Available:*
Library | Item Barcode | Call Number | Material Type | Item Category 1 | Status |
---|---|---|---|---|---|
Searching... | 30000010184480 | TA1634 A37 2008 | Open Access Book | Book | Searching... |
Searching... | 30000003500869 | TA1634 A37 2008 | Open Access Book | Book | Searching... |
On Order
Summary
Summary
An active robot system can change its visual parameters in an intentional manner and perform its sensing actions purposefully. A general vision task thus can be performed in an efficient way by means of strategic control of the perception process. The controllable processes include 3D active sensing, sensor configuration and recalibration, automatic sensor placement, and 3D sensing. This book explores these important issues in studying for active visual perception.
Vision sensors have limited fields of views and can only "see" a portion of a scene from a single viewpoint. To make the entire object visible, the sensor has to be moved from one place to another around the object to observe all features of interest. The sensor planning presented in this book describes an effective strategy to generate a sequence of viewing poses and sensor settings for optimally completing a perception task. Several methods are proposed to solve the problems in both model-based and nonmodel-based vision tasks. For model-based applications, the method involves determination of the optimal sensor placements and a shortest path through these viewpoints for automatic generation of a perception plan. A topology of viewpoints is achieved by a genetic algorithm in which a min-max criterion is used for evaluation. A shortest path is also determined by graph algorithms. For nonmodel-based applications, the method involves determination of the best next view and sensor settings. The trend surface is proposed as the cue to predict the unknown portion of an object or environment.
The 11 chapters in Active Vision Planning draw on recent work in robot vision over ten years, particularly in the use of new concepts of active sensing, reconfiguration, recalibration, sensor model, sensing constraints, sensing evaluation, viewpoint decision, sensor placement graph, model based planning, path planning, planning for robot in unknown environment, dynamic 3D construction,surface prediction, etc. Implementation examples are also provided with theoretical methods for testing in a real robot system. With these optimal sensor planning strategies, this book will give the robot vision system the adaptability needed in many practical applications.
Table of Contents
Preface | p. V |
Chapter 1 Introduction | p. 1 |
1.1 Motivations | p. 1 |
1.1.1 The Tasks | p. 1 |
1.1.2 From a Biological View | p. 3 |
1.1.3 The Problems and Goals | p. 4 |
1.1.4 Significance and Applications | p. 6 |
1.2 Objectives and Solutions | p. 7 |
1.3 Book Structure | p. 8 |
Chapter 2 Active Vision Sensors | p. 11 |
2.1 3D Visual Sensing by Machine Vision | p. 11 |
2.1.1 Passive Visual Sensing | p. 11 |
2.1.2 Active Visual Sensing | p. 14 |
2.2 3D Sensing by Stereo Vision Sensors | p. 19 |
2.2.1 Setup with Two Cameras | p. 19 |
2.2.2 Projection Geometry | p. 20 |
2.2.3 3D Measurement Principle | p. 21 |
2.3 3D Sensing by Stripe Light Vision Sensors | p. 23 |
2.3.1 Setup with a Switchable Line Projector | p. 23 |
2.3.2 Coding Method | p. 24 |
2.3.3 Measurement Principle | p. 25 |
2.4 3D Sensor Reconfiguration and Recalibration | p. 27 |
2.4.1 The Motivation for Sensor Reconfiguration and Recalibration | p. 28 |
2.4.2 Setup of a Reconfigurable System | p. 29 |
2.4.3 Geometrical Constraint | p. 33 |
2.4.4 Rectification of Stripe Locations | p. 34 |
2.4.5 Solution Using the Geometrical Cue | p. 35 |
2.5 Summary | p. 38 |
Chapter 3 Active Sensor Planning - the State-of-the-Art | p. 39 |
3.1 The Problem | p. 39 |
3.2 Overview of the Recent Development | p. 40 |
3.3 Fundamentals of Sensor Modeling and Planning | p. 43 |
3.4 Planning for Dimensional Inspection | p. 48 |
3.5 Planning for Recognition and Search | p. 51 |
3.6 Planning for Exploration, Navigation, and Tracking | p. 54 |
3.7 Planning for Assembly and Disassembly | p. 59 |
3.8 Planning with Illumination | p. 60 |
3.9 Other Planning Tasks | p. 63 |
3.9.1 Interactive Sensor Planning | p. 63 |
3.9.2 Placement for Virtual Reality | p. 64 |
3.9.3 Robot Localization | p. 64 |
3.9.4 Attention and Gaze | p. 65 |
3.10 Summary | p. 66 |
Chapter 4 Sensing Constraints and Evaluation | p. 67 |
4.1 Representation of Vision Sensors | p. 67 |
