Machine Learning-Based Natural Scene Recognition for Mobile Robot Localization in an Unknown Environment

ISBN-13: 9789811392160 / Angielski / Twarda / 2019 / 328 str.

Xiaochun Wang; Xiali Wang; Don Mitchell Wilkes

Spis treści

Part I Introduction

1 Overview and Contributions

2 Developments in Mobile Robot Localization Research

3 A Computer Vision System for Visual Perception in Unknown Environments

Part II Unsupervised Learning

4 Theory: Clustering

5 Algorithm I: A Fast Approximate EMST Algorithm for High-Dimensional Image Data

6 Algorithm II: An Efficient K-medoids Clustering Algorithm for Large Scale Image Data

7 Algorithm III: Enhancing Complete Linkage Clustering via Boundary Point Detection

8 Algorithm IV: A New Fast k-Nearest Neighbor-Based Clustering Algorithm

Part III Supervised Learning and Semi-Supervised Learning

9 Theory: K-nearest Neighbor Classifiers

10 Application I: A Fast Image Retrieval Method Based on Quantization Tree

11 Application II: A Fast Incremental Spectral Clustering Algorithm for Image Segmentation

Part IV Reinforcement Learning

12 Theory: Human-Like Localization Inspired by a Hippocampal Memory Mechanism

13 Application I: A Developmental Robotic Paradigm Using Working Memory Learning Mechanism

14 Application II: An Autonomous Vision System Based Sensor-Motor Coordination for Open Space Detection

15 Application III: Visual Percepts Learning for Mobile Robot Localization in An Indoor Environment

16 Application IV: An Automatic Natural Scene Recognition Method for Mobile Robot Localization in An Outdoor Environment

O autorze

Xiaochun Wang received her BS degree from Beijing University and the PhD degree from the Department of Electrical Engineering and Computer Science, Vanderbilt University. She is currently an associate professor of School of Software Engineering at Xi’an Jiaotong University. Her research interests are in computer vision, signal processing, and pattern recognition.

Xia Li Wang received the PhD degree from the Department of Computer Science, Northwest University, China, in 2005. He is a faculty member in the Department of Computer Science, Changan University, China. His research interests are in computer vision, signal processing, intelligent traffic system, and pattern recognition.

D. Mitchell Wilkes received the BSEE degree from Florida Atlantic, and the MSEE and PhD degrees from Georgia Institute of Technology. His research interests include digital signal processing, image processing and computer vision, structurally adaptive systems, sonar, as well as signal modeling. He is a member of the IEEE and a faculty member at the Department of Electrical Engineering and Computer Science, Vanderbilt University. He is a member of the IEEE.

Blurb

This book advances research on mobile robot localization in unknown environments by focusing on machine-learning-based natural scene recognition. The respective chapters highlight the latest developments in vision-based machine perception and machine learning research for localization applications, and cover such topics as: image-segmentation-based visual perceptual grouping for the efficient identification of objects composing unknown environments; classification-based rapid object recognition for the semantic analysis of natural scenes in unknown environments; the present understanding of the Prefrontal Cortex working memory mechanism and its biological processes for human-like localization; and the application of this present understanding to improve mobile robot localization. The book also features a perspective on bridging the gap between feature representations and decision-making using reinforcement learning, laying the groundwork for future advances in mobile robot navigation research.