Screen LibraryComputer vision for assistive healthcare /
Computer Vision for Assistive Healthcare describes how advanced computer vision techniques provide tools to support common human needs, such as mental functioning, personal mobility, sensory functions, daily living activities, image processing, pattern recognition, machine learning and how language...
Saved in:
| Corporate Authors: | |
|---|---|
| Group Author: | ; |
| Published: |
Elsevier/Academic Press,
|
| Publisher Address: | [Place of publication not identified] |
| Publication Dates: | 2018. |
| Literature type: | eBook |
| Language: | English |
| Series: |
Computer vision and pattern recognition series
|
| Subjects: | |
| Online Access: |
https://www.sciencedirect.com/science/book/9780128134450 |
| Summary: |
Computer Vision for Assistive Healthcare describes how advanced computