3D Point Cloud Analysis: Traditional, Deep Learning, and Explainable Machine Learning Methods

This book provides an overview of point clouds, their applications in industry, and the most frequently used datasets. It focuses on three computer vision tasks: point cloud classification, segmentation, and registration. It also introduces explainable machine learning methods for point cloud learning, which are lightweight and easy to train. Quantitative and qualitative performance evaluations are provided, and the comparison and analysis between the three types of methods are given to help readers have a deeper understanding.

Format: Paperback / softback
Length: 146 pages
Publication date: 11 December 2022
Publisher: Springer Nature Switzerland AG

This comprehensive book delves into the realm of point clouds, exploring their applications across various industries and the most commonly used datasets. It primarily concentrates on three fundamental computer vision tasks: point cloud classification, segmentation, and registration, which are essential components of any point cloud-based system. To provide a solid foundation for readers, an overview of traditional point cloud processing methods is offered, enabling them to quickly acquire background knowledge. Furthermore, the book delves into the latest advancements in deep learning on point clouds, encompassing a comprehensive analysis of recent breakthroughs. Additionally, brand-new explainable machine learning methods for point cloud learning are introduced, offering lightweight and easy-to-train solutions. Quantitative and qualitative performance evaluations are provided to assess the effectiveness of these methods.

A comparative analysis between the three types of methods is conducted to deepen readers' understanding. The book aims to familiarize readers with this evolving field by presenting a comprehensive overview of traditional methods and state-of-the-art deep learning techniques.

A significant portion of the book is dedicated to explainable machine learning, presenting it as a distinct approach to deep learning. Explainable machine learning methods offer a range of advantages over traditional and deep learning methods. These methods facilitate the interpretation and understanding of the underlying decision-making processes of machine learning models, enabling stakeholders to trust and validate the results.

In conclusion, this book serves as a valuable resource for researchers, practitioners, and students interested in point clouds and their applications. It provides a comprehensive coverage of traditional and deep learning methods, as well as introduce explainable machine learning, enabling readers to stay up-to-date with the latest advancements in this field.

Weight: 256g
Dimension: 235 x 155 (mm)
ISBN-13: 9783030891824
Edition number: 1st ed. 2021