WorldView-2 Bands Research Articles

The impact of integrating WorldView-2 sensor and environmental variables in estimating plantation forest species aboveground biomass and carbon stocks in uMgeni Catchment, South Africa

Reliable and accurate mapping and extraction of key forest indicators of ecosystem development and health, such as aboveground biomass (AGB) and aboveground carbon stocks (AGCS) is critical in understanding forests contribution to the local, regional and global carbon cycle. This information is critical in assessing forest contribution towards ecosystem functioning and services, as well as their conservation status. This work aimed at assessing the applicability of the high resolution 8-band WorldView-2 multispectral dataset together with environmental variables in quantifying AGB and aboveground carbon stocks for three forest plantation species i.e. Eucalyptus dunii (ED), Eucalyptus grandis (EG) and Pinus taeda (PT) in uMgeni Catchment, South Africa. Specifically, the strength of the Worldview-2 sensor in terms of its improved imaging agilities is examined as an independent dataset and in conjunction with selected environmental variables. The results have demonstrated that the integration of high resolution 8-band Worldview-2 multispectral data with environmental variables provide improved AGB and AGCS estimates, when compared to the use of spectral data as an independent dataset. The use of integrated datasets yielded a high R2 value of 0.88 and RMSEs of 10.05tha−1 and 5.03tCha−1 for E. dunii AGB and carbon stocks; whereas the use of spectral data as an independent dataset yielded slightly weaker results, producing an R2 value of 0.73 and an RMSE of 18.57tha−1 and 09.29tCha−1. Similarly, high accurate results (R2 value of 0.73 and RMSE values of 27.30tha−1 and 13.65tCha−1) were observed from the estimation of inter-species AGB and carbon stocks. Overall, the findings of this work have shown that the integration of new generation multispectral datasets with environmental variables provide a robust toolset required for the accurate and reliable retrieval of forest aboveground biomass and carbon stocks in densely forested terrestrial ecosystems.

Posterior Probability Modeling and Image Classification for Archaeological Site Prospection: Building a Survey Efficacy Model for Identifying Neolithic Felsite Workshops in the Shetland Islands

The application of custom classification techniques and posterior probability modeling (PPM) using Worldview-2 multispectral imagery to archaeological field survey is presented in this paper. Research is focused on the identification of Neolithic felsite stone tool workshops in the North Mavine region of the Shetland Islands in Northern Scotland. Sample data from known workshops surveyed using differential GPS are used alongside known non-sites to train a linear discriminant analysis (LDA) classifier based on a combination of datasets including Worldview-2 bands, band difference ratios (BDR) and topographical derivatives. Principal components analysis is further used to test and reduce dimensionality caused by redundant datasets. Probability models were generated by LDA using principal components and tested with sites identified through geological field survey. Testing shows the prospective ability of this technique and significance between 0.05 and 0.01, and gain statistics between 0.90 and 0.94, higher than those obtained using maximum likelihood and random forest classifiers. Results suggest that this approach is best suited to relatively homogenous site types, and performs better with correlated data sources. Finally, by combining posterior probability models and least-cost analysis, a survey least-cost efficacy model is generated showing the utility of such approaches to archaeological field survey.

Evaluation of a WorldView-2 image for soil salinity monitoring in a moderately affected irrigated area

Conventional methods for monitoring salt accumulation within irrigation schemes involve regular field visits to collect soil samples for laboratory analysis. Remote sensing has been proposed as a less time-consuming, more cost-effective alternative as it provides imagery covering large areas throughout the year. This study evaluated the efficacy of very high resolution (VHR) WorldView-2 imagery to map areas affected by salt accumulation. Classifications based on thresholds obtained from Jeffries–Matusita distance, regression modeling, classification and regression trees, as well as supervised classification approaches, were evaluated for discriminating between salt-affected and unaffected soils in Vaalharts, South Africa. The WorldView-2 bands were supplemented with salinity indices (SIs), principal components, and texture measures to increase the number of predictive variables. In situ soil samples were used for model development, classifier training, and accuracy assessment. The results showed that a simple threshold implemented on a normalized difference SI was the most successful in separating classes, with an overall accuracy of 80%. The findings suggest that VHR satellite imagery holds much potential for monitoring salt accumulation, but more research is needed to investigate why the classification results tend to overestimate salt-affected areas. More work is also needed to evaluate the transferability of the techniques to other irrigation schemes.

