tensor voting理论详解（含有伪代码实现）

【实例简介】
tensor voting理论详解（含有伪代码实现） 是我看到的所有关于tensor voting外文中最通俗易懂的算法理论和实现 伪代码在 附录2
CONTENTS LIST OF TABLES LIST OF FIGURES ACKNOWLEDGMENT ABstract XIV 1. Introduction 1.1 Objectives ee-Space .modeling 1.⊥.2 Change Detection 4 1.1.3 Tensor Voting 4 1.1.4 Terrain Extracti 1.2 Challenges 1.3 Approaches 1.4 Contributions 12 1.5 Organization of Thes 2. Back 15 2.1 Range data 15 2.1.1 Triangulation .15 2. 1.2 Structured Light 16 2.1.3 Time-of-Flight 17 2.1.4 Representation 2.2 Methods 2.2.1 Segmentation 18 2.2.2 Registration 2.2.3 tial Data Struct 21 2.3 Modeling 22 2.3.1 Indo 22 2.3.2 Urban 23 2.3.3 Terrain 24 2.3.4 Free-Space 25 2.3.5 Change Detection 25 2.4 TensorⅤ oting.·,· 26 Summary 27 3. Free-Space Modeling for Change Detection 29 3.1 Introduction 3.⊥. 1 Probler. 29 3.1.2 Approach....,,,.. 30 3.1.3 Contributions 30 3. 1.4 Organization of Chapter 3.2 Free-Space Modeling from a Single viewpoint 3.2.1 Free-Space of a Single Scan 32 3.2.2 Preprocessing of Scans 3.2.3 The Free-Space Polyhedron 37 3.2.4 Free-Space Queries 40 3.3 The Spherical Quad-Tree 43 3.3.1 Spherical Parameterization 43 3.3.2 Hierarchica.I Subdivision 44 3.3.3 Spatial Queries 46 3.4 Change Detection 48 3.4.1 SQT Volumes 48 3.4.2 Scan index octree 48 3.4.3 Detecting Changes 49 3.5 results 51 3.5.1 Indoor Experiments 51 3.5.2 Outdoor Experiments 51 3.5.3 Performance 55 3.6 Summary 60 4. Tensor Voting Theory 63 4.1 Introduction 63 4.1.1 Types of Structure 63 4.1.2 Encoding structure 64 4.1.3 Voting procedure 64 4.1.4 Inferring structure 4.1.5 Contributions 68 4.1.6 Organiza pte 69 4.2 Formulation 70 4.2.1 Normal and Tangent Subspaces 70 4.2.2 Representing Structure 70 4.2.3 Communicating structure 71 4.2.4 Fundamental Stick Vote 72 4.2.5 Computing a Vote Componen 73 2.6 Collecting Votes 76 4.3 Attenuation 77 4.3.1 Traditional weight Profi 77 4.3.2 Selection of a Curvature Penalty 77 4.3.3 Intuit 79 4.3.4 Decoupling distance and angle 84 4.3.5 Smooth Weight Profile 86 4.4 Differentiation 89 4.4. 1 Derivative of saliency 89 4.4.2 Derivative of vote tensor 4.4.3 Derivative of Traditional Weight 4.4.4 Derivative of smooth weight 4.5 Discussion .93 4.5.1 Curvature Penalty 93 4.5.2 Weight profiles 3 4.5.3 Computational complexi 96 4.5.4 Gradient Computation 4.6 Summary 98 5. Terrain Extraction by Tensor Votin 9 5. 1 Introduction· 99 5.1.1 Problem 99 5.1.2 Approach 100 5.1. 3 Contributions ...100 5.1.4 Organization of Chapter 101 5.2 Multi-Scale Tensor Voting .102 5.2.1 Sampling Issues 102 5.2.2 Fine-to-Coarse Token refinement 103 5.2.3 Sample Selection and Masking 105 5.2.4 Inter-Scale Communication 107 5.2.5 Saliency Threshold 109 5.3 Terrain extraction 112 5.3.1 Approach ,,112 5.3.2 Coarse-to-Fine extraction ..113 3.3 Line segment search 115 5.3.4 Discussion 117 5. 4 Experiments 119 5.4.1 Token refinement results 119 5.4.2 Terrain extraction results 125 5.5 Summary .,,,131 6. Conclusion 133 6.1 Contributions to Free-Space modeling 133 6.1.1 Inference 133 6.1.2 Representation 133 6. 