Rezaei / Klette Computer Vision for Driver Assistance

Simultaneous Traffic and Driver Monitoring
1. Auflage 2017
ISBN: 978-3-319-50551-0
Verlag: Springer Nature Switzerland
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 45, 236 Seiten

Reihe: Computational Imaging and Vision

This book summarises the state of the art in computer vision-based driver and road monitoring, focussing on monocular vision technology in particular, with the aim to address challenges of driver assistance and autonomous driving systems.While the systems designed for the assistance of drivers of on-road vehicles are currently converging to the design of autonomous vehicles, the research presented here focuses on scenarios where a driver is still assumed to pay attention to the traffic while operating a partially automated vehicle. Proposing various computer vision algorithms, techniques and methodologies, the authors also provide a general review of computer vision technologies that are relevant for driver assistance and fully autonomous vehicles.
Computer Vision for Driver Assistance is the first book of its kind and will appeal to undergraduate and graduate students, researchers, engineers and those generally interested in computer vision-related topics in modern vehicle design. 


Mahdi Rezaei is Assistant Professor at Qazvin Islamic Azad University, Iran, and Honorary Academic Staff at the University of Auckland, New Zealand. He has a PhD in Computer Science and was awarded the Best Thesis Award from the University of Auckland. His research interests include computer vision, pattern recognition, and advanced driver assistance systems. Rezaei is the author of numerous contributions to top publications, including IEEE Transactions on Intelligent Transportation Systems and IEEE Conference on Computer Vision and Pattern Recognition, CVPR. Reinhard Klette, Fellow of the Royal Society of New Zealand, is Professor at the Auckland University of Technology, New Zealand. He previously held positions at the University of Auckland, the Technical University of Berlin, and the Academy of Sciences Berlin. His research interests include computer vision, pattern recognition, and algorithm design. From 2003 to 2008, he was Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence.

Autoren/Hrsg.

