WorldView-2 Satellite Images Research Articles

A multi-layer Classification Technique for High Resolution Satellite Images Using Radiometric Calibration Modelling

Recent developments in satellite sensors tend to the availability of highspatial and spectral resolution images. The motivation of this researchpaper is to get maximum benefits of different bands in high resolutionsatellite images. In this research paper, a novel classification technique isintroduced where the shared texture features properties problem isaddressed. Atmospheric correction is applied on a high resolution WorldView 2 (WV2) image to produce reflectance value for all spectral bands.Reflectance image is produced by knowing the environmental parametersof the images at the capturing time, which can be extracted from auxiliaryfiles associated with the input image. A multi-layer classification treeanalysis is applied on a reflectance image to extract urban area featuresbased on investigated thresholding values. The proposed technique isinvestigated through MATLAB environment. The results of the proposedtechnique are assessed versus classification results of MaximumLikelihood classification technique that is applied through ENVI software.The assessment of classification results is represented in confusion matrixformat and determination of Kappa Coefficient. The investigatedtechnique succeeded in classifying urban area features up to 90%. Theproposed technique is fast, automated and suitable for any image withsame spectral bands as WV2 satellite image.

Estimation of leaf area index using WorldView-2 and Aster satellite image: a case study from Turkey.

The objective of this study is to estimate the leaf area index (LAI) of a forest ecosystem using two different satellite images, WorldView-2 and Aster. For this purpose, 108 sample plots were taken from pure Crimean pine forest stands of Yenice Forest Management Planning Unit in Ilgaz Forest Management Enterprise, Turkey. Each sample plot was imaged with hemispherical photographs with a fish-eye camera to determine the LAI. These photographs were analyzed with the help of Hemisfer Hemiview software program, and thus, the LAI of each sample plot was estimated. Furthermore, multiple regression analysis method was used to model the statistical relationships between the LAI values and band spectral reflection values and some vegetation indices (Vis) obtained from satellite images. The results show that the high-resolution WorldView-2 satellite image is better than the medium-resolution Aster satellite image in predicting the LAI. It was also seen that the results obtained by using the VIs are better than the bands when the LAI value is predicted with satellite images.

그림자 영역의 수직 경계선을 이용한 고해상도 위성 영상의 그림자 제거

The effect of shadows in very-high resolution (VHR) satellite imagery has become one of major issues in urban area analysis. The shadows in VHR satellite imagery, such as Kompsat-3A, covers a wide range of urban areas due to the buildings and affects the analysis of land cover and land use. This paper presents a shadow-removal method using the linear relationship between inner and outer intensities of shadow region borders. Vertical shadow borders, which have constant orientation in the whole image according to the altitude and azimuth of the sun at the image acquisition time, are extracted from shadow regions based on the orientation and linearity of the vertical border pixels. We estimate the pixel intensities in the shadow region based on RANdom Sample Consensus (RANSAC)-based linear transformation using only the pixels belonging to the shadow and non-shadow regions located outside a narrow border region. The pixel intensities in the narrow border region are interpolated using the least-square method which calculates the intensity plane parameters using the pixels belonging to small shadow and non-shadow regions. The proposed shadow removal method was tested using a part of WorldView-3 satellite images and showed improved shadow removal performance than the conventional linear correlation correction method in terms of image contrast and detailed-information improvement in the restored shadow region.

OBJECT-ORIENTED ANALYSIS OF SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS FOR POST-EARTHQUAKE BUILDINGS CHANGE DETECTION

Abstract. Earthquake is one of the most divesting natural events that threaten human life during history. After the earthquake, having information about the damaged area, the amount and type of damage can be a great help in the relief and reconstruction for disaster managers. It is very important that these measures should be taken immediately after the earthquake because any negligence could be more criminal losses. The purpose of this paper is to propose and implement an automatic approach for mapping destructed buildings after an earthquake using pre- and post-event high resolution satellite images. In the proposed method after preprocessing, segmentation of both images is performed using multi-resolution segmentation technique. Then, the segmentation results are intersected with ArcGIS to obtain equal image objects on both images. After that, appropriate textural features, which make a better difference between changed or unchanged areas, are calculated for all the image objects. Finally, subtracting the extracted textural features from pre- and post-event images, obtained values are applied as an input feature vector in an artificial neural network for classifying the area into two classes of changed and unchanged areas. The proposed method was evaluated using WorldView2 satellite images, acquired before and after the 2010 Haiti earthquake. The reported overall accuracy of 93% proved the ability of the proposed method for post-earthquake buildings change detection.

