Search

Blue ground objects are typical ground objects in the urban environment, and the extraction of this type of ground objects is of great significance in urban environmental monitoring. To quickly extract blue ground objects from remote sensing images, this study takes WorldView-2 data as an example through the difference operation between some key bands, accumulates the difference image and performs ratio processing, enhances the information of blue ground objects and weakens the information of other ground objects in the newly generated image. A spectral index that can extract blue ground objects is then created. After the creation of the blue ground objects spectral index, an appropriate threshold is used to extract the blue ground objects in the image. Experimental results show that the new spectral threshold method can effectively detect blue ground objects in the urban image of WorldView-2 with high extraction accuracy, simple process and fast speed. [ABSTRACT FROM AUTHOR]

The last few decades have witnessed a tremendous increase in nutrient levels (phosphorus and nitrogen) in coastal water leading to excessive algal growth (Eutrophication). The presence of large amounts of algae turns the water’s color into green or red, in the case of algal blooms. Chlorophyll-a is often used as an indicator of algal biomass. Due to increased human activities surrounding Dubai creek, there have been eutrophication concerns given the levels of nutrients in that creek. This study aims to map chlorophyll-a in Dubai Creek from WorldView-2 imagery and explore the relationship between chlorophyll-a and other eutrophication indicators. A geometrically- and atmospherically-corrected WorldView-2 image and in-situ data have been utilized to map chlorophyll-a in the creek. A spectral model, developed from the WorldView-2 multispectral image to monitor Chlorophyll-a concentration, yielded 0.82 R2 with interpolated in-situ chlorophyll-a data. To address the time lag between the in-situ data and the image, Landsat 7 Enhanced Thematic Mapper Plus (ETM+) images were used to demonstrate the accuracy of the WorldView-2 model. The images, acquired on 20 May and 23 July 2012, were processed to extract chlorophyll-a band ratios (Band 4/Band 3) following the standard approach. Based on the availability, the 20 May image acquisition date is the closest to the middle of Quarter 2 (Q2) of the in-situ data (15 May). The 23 July 2012 image acquisition date is the closest to the WorldView-2 image date (24 July). Another model developed to highlight the relationship between spectral chlorophyll-a levels, and total nitrogen and orthophosphate levels, yielded 0.97 R2, which indicates high agreement. Furthermore, the generated models were found to be useful in mapping chlorophyll-a, total nitrogen, and orthophosphate, without the need for costly in-situ data acquisition efforts.

Remote sensing technology is so advanced that recently produced satellite sensors with the capability to provide imagery options with very high spatial resolutions. One of the options is WorldView-2 that has 1.84 meter of spatial resolution. Besides, WorldView-2 also has at least five bands on visible rays. The capability of remote sensing for underwater detection through specific depths and the availability of its bands on visible rays give more appropriate options to apply logarithm bands ratio on shallow water depth estimation. This research is aimed at analyzing the capability of WorldView-2 imagery to estimate shallow water depth of Kelapa-Harapan islands by using bands ratio algorithm. There were six bands combination used in applying band 1 through band 4 of WorldView-2 imagery. The results have shown that the best combination of bands to estimate the shallow water depth in the study area is the ratio between band 1 and band 3 with the R2 value of 0.067 and the average bias of 0.66 m. The ratio between band 1 and band 4 gave the value of R2 as big as 0.55 of its regression to the field depth samples. Meanwhile, the other four bands combination ratios have shown very low correlations to the water depth in the field. © 2015 GJGP UNDIP. All rights reserved.

