book

Hyperspectral Remote Sensing in Urban Environments

Name: Hyperspectral Remote Sensing in Urban Environments
ISBN: 9781000955224

by Shailesh Shankar Deshpande, Arun B. Inamdar

October 2023

Intermediate to advanced

300 pages

10h 4m

English

CRC Press

Read now

Unlock full access

Cover
Half-Title Page
Title Page
Copyright Page
Dedication
Table of Contents
Preface
Acknowledgements
About the Authors
1 Cities Means to Menace?
1.1 Urban Enterprise: Chaos of the People, by the People, for the People!1.1.1 Impact of Urbanization on Water1.1.2 Impact of Urbanization on Air1.2 Urban Sustainability and Systemic View of an Urban Enterprise1.2.1 Urban Systems1.2.2 Measuring Sustainability – Sustainable Development Goals Indicator Framework1.3 Urban Metabolism Model as an Instrument to Reduce Complexity1.3.1 Urban Metabolism Framework Using Remote Sensing1.3.2 Modules of Urban Metabolism Framework1.3.3 Example Remote Sensing Models in Urban Metabolism Framework1.4 Remote Sensing Opportunities1.5 SummaryNotesWorks Cited

2 Introduction to Hyperspectral Imaging
2.1 Hyperspectral Data2.1.1 Definition and Characteristics2.1.2 Some Useful Terms2.1.3 Quantum Mechanical Explanation of Radiation Absorption2.2 Multispectral, Superspectral, Hyperspectral, Ultraspectral2.3 Challenges2.3.1 Coarse Spatial Resolution2.3.2 Increased data size2.3.3 Small Number of Samples and High Dimensions2.3.4 Lack of Unique Spectral Signature2.4 Sensors and Platforms2.4.1 Spaceborne Platforms2.4.2 Airborne Sensors2.4.3 Standard Data Sets for Research2.5 Visual Interpretation of Hyperspectral Images2.5.1 Vegetation2.5.2 Soil2.5.3 Impervious Surfaces (Built-up)2.6 Common Workflow for Hyperspectral Image Processing2.6.1 Convert the Digital Numbers (DN) to Radiances2.6.2 Solar Elevation Angle Correction2.6.3 Convert Radiance to Reflectance2.6.4 Extract the Features2.6.5 Use Supervised or Unsupervised Learning Approach2.6.6 Dissemination2.7 SummaryWorks Cited
3 Reflectance Calibration
3.1 Reflectance Calibration3.1.1 Atmospheric Effects3.2 Physics-based Methods3.2.1 EO-1 Hyperion Equation for Clear Atmosphere3.2.2 Second Simulation of a Satellite Signal in the Solar Spectrum-Vector (6SV)3.2.3 MODerate Resolution Atmospheric TRANsmission (MODTRAN®)3.2.4 Discrete Ordinated Radiative Transfer Code (DISORT)3.3 Image-based Methods3.3.1 Dark Object Subtraction3.3.2 Improved Dark Object Subtraction3.3.3 Improved Dark Object with Overlap Correction3.3.4 IAR and FAR3.4 Empirical Line Method3.5 Simplifying Assumptions and the Methods3.6 Working Example3.6.1 Data3.6.2 Method3.6.3 Experimental Set up for Classification Experiments3.6.4 Results of Image-based Reflectance Calibration Experiments3.6.5 Calibration Performance for IAR and FAR3.6.6 Overall Performance of Physics-based Methods3.6.7 Optimal Flat Field Assessment3.6.8 Summary of the Case Study for Image-based Methods3.7 SummaryWorks Cited
4 Spectral Resources
4.1 Significance of Spectral Resources4.2 Spectral Libraries4.2.1 USGS Digital Spectral Library – Version 7.04.2.2 ECOSTRESS Spectral Library – Version 1.04.2.3 JPL Library4.2.4 Tarang – Spectral Library of Indian Urban Materials4.3 Analysis Methods4.3.1 Basic Statistics4.3.2 The Bhattacharyya distance analysis for urban classes4.3.3 Most Significant Wavelength Span: Fine Granularity4.3.4 Most Significant Span: Coarse Granularity (VNIR vs SWIR)4.3.5 Chromatic Properties of the Urban Materials4.4 Spectral Analysis4.4.1 Spectral Properties of Various Urban Materials4.4.2 The Bhattacharyya Distance Analysis for Urban Classes4.4.2.1 B-distances for Broader Urban Classes4.4.2.2 Bhattacharyya Distances for Cement Composites and Metal Roofs4.4.5 Most Significant Wavelengths for Discrimination of Urban Classes4.4.6 Most Optimal Span and Important Wavelengths for Urban Material at Intra-class Level for a Few Important Classes Such as Cement Composites and Metal Roofs4.4.7 Chromatic Properties4.5 Tarang – The Spectral Library and Web Services4.5.1 Tarang Components4.5.2 Using a Spectral Library4.6 Spectral Characteristics of Urban Materials4.6.1 Park City and Santa Barbara/Goleta Observations4.6.2 Tarang Observations4.6.3 Significant Bands for Urban Materials4.7 SummaryNoteWorks Cited
5 Classification of Urban Land Use and Land Cover
5.1 Introduction5.1.1 Classification5.1.2 Hyperspectral Image Classification5.1.3 Mathematical Preliminaries5.1.4 Features for Hyperspectral Image Classification5.1.5 Urban Land Cover and Land Use5.2 Classification with Urban Indices5.2.1 Useful Properties of Urban Materials for Developing Indices5.2.2 Various Urban Indices5.3 Nearest Neighbour Classification5.3.1 Spectral Angel or Cosine Similarity5.3.2 Normalized Spectral Similarity Score (NS3)5.3.3 Hamming Distance5.3.4 Cross Correlogram Spectral Matching (CCSM)5.4 Maximum Likelihood Classifier5.5 Economic Zone Classification5.5.1 Study Area5.5.2 Hyperspectral Data5.5.3 Semi-supervised Learning Background5.5.4 Experimental Setup5.5.5 Results of Land Use Analysis Using Proxy Features5.6 Advanced Machine Learning Methods Such as Deep Learning5.6.1 Understanding 1D, 2D, and 3D Convolutions5.6.2 Deep Learning for Hyperspectral Images5.6.3 Spectral, Spatial, and Spectral-Spatial Neural Networks5.7 Performance Evaluation of Various Classifiers on Benchmark Datasets5.8 Explaining Convolutional Spectral Features5.8.1 Capsule Net5.9 SummaryNotesWorks Cited
6 Appendix
6.1 Summary of Important Work in Hyperspectral Remote Sensing of Urban Areas6.2 Hyperion Top of the Atmosphere Irradiance (Wavelength in nm; Irradiance in W m-2 µm-1)6.3 The Book Code Help6.3.1 Code Components6.3.2 Main Calibration Script6.3.3 Deep Learning ModelsWorks Cited
Index

Overview

This book is intended to provide a detailed perspective on techniques and challenges in detecting the urban materials using hyperspectral data including systematic perspective on spectral properties of the materials and methods. It provides in depth information on hyperspectral remote sensing of urban materials including global case studies.

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781000955224

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills