characteristics of IKONOS imagery and explores the applicability of SMA for impervious surface estimation. Results suggest that with improved spatial resolution, IKONOS imagery contains 40–50% of mixed urban pixels for the study area, and the within‐class variability is a severe problem for spectral analysis. To address this problem, this paper proposes two approaches, interior end‐member set selection and spectral normalization, for SMA. Analysis of results indicates that these approaches can reasonably reduce the problems associated with boundary effects and within‐class variability, therefore generating better impervious surface estimates.     

A comparison of two spectral mixture modelling approaches for impervious surface mapping in urban areas

Urban change processes that have been occurring over the past decades are affecting the human and natural environment in many ways, and have stressed the need for new, more effective urban management approaches. In this context, mapping man-made impervious surfaces has been the focus of attention as impervious surfaces can be used as a general indicator to quantify urban change and its environmental impact. Despite the currently available digital imagery from high-resolution satellite sensors such as Ikonos and Quickbird, or from airborne cameras, spectral unmixing approaches applied on medium-resolution data from sensors such as Landsat Thematic Mapper (TM)/Enhanced TM Plus (ETM+) or Syst?me Probatoire d' Observation de la Terre-Haute Résolution Visible (SPOT-HRV) offer interesting perspectives to map impervious surfaces for large spatial extents. Several techniques for subpixel impervious surface mapping have been examined previously but there is a lack of comparative analysis. Our objective was to compare two spectral mixture analysis (SMA) models: the linear spectral unmixing model and the multilayer perceptron (MLP) model. Both models were implemented in a multiresolution framework, where reference data for model training were obtained from a high-resolution land-cover classification (derived from Ikonos imagery), while the models themselves were applied on medium-resolution data (Landsat ETM+). As a secondary objective, the effect of spectral normalization on the performance of both models was assessed. The MLP model clearly performed better than the linear mixture model. The average absolute error of the impervious surface proportion estimate within each medium-resolution pixel was 10.4% for the MLP model versus 12.9% for the linear mixture model. Spectral normalization was used to improve the results obtained by the linear mixture model, with the mean absolute error (MAE) for impervious surfaces decreasing from 14.8% to 12.9% after normalization. Its effects on the MLP model appeared to be insignificant. The outcome of this study can help to provide guidance for the selection of an approach to estimate continuous impervious surface fractions from medium-resolution data.     

Partially supervised hierarchical classification for urban features from lidar data with aerial imagery

Although spatial and spectral resolutions of remotely sensed data have been improved, the usage of multispectral imagery is not sufficient for urban feature classification. This article addresses the problem of automated classification by integrating airborne lidar range data and aerial imagery. In this study, the classification procedure is divided into three phases. We first use the lidar range data to obtain the coarse lidar-based classification results, by which a lidar-driven labelled image and a lidar-driven high-rise object mask are acquired in this phase. Then, at the image-based classification level, we train samples based on the lidar-driven labelled image and conduct maximum likelihood classification experience with the lidar-driven normalized digital surface model as a high-rise object mask. Finally, we propose a knowledge-based cross-validation (KBCV) for misclassification between the lidar-based classification results and the image-based classification results. Experimental results are presented to demonstrate the benefits of the training sample selection of the lidar-driven labelled image, using the lidar-driven high-rise object mask, and the greater classification accuracy of the KBCV.     

Multi-scale GEOBIA with very high spatial resolution digital aerial imagery: scale,texture and image objects

This study used geographic object-based image analysis (GEOBIA) with very high spatial resolution (VHR) aerial imagery (0.3 m spatial resolution) to classify vegetation, channel and bare mud classes in a salt marsh. Three classification issues were investigated in the context of segmentation scale: (1) a comparison of single- and multi-scale GEOBIA using spectral bands, (2) the relative benefit of incorporating texture derived from the grey-level co-occurrence matrix (GLCM) in classifying the salt marsh features in single- and multi-scale GEOBIA and (3) the effect of quantization level of GLCM texture in the context of multi-scale GEOBIA. The single-scale GEOBIA experiments indicated that the optimal segmentation was both class and scale dependent. Therefore, the single-scale approach produced an only moderately accurate classification for all marsh classes. A multi-scale approach, however, facilitated the use of multiple scales that allowed the delineation of individual classes with increased between-class and reduced within-class spectral variation. With only spectral bands used, the multi-scale approach outperformed the single-scale GEOBIA with an overall accuracy of 82% vs. 76% (Kappa of 0.71 vs. 0.62). The study demonstrates the potential importance of ancillary data, GLCM texture, to compensate for limited between-class spectral discrimination. For example, gains in classification accuracies ranged from 3% to 12% when the GLCM mean texture was included in the multi-scale GEOBIA. The multi-scale classification overall accuracy varied with quantization level of the GLCM texture matrix. A quantization level of 2 reduced misclassifications of channel and bare mud and generated a statistically higher classification than higher quantization levels. Overall, the multi-scale GEOBIA produced the highest classification accuracy. The multi-scale GEOBIA is expected to be a useful methodology for creating a seamless spatial database of marsh landscape features to be used for further geographic information system (GIS) analyses.     

基于混合光谱分解的兰州城市热岛与下垫面空间关系分析

利用Landsat ETM+数据,采用混合像元线性光谱分解方法提取的城市植被覆盖度与不透水面表征城市下垫面,通过单窗算法反演地表真实温度,对兰州市中心城区的夏季城市热岛强度与城市下垫面的空间分布关系进行相关分析。结果显示,利用中等分辨率ETM+影像对兰州中心城区不透水面和植被盖度分布提取,其成本较低,精度令人满意;兰州城区植被覆盖、不透水面与热岛强度的分布呈空间正自相关,地表温度的空间依赖性极强,与植被盖度和不透水面在空间方向上的相关性差异较大。     

Impervious surface mapping with Quickbird imagery

This research selects two study areas with different urban developments, sizes and spatial patterns to explore suitable methods for mapping impervious surface distribution using Quickbird imagery. The selected methods include per-pixel based supervised classification, segmentation-based classification and a hybrid method. A comparative analysis of the results indicates that per-pixel based supervised classification produces a large number of ‘salt-and-pepper’ pixels, and segmentation-based methods can significantly reduce this problem. However, neither method can effectively solve the spectral confusion of impervious surfaces with water/wetland and bare soils and the impacts of shadows. To accurately map impervious surface distribution from Quickbird images, manual editing is necessary and may be the only way to extract impervious surfaces from the confused land covers and the shadow problem. This research indicates that the hybrid method consisting of thresholding techniques, unsupervised classification and limited manual editing provides the best performance.