Moving Objects Detection Using Machine Learning (SpringerBriefs in Electrical and Computer Engineering)

✍ Scribed by Navneet Ghedia, Chandresh Vithalani, Ashish M. Kothari, Rohit M. Thanki

• Publisher: Springer
• Year: 2021
• Tongue: English
• Leaves: 91
• Category: Library

✦ Synopsis

This book shows how machine learning can detect moving objects in a digital video stream. The authors present different background subtraction approaches, foreground segmentation, and object tracking approaches to accomplish this. They also propose an algorithm that considers a multimodal background subtraction approach that can handle a dynamic background and different constraints. The authors show how the proposed algorithm is able to detect and track 2D & 3D objects in monocular sequences for both indoor and outdoor surveillance environments and at the same time, also able to work satisfactorily in a dynamic background and with challenging constraints. In addition, the shows how the proposed algorithm makes use of parameter optimization and adaptive threshold techniques as intrinsic improvements of the Gaussian Mixture Model. The presented system in the book is also able to handle partial occlusion during object detection and tracking. All the presented work and evaluations were carried out in offline processing with the computation done by a single laptop computer with MATLAB serving as software environment.

✦ Table of Contents

Preface
Overview of the Book
Features of the Book
Acknowledgments
Contents
Chapter 1: Introduction
1.1 Introduction
1.2 Challenges in Video Surveillance System
1.3 Contributions in This Book
1.4 Book Organization
References
Chapter 2: Existing Research in Video Surveillance System
2.1 Introduction
2.2 Gaussian Mixture Model-Based Background Modeling and Its Improvements
2.3 Pixel-Based Background Modeling
2.4 Region-Based Background Modeling
2.5 Hybrid Background Modeling
2.6 3D Object Detection
2.7 Object Tracking
2.7.1 Feature-Based Tracking
2.7.2 Region-Based Tracking
2.7.3 Contour-Based Tracking
2.7.4 Model-Based Tracking
2.7.5 Kalman Filtering
2.8 Performance Evaluation
2.9 Summary of Chapter
References
Chapter 3: Background Modeling
3.1 Introduction
3.2 Background Modeling
3.3 Background Subtraction
3.3.1 Background Initialization
3.3.2 Background Maintenance
3.3.3 Foreground Detection
3.3.4 Picture Element
3.3.5 Features
3.4 Modified Gaussian Mixture Model
3.4.1 Frame Analysis
3.4.2 Preprocessing
3.4.3 Background Modeling
3.5 Pixel Belongs to the Background
3.6 Pixel Belongs to the Foreground
3.6.1 Preprocessing
3.7 3D Monocular Object Detection
3.7.1 Foreground Voxel Classification
3.7.2 Maximum a Posteriori-Expectation Maximization
3.8 Results and Discussion
3.9 Summary of Chapter
References
Chapter 4: Object Tracking
4.1 Introduction
4.2 Kalman Filtering
4.2.1 Kalman Gain
4.2.2 Current/New Estimate
4.2.3 New Error in Estimate
4.2.4 Kalman Filter Process Derivations-State-Space Derivation
4.3 Object Tracking Using Kalman Filtering
4.4 Summary of Chapter
References
Chapter 5: Summary of the Book
5.1 Introduction
5.2 Outcome of the Presented Work
5.3 Future Research Direction
Index