A Comparative Analysis of Machine Learning with WorldView-2 Pan-Sharpened Imagery for Tea Crop Mapping.

Tea is an important but vulnerable economic crop in East Asia, highly impacted by climate change. This study attempts to interpret tea land use/land cover (LULC) using very high resolution WorldView-2 imagery of central Taiwan with both pixel and object-based approaches. A total of 80 variables derived from each WorldView-2 band with pan-sharpening, standardization, principal components and gray level co-occurrence matrix (GLCM) texture indices transformation, were set as the input variables. For pixel-based image analysis (PBIA), 34 variables were selected, including seven principal components, 21 GLCM texture indices and six original WorldView-2 bands. Results showed that support vector machine (SVM) had the highest tea crop classification accuracy (OA = 84.70% and KIA = 0.690), followed by random forest (RF), maximum likelihood algorithm (ML), and logistic regression analysis (LR). However, the ML classifier achieved the highest classification accuracy (OA = 96.04% and KIA = 0.887) in object-based image analysis (OBIA) using only six variables. The contribution of this study is to create a new framework for accurately identifying tea crops in a subtropical region with real-time high-resolution WorldView-2 imagery without field survey, which could further aid agriculture land management and a sustainable agricultural product supply.

Identification of WorldView-2 spectral and spatial factors in detecting salt accumulation in cultivated fields

Soil salinity is a global threat to agricultural production and necessitates the monitoring thereof. Saline conditions in South African irrigation schemes generally occur in small patches (some only a few metres in diameter) and this study, which forms part of a Water Research Commission (WRC) project, evaluates the use of very high resolution (VHR) satellite imagery, in particular those produced by the WorldView 2 (WV2) sensor, for the detection of salt accumulation in irrigated areas. A range of features derived from the WV2 image were evaluated, namely 8 WV2 bands, 10 vegetation indices (VIs), 25 texture measures and 2 principle component analysis (PCA) components. These features were generated at six spatial resolutions (0.5m, 2m, 6m, 10m, 15m and 20m) to investigate the value of high spatial resolution for detecting affected areas. The relationships between the image features and electric conductivity measurements of 30 soil samples were studied by means of regression analysis and classification and regression tree (CART) modelling. The regression analysis results showed that a spatial resolution of 6m or higher is ideal when VIs are used as input. When texture measures are used, higher spatial resolution (0.5m) produced better models. The regression results also showed that the relatively high spectral resolution of the WV2 sensor (compared to other VHR sensors) did not provide a significant improvement in accuracy. The CART results provided a categorical quantification of salt accumulation and showed that VIs generated at 0.5m resolution were the best features to use. Because the use of WV2 images is not financially viable for operational use in very large irrigation schemes, the study concludes with some guidelines on the spectral and spatial requirements of images when monitoring salt accumulation in irrigation schemes with similar conditions.

Deriving Bathymetry from Multispectral Remote Sensing Data

The use of passive satellite sensor data in shallow waters is complicated by the combined atmospheric, water, and bottom signals. Accurate determination of water depth is important for monitoring underwater topography and detection of moved sediments and in support of navigation. A Worldview 2 (WV2) image was used to develop high-resolution bathymetric maps (four meters) that were validated using bathymetry from an active sensor Light Detection and Ranging (LiDAR). The influence of atmospheric corrections in depth retrievals was evaluated using the Dark Substract, Fast Line-of-Sight Atmospheric Analysis of Spectral Hypercubes (FLAASH) and the Cloud Shadow Approach (CSA) atmospheric corrections. The CSA combined with a simple band ratio (Band2/Band3) provided the best performance, where it explained 82% of model values. The WV2 depth model was validated at another site within the image, where it successfully retrieved depth values with a coefficient of determination (r2) of 0.90 for all the depth values sampled, and an r2 of 0.70, for a depth range to 20 m. The WV2 bands in the visible region were useful for testing different band combinations to derive bathymetry that, when combined with a robust atmospheric correction, provided depth retrievals even in areas with variable bottom composition and near the limits of detection.