Mapping urban vegetation is a prerequisite to accurately understanding landscape patterns and ecological services provided by urban vegetation. However, the uncertainties in fine-scale vegetation biodiversity mapping still exist in capturing vegetation functional types efficiently at fine scale. To facilitate the application of fine-scale vegetation spatial configuration used for urban landscape planning and ecosystem service valuation, we present an approach integrating object-based classification with vegetation phenology for fine-scale vegetation functional type mapping in compact city of Beijing, China. The phenological information derived from two WorldView-2 imagery scenes, acquired on 14 September 2012 and 26 November 2012, was used to aid in the classification of tree functional types and grass. Then we further compared the approach to that of using only one WorldView imagery. We found WorldView-2 imagery can be successfully applied to map functional types of urban vegetation with its high spatial resolution and relatively high spectral resolution. The application of the vegetation phenology into classification greatly improved the overall accuracy of classification from 82.3% to 91.1%. In particular, the accuracies of vegetation types was improved by from 10% to 13.26%. The approach integrating vegetation phenology with high-resolution remote sensed images provides an efficient tool to incorporate multi-temporal data into fine-scale urban classification. [ABSTRACT FROM AUTHOR]

Marine aquaculture plays an important role in seafood supplement, economic development, and coastal ecosystem service provision. The precise delineation of marine aquaculture areas from high spatial resolution (HSR) imagery is vital for the sustainable development and management of coastal marine resources. However, various sizes and detailed structures of marine objects make it difficult for accurate mapping from HSR images by using conventional methods. Therefore, this study attempts to extract marine aquaculture areas by using an automatic labeling method based on the convolutional neural network (CNN), i.e., an end-to-end hierarchical cascade network (HCNet). Specifically, for marine objects of various sizes, we propose to improve the classification performance by utilizing multi-scale contextual information. Technically, based on the output of a CNN encoder, we employ atrous convolutions to capture multi-scale contextual information and aggregate them in a hierarchical cascade way. Meanwhile, for marine objects with detailed structures, we propose to refine the detailed information gradually by using a series of long-span connections with fine resolution features from the shallow layers. In addition, to decrease the semantic gaps between features in different levels, we propose to refine the feature space (i.e., channel and spatial dimensions) using an attention-based module. Experimental results show that our proposed HCNet can effectively identify and distinguish different kinds of marine aquaculture, with 98% of overall accuracy. It also achieves better classification performance compared with object-based support vector machine and state-of-the-art CNN-based methods, such as FCN-32s, U-Net, and DeeplabV2. Our developed method lays a solid foundation for the intelligent monitoring and management of coastal marine resources.

To accurately estimate leaf area index (LAI) in mangrove areas, the selection of appropriate models and predictor variables is critical. However, there is a major challenge in quantifying and mapping LAI using multi-spectral sensors due to the saturation effects of traditional vegetation indices (VIs) for mangrove forests. World View-2 (WV2) imagery has proven to be effective to estimate LAI of grasslands and forests, but the sensitivity of its vegetation indices (VIs) has been uncertain for mangrove forests. Furthermore, the single model may exhibit certain randomness and instability in model calibration and estimation accuracy. Therefore, this study aims to explore the sensitivity of WV2 VIs for estimating mangrove LAI by comparing artificial neural network regression (ANNR), support vector regression (SVR) and random forest regression (RFR). The results suggest that the RFR algorithm yields the best results (RMSE = 0.45, 14.55% of the average LAI), followed by ANNR (RMSE = 0.49, 16.04% of the average LAI), and then SVR (RMSE = 0.51, 16.56% of the average LAI) algorithms using 5-fold cross validation (CV) using all VIs. Quantification of the variable importance shows that the VIs derived from the red-edge band consistently remain the most important contributor to LAI estimation. When the red-edge band-derived VIs are removed from the models, estimation accuracies measured in relative RMSE (RMSEr) decrease by 3.79%, 2.70% and 4.47% for ANNR, SVR and RFR models respectively. VIs derived from red-edge band also yield better accuracy compared with other traditional bands of WV2, such as near-infrared-1 and near-infrared-2 band. Furthermore, the estimated LAI values vary significantly across different mangrove species. The study demonstrates the utility of VIs of WV2 imagery and the selected machine-learning algorithms in developing LAI models in mangrove forests. The results indicate that the red-edge band of WV2 imagery can help alleviate the saturation problem and improve the accuracy of LAI estimation in a mangrove area. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Sunglint is a specular reflection of light from water surfaces that may cause misclassification and poor accuracy for benthic habitats mapping. The aim of this research was to investigate sunglint intensity for each benthic habitats and compared the accuracy result before and after sunglint correction from worldview-2 imagery. Hedley method and analysis coefficient of variation (COV) was used to estimate and remove the glint radiance component, while Mahalanobis distance was used to classify before and after sunglint correction from those imagery. The result showed that the average of sunglint intensity on benthic habitats was 38,9%. The highest sunglint intensity effect found in coral reef class (44%) and the lowest one in sand class (34%). The overall accuracy before and after sunglint correction were 53% and 60%. Sunglint correction well to do in reducing the effect of sunglint and increase the overall accuracy till 7%. [ABSTRACT FROM AUTHOR]