Influence of the weights in IHS and Brovey methods for pan-sharpening WorldView-3 satellite images

The purpose of this paper is to investigate the impact of weights in pan-sharpening methods applied to satellite images. Indeed, different data sets of weights have been considered and compared in the IHS and Brovey methods. The first dataset contains the same weight for each band while the second takes in account the weighs obtained by spectral radiance response; these two data sets are most common in pan-sharpening application. The third data set is resulting by a new method. It consists to compute the inertial moment of first order of each band taking in account the spectral response. For testing the impact of the weights of the different data sets, WorlView-3 satellite images have been considered. In particular, two different scenes (the first in urban landscape, the latter in rural landscape) have been investigated. The quality of pan-sharpened images has been analysed by three different quality indexes: Root mean square error (RMSE), Relative average spectral error (RASE) and Erreur Relative Global Adimensionnelle de Synthèse (ERGAS).

Mathematical Modeling and Accuracy Testing of WorldView-2 Level-1B Stereo Pairs without Ground Control Points

With very high resolution satellite (VHRS) imagery of 0.5 m, WorldView-2 (WV02) satellite images have been widely used in the field of surveying and mapping. However, for the specific WV02 satellite image geometric orientation model, there is a lack of detailed research and explanation. This paper elaborates the construction process of the WV02 satellite rigorous sensor model (RSM), which considers the velocity aberration, the optical path delay and the atmospheric refraction. We create a new physical inverse model based on a double-iterative method. Through this inverse method, we establish the virtual control grid in the object space to calculate the rational function model (RFM) coefficients. In the RFM coefficient calculation process, we apply the correcting characteristic value method (CCVM) and least squares (LS) method to compare the two experiments’ accuracies. We apply two stereo pairs of WV02 Level 1B products in Qinghai, China to verify the algorithm and test image positioning accuracy. Under the no-control conditions, the monolithic horizontal mean square error (RMSE) of the rational polynomial coefficient (RPC) is 3.8 m. This result is 13.7% higher than the original RPC positioning accuracy provided by commercial vendors. The stereo pair horizontal positioning accuracy of both the physical and RPC models is 5.0 m circular error 90% (CE90). This result is in accordance with the WV02 satellite images nominal positioning accuracy. This paper provides a new method to improve the positioning accuracy of the WV02 satellite image RPC model without GCPs.

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

ABSTRACTThe 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.

INVESTIGATION OF SPATIAL ACCURACY OF HIGH-RESOLUTION (50cm) WORLDVIEW-2 SATALLITE IMAGES

Nowadays, Very High Resolution Satellite (VHRS) images have been used for many applications intensively. Using of the digital satellite images in relevant approaches may give more accurate ideas about the researched fields. Besides, different methods could be used for geospatial informations from relevant digital data in many disciplines. The most importance reason of using the maps, which are derived from VHRS images, is accuracy of data. To obtain maps from VHRS images or use VHRS images as map, the VHRS images require rectification. For an accurate rectification process, Ground Control Points (GCPs) must be marked in the field. In this study, spatial accuracy of the stereo WorldView-2 satellite image (0.5 m resolution) was investigated at a test area. For this, 31 GCP points were established. These points were used as controls and check point. Block adjustment was made using a different number of control and check points. The impact of the number of control points upon the adjustment results was also investigated. As a result of adjustment using a 5-point control and 26 check points; root mean square error in the 53 cm x direction, 17 cm y direction, 63 cm in z-direction for control points have been obtained. For check points, 55 cm x direction, 26 cm y direction and z direction 65 cm root mean square error were found. Also coordinates obtained from the stereo model and the field determined by the geodetic methods coordinates of points were compared. The average position error of a point is 48 cm according to comparison results.

SATELLITE-DERIVED BATHYMETRY USING RANDOM FOREST ALGORITHM AND WORLDVIEW-2 IMAGERY

In empirical approach, the satellite-derived bathymetry (SDB) is usually derived from a linear regression. However, the depth variable in surface reflectance has a more complex relation. In this paper, a methodology was introduced using a nonlinear regression of Random Forest (RF) algorithm for SDB in shallow coral reef water. Worldview-2 satellite images and water depth measurement samples using single beam echo sounder were utilized. Furthermore, the surface reflectance of six visible bands and their logarithms were used as an input in RF and then compared with conventional methods of Multiple Linear Regression (MLR) at ten times cross validation. Moreover, the performance of each possible pair from six visible bands was also tested. Then, the estimated depth from two methods and each possible pairs were evaluated in two sites in Indonesia: Gili Mantra Island and Panggang Island, using the measured bathymetry data. As a result, for the case of all bands used the RF in compared with MLR showed better fitting ensemble, -0.14 and -1.27m of RMSE and 0.16 and 0.47 of R2 improvement for Gili Mantra Islands and Panggang Island, respectively. Therefore, the RF algorithm demonstrated better performance and accuracy compared with the conventional method. While for best pair identification, all bands pair wound did not give the best result. Surprisingly, the usage of green, yellow, and red bands showed good water depth estimation accuracy.

Spatial and temporal variation in reef-scale carbonate storage of large benthic foraminifera: a case study on One Tree Reef

Large benthic foraminifera (LBFs) are a vital component of coral reef carbonate production, often overlooked due to their small size. These super-abundant calcifiers are crucial to reef calcification by generation of lagoon and beach sands. Reef-scale carbonate production by LBFs is not well understood, and seasonal fluctuations in this important process are largely unquantified. The biomass of five LBF species in their algal flat habitat was quantified in the austral winter (July 2013), spring (October 2013), and summer (February 2014) at One Tree Reef. WorldView-2 satellite images were used to characterize and create LBF habitat maps based on ground-referenced photographs of algal cover. Habitat maps and LBF biomass measurements were combined to estimate carbonate storage across the entire reef flat. Total carbonate storage of LBFs on the reef flat ranged from 270 tonnes (winter) to 380 tonnes (summer). Satellite images indicate that the habitat area used by LBFs ranged from 0.6 (winter) to 0.71 km2 (spring) of a total possible area of 0.96 km2. LBF biomass was highest in the winter when algal habitat area was lowest, but total carbonate storage was the highest in the summer, when algal habitat area was intermediate. Our data suggest that biomass measurements alone do not capture total abundance of LBF populations (carbonate storage), as the area of available habitat is variable. These results suggest LBF carbonate production studies that measure biomass in discrete locations and single time points fail to capture accurate reef-scale production by not incorporating estimates of the associated algal habitat. Reef-scale measurements in this study can be incorporated into carbonate production models to determine the role of LBFs in sedimentary landforms (lagoons, beaches, etc.). Based on previous models of entire reef metabolism, our estimates indicate that LBFs contribute approximately 3.9–5.4% of reef carbonate budgets, a previously underappreciated carbon sink.

An Improvement on the Clustering of High-Resolution Satellite Images Using a Hybrid Algorithm

The challenge of obtaining training data for supervised classifications of satellite images has led researchers to unsupervised algorithms, i.e. cluster analysis. Numerous researches have been conducted to improve quality and decrease uncertainty of results of this analysis. This study proposes a hybrid cost function as well as a hybrid clustering algorithm-Artificial Bee Colony optimization approach for the clustering of high-resolution satellite images. In order to evaluate viability of the proposed methodology, it is compared to some other classic clustering algorithms such as modified K-Means, K-Medoids, Fuzzy C-Means, and Kernel-based Fuzzy C-Means methods over three different study areas selected from a WorldView-2 satellite image. The Shannon entropy technique, Kappa coefficient, compactness, and separation criteria are used as quality and uncertainty indicators for the evaluation. The results of the study show that, compared to other methods, the hybrid algorithm obtained from the proposed cost function, Kernel-based Fuzzy C-Means method, and ABC algorithm provide clustering capabilities of higher quality and lower uncertainty levels.