Rezaei, Mahdi

Klette, Reinhard

Inhaltsverzeichnis

1;Preface;7
2;Contents;10
3;Symbols;13
4;1 Vision-Based Driver-Assistance Systems;15
4.1;1.1 Driver-Assistance Towards Autonomous Driving;15
4.2;1.2 Sensors;16
4.3;1.3 Vision-Based Driver Assistance;18
4.4;1.4 Safety and Comfort Functionalities;21
4.5;1.5 VB-DAS Examples;22
4.6;1.6 Current Developments;26
4.7;1.7 Scope of the Book;29
5;2 Driver-Environment Understanding;33
5.1;2.1 Driver and Environment;33
5.2;2.2 Driver Monitoring;34
5.3;2.3 Basic Environment Monitoring;39
5.4;2.4 Midlevel Environment Perception;44
6;3 Computer Vision Basics;51
6.1;3.1 Image Notations;51
6.2;3.2 The Integral Image;53
6.3;3.3 RGB to HSV Conversion;54
6.4;3.4 Line Detection by Hough Transform;55
6.5;3.5 Cameras;57
6.6;3.6 Stereo Vision and Energy Optimization;58
6.7;3.7 Stereo Matching;61
7;4 Object Detection, Classification, and Tracking;64
7.1;4.1 Object Detection and Classification;64
7.2;4.2 Supervised Classification Techniques;66
7.2.1;4.2.1 The Support Vector Machine;66
7.2.2;4.2.2 The Histogram of Oriented Gradients;72
7.2.3;4.2.3 Haar-Like Features;76
7.3;4.3 Unsupervised Classification Techniques;81
7.3.1;4.3.1 k-Means Clustering;81
7.3.2;4.3.2 Gaussian Mixture Models;85
7.4;4.4 Object Tracking;91
7.4.1;4.4.1 Mean Shift;93
7.4.1.1;4.4.1.1 Mean Shift Tracking;95
7.4.2;4.4.2 Continuously Adaptive Mean Shift;97
7.4.3;4.4.3 The Kanade–Lucas–Tomasi (KLT) Tracker;98
7.4.4;4.4.4 Kalman Filter;102
7.4.4.1;4.4.4.1 Filter Implementation;104
7.4.4.2;4.4.4.2 Tracking by Prediction and Refinement;106
8;5 Driver Drowsiness Detection;108
8.1;5.1 Introduction;108
8.2;5.2 Training Phase: The Dataset;110
8.3;5.3 Boosting Parameters;112
8.4;5.4 Application Phase: Brief Ideas;112
8.5;5.5 Adaptive Classifier;115
8.5.1;5.5.1 Failures Under Challenging Lighting Conditions;115
8.5.2;5.5.2 Hybrid Intensity Averaging;117
8.5.3;5.5.3 Parameter Adaptation;118
8.6;5.6 Tracking and Search Minimization;120
8.6.1;5.6.1 Tracking Considerations;120
8.6.2;5.6.2 Filter Modelling and Implementation;121
8.7;5.7 Phase-Preserving Denoising;123
8.8;5.8 Global Haar-Like Features;124
8.8.1;5.8.1 Global Features vs. Local Features;125
8.8.2;5.8.2 Dynamic Global Haar Features;127
8.9;5.9 Boosting Cascades with Local and Global Features;127
8.10;5.10 Experimental Results;128
8.11;5.11 Concluding Remarks;138
9;6 Driver Inattention Detection;140
9.1;6.1 Introduction;140
9.2;6.2 Asymmetric Appearance Models;142
9.2.1;6.2.1 Model Implementation;142
9.2.2;6.2.2 Asymmetric AAM;144
9.3;6.3 Driver's Head-Pose and Gaze Estimation;146
9.3.1;6.3.1 Optimized 2D to 3D Pose Modelling;147
9.3.2;6.3.2 Face Registration by Fermat-Transform;149
9.4;6.4 Experimental Results;152
9.4.1;6.4.1 Pose Estimation;152
9.4.2;6.4.2 Yawning Detection and Head Nodding;152
9.5;6.5 Concluding Remarks;157
10;7 Vehicle Detection and Distance Estimation;159
10.1;7.1 Introduction;159
10.2;7.2 Overview of Methodology;161
10.3;7.3 Adaptive Global Haar Classifier;164
10.4;7.4 Line and Corner Features;167
10.4.1;7.4.1 Horizontal Edges;168
10.4.2;7.4.2 Feature-Point Detection;169
10.5;7.5 Detection Based on Taillights;171
10.5.1;7.5.1 Taillight Specifications: Discussion;171
10.5.2;7.5.2 Colour Spectrum Analysis;173
10.5.3;7.5.3 Taillight Segmentation;174
10.5.4;7.5.4 Taillight Pairing by Template Matching;175
10.5.5;7.5.5 Taillight Pairing by Virtual Symmetry Detection;177
10.6;7.6 Data Fusion and Temporal Information;180
10.7;7.7 Inter-vehicle Distance Estimation;183
10.8;7.8 Experimental Results;186
10.8.1;7.8.1 Evaluations of Distance Estimation;187
10.8.2;7.8.2 Evaluations of the Proposed Vehicle Detection;188
10.9;7.9 Concluding Remarks;199
11;8 Fuzzy Fusion for Collision Avoidance;201
11.1;8.1 Introduction;201
11.2;8.2 System Components;203
11.3;8.3 Fuzzifier and Membership Functions;204
11.4;8.4 Fuzzy Inference and Fusion Engine;207
11.4.1;8.4.1 Rule of Implication;208
11.4.2;8.4.2 Rule of Aggregation;208
11.5;8.5 Defuzzification;209
11.6;8.6 Experimental Results;209
11.7;8.7 Concluding Remarks;216
12;Erratum to: Computer Vision for Driver Assistance: Simultaneous Traffic and Driver Monitoring;218
13;Bibliography;219
14;Index;233