book

Urban High-Resolution Remote Sensing

Name: Urban High-Resolution Remote Sensing
Author: Guoqing Zhou
ISBN: 9781000287714

by Guoqing Zhou

December 2020

Intermediate to advanced

368 pages

12h 25m

English

CRC Press

Read now

Unlock full access

Cover
Half Title
Title Page
Copyright Page
Table of Contents
Foreword
Preface
Acknowledgments
A Note on the Author
List of Abbreviations

Section I: Introduction
Chapter 1: Introduction
1.1 What Is Urban Remote Sensing?1.2 Simple Overview of the History of Urban Remote Sensing1.3 Journals Relevant to Urban Remote Sensing1.4 About This BookReferences
Chapter 2: Urban Remote Sensing and Urban Studies
2.1 Characteristics of Urban Remote Sensing2.2 Studies on Urban Remote Sensing2.2.1 Architecture of Urban Remote Sensing2.2.2 Topics of Studies on Urban Remote SensingReferences
Chapter 3: Advances in Urban Remote Sensing
3.1 Urban Remote Sensing Big Data3.2 Characteristics of Urban Remote Sensing Big Data3.3 Challenges in Urban Remotely Sensed Big Data Processing3.3.1 Storage and Management of Urban Remote Sensing Big Data3.3.2 Processing of Urban Remote Sensing Big Data3.4 Challenges of Urban Remote Sensing Big Data3.5 Intelligent Earth Observing Satellite System for Urban Remote Sensing3.5.1 Change in Users’ Need from Image-Based Product to Image‑Based Information/Knowledge3.5.2 Intelligent Earth Observing Satellite System for Urban Remote SensingReferences
Section II: Information Extroduction
Chapter 4: Urban 3D Surface Information Extraction from Aerial Image Sequences
4.1 Introduction4.2 Principle of Temporal and Spatial Analysis4.3 Geometric Rectification of Image Sequences4.4 Experiments in Spatio-Temporal Analysis4.4.1 Image Data Processing4.4.2 Sensitivity to Occlusion4.4.3 Rectification of Distorted Image Sequence Data4.4.4 DEM Generation4.5 Error Analysis4.6 System Development4.7 ConclusionsAppendix AAppendix BReferences
Chapter 5: Urban 3D Surface Information Extraction from Linear Pushbroom Stereo Imagery
5.1 Introduction5.2 Linear Array Stereo Imaging Principle with Pushbroom Scanning Technique5.2.1 Basic Principle of Linear Array Stereo Imaging System5.2.2 Three Typical Linear Array Stereo Imaging Systems5.3 Mathematical Model of 3D Ground Coordinates from Linear Array Stereo Imaging System5.3.1 Coordinate Systems5.3.2 Interior Orientation5.3.3 Transformation from Image to Reference Coordinate System5.3.4 Collinearity Equations5.3.5 Navigation Data as Exterior Orientation Parameters5.3.6 Observation Equations5.3.7 Adjustment Computation5.4 Test Field Establishment5.4.1 The High-Altitude Test Range – the First Test Field5.4.2 The Test Field 1185 – The Second Test Field5.5 Image Simulation of Satellite IKONOS5.5.1 Simulation of IKONOS Imaging5.5.2 The Brightness on Satellite Imagery5.5.3 Error Analysis5.6 Potential Accuracy Attainable for Ground Points of IKONOS5.6.1 Accuracy Assessment Based on the First Test Field5.6.2 Accuracy Assessment Based on the Second Test Field5.7 Airborne HRSC and Space Shuttle MOMS-2P Three-Line Sensor5.7.1 Data Processing and Accuracy Evaluation for HRSC Imaging Data5.7.2 Data Processing and Accuracy Evaluation for MOMS-2P5.8 ConclusionsReferences
Chapter 6: Urban 3D Building Extraction Through LiDAR and Aerial Imagery
6.1 Introduction6.2 Principle of Aspect Code and Creation of Aspect Code Database6.2.1 Selection of the 3D Primitives (Houses)6.2.2 Creation of 2D Aspects6.2.3 Coding Regulation for Aspect6.2.4 Coding Regulation for Aspect Merging6.2.5 Discussion of the Proposed Coding Regulation6.2.6 Creation of Aspect Graphs6.2.7 Creation of Aspect Codes Database6.3 Experiments and Analyses6.3.1 Data Set6.3.2 Preprocessing of Aerial Imagery6.3.3 Creation of Aspect Graphs and Extraction of Houses6.3.4 Occlusion Analysis6.3.5 Comparison Analysis6.4 ConclusionsReferences
Chapter 7: Urban 3D Building Extraction from LiDAR and Orthoimages
7.1 Introduction7.2 Building Detection and Extraction7.2.1 Edge Detection from Orthoimage7.2.2 Image Interpretation and Building Extraction7.3 Digitally Modeling Buildings7.4 Creation of Digital Surface Model (DSM)7.4.1 Establish the Relationship Between Images and LiDAR Point Cloud Data7.4.2 Interpolation Algorithm via Planar Equation7.5 Creation of Digital Terrain Model (DTM)7.6 Experiments7.6.1 Data Set7.6.1.1 LiDAR Data7.6.1.2 Aerial Image Data7.6.2 System Development7.7 ConclusionsReferences
