Automated Water Extraction Index: a new technique for surface water mapping using Landsat imagery.

The normalized difference water index (NDWI) has been successfully used to delineate surface water features. However, two major problems have been often encountered: (a) NDWIs calculated from different band combinations [visible, nearinfrared, or shortwave-infrared (SWIR)] can generate different results, and (b) NDWI thresholds vary depending on the proportions of subpixel water/non-water components. We need to evaluate all the NDWIs for determining the best performing index and to establish appropriate thresholds for clearly identifying water features. We used the spectral data obtained from a spectral library to simulate the satellite sensors Landsat ETM, SPOT-5, ASTER, and MODIS, and calculated the simulated NDWI in different forms. We found that the NDWI calculated from (green ‐ SWIR)/(green SWIR), where SWIR is the shorter wavelength region (1.2 to 1.8 mm), has the most stable threshold. We recommend this NDWI be employed for mapping water, but adjustment of the threshold based on actual situations is necessary.

Analysis of Dynamic Thresholds for the Normalized Difference Water Index

The Brazilian tropical savanna (Cerrado), encompassing more than 204 million hectares in the central part of the country, is the second richest biome in Brazil in terms of biodiversity and presents high land use pressure. The objective of this study was to map the land cover of the Cerrado biome based on the segmentation and visual interpretation of 170 Landsat Enhanced Thematic Mapper Plus satellite scenes acquired in 2002. The following land cover classes were discriminated: grasslands, shrublands, forestlands, croplands, pasturelands, reforestations, urban areas, and mining areas. The results showed that the remnant natural vegetation is still covering about 61% of the biome, however, on a highly asymmetrical basis. While natural physiognomies comprise 90% of the northern part of the biome, only 15% are left in its southern portions. Shrublands were the dominant natural land cover class, while pasturelands were the dominant land use class in the Cerrado biome. The final Cerrado’s land cover map confirmed the intensive land use pressure in this unique biome. This paper also showed that Landsat-like sensors can provide feasible land cover maps of Cerrado, although ancillary data are required to help image interpretation.

Land cover mapping of the tropical savanna region in Brazil.

Assessment of inundation changes of Poyang Lake using MODIS observations between 2000 and 2010

In recent years, the resolution of remotely sensed imagery has become increasingly high in both the spectral and spatial domains, which simultaneously provides more plentiful spectral and spatial information. Accordingly, the accurate interpretation of high-resolution imagery depends on effective integration of the spectral, structural and semantic features contained in the images. In this paper, we propose a new multifeature model, aiming to construct a support vector machine (SVM) ensemble combining multiple spectral and spatial features at both pixel and object levels. The features employed in this study include a gray-level co-occurrence matrix, differential morphological profiles, and an urban complexity index. Subsequently, three algorithms are proposed to integrate the multifeature SVMs: certainty voting, probabilistic fusion, and an object-based semantic approach, respectively. The proposed algorithms are compared with other multifeature SVM methods including the vector stacking, feature selection, and composite kernels. Experiments are conducted on the hyperspectral digital imagery collection experiment DC Mall data set and two WorldView-2 data sets. It is found that the multifeature model with semantic-based postprocessing provides more accurate classification results (an accuracy improvement of 1-4% for the three experimental data sets) compared to the voting and probabilistic models.

An SVM Ensemble Approach Combining Spectral, Structural, and Semantic Features for the Classification of High-Resolution Remotely Sensed Imagery

This study aims at providing expertise for preparing public-based flood mapping and estimating flood risks in growing urban areas. To model and predict the magnitude of flood risk areas, an integrated Analytical Hierarchy Process (AHP) and Geographic Information System (GIS) analysis techniques are used for the case of Eldoret Municipality in Kenya. The flood risk vulnerability mapping follows a multi-parametric approach and integrates some of the flooding causative factors such as rainfall distribution, elevation and slope, drainage network and density, land-use/land-cover and soil type. From the vulnerability mapping, urban flood risk index (UFRI) for the case study area, which is determined by the degree of vulnerability and exposure is also derived. The results are validated using flood depth measurements, with a minimum average difference of 0.01 m and a maximum average difference of 0.37 m in depth of observed flooding in the different flood prone areas. Similarly with respect to area extents, a maximum error of not more than 8% was observed in the highly vulnerable flood zones. In addition, the Consistency Ratio which shows an acceptable level of 0.09 was calculated and further validated the strength of the proposed approach.