Object-Based Land Cover Classification Using Airborne Lidar and Different Spectral Images

Both land cover spectral information and 3D surface information can be obtained efficiently via remote sensing technologies. Spectral images provide spectral features whereas lidar point clouds contain 3D spatial features. Therefore, the multi-sensor data can be integrated to obtain useful information for different applications. This study integrates lidar with different spectral features for land cover classification. Because different spectral images have different characteristics, this study used hyperspectral images, 4- and 8-band WorldView-2 multispectral images, to distinguish different land covers. The major works include features selection, object-based classification, and evaluation. In features selection appropriate features were selected according to the land cover characteristics. Object-based classification was implemented using image segmentation and supervised classification. Finally, different combinations were evaluated using reference data to provide comprehensive analyses. We use ITRES CASI-1500 airborne hyperspectral images, WorldView-2 multispectral images and Optech ALTM Pegasus in this study. The experiment compared the results with and without data fusion. The importance of different spectral features is also discussed. In summary, different land covers with similar spectral features can be identified using lidar spatial features. Spectral image integration with lidar data may improve land cover classification accuracy.

Exploring the utility of the additional WorldView-2 bands and support vector machines in mapping land use/land cover in a fragmented ecosystem, South Africa

Land use/land cover (LULC) classification is a key research field in environmental applications of remote sensing on the earthfs surface. The advent of new high resolution multispectral sensors with unique bands has provided an opportunity to map the spatial distribution of detailed LULC classes over a large fragmented area. The objectives of the present study were: (1) to map LULC classes using multispectral WorldView-2 (WV-2) data and SVM in a fragmented ecosystem; and (2) to compare the accuracy of three WV-2 spectral data sets in distinguishing amongst various LULC classes in a fragmented ecosystem. WV-2 image was spectrally resized to its four standard bands (SB: blue, green, red and near infrared-1) and four strategically located bands (AB: coastal blue, yellow, red edge and near infrared-2). WV-2 image (8bands: 8B) together with SB and AB subsets were used to classify LULC using support vector machines. Overall classification accuracies of 78.0% (total disagreement = 22.0%) for 8B, 51.0% (total disagreement = 49.0%) for SB, and 64.0% (total disagreement = 36.0%) for AB were achieved. There were significant differences between the performance of all WV-2 subset pair comparisons (8B versus SB, 8B versus AB and SB versus AB) as demonstrated by the results of McNemarfs test (Z score .1.96). This study concludes that WV-2 multispectral data and the SVM classifier have the potential to map LULC classes in a fragmented ecosystem. The study also offers relatively accurate information that is important for the indigenous forest managers in KwaZulu-Natal, South Africa for making informed decisions regarding conservation and management of LULC patterns. Keywords : land use/cover classification, fragmented ecosystem, WorldView-2, support vector machines

Quantifying Libya-4 Surface Reflectance Heterogeneity With WorldView-1, 2 and EO-1 Hyperion

The land surface imaging (LSI) virtual constellation approach promotes the concept of increasing Earth observations from multiple but disparate satellites. We evaluated this through spectral and spatial domains, by comparing surface reflectance from 30-m Hyperion and 2-m resolution WorldView-2 (WV-2) data in the Libya-4 pseudoinvariant calibration site. We convolved and resampled Hyperion to WV-2 bands using both cubic convolution and nearest neighbor (NN) interpolation. Additionally, WV-2 and WV-1 same-date imagery were processed as a cross-track stereo pair to generate a digital terrain model to evaluate the effects from large ( $>$ 70 m) linear dunes. Agreement was moderate to low on dune peaks between WV-2 and Hyperion $(R^{2} but higher in areas of lower elevation and slope $(R^{2} > 0.6)$ . Our results provide a satellite sensor intercomparison protocol for an LSI virtual constellation at high spatial resolution, which should start with geolocation of pixels, followed by NN interpolation to avoid tall dunes that enhance surface reflectance differences across this internationally utilized site.

Testing the Contribution of WorldView-2 Improved Spectral Resolution for Extracting Vegetation Cover in Urban Environments

Detailed spatial data concerning land cover constitutes valuable information not only for urban design and planning but also to support informed decisions toward urban sustainable development. Obtaining such information from satellite imagery, with quality compatible with cartographic and thematic standards, is still a challenging task. Until recently, very high-resolution (VHR) satellites acquired data with high spatial resolution (1 m or less) but with only four spectral bands, typically in the visible and infrared regions. WorldView-2 (WV-2) offers improved spectral capability by acquiring data in an additional set of spectral bands. Using Lisbon as the case study, this research tests the contribution of the new bands of WV-2 sensor for extracting vegetation information in urban landscapes with different levels of plant heterogeneity. The methodology is based on an automated feature extraction procedure, followed by an object-based accuracy assessment. Results show that including the new WV-2 bands coastal and yellow (bands 1 and 8), along with the standard four-band set, increases the overall accuracy by 1–6%. However, the magnitude of improvement depends on the homogeneity of plants species present in the site.

