Shailesh Deshpande

Animating Maps: Visual Analytics Meets GeoWeb 2.0

Improved visualization techniques for spatiotemporal data have potential to reveal interesting insights from GIS data. Thus, visual analytics has captured the attention of GIS researchers in the recent past. Furthermore, developments in free tools, such as Google Map API and OpenStreetMap, provide easy access to geospatial data that can be leveraged by visual analytics. In this chapter, we propose such a system that utilizes free GIS APIs to visualize spatiotemporal data effectively. Our application allows a user to create a time slide bar control to connect time and position of various GIS objects on a map and to display them in animated mode. This control can handle vector and raster data with equal ease. The resulting effective visualization makes it is very easy to understand some complex spatiotemporal patterns, as exemplified in this chapter.

Assessment of optimal flat field in urban environment for EO1-hyperion scene

In this paper, we suggest optimal flat fields for calibration of hyperspectral data (EO1) — predominantly of urban nature. We compare the suitability of various flat field candidates by performing vegetation, soil, and impervious surface (VIS) classification. Flat Field methods provide 90% average overall accuracy (with best 100% and 77% worst accuracies) over number of conducted experiments. Flat fields show marginal improvement over IAR. Most common urban land covers such as play grounds, concrete parking lots, and especially industrial roof covers have been found adequate for the image calibration.

Overview of Hyperspectral Remote Sensing of Impervious Surfaces in Urban Environment

In this paper we provide a concise overview of hyperspectral studies of impervious surface in urban environment. We highlight socio-ecological impact of urban conglomerate on the surroundings. We present few important techniques of material detection using spectral matching methods - a unique opportunity provided by hyperspectral data. The paper then discusses signatures of urban materials and reviews how various investigators have utilized hyperspectral data to study impervious surface in urban area.

CogVis: attention-driven cognitive architecture for visual change detection

The role played by attention in the increasingly important area of change detection is well recognized. The construction of automated visual change detection systems will benefit from an architecture based on sound cognitive principles. This paper proposes an attention-driven cognitive vision architecture for change detection and shows its utility with a remote sensing case study.

Comparison of internal area relative reflectance and 6SV reflectance calibration for impervious surface detection

Objective of this research is to compare performance of the Internal Areal Relative Reflectance (IAR), and Second Simulation of a Satellite Signal in the Solar Spectrum (6SV) surface calibration methods for discriminating impervious surfaces in urban settings. We used EO1-Hyperion image of Pune city recorded on April 2013. We converted the radiance values to reflectance using IAR and 6SV and then classified image in to Vegetation, Impervious surface, and Soil (VIS) classes. Preliminary results indicated that 6SV does not provide any advantages over IAR. Average overall accuracy of classification over 8 different experiments was increased by ∼1% for IAR.

Assessment of anticipated runoff because of impervious surface increase in Pune Urban Catchments, India: a remote sensing approach

Unbalanced economic growth of cities in developing countries in recent past has affected urban environment adversely. Rapid urbanization has led to increase in the impervious surface within urban landscape. Further, this increase is associated with partial or complete loss of natural drainage in urban catchment area. This paper presents anticipated increase in runoff within a urban catchment area of Pune-Pimpri-Chinchwad Municipal Corporation (PPCMC), India due to increase in the impervious surface over a decade. We used Landsat 7 images from 2001-2014 for detecting impervious surfaces within the region. Supervised classification of the area was done using Support Vector Machine (SVM). Digital Elevation Image (DEM) is acquired from CARTOSAT-1 for analysis of various catchment basins present in region. Finally we calculated runoff for 2001 and 2014 using rational flow equation. The comparison of 2001 and 2014 for PPCMC indicates increase in urban runoff by 87.8 percent just because of increase in impervious surface.

Chromatic discrimination of impervious surfaces using artificial colors for hyper spectral data

Extending color vision principles to display hyperspectral data has been investigated by researchers in recent past. However, color obtained by this approach (artificial color) is not used comprehensively for discriminating different materials. Especially, some of the interesting artificial color properties could be used effectively in this regard. We investigate such a case of impervious surfaces. Our hypothesis is: artificial color of impervious surfaces would be grey because of its spectral blandness over 350–2500 nm range. We investigate our hypothesis by performing chromatic discrimination analysis using artificial color of variety of urban materials. We use field spectra recorded by spectrometer, and spectra extracted from EO1-Hyperion image. Further, we filter these spectra by stretched CIE 1964 color matching functions to provide an artificial color to it. Analysis confirms our observations about the artificial color properties of impervious surfaces. Further it shows potential of artificial color to discriminate sub classes of impervious surfaces.