Intelligent Scene Modeling and Human-Computer Interaction

by Nadia Magnenat Thalmann (Editor), Jian Jun Zhang (Editor), Manoj Ramanathan (Editor), Daniel Thalmann (Editor)

Overview

This edited book is one of the first to describe how Autonomous Virtual Humans and Social Robots can interact with real people and be aware of the surrounding world using machine learning and AI. It includes:

· Many algorithms related to the awareness of the surrounding world such as the recognition of objects, the interpretation of various sources of data provided by cameras, microphones, and wearable sensors

· Deep Learning Methods to provide solutions to Visual Attention, Quality Perception, and Visual Material Recognition

· How Face Recognition and Speech Synthesis will replace the traditional mouse and keyboard interfaces

· Semantic modeling and rendering and shows how these domains play an important role in Virtual and Augmented Reality Applications.

Intelligent Scene Modeling and Human-Computer Interaction explains how to understand the composition and build very complex scenes and emphasizes the semantic methods needed to have an intelligent interaction with them. It offers readers a unique opportunity to comprehend the rapid changes and continuous development in the fields of Intelligent Scene Modeling.

Product Details

ISBN-13:	9783030710040
Publisher:	Springer International Publishing
Publication date:	06/09/2021
Series:	Human-Computer Interaction Series
Edition description:	1st ed. 2021
Pages:	282
Product dimensions:	6.10(w) x 9.25(h) x (d)

Table of Contents

Preface.- Part I: Intelligent Scene Modeling.- Introduction.- Object Detection: State of the Art and Beyond.- NBNN-Based Discriminative 3D Action and Gesture Recognition.- Random Forests with Optimized Leaves for Hough-Voting.- Modeling Human Perception of 3D Scenes.- Model Reconstruction of Real-world 3D Objects: An Application with Microsoft HoloLens.- Semantic Modeling and Rendering.- Content-aware Semantic Indoor Scene Modeling from a Single Image.- Interactive Labeling for Generation of CityGML Building Models from Meshes.- TooltY: An Approach for the Combination of Motion Capture and 3D Reconstruction to Present Tool Usage in 3D Environments.- Generating 3D Facial Expressions with Recurrent Neural Networks.- Part 2: Human-computer Interaction.- Facilitating Decision Making with Multimodal Interfaces in Collaborative Analytical Sessions.- Human – Technology Interaction: The State of the Art and the Lack of Naturalism.- Survey of Speechless Interaction Techniques in Social Robotics.- Exploring Potential and Acceptance of Socially Intelligent Robot.