Optimizing the spatial resolution of WorldView-2 imagery for discriminating forest vegetation at subspecies level in KwaZulu-Natal, South Africa

The objective of this study was to identify an appropriate spatial resolution for discriminating forest vegetation at subspecies level. WorldView-2 imagery was progressively resampled to coarser spatial resolutions. At a compartment level, 30 × 30-m subsets were generated across forest compartments to represent the five forest subspecies investigated in this study. From the centre of each subset, the spatial resolution of the original WorldView-2 image was resampled from 6 to 34-m, with increments of 4-m. The variance was then calculated at every resampled spatial resolution using each of the eight WorldView-2 bands. Based on the sampling theorem, the 3-m spatial resolution provided an appropriate resolution for all subspecies investigated. The WorldView-2 image was subsequently classified using the partial least squares linear discriminant analysis algorithm and the appropriate spatial resolution. An overall classification accuracy of 90% was established with an allocation disagreement of 9 and a quantity disagreement of 1.

Performance of Support Vector Machines and Artificial Neural Network for Mapping Endangered Tree Species Using WorldView-2 Data in Dukuduku Forest, South Africa

Endangered tree species (ETS) play a significant role in ecosystem functioning and services, land use dynamics, and other socio-economic aspects. Such aspects include ecological, economic, livelihood, and security-based and well-being benefits. The development of techniques for mapping and monitoring ETS is thus critical for understanding functioning of ecosystems. The advent of advanced imaging systems and supervised learning algorithms has provided an opportunity to map ETS over fragmenting areas. Recently, vegetation maps have been produced using advanced imaging systems such as WorldView-2 (WV-2) and robust classification algorithms such as support vector machines (SVM) and artificial neural network (ANN). However, delineation of ETS in a fragmenting ecosystem using high-resolution imagery has largely remained elusive due to the complexity of the species structure and their distribution. Therefore, the aim of the present study was to examine the utility of the advanced WV-2 data for mapping ETS in the fragmenting Dukuduku indigenous forest of South Africa using SVM and ANN classification algorithms. Specifically, the study looked at testing the advent of the additional WV-2 bands in mapping six ETS. WV-2 image was spectrally resized to separate four standard bands (SB) and four additional bands (AB). WV-2 image (8 bands: 8B) together with the SB and AB subsets was classified using SVM and ANN methods. The results showed the robustness of the two machine learning algorithms with an overall accuracy (OA) of 77.00% for SVM and 75.00% for ANN using 8B. The SB produced OA of 65.00% for SVM and 64.00% for ANN. The AB produced almost the same OA of 70.00% for both SVM and ANN. There were significant differences between the performances of the two algorithms as demonstrated by the results of McNemar’s test ( ${\text Z}\;\text {score} \geq {1}.{96}$ ). This study concludes that SVM and ANN classification algorithms with WV-2 8B have the potential to map ETS in the Dukuduku indigenous forest. This study offers relatively accurate information that is important for forest managers to make informed decisions regarding management and conservation protocols of ETS.

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.

Multi-sensor multi-resolution image fusion for improved vegetation and urban area classification

Abstract. In this paper, we perform multi-sensor multi-resolution data fusion of Landsat-5 TM bands (at 30 m spatial resolution) and multispectral bands of World View-2 (WV-2 at 2 m spatial resolution) through linear spectral unmixing model. The advantages of fusing Landsat and WV-2 data are two fold: first, spatial resolution of the Landsat bands increases to WV-2 resolution. Second, integration of data from two sensors allows two additional SWIR bands from Landsat data to the fused product which have advantages such as improved atmospheric transparency and material identification, for example, urban features, construction materials, moisture contents of soil and vegetation, etc. In 150 separate experiments, WV-2 data were clustered in to 5, 10, 15, 20 and 25 spectral classes and data fusion were performed with 3x3, 5x5, 7x7, 9x9 and 11x11 kernel sizes for each Landsat band. The optimal fused bands were selected based on Pearson product-moment correlation coefficient, RMSE (root mean square error) and ERGAS index and were subsequently used for vegetation, urban area and dark objects (deep water, shadows) classification using Random Forest classifier for a test site near Golden Gate Bridge, San Francisco, California, USA. Accuracy assessment of the classified images through error matrix before and after fusion showed that the overall accuracy and Kappa for fused data classification (93.74%, 0.91) was much higher than Landsat data classification (72.71%, 0.70) and WV-2 data classification (74.99%, 0.71). This approach increased the spatial resolution of Landsat data to WV-2 spatial resolution while retaining the original Landsat spectral bands with significant improvement in classification.