Urban Flood Vulnerability and Risk Mapping Using Integrated Multi-Parametric AHP and GIS: Methodological Overview and Case Study Assessment

Because of the complicated shorelines, inaccessibility and vast spread of some lakes, information on changing shorelines is difficult to acquire. A new water index (WI) has been applied to quantify changes in five saline and non‐saline Rift Valley lakes in Kenya using Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper (ETM+) data. The WI is based on a logical combination of the Tasseled Cap Wetness (TCW) index and the Normalized Difference Water Index (NDWI). Using regression analysis with estimated shoreline coordinates, the WI detected the shorelines with an accuracy of 98.4%, which was 22.3% higher than the TCW, and 43.2% more accurate than the NDWI. Change detection was derived using image differencing followed by density slicing and unsupervised classification. The saline lakes (Bogoria, Nakuru and Elementaita) changed more with respect to the ratio of the change in the original surface areas than the non‐saline lakes (Baringo and Naivasha).

A water index for rapid mapping of shoreline changes of five East African Rift Valley lakes : an empirical analysis using Landsat TM and ETM+ data

Pothole detection on asphalt pavements from 2D-colour pothole images using fuzzy c-means clustering and morphological reconstruction

The extraction of texture features from high-resolution remote sensing imagery provides a complementary source of data for those applications in which the spectral information is not sufficient for identification or classification of spectrally similar landscape features. This study presents the results of grey-level co-occurrence matrix (GLCM) and wavelet transform (WT) texture analysis for forest and non-forest vegetation types differentiation in QuickBird imagery. Using semivariogram fitting, the optimal GLCM windows for the land cover classes within the scene were determined. These optimal window sizes were then applied to eight GLCM texture measures (mean, variance, homogeneity, dissimilarity, contrast, entropy, angular second moment, and correlation) for the scene classification. Using wavelet transformation, up to five levels of macro-texture were computed and tested in the classification process. Comparing the classification results, (1) the spectral-only bands classification gave an overall accuracy of 58.69%; (2) the statistically derived 21×21 optimal mean texture combined with spectral information gave the best results among the GLCM optimal windows with an accuracy of 73.70%; and (3) the combined optimal WT-texture levels 4 and 5 gave an accuracy of 63.56%. The combined classification of these three optimal results gave an overall accuracy of 77.93%. The results indicate that even though vegetation texture was generally measured better by the GLCM-mean texture (micro-textures) than by WT-derived texture (macro-textures), the results show that the micro-macro texture combination would improve the differentiation and classification of the overall vegetation types. Overall, the results suggests that computer-assisted classification of high-spatial-resolution remotely sensed imagery has a good potential to augment the present ground-based forest inventory methods.

/pdf/analysis-of-co-occurrence-and-discrete-wavelet-transform-2a2h1tpp2f.pdf

Analysis of co-occurrence and discrete wavelet transform textures for differentiation of forest and non-forest vegetation in very-high-resolution optical-sensor imagery

Wavelet-morphology based detection of incipient linear cracks in asphalt pavements from RGB camera imagery and classification using circular Radon transform

Yashon O. Ouma

Papers

Urban Flood Vulnerability and Risk Mapping Using Integrated Multi-Parametric AHP and GIS: Methodological Overview and Case Study Assessment

A water index for rapid mapping of shoreline changes of five East African Rift Valley lakes : an empirical analysis using Landsat TM and ETM+ data

Pothole detection on asphalt pavements from 2D-colour pothole images using fuzzy c-means clustering and morphological reconstruction

Analysis of co-occurrence and discrete wavelet transform textures for differentiation of forest and non-forest vegetation in very-high-resolution optical-sensor imagery

Wavelet-morphology based detection of incipient linear cracks in asphalt pavements from RGB camera imagery and classification using circular Radon transform