Atjaunināt sīkdatņu piekrišanu

E-grāmata: Building Feature Extraction with Machine Learning: Geospatial Applications [Taylor & Francis e-book]

,
  • Formāts: 128 pages, 18 Tables, black and white; 6 Line drawings, color; 11 Line drawings, black and white; 21 Halftones, color; 15 Halftones, black and white; 53 Illustrations, color
  • Izdošanas datums: 29-Dec-2022
  • Izdevniecība: CRC Press
  • ISBN-13: 9781003288046
Citas grāmatas par šo tēmu:
  • Taylor & Francis e-book
  • Cena: 120,07 €*
  • * this price gives unlimited concurrent access for unlimited time
  • Standarta cena: 171,52 €
  • Ietaupiet 30%
Building Feature Extraction with Machine Learning: Geospatial ApplicationsPalielināt
  • Formāts: 128 pages, 18 Tables, black and white; 6 Line drawings, color; 11 Line drawings, black and white; 21 Halftones, color; 15 Halftones, black and white; 53 Illustrations, color
  • Izdošanas datums: 29-Dec-2022
  • Izdevniecība: CRC Press
  • ISBN-13: 9781003288046
Citas grāmatas par šo tēmu:
Taylor & Francis e-booksMore info about Taylor & Francis e-books
Rokasgrāmatas mājas lapa: https://www.taylorfrancis.com/books/9781003288046
Big geospatial datasets created by large infrastructure projects require massive computing resources to process. Feature extraction is a process used to reduce the initial set of raw data for manageable image processing, and machine learning (ML) is the science that supports it. This book focuses on feature extraction methods for optical geospatial data using ML. It is a practical guide for professionals and graduate students who are starting a career in information extraction. It explains spatial feature extraction in an easy-to-understand way and includes real case studies on how to collect height values for spatial features, how to develop 3D models in a map context, and others.

Features





Provides the basics of feature extraction methods and applications along with the fundamentals of machine learning Discusses in detail the application of machine learning techniques in geospatial building feature extraction Explains the methods for estimating object height from optical satellite remote sensing images using Python Includes case studies that demonstrate the use of machine learning models for building footprint extraction and photogrammetric methods for height assessment Highlights the potential of machine learning and geospatial technology for future project developments