A novel spectral index to automatically extract road networks from WorldView-2 satellite imagery

This research develops a spectral index to automatically extract asphalt road networks named road extraction index (REI). This index uses WorldView-2 (WV-2) imagery, which has high spatial resolution and is multispectral. To determine the best bands for WV-2, field spectral data using a field spectroradiometer were collected. These data were then analyzed statistically. The bands were selected through the methodology of stepwise discriminant analysis. The appropriate WV-2 bands were distinguished from one another as per significant wavelengths. The proposed index is based on this classification. By applying REI to WV-2 imagery, we can extract asphalt roads accurately. Results demonstrate that REI is automated, transferable, and efficient in asphalt road extraction from high-resolution satellite imagery.

Quality assessment of ten fusion techniques applied on Worldview-2

Fusion or merging or pansharpening is the digital processing that combines the high spatial and multispectral information to obtain a fused multispectral image that retains the spatial information from the high resolution panchromatic image, as well as the spectral characteristics of the lower resolution multispectral image. Many fusion algorithms were developed and tested on different commercial satellite data such as Ikonos and Quickbird, however, the efficacy of these algorithms is weakly assessed on the new satellite images of Worldview-2 with very high spatial resolution. In the present study ten well known fusion techniques namely Color Normalized (CN), Ehlers, Gram-Schmidt, High Pass Filter (HPF), Local Mean Matching (LMM), Local Mean and Variance Matching (LMVM), Modified IHS (Modihs), Pansharp, PCA and Wavelet are used for the fusion of Worldview-2 panchromatic and multispectral data. Fused images were evaluated for spectral and spatial fidelity using visual inspection and different quality indexes such as the correlation coefficient (CC), ERGAS, the Universal Image Quality Index (Q), the Expanded Quality Index (Q4expand) and the Entropy values. Under each quality metric the fusion algorithms were ranked and best performances were indentified. It has been proved that all fusion algorithms have a different performance with the new multispectral bands of Worldview-2 in comparison to the classical ones. It has also been proved that almost all quality indices present a very strong dependency to the spatial resolution of the input data. The Q4expand quality index is proposed as the main quality discriminator since it gave the most robust results independently of the spectral and spatial input resolution. Pansharp algorithm took the lead in spatial enhancement while Ehlers and HPF are ranked in the first places for spectral preservation.

Enhanced Urban Landcover Classification for Operational Change Detection Study Using Very High Resolution Remote Sensing Data