1. 3 Change Detection System 133 6.2 Contributions to Tensor Voting 134 6.2. 1 Theory 134 6.2.2 Practical Application to Terrain Extraction .134 6.3 Future Work 135 6.3.1 Free-spac 135 6.3.2 Change detection 136 6.3.3 Tensor voting 136 6.3.4 Terrain extraction 137 6.3.5 Combining Methods 137 6. 4 Summary 138 Refe 139 APPENdiCes A. Derivative of an Eigenvalue 169 B. Tensor Voting algorithm 171 LIST OF TABLES 3. 1 Experiment Sizes and Times 58 4.1 Gradient Computation Time by Method 97 5.1 Token Refinement Performance: 86-Field-West 123 5.2 Token refinement performance: 86-Field-east 123 5. 3 Token refinement performance ErDc- Track..,.,......... 124 5.4 Terrain Extraction Performance: 86-Field-West 129 5 Terrain extraction performance: 86-Field-east 29 5.6 Terrain Extraction Performance: ERDC- Track 130 B. 1 Algorithm VOTE COMPLETEO 172 B2 Algorithm VOTECOMPONENT( .173 B3 Algorithm VOTEWEIGHTTRADITIONALO 173 B4 Algorithm VOTEWEIGHTSMOOTHO 173 LIST OF FIGURES 1.1 Range data 1.2 Applications of Free-Space Modeling 1.3 Change Detection in Range Data 1. 4 Saliency in Traditional Tensor Voting 1.5 Terrain extraction from ground-Based range data 6 Challenges in Range data 10 3. 1 Range Data for Change detection 2 Free-Space of a Single Scan 3.3 Zeroth-Order(Depth) Discontinuity 34 3.4 First-Order(Orientation) Discontinuity .35 3.5 Triangulation with primal and dual grid vertices 38 3.6 Half-Edge Loops Bound smooth Surfaces 40 3.7 Zeroth-Order(Depth) Discontinuity on Real Data 3.8 First-Order(Orientation) Discontinuity on Real Data 42 3.9 Free-Space Sign Test 42 3.10 Parameterization used by Spherical Quad-Tree in 3-D 44 3.11 Spherical Quad-Tree Hierarchy in 2-D 3. 12 Spherical Quad-Tree for a 2-D Point Set 3.13 Scan Index Octree 49 3. 14 Indoor Experiment: Lab ...,52 3.15 Indoor Experiment: Climbing Wall ...,53 3.16 Outdoor experiment Loading dock 54 3. 17 Outdoor Experiment: Tree Removed 55 3.18 Outdoor Experiment: Solar Panels rotated .,56 3.19 Outdoor Experiment: Occluded Tree Removed 3.20 Outdoor Experiment: Vehicles and Transient Objects 57 3.21 Outdoor Experiment: Need for Conservative Free-Space ....58 3.22 Outdoor Experiment: False Positive 59 4.1 Structure Types in 3-D 64 4.2 Tensor Voting Overview 66 4.3 Maximal curve extraction 68 4.4 Fundamental stick vote 4.5 Projecting Votee into Voter Normal Space 74 4.6 Traditional Weight Profile ...80 4.7 Saliency and scale 4.8 Evidence Provided by a stick Vote 4.9 Refinement of Two tokens 83 4.10 Candidates for Weighting by Distance 4.11 Smooth weight profile 4.12 Dense Saliency with Traditional weight 94 4.13 Dense Saliency with Proposed Weight 95 1 Input Data: 86-Field-West 100 5. 2 Sample Density and Bias .103 5.3 Multi-Scale Token Selection 104 5.4 Fine-to-Coarse procedure 106 5 Inter-Scale Tensor Communication 108 Terrain Extraction Approach 14 5.7 Input Data: 86-Field-East 120 5.8 Input Data: ERDC-Track 121 5.9 Token refinement: 86-Field-West 122 【实例截图】
【核心代码】