Dyke geometries are useful indicators of the palaeostress field during magma emplacement. In this paper, we present a multi-scale extraction method of dyke geometries by integrating WorldView-2 (WV2) imagery and terrestrial light detection and ranging (LiDAR) data. Color composite and fusion WV2 images with 0.5-m resolution were generated by using the Gramm–Schmidt Spectral Sharpening approach, which facilitates the discrimination of dyke swarms and provides the ability to measure the orientation, exposed length, and thickness of dykes in sub-horizontal topographic exposures. A terrestrial laser scanning survey was performed on a sub-vertical exposure of dykes to obtain LiDAR data with point spacing of ~ 0.02 m at 30 m. The LiDAR data were transformed to images for extracting dyke margins based on image segmentation, then the dyke attitudes, thicknesses, and irregularity of dyke margins were measured according to the points on dyke margins. This method was applied at Sijiao Island, Zhejiang, China where late Cretaceous mafic dyke swarms are widespread. The results show that integrating WV2 imagery and terrestrial LiDAR improves the accuracy, efficiency, and objectivity in determining dyke geometries in two and three dimensions. The ENE striking dykes are dominant, and intruded the host rock (mainly granite) with sub-vertical dips. Based on the aspect ratios of the dykes, the magmatic overpressure was estimated to be less than 11.5 MPa, corresponding to a magma chamber within 6.6 km in the lithosphere. [ABSTRACT FROM AUTHOR]

3D building reconstruction from point clouds is an active research topic in remote sensing, photogrammetry and computer vision. Most of the prior research has been done on 3D building reconstruction from LiDAR data which means high resolution and dense data. The interest of this work is 3D building reconstruction from Digital Surface Models (DSM) of stereo image matching of space borne satellite data which cover larger areas than LiDAR datasets in one data acquisition step and can be used also for remote regions. The challenging problem is the noise of this data because of low resolution and matching errors. In this paper, a top-down and bottom-up method is developed to find building roof models which exhibit the optimum fit to the point clouds of the DSM. In the bottom up step of this hybrid method, the building mask and roof components such as ridge lines are extracted. In addition, in order to reduce the computational complexity and search space, roofs are classified to pitched and flat roofs as well. Ridge lines are utilized to estimate the roof primitives from a building library such as width, length, positions and orientation. Thereafter, a topdown approach based on Markov Chain Monte Carlo and simulated annealing is applied to optimize roof parameters in an iterative manner by stochastic sampling and minimizing the average of Euclidean distance between point cloud and model surface as fitness function. Experiments are performed on two areas of Munich city which include three roof types (hipped, gable and flat roofs). The results show the efficiency of this method in even for this type of noisy datasets. [ABSTRACT FROM AUTHOR]