Chapter 8: Vehicle Extraction from High-Resolution Aerial Images
8.1 Introduction8.2 Vehicle Detection from Aerial Imagery8.2.1 Structure Element Identification8.2.2 Gray-Scale Morphological Method8.2.3 Background Estimation8.2.4 Vehicle Detection8.3 Experiments and Discussion8.3.1 Data Set8.3.2 Vehicle Extraction Results8.3.3 Discussion8.4 ConclusionsReferences
Chapter 9: Single Tree Canopy Extraction from LiDAR Point Cloud Data
9.1 Introduction9.2 K-Means Clustering Watershed Algorithm9.2.1 K-Means Clustering9.2.2 Watershed Segmentation Combining with K-means Clustering9.3 Validation and Analysis9.3.1 Study Area9.3.2 Data Preprocessing9.3.2.1 Point Cloud Filtering9.3.2.2 Generation of CHM9.3.3 Treetop Detection9.3.4 Accuracy Assessment and Comparison Analysis9.4 ConclusionsReferences
Chapter 10: Power Lines Extraction from Aerial Images
10.1 Introduction10.2 Power Line Extraction Method10.2.1 Imaged Properties of Power Lines10.2.1.1 Line Detector Mask10.2.1.2 Ratio Line Detector10.2.2 Power Line Pixel Detection10.2.3 Line Segments Detecting and Grouping10.2.3.1 Radon Transform10.2.3.2 Line Segments Grouping10.2.4 Kalman Filter to Track Line10.2.5 Other Cases10.3 Experimental Results and Analysis10.3.1 Experimental Results10.3.2 Discussion10.4 ConclusionsReferences
Section III: Urban Orthophotomap Generation
Chapter 11: The Basic Principle of Urban True Orthophotomap Generation
11.1 Introduction11.2 Principle of Urban True Orthoimage Map Generation11.2.1 Basic Steps of True Orthoimage Map Generation11.2.2 DBM-Based Orthoimage Map Generation and Occlusion Detection11.2.3 DTM-Based Orthoimage Map Generation11.2.4 Near True Orthoimage Map Generation11.2.5 Occlusion Compensation11.3 Experiments and Analyses11.3.1 Data Set11.3.2 Shadow Detection and Restoration11.3.3 Occlusion Detection and Compensation11.3.4 Radiometric Balancing11.3.5 True Orthoimage Map (TOM) Generation11.4 ConclusionsReferences
Chapter 12: Orthophotomap Creation with Extremely High Buildings
12.1 Introduction12.2 Relative Constraint for Orthorectification12.2.1 Traditional Orthorectification Model12.2.2 Perpendicular Control Condition12.2.3 Collinear Constraint Condition12.3 Experiments and Analyses12.3.1 Experimental Data12.3.2 Control Information12.3.3 Constraint Line Extraction12.3.4 Accurate Comparison12.4 ConclusionReferences
Chapter 13: Near Real-Time Orthophotomap Generation from UAV Video
13.1 Introduction13.2 Mathematical Model of Georeferencing13.2.1 Calibration of Video Camera13.2.2 Determination of the Offset Between GPS Antenna and Camera13.2.3 Solution of Kinematic GPS Errors13.2.4 Estimation of Boresight Matrix13.3 Georectification of Video Stream13.3.1 Determination of Orthorectified Image Size13.3.2 Orthorectification13.3.3 Mosaicking13.4 Experiments and Analysis13.4.1 Experimental Field Establishment13.4.2 UAV System13.4.3 Data Collection13.4.4 Bundle Adjustment of Video13.4.5 Orthorectification and Accuracy Analysis13.5 ConclusionsReferences
Chapter 14: Orthophotomap Generation from Satellite Imagery Without Camera Parameters
14.1 Introduction14.2 The Second Order Polynomial Equation-Based Rectification Model Method14.2.1 Polynomial Equation-Based Block Adjustment Model14.2.2 Orthorectification of DISP Images14.2.3 Data Set14.3 Results and Accuracy Analysis14.3.1 Image Preprocessing14.3.2 DISP Image Orthorectification and Accuracy Analysis14.3.2.1 DISP Image Orthorectification14.3.2.2 Accuracy Comparison Analysis14.3.3 Image Mosaicking14.3.4 Radiance Balance14.3.5 Mosaicking Result and Accuracy Evaluation14.4 Discussions14.5 ConclusionsReferences
Chapter 15: Building Occlusion Detection in an Urban True Orthophotomap
15.1 Introduction15.2 The Principle of Building Occlusion Detection from Ghost Images15.2.1 The Relationship Between Building Occlusion and Ghost Images15.2.2 The Methodologies for Two Typical Cases15.2.2.1 Buildings Occluding the Ground15.2.2.2 Building Occluding Other Buildings15.3 Experimental Results and Analysis15.3.1 Experimental Data Set15.3.1.1 Experimental Results and Analysis15.3.1.2 Accuracy Comparison15.3.1.3 Occlusion Compensation for True Orthophotomap Generation15.4 ConclusionsReferences
Section IV: Advanced Algorithms Urban Remote Sensing Application
Chapter 16: Hierarchical Spatial Features Learning for Image Classification
16.1 Introduction16.2 The Basic Principle of HCNNs16.2.1 Image Pyramid Product16.2.2 Pixel-Level HSFS Extraction16.3 Experiments and Analysis16.3.1 Environmental Variables16.3.2 Tract Morphological Pattern16.3.3 Parameters16.3.4 Pyramid Images Production for Training the HCNNs16.3.5 Structure Details of HCNNs16.3.6 HSFS Extraction16.3.7 Results of Classification16.4 Discovery of Relationship Between UHI and Various Variables16.4.1 The Relationship Between LST and Environmental and Social Variables16.4.2 The Relationship Between LST and Urban Landscape Metrics16.5 ConclusionsReferences
Chapter 17: Surface Soil Moisture Retrieval from CBERS‑02B Satellite Imagery
17.1 Introduction17.2 Model for SSM Retrieval from CBERS-02B Imagery17.2.1 SSM Retrieval Model of Landsat TM Image17.2.2 Spectral Radiance Relationships Between Landsat TM and CBERS-02B Images17.2.3 Average Spectral Reflectance17.2.4 Average Atmospheric Transmittance17.2.5 Average Solar Radiance17.2.6 SSM Model for Retrieval from CBERS-02B Image17.2.7 Accuracy Evaluation Method17.3 Experiment and Analysis17.3.1 Test Area and Data17.3.2 Image Preprocessing17.3.3 SSM Retrieval and Analysis17.4 ConclusionsReferences
Chapter 18: Measuring Control Delay at Signalized Intersections Using GPS and Video Flow
18.1 Introduction18.2 Model for Calculating the Control Delay18.3 Travel Time Data Collection18.3.1 RTK GPS Technology18.3.2 GPS Test Car Configuration18.3.3 Field Data Collection18.3.4 Data Preprocessing18.4 Delay Measures with GPS at Signalized Intersections18.4.1 Video Data Resampling18.4.2 Interpolation for Video Recorded GPS Test Car18.4.3 Interpolation for Other Video Recorded Vehicles18.4.3.1 Multi-Vehicle Tracking18.4.3.2 Interpolation of Vehicle Position18.4.3.3 Extraction of Control Time Delay18.4.4 Comparison of GPS-Measured and Manually Measured Stopped-Time Delays18.5 ConclusionsReferences
Chapter 19: Measurement of Dry Asphalt Road Surface Friction Using Hyperspectral Images
19.1 Introduction19.2 Study Area and Data Set19.2.1 Study Area19.2.2 Data Set19.2.2.1 Road Condition Data19.2.2.2 Spectral Library19.2.2.3 Remote Sensing Data19.3 Road Texture and Spectral Image Properties19.3.1 Road Texture and Friction19.3.2 Hyperspectral Images and Road Friction19.3.2.1 Spectral Properties of Asphalt Aging19.3.2.2 Spectral Properties of Typical Asphalt Road Distresses19.3.2.3 Spectral Properties of Asphalt Paint19.4 Measurement and Mapping of Skid Resistance19.4.1 Relationship Between PCI and Friction Coefficient19.4.2 Modeling the Relationship Between Spectral Reflectance and Skid Resistance19.4.3 Validation of Established Model19.5 ConclusionsReferences
Index

Content preview from Urban High-Resolution Remote Sensing

16Hierarchical Spatial Features Learning for Image Classification

Very high resolution (VHR) remotely sensed (RS) images are widely available because of the fast development of advanced remote sensing technology. As the VHR RS images contain abundant ground information at pixel-level, they have therefore attracted end users’ attention to their application in urban mapping, precision agriculture, forest monitoring, and so on. However, the traditional RS image classification methods depending only on spectral information have been demonstrated to be inadequate (Dell’Acqua et al. 2004). On the one hand, the VHR RS image classification suffers from uncertainty of spectral information due to the low intra-class variance and ...

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: 9781000287714

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Urban High-Resolution Remote Sensing

by Guoqing Zhou

16Hierarchical Spatial Features Learning for Image Classification

16.1Introduction

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.