4.2 Placement Constraints | p. 68 |
4.2.1 Visibility | p. 68 |
4.2.2 Viewing Angle | p. 69 |
4.2.3 Field of View | p. 69 |
4.2.4 Resolution | p. 70 |
4.2.5 In Focus and Viewing Distance | p. 71 |
4.2.6 Overlap | p. 72 |
4.2.7 Occlusion | p. 72 |
4.2.8 Image Contrast | p. 73 |
4.2.9 Robot Environment Constraints | p. 73 |
4.3 Common Approaches to Viewpoint Evaluation | p. 75 |
4.4 Criterion of Lowest Operation Cost | p. 77 |
4.5 Summary | p. 80 |
Chapter 5 Model-Based Sensor Planning | p. 81 |
5.1 Overview of the Method | p. 81 |
5.2 Sensor Placement Graph | p. 82 |
5.2.1 HGA Representation | p. 82 |
5.2.2 Min-Max Objective and Fitness Evaluation | p. 83 |
5.2.3 Evolutionary Computing | p. 84 |
5.3 The Shortest Path | p. 85 |
5.3.1 The Viewpoint Distance | p. 85 |
5.3.2 Determination of a Shortest Path | p. 86 |
5.4 Practical Considerations | p. 87 |
5.4.1 Geometry Scripts | p. 87 |
5.4.2 Inspection Features | p. 87 |
5.4.3 Sensor Structure | p. 88 |
5.4.4 Constraint Satisfaction | p. 89 |
5.4.5 Viewpoint Initialization | p. 90 |
5.5 Implementation | p. 92 |
5.5.1 The Viewpoint Planner | p. 92 |
5.5.2 Examples of Planning Results | p. 92 |
5.5.3 Viewpoint Observation | p. 97 |
5.5.4 Experiments with a Real System | p. 98 |
5.6 Summary | p. 100 |
Chapter 6 Planning for Freeform Surface Measurement | p. 101 |
6.1 The Problem | p. 101 |
6.2 B-Spline Model Representation | p. 104 |
6.2.1 B-Spline Representation | p. 104 |
6.2.2 Model Selection | p. 105 |
6.3 Uncertainty Analysis | p. 108 |
6.4 Sensing Strategy for Optimizing Measurement | p. 110 |
6.4.1 Determining the Number of Measurement Data | p. 110 |
6.4.2 Optimizing the Locations of Measurement Data | p. 110 |
6.5 Experiments | p. 112 |
6.6 Summary | p. 118 |
Chapter 7 Sensor Planning for Object Modeling | p. 119 |
7.1 Planning Approaches to Model Construction | p. 119 |
7.1.1 Model Construction from Multiple Views | p. 119 |
7.1.2 Previous Planning Approaches for Modeling | p. 122 |
7.2 The Procedure for Model Construction | p. 124 |
7.3 Self-Termination Criteria | p. 127 |
7.3.1 The Principle | p. 127 |
7.3.2 Termination Judgment | p. 128 |
7.4 Experiments | p. 131 |
7.5 Summary | p. 144 |
Chapter 8 Information Entropy Based Planning | p. 147 |
8.1 Overview | p. 147 |
8.2 Model Representation | p. 148 |
8.2.1 Curve Approximation | p. 149 |
8.2.2 Improved BIC Criterion | p. 150 |
8.3 Expected Error | p. 154 |
8.3.1 Information Entropy of a B-Spline Model | p. 155 |
8.3.2 Information Gain | p. 156 |
8.4 View Planning | p. 157 |
8.5 Experiments | p. 159 |
8.5.1 Setup | p. 159 |
8.5.2 Model Selection | p. 160 |
8.5.3 Determining the NBV | p. 163 |
8.5.4 Another Example | p. 172 |
8.6 Summary | p. 175 |
Chapter 9 Model Prediction and Sensor Planning | p. 177 |
9.1 Surface Trend and Target Prediction | p. 177 |
9.1.1 Surface Trend | p. 177 |
9.1.2 Determination of the Exploration Direction | p. 179 |
9.1.3 Surface Prediction | p. 182 |
9.2 Determination of the Next Viewpoint | p. 183 |
9.3 Simulation | p. 186 |
9.3.1 Practical Considerations | p. 186 |
9.3.2 Numerical Simulation | p. 187 |
9.4 Practical Implementation | p. 191 |
9.5 Discussion and Conclusion | p. 203 |
9.5.1 Discussion | p. 203 |
9.5.2 Conclusion | p. 205 |
Chapter 10 Integrating Planning with Active Illumination | p. 207 |
10.1 Introduction | p. 207 |
10.2 From Human Vision to Machine Vision | p. 209 |
10.3 Evaluation of Illumination Conditions | p. 210 |
10.3.1 SNR | p. 210 |
10.3.2 Dynamic Range | p. 210 |
10.3.3 Linearity | p. 211 |
10.3.4 Contrast | p. 211 |
10.3.5 Feature Enhancement | p. 211 |
10.4 Controllable Things | p. 212 |
10.4.1 Brightness | p. 212 |
10.4.2 Color Temperature and Color Rendering Index | p. 212 |
10.4.3 Glare | p. 213 |
10.4.4 Uniform Intensity | p. 213 |
10.5 Glare Avoidance | p. 214 |
10.5.1 Disability Glare | p. 214 |
10.5.2 Discomfort Glare | p. 215 |
10.6 Intensity Estimation | p. 216 |
10.6.1 Sensor Sensitivity | p. 216 |
10.6.2 Estimation of Image Irradiance | p. 217 |
10.7 Intensity Control | p. 221 |
10.7.1 The Setpoint | p. 221 |
10.7.2 System Design | p. 223 |
10.8 Simulation | p. 224 |
10.9 Implementation | p. 227 |
10.9.1 Design for Active Illumination | p. 227 |
10.9.2 Experimental Robots | p. 228 |
10.10 Summary | p. 231 |
Bibliography | p. 233 |
A | p. 233 |
B | p. 234 |
C | p. 235 |
D, E | p. 237 |
F, G | p. 238 |
H | p. 240 |
I, J | p. 242 |
K | p. 243 |
L | p. 244 |
M | p. 248 |
N, O, P, Q | p. 248 |
R | p. 250 |
S | p. 251 |
T | p. 254 |
U, V, W | p. 255 |
X, Y, Z | p. 257 |
Index | p. 261 |