DEM EXTRACTION FROM WORLDVIEW-3 STEREO-IMAGES AND ACCURACY EVALUATION

Abstract. This paper validates the potentials of Worldview-3 satellite images in large scale topographic mapping, by choosing Worldview-3 along-track stereo-images of Yi Mountain area in Shandong province China for DEM extraction and accuracy evaluation. Firstly, eighteen accurate and evenly-distributed GPS points are collected in field and used as GCPs/check points, the image points of which are accurately measured, and also tie points are extracted from image matching; then, the RFM-based block adjustment to compensate the systematic error in image orientation is carried out and the geo-positioning accuracy is calculated and analysed; next, for the two stereo-pairs of the block, DSMs are separately constructed and mosaicked as an entirety, and also the corresponding DEM is subsequently generated; finally, compared with the selected check points from high-precision airborne LiDAR point cloud covering the same test area, the accuracy of the generated DEM with 2-meter grid spacing is evaluated by the maximum (max.), minimum (min.), mean and standard deviation (std.) values of elevation biases. It is demonstrated that, for Worldview-3 stereo-images used in our research, the planimetric accuracy without GCPs is about 2.16 m (mean error) and 0.55 (std. error), which is superior to the nominal value, while the vertical accuracy is about -1.61 m (mean error) and 0.49 m (std. error); with a small amount of GCPs located in the center and four corners of the test area, the systematic error can be well compensated. The std. value of elevation biases between the generated DEM and the 7256 LiDAR check points are about 0.62 m. If considering the potential uncertainties in the image point measurement, stereo matching and also elevation editing, the accuracy of generating DEM from Worldview-3 stereo-images should be more desirable. Judging from the results, Worldview-3 has the potential for 1:5000 or even larger scale mapping application.

DEM EXTRACTION FROM WORLDVIEW-3 STEREO-IMAGES AND ACCURACY EVALUATION

This paper validates the potentials of Worldview-3 satellite images in large scale topographic mapping, by choosing Worldview-3 along-track stereo-images of Yi Mountain area in Shandong province China for DEM extraction and accuracy evaluation. Firstly, eighteen accurate and evenly-distributed GPS points are collected in field and used as GCPs/check points, the image points of which are accurately measured, and also tie points are extracted from image matching; then, the RFM-based block adjustment to compensate the systematic error in image orientation is carried out and the geo-positioning accuracy is calculated and analysed; next, for the two stereo-pairs of the block, DSMs are separately constructed and mosaicked as an entirety, and also the corresponding DEM is subsequently generated; finally, compared with the selected check points from high-precision airborne LiDAR point cloud covering the same test area, the accuracy of the generated DEM with 2-meter grid spacing is evaluated by the maximum (max.), minimum (min.), mean and standard deviation (std.) values of elevation biases. It is demonstrated that, for Worldview-3 stereo-images used in our research, the planimetric accuracy without GCPs is about 2.16 m (mean error) and 0.55 (std. error), which is superior to the nominal value, while the vertical accuracy is about -1.61 m (mean error) and 0.49 m (std. error); with a small amount of GCPs located in the center and four corners of the test area, the systematic error can be well compensated. The std. value of elevation biases between the generated DEM and the 7256 LiDAR check points are about 0.62 m. If considering the potential uncertainties in the image point measurement, stereo matching and also elevation editing, the accuracy of generating DEM from Worldview-3 stereo-images should be more desirable. Judging from the results, Worldview-3 has the potential for 1:5000 or even larger scale mapping application.

Multi-Temporal Correlation Method for Damage Assessment of Buildings from High-Resolution SAR Images of the 2013 Typhoon Haiyan

In this study, damage caused by Typhoon Haiyan in the city of Tacloban, Philippines is extracted from COSMO-SkyMed imagery data. A multitemporal correlation map, i.e., a color composite of the backscattering coefficients obtained on different days and their correlation coefficients, is used to indicate changes. The Hyperboloid Change Index is proposed as a measure of the level of destruction. The method is demonstrated in a three-dimensional Cartesian coordinate system to elaborate the relationships among the aforementioned parameters. Compared to other candidate methods, a hyperboloid equation is found to be the most suitable for change detection, and its resulting positive value indicates that the typhoon had a high level of impact on the area. Potential damage areas are extracted using a thresholding operation, and the results are compared to two WorldView-2 satellite images to specifically assess coastal erosion and damage to buildings and offshore fish traps.