Abstract: This study integrated environmental variables together with high spectral resolution WorldView-2 imagery to detect and map Thaumastocoris peregrinus damage in Eucalypt plantation forests in KwaZulu-Natal, South Africa. The WorldView-2 bands, vegetation indices and environmental variables were entered separately into PLS regression models to predict T. peregrinus damage. The datasets were then integrated to test the collective strength in predicting T. peregrinus damage. Important variables were identified by variable importance (VIP) scores and were re-entered into a PLS regression model. The VIP model was then extrapolated to map the severity of damage and predicted T. peregrinus damage with an R 2 value of 0.71 and a RMSE of 3.26% on an independent test dataset. The red edge and near-infrared bands of the WorldView-2 sensor together with the temperature dataset were identified as important variables in predicting T. peregrinus damage. The results indicate the potential of integrating WorldView-2 data and environmental variables to improve the mapping and monitoring of insect outbreaks in plantation forests. The result is critical for plantation health monitoring using a new sensor which contains important vegetation wavelengths. [Copyright &y& Elsevier]

The last few decades have witnessed a tremendous increase in nutrient levels (phosphorus and nitrogen) in coastal water leading to excessive algal growth (Eutrophication). The presence of large amounts of algae turns the water's color into green or red, in the case of algal blooms. Chlorophyll-a is often used as an indicator of algal biomass. Due to increased human activities surrounding Dubai creek, there have been eutrophication concerns given the levels of nutrients in that creek. This study aims to map chlorophyll-a in Dubai Creek from WorldView-2 imagery and explore the relationship between chlorophyll-a and other eutrophication indicators. A geometrically- and atmospherically-corrected WorldView-2 image and in-situ data have been utilized to map chlorophyll-a in the creek. A spectral model, developed from the WorldView-2 multispectral image to monitor Chlorophyll-a concentration, yielded 0.82 R2 with interpolated in-situ chlorophyll-a data. To address the time lag between the in-situ data and the image, Landsat 7 Enhanced Thematic Mapper Plus (ETM+) images were used to demonstrate the accuracy of the WorldView-2 model. The images, acquired on 20 May and 23 July 2012, were processed to extract chlorophyll-a band ratios (Band 4/Band 3) following the standard approach. Based on the availability, the 20 May image acquisition date is the closest to the middle of Quarter 2 (Q2) of the in-situ data (15 May). The 23 July 2012 image acquisition date is the closest to the WorldView-2 image date (24 July). Another model developed to highlight the relationship between spectral chlorophyll-a levels, and total nitrogen and orthophosphate levels, yielded 0.97 R2, which indicates high agreement. Furthermore, the generated models were found to be useful in mapping chlorophyll-a, total nitrogen, and orthophosphate, without the need for costly in-situ data acquisition efforts. [ABSTRACT FROM AUTHOR]

Marine aquaculture plays an important role in seafood supplement, economic development, and coastal ecosystem service provision. The precise delineation of marine aquaculture areas from high spatial resolution (HSR) imagery is vital for the sustainable development and management of coastal marine resources. However, various sizes and detailed structures of marine objects make it difficult for accurate mapping from HSR images by using conventional methods. Therefore, this study attempts to extract marine aquaculture areas by using an automatic labeling method based on the convolutional neural network (CNN), i.e., an end-to-end hierarchical cascade network (HCNet). Specifically, for marine objects of various sizes, we propose to improve the classification performance by utilizing multi-scale contextual information. Technically, based on the output of a CNN encoder, we employ atrous convolutions to capture multi-scale contextual information and aggregate them in a hierarchical cascade way. Meanwhile, for marine objects with detailed structures, we propose to refine the detailed information gradually by using a series of long-span connections with fine resolution features from the shallow layers. In addition, to decrease the semantic gaps between features in different levels, we propose to refine the feature space (i.e., channel and spatial dimensions) using an attention-based module. Experimental results show that our proposed HCNet can effectively identify and distinguish different kinds of marine aquaculture, with 98% of overall accuracy. It also achieves better classification performance compared with object-based support vector machine and state-of-the-art CNN-based methods, such as FCN-32s, U-Net, and DeeplabV2. Our developed method lays a solid foundation for the intelligent monitoring and management of coastal marine resources. [ABSTRACT FROM AUTHOR]