Building Feature Extraction with Machine Learning: Geospatial Applications

✍ Scribed by Bharath H. Aithal, Prakash P.S.

• Publisher: CRC Press
• Year: 2022
• Tongue: English
• Leaves: 145
• Category: Library

✦ Synopsis

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.

✦ Table of Contents

Cover
Half Title
Title Page
Copyright Page
Dedication
Contents
Preface
Acknowledgements
Author Biographies
1. Introduction
1.1 Geospatial technologies
1.2 Feature extraction
1.3 Geospatial machine learning
1.4 Height estimation
1.5 Three-dimensional mapping
References
2. Geospatial Big Data for Machine Learning
2.1 Geospatial big data
2.2 Machine learning framework for geospatial big data
2.3 Data sources
2.3.1 USGS - NASA's Mission
2.3.2 Copernicus Missions
2.3.3 ISRO Missions
2.3.4 Other Missions
2.4 The challenge with EO data
2.5 GeoAI platforms
2.6 Choosing the right data
References
3. Spatial Feature Extraction
3.1 Feature extraction
3.2 Machine learning models
3.2.1 Maximum Likelihood Classifiers
3.2.2 Random Forest
3.2.3 Naïve Bayes
3.2.4 The SVM
3.2.5 Neural Networks
3.2.6 Convolutional Neural Networks
3.3 Deep learning architecture
3.4 Model architecture
3.4.1 Loss Function
3.4.2 Data Augmentation
3.4.3 Hyperparameters
3.4.4 Data Normalization
3.4.5 Transfer Learning
3.5 Methods
3.5.1 Image Pre-Processing
3.5.2 Model Training
3.5.3 Post-processing
3.5.4 Accuracy Evaluation
3.6 Findings and conclusions
References
4. Building Height Estimation
4.1 Significance of building height
4.2 Background
4.3 Estimation of height from stereo satellite images
4.3.1 Stereo Satellite Images
4.3.2 Surface Model Preparation
4.3.3 DSM Quality Evaluation
4.3.4 Preparation of a Terrain Model
4.3.4.1 MDS Filtering
4.3.4.2 Grid-Based Method
4.3.4.3 Interpolation
4.3.4.4 Slope-Based Filter
4.3.4.5 Road Buffers
4.4 Estimating the height of a building
4.4.1 DTM Method
4.4.2 Buffer Polygons
4.5 Height estimations and quality evaluation
4.5.1 DSM Quality Evaluation
4.5.2 DTM Quality Evaluation
4.5.3 Building Height Values
4.6 Future scope of height estimations
References
5. 3D Feature Mapping
5.1 3D mapping from geospatial data
5.2 History of 3D mapping
5.3 Data standards and interoperability
5.4 Data sources for 3D mapping
5.5 Software tools for 3D mapping
5.6 Experiments
References
6. Application Use Cases
6.1 Potential applications
6.2 Case study #1: Urban structure extraction - An Indian context
6.2.1 Study Area
6.2.2 Datasets
6.2.3 Method
6.2.4 Results and Conclusions
6.3 Case study #2: Rooftop solar potential estimation
6.3.1 Solar Radiation
6.3.2 UAV or Drone-Captured Imagery
6.3.3 Building Roof Extraction
6.3.4 Shadow Removal
6.3.5 Energy Estimations
6.4 Case study #3: Assessment of urban built-up volume
6.4.1 Study Area and Datasets
6.4.2 Method
6.4.3 DSM Generation
6.4.4 Built-Up Area Extraction
6.4.5 Built-Up Volume Estimation
6.4.6 Inference and Conclusions
References
Index