Multi-View Geometry Based Visual Perception and Control of Robotic Systems

✍ Scribed by Chen, Jian; Jia, Bingxi; Zhang, Kaixiang

• Publisher: CRC Press
• Year: 2018
• Tongue: English
• Leaves: 361
• Edition: First edition
• Category: Library

✦ Synopsis

"This book describes visual perception and control methods for robotic systems that need to interact with the environment. Multiple view geometry is utilized to extract low-dimensional geometric information from abundant and high-dimensional image information, making it convenient to develop general solutions for robot perception and control tasks. In this book, multiple view geometry is used for geometric modeling and scaled pose estimation. Then Lyapunov methods are applied to design stabilizing control laws in the presence of model uncertainties and multiple constraints."--Provided by publisher. Read more...

Abstract: "This book describes visual perception and control methods for robotic systems that need to interact with the environment. Multiple view geometry is utilized to extract low-dimensional geometric information from abundant and high-dimensional image information, making it convenient to develop general solutions for robot perception and control tasks. In this book, multiple view geometry is used for geometric modeling and scaled pose estimation. Then Lyapunov methods are applied to design stabilizing control laws in the presence of model uncertainties and multiple constraints."--Provided by publisher

✦ Table of Contents

Content: Cover
Half Title
Title Page
Copyright Page
Contents
Preface
Authors
PART I: FOUNDATIONS
1 Robotics
1.1 Pose Representation
1.1.1 Position and Translation
1.1.2 Orientation and Rotation
1.1.3 Homogeneous Pose Transformation
1.2 Motion Representation
1.2.1 Path and Trajectory
1.2.2 Pose Kinematics
1.3 Wheeled Mobile Robot Kinematics
1.3.1 Wheel Kinematic Constraints
1.3.2 Mobile Robot Kinematic Modeling
1.3.3 Typical Nonholonomic Mobile Robot
2 Multiple-View Geometry
2.1 Projective Geometry
2.1.1 Homogeneous Representation of Points and Lines 2.1.2 Projective Transformation2.2 Single-View Geometry
2.2.1 Pinhole Camera Model
2.2.2 Camera Lens Distortion
2.3 Two-View Geometry
2.3.1 Homography for Planar Scenes
2.3.2 Epipolar Geometry for Nonplanar Scenes
2.3.3 General Scenes
2.4 Three-View Geometry
2.4.1 General Trifocal Tensor Model
2.4.2 Pose Estimation with Planar Constraint
2.5 Computation of Multiple-View Geometry
2.5.1 Calibration of Single-View Geometry
2.5.2 Computation of Two-View Geometry
2.5.2.1 Computation of Homography
2.5.2.2 Computation of Epipolar Geometry
2.5.3 Computation of Three-View Geometry 2.5.3.1 Direct Linear Transform2.5.3.2 Matrix Factorization
2.5.4 Robust Approaches
3 Vision-Based Robotic Systems
3.1 System Overview
3.1.1 System Architecture
3.1.2 Physical Configurations
3.2 Research Essentials
PART II: VISUAL PERCEPTION OF ROBOTICS
4 Introduction to Visual Perception
4.1 Road Reconstruction and Detection for Mobile Robots
4.1.1 Previous Works
4.1.2 A Typical Vehicle Vision System
4.1.2.1 System Configuration
4.1.2.2 Two-View Geometry Model
4.1.2.3 Image Warping Model
4.1.2.4 Vehicle-Road Geometric Model
4.1.2.5 More General Configurations 4.2 Motion Estimation of Moving Objects4.3 Scaled Pose Estimation of Mobile Robots
4.3.1 Pose Reconstruction Based on Multiple-View Geometry
4.3.2 Dealing with Field of View Constraints
4.3.2.1 Key Frame Selection
4.3.2.2 Pose Estimation
4.3.3 Dealing with Measuring Uncertainties
4.3.3.1 Robust Image Feature Extraction
4.3.3.2 Robust Observers
4.3.3.3 Robust Controllers
4.3.3.4 Redundant Degrees of Freedom
5 Road Scene 3D Reconstruction
5.1 Introduction
5.2 Algorithm Process
5.3 3D Reconstruction
5.3.1 Image Model
5.3.2 Parameterization of Projective Parallax 5.3.3 Objective Function Definition and Linearization5.3.4 Iterative Maximization
5.3.5 Post Processing
5.4 Road Detection
5.4.1 Road Region Segmentation
5.4.2 Road Region Diffusion
5.5 Experimental Results
5.5.1 Row-Wise Image Registration
5.5.2 Road Reconstruction
5.5.3 Computational Complexity
5.5.4 Evaluation for More Scenarios
6 Recursive Road Detection with Shadows
6.1 Introduction
6.2 Algorithm Process
6.3 Illuminant Invariant Color Space
6.3.1 Imaging Process
6.3.2 Illuminant Invariant Color Space
6.3.3 Practical Issues
6.4 Road Reconstruction Process

✦ Subjects

Robotics;CRC/IHC Default Subject Code;Intelligent Systems;Systems & Controls;ENGnetBASE;ElectricalEngineeringnetBASE;SCI-TECHnetBASE;COMPUTERSCIENCEnetBASE;INFORMATIONSCIENCEnetBASE;STMnetBASE;Neural computers;Linear control systems