Effects of Per-Pixel Variability on Uncertainties in Bathymetric Retrievals from High-Resolution Satellite Images

Increased sophistication of high spatial resolution multispectral satellite sensors provides enhanced bathymetric mapping capability. However, the enhancements are counter-acted by per-pixel variability in sunglint, atmospheric path length and directional effects. This case-study highlights retrieval errors from images acquired at non-optimal geometrical combinations. The effects of variations in the environmental noise on water surface reflectance and the accuracy of environmental variable retrievals were quantified. Two WorldView-2 satellite images were acquired, within one minute of each other, with Image 1 placed in a near-optimal sun-sensor geometric configuration and Image 2 placed close to the specular point of the Bidirectional Reflectance Distribution Function (BRDF). Image 2 had higher total environmental noise due to increased surface glint and higher atmospheric path-scattering. Generally, depths were under-estimated from Image 2, compared to Image 1. A partial improvement in retrieval error after glint correction of Image 2 resulted in an increase of the maximum depth to which accurate depth estimations were returned. This case-study indicates that critical analysis of individual images, accounting for the entire sun elevation and azimuth and satellite sensor pointing and geometry as well as anticipated wave height and direction, is required to ensure an image is fit for purpose for aquatic data analysis.

Integrated approach using data mining-based decision tree and object-based image analysis for high-resolution urban mapping of WorldView-2 satellite sensor data

This paper integrates decision tree–based data mining (DM) and object-based image analysis (OBIA) to provide a transferable model for the detailed characterization of urban land-cover classes using WorldView-2 (WV-2) satellite images. Many articles have been published on OBIA in recent years based on DM for different applications. However, less attention has been paid to the generation of a transferable model for characterizing detailed urban land cover features. Three subsets of WV-2 images were used in this paper to generate transferable OBIA rule-sets. Many features were explored by using a DM algorithm, which created the classification rules as a decision tree (DT) structure from the first study area. The developed DT algorithm was applied to object-based classifications in the first study area. After this process, we validated the capability and transferability of the classification rules into second and third subsets. Detailed ground truth samples were collected to assess the classification results. The first, second, and third study areas achieved 88%, 85%, and 85% overall accuracies, respectively. Results from the investigation indicate that DM was an efficient method to provide the optimal and transferable classification rules for OBIA, which accelerates the rule-sets creation stage in the OBIA classification domain.

A quantitative approach to monitoring new sand cay migration in Nansha Islands

Sand cay is a special kind of islet formed by coral detritus and bioclast, which is common in Nansha Islands of China. Some sand cays play an important role in ocean strategy and economy, but surprisingly we know little about them, especially those recently formed sand cays. In this research, we monitor migration of a new sand cay in Nanxun Jiao (Gaven Reef) using a series of QuickBird and WorldView-2 satellite images between June 2006 and August 2013. We conduct a regression between migration distance and wind observational data to examine the migration patterns of the new sand cay. The migration distance is calculated based on the sand cay locations extracted based on Normalized Difference Water Index (NDWI). The wind observational data downloaded from NOAA are reformed into four wind direction vectors. Based on the results of regression, we concluded that the migration of the new sand cay on Nanxun Jiao was significantly associated with the east, west and north wind. East wind was the main influence factor of the migration; its impact strength was almost twice as the west and north wind. The south wind has little effect on the migration of the sand cay, which is partly blocked by the artificial structure in the south.

Fast and Efficient Satellite Imagery Fusion Using DT-CWT Proportional and Wavelet Zero-Padding

Among the various image fusion or pan-sharpening methods, those wavelet-based methods provide superior radiometric quality. However, the fusion processing is not only simple but also flexible, since many low- and high-frequency sub-bands are often produced in the wavelet domain. To address this issue, a novel DT-CWT (Dual-Tree Complex Wavelet Transform) proportional to the fusion method by a WZP (Wavelet Zero-Padding) is proposed. The proposed method produces a single high-frequency image in the spatial domain that is injected into the LRM (Low-Resolution Multispectral) image. Thus, a wavelet domain fusion can be simplified to spatial domain fusion. In addition, in the proposed DT-CWTP (DT-CWT Proportional) fusion method, it is unnecessary to decompose the LRM image by adopting WZP. The comparison indicates that the proposed fusion method is nearly five times faster than the DT-CWT with SW (Substitute-Wavelet) fusion method, meanwhile simultaneously maintaining the radiometric quality. The conducted experiments with WorldView-2 satellite images demonstrated promising results with the computation efficiency and fused image quality.

WorldView-2 위성영상의 분광지수를 이용한 개체 추출 연구

개체 추출은 원격탐사 분야의 주된 연구분야 중 하나로, 고해상도 위성영상의 활용도가 높아짐에 따라 보다 세밀하고 특정적인 개체를 추출할 수 있게 되었다. 기존의 화소 기반의 영상 처리 기법들은 고해상도 위성영상의 분광 및 기하학적인 다양성과 복잡성을 제대로 반영하기 어렵기 때문에 근래에는 영상분할 기술을 기반으로 하는 많은 연구가 진행되고 있다. 그런데 단순히 RGB 밴드 영상에 한 가지 영상분할 기법을 적용하는 것으로는 다양한 분광 특성과 형태를 갖는 여러 대상 개체들을 추출하는데 한계가 있다. 지표면의 피복의 종류를 식별하고, 상태를 모니터링 하는데 효과적인 분광지수는 개체 추출 과정에 효율적으로 이용할 수 있다. 본 연구에서는 영상분할 기술을 기반으로 하여 분광지수를 이용한 보다 효과적인 개체 추출 기술을 제안하고자 하였다. 다양한 종류의 개체를 추출하기 위하여 의사결정 트리 분류 기술을 사용하였으며 고해상도 위성인 WorldView-2의 8밴드 다중분광 영상을 이용한 실험을 통해 각 대상 개체를 추출하기에 적합한 분광지수들을 선택하고 이의 효용성을 평가해보고자 하였다. 그 결과, 건물, 도로, 나지, 식생, 수계, 그림자의 6개 클래스에 대한 개체들을 선택적으로 분류할 수 있었고, 식생지수를 비롯한 다양한 분광지수들이 각 개체의 종류를 선별해내는데 효과적으로 사용될 수 있음을 확인하였다. Feature extraction is one of the main goals in many remote sensing analyses. After high-resolution imagery became more available, it became possible to extract more detailed and specific features. Thus, considerable image segmentation algorithms have been developed, because traditional pixel-based analysis proved insufficient for high-resolution imagery due to its inability to handle the internal variability of complex scenes. However, the individual segmentation method, which simply uses color layers, is limited in its ability to extract various target features with different spectral and shape characteristics. Spectral indices can be used to support effective feature extraction by helping to identify abundant surface materials. This study aims to evaluate a feature extraction method based on a segmentation technique with spectral indices. We tested the extraction of diverse target features-such as buildings, vegetation, water, and shadows from eight band WorldView-2 satellite image using decision tree classification and used the result to draw the appropriate spectral indices for each specific feature extraction. From the results, We identified that spectral band ratios can be applied to distinguish feature classes simply and effectively.

Object-based classification with rotation forest ensemble learning algorithm using very-high-resolution WorldView-2 image

Machine learning algorithms reported to be robust and superior to the conventional parametric classifiers have been recently employed in object-based classification. Within these algorithms, ensemble learning methods that construct set of individual classifiers and combining their predictions to make final decision about unlabelled data have been successfully applied. In this study, performance and effectiveness of a novel ensemble learning algorithm, rotation forest (RotFor) aiming to build diverse and accurate classifiers, was investigated for the first time in object-based classification using a WorldView-2 (WV-2) satellite image. Also, the combination of satellite imagery and ancillary data (i.e. normalized difference vegetation index and principal components) were assessed. Random forest (RF), support vector machine (SVM) and nearest neighbour (NN) algorithms were also used as benchmark classifiers to evaluate the power of RotFor. The classification results confirmed that integration of ancillary data increased the classification accuracy in comparison to using solely spectral bands of WV-2. While RotFor and SVM generally produced similar results, they outperformed the RF and NN based on McNemar’s and Wilcoxon’s signed-rank test of statistical significance results.