Abstract. This study presents an operational case of advancements in urban land cover classification and change detection by using very high resolution spatial and multispectral information from 4-band QuickBird (QB) and 8-band WorldView-2 (WV-2) image sequence. Our study accentuates quantitative, pixel based, image difference approach for operational change detection using very high resolution pansharpened QB and WV-2 images captured over San Francisco city, California, USA (37° 44" 30N', 122° 31" 30' W and 37° 41" 30° N ,122° 20" 30' W). In addition to standard QB image, we compiled three multiband images from eight pansharpened WV-2 bands: (1) multiband image from four traditional spectral bands, i.e., Blue, Green, Red and near-infrared 1 (NIR1) (henceforth referred as "QB equivalent WV-2"), (2) multiband image from four new spectral bands, i.e., Coastal, Yellow, Red Edge and NIR2 (henceforth referred as "new band WV-2"), and (3) multiband image consisting of four traditional and four new bands (henceforth referred as "standard WV-2"). All the four multiband images were classified using support vector machine (SVM) classifier into four most abundant land cover classes, viz, hard surface, vegetation, water and shadow. The assessment of classification accuracy was performed using random selection of 356 test points. Land cover classifications on "standard QB" image (kappa coeffiecient, κ = 0.93), "QB equivalent WV-2" image (κ = 0.97), and "new band WV-2" image (κ = 0.97) yielded overall accuracies of 96.31 %, 98.03 % and 98.31 %, respectively, while "standard WV-2" image (κ = 0.99) yielded an improved overall accuracy of 99.18 %. It is concluded that the addition of four new spectral bands to the existing four traditional bands improved the discrimination of land cover targets, due to increase in the spectral characteristics of WV-2 satellite. Consequently, to test the validity of improvement in classification process for implementation in operational change detection application, comparative assessment of transition of various landcover classes in three WV-2 images with respect to "standard QB" image was carried out using image difference method. As far as waterbody class is concerned, there was no significant transition observed in all the three WorldView-2 Images, whereas, hard surface class showed lowest transition in "standard WV-2" image and highest in case of "new band WV-2". The most significant transition was occurred in vegetation class in all of the three images, showing positive change (increase) in standard WV-2 image (0.31 Sq. Km) and negative change (decrease) in other two images (−0.12 Sq. Km for "QB equivalent WV-2" image and −31.15 Sq. Km in "new band WV-2" image) with considerable amount. Similar case was observed with the shadow class, but the difference is, transition from shadow to other classes was negative in all the three WV-2 images which can be attributed to the fact that, "standard QB" image had more shadow area (based on acquisition time and sun position) than WV-2, that means all the band combinations of WV-2 succeeded in extracting the features hidden below the shadow in "standard QB" image. These trends indicate that the overall bandwise transition in landcover classes in case of "standard WV-2" is more precise than other two images. We note that "QB equivalent WV-2" image had narrower band widths than those of "standard QB" image but the observed vegetation change is not prominent as in case of other two images, but at the same time, transition in hard surface and waterbody was discerned more efficiently than "new band WV-2" image. The addition of new bands in WV-2 enabled more effective vegetation analysis, so the vegetation transition results shown by "new band WV-2" image were at par with the "standard WV-2" image, showing the importance of these newly added bands in the WV-2 imagery, with comparatively lower transitions in other classes. In a nutshell, it can be claimed that incorporation of new bands along with even narrower Red, Green, Blue and Near Infrared-1 bands in WV-2 image holds remarkable importance which leads to enhancement in the potential of WV-2 imagery in change detection and other feature extraction studies.

Comparison between WorldView-2 and SPOT-5 images in mapping the bracken fern using the random forest algorithm

Plant species invasion is known to be a major threat to socioeconomic and ecological systems. Due to high cost and limited extents of urban green spaces, high mapping accuracy is necessary to optimize the management of such spaces. We compare the performance of the new-generation WorldView-2 (WV-2) and SPOT-5 images in mapping the bracken fern [Pteridium aquilinum (L) kuhn] in a conserved urban landscape. Using the random forest algorithm, grid-search approaches based on out-of-bag estimate error were used to determine the optimal ntree and mtry combinations. The variable importance and backward feature elimination techniques were further used to determine the influence of the image bands on mapping accuracy. Additionally, the value of the commonly used vegetation indices in enhancing the classification accuracy was tested on the better performing image data. Results show that the performance of the new WV-2 bands was better than that of the traditional bands. Overall classification accuracies of 84.72 and 72.22% were achieved for the WV-2 and SPOT images, respectively. Use of selected indices from the WV-2 bands increased the overall classification accuracy to 91.67%. The findings in this study show the suitability of the new generation in mapping the bracken fern within the often vulnerable urban natural vegetation cover types.

A Semiautomatic Extraction of Antarctic Lake Features Using Worldview-2 Imagery

We devised a semiautomatic approach for extracting lake features based on a customized set of normalized difference water index (NDWI) information which was obtained by incorporating high resolution, 8-band WorldView-2 data. An extensive accuracy assessment was carried out for three semiautomatic feature extraction approaches for extracting 36 lake features on Larsemann Hills, Antarctica. The method was tested on five existing PAN-sharpening algorithms, which suggest that the customized NDWI approach renders intermediate performance (root mean square error varies from ~227 to ~235 m 2 ) and highest stability when compared with existing feature extraction techniques. In general, the customized NDWI rendered a least misclassification ( ≈11 percent), followed by target detection (≈16 percent) and spectral processing (≈17 percent) methods for extraction of 36 lakes. We also found that customized NDWI caused consistently least misclassification ( ≈21 percent) than the target detection (≈23 percent) and spectral processing (≈30 percent) methods for extraction of partially snow or ice-covered 11 lakes. Our results indicate that the use of the customized NDWI approach and appropriate PANsharpening algorithm can greatly improve the semiautomatic extraction of lake features in cryospheric environment.

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.