This book will be of interest to professionals, researchers, and graduate students in geoscience and earth observation, machine learning and data science, civil engineers, and urban planners.
Preface xi
Acknowledgements xiii
Authors xv
Chapter 1 Introduction
1(8)
1.1 Geospatial Technologies
1(1)
1.2 Feature Extraction
2(1)
1.3 Geospatial Machine Learning
3(2)
1.4 Height Estimation
5(1)
1.5 Three-Dimensional Mapping
6(3)
References
7(2)
Chapter 2 Geospatial Big Data for Machine Learning
9(24)
2.1 Geospatial Big Data
9(2)
2.2 Machine Learning Framework for Geospatial Big Data
11(2)
2.3 Data Sources
13(5)
2.3.1 USGS - NASA's Mission
13(2)
2.3.2 Copernicus Missions
15(1)
2.3.3 ISRO Missions
16(1)
2.3.4 Other Missions
17(1)
2.4 The Challenge with EO Data
18(1)
2.5 GeoAI Platforms
18(2)
2.6 Choosing the Right Data
20(13)
References
27(6)
Chapter 3 Spatial Feature Extraction
33(34)
3.1 Feature Extraction
33(1)
3.2 Machine Learning Models
33(15)
3.2.1 Maximum Likelihood Classifiers
34(1)
3.2.2 Random Forest
35(1)
3.2.3 Naive Bayes
36(2)
3.2.4 The SVM
38(3)
3.2.5 Neural Networks
41(3)
3.2.6 Convolutional Neural Networks
44(4)
3.3 Deep Learning Architecture
48(3)
3.4 Model Architecture
51(3)
3.4.1 Loss Function
52(1)
3.4.2 Data Augmentation
53(1)
3.4.3 Hyperparameters
53(1)
3.4.4 Data Normalization
54(1)
3.4.5 Transfer Learning
54(1)
3.5 Methods
54(4)
3.5.1 Image Pre-Processing
55(1)
3.5.2 Model Training
55(1)
3.5.3 Post-Processing
56(1)
3.5.4 Accuracy Evaluation
56(2)
3.6 Findings and Conclusions
58(9)
References
61(6)
Chapter 4 Building Height Estimation
67(16)
4.1 Significance of Building Height
67(1)
4.2 Background
68(2)
4.3 Estimation of Height from Stereo Satellite Images
70(6)
4.3.1 Stereo Satellite Images
71(1)
4.3.2 Surface Model Preparation
72(1)
4.3.3 DSM Quality Evaluation
73(1)
4.3.4 Preparation of a Terrain Model
74(1)
4.3.4.1 MDS Filtering
74(1)
4.3.4.2 Grid-Based Method
74(1)
4.3.4.3 Interpolation
75(1)
4.3.4.4 Slope-Based Filter
75(1)
4.3.4.5 Road Buffers
75(1)
4.4 Estimating the Height of a Building
76(1)
4.4.1 DTM Method
76(1)
4.4.2 Buffer Polygons
76(1)
4.5 Height Estimations and Quality Evaluation
77(2)
4.5.1 DSM Quality Evaluation
77(1)
4.5.2 DTM Quality Evaluation
78(1)
4.5.3 Building Height Values
78(1)
4.6 Future Scope of Height Estimations
79(4)
References
80(3)
Chapter 5 3D Feature Mapping
83(16)
5.1 3D Mapping from Geospatial Data
83(1)
5.2 History of 3D Mapping
84(1)
5.3 Data Standards and Interoperability
85(3)
5.4 Data Sources for 3D Mapping
88(1)
5.5 Software Tools for 3D Mapping
89(1)
5.6 Experiments
90(9)
References
93(6)
Chapter 6 Application Use Cases
99(26)
6.1 Potential Applications
99(1)
6.2 Case Study #1: Urban Structure Extraction - An Indian Context
100(6)
6.2.1 Study Area
102(1)
6.2.2 Datasets
103(1)
6.2.3 Method
104(1)
6.2.4 Results and Conclusions
104(2)
6.3 Case Study #2: Rooftop Solar Potential Estimation
106(9)
6.3.1 Solar Radiation
107(2)
6.3.2 UAV or Drone-Captured Imagery
109(1)
6.3.3 Building Roof Extraction
110(1)
6.3.4 Shadow Removal
110(2)
6.3.5 Energy Estimations
112(3)
6.4 Case Study #3: Assessment of Urban Built-Up Volume
115(10)
6.4.1 Study Area and Datasets
116(1)
6.4.2 Method
116(1)
6.4.3 DSM Generation
117(2)
6.4.4 Built-Up Area Extraction
119(1)
6.4.5 Built-Up Volume Estimation
120(1)
6.4.6 Inference and Conclusions
121(1)
References
122(3)
Index 125
Dr. Bharath H. Aithal, is currently an assistant professor at Ranbir and Chitra Gupta School of Infrastructure Design and Management at Indian Institute of Technology Kharagpur. He obtained his Ph.D. from Indian Institute of Science. His areas of interest are spatial pattern analysis, Urban growth modelling, natural disasters, geoinformatics, landscape modelling, urban planning, open-source GIS, and digital image processing. He has published over 50 research papers in reputed peer reviewed journals and has presented over 100 papers in international and national conferences and symposiums. In 2020 he published with CRC Press, Urban Growth Patterns in India: Spatial Analysis for Sustainable Development and has contributed 6 book chapters to other publications.

Dr. Prakash P.S. is a postdoctoral researcher at Irish Centre of High-End Computing, Galway, Ireland, working on geo-spatial technologies. Prakash has substantial experience with earth observation datasets, including remote sensing, drone-based imagery, surveying, spatial libraries, machine learning, and artificial intelligence technologies. He has worked in geospatial technology and the renewable energy industry for over four years. His other qualifications include a Master of Technology in Geoinformatics from Bangalore's Karnataka State Remote Sensing Application Center and a Bachelor of Civil Engineering from Bangalore's Rashtreeya Vidyalaya College of Engineering.
Permanent link: https://www.kriso.lv/db/9781003288046_pe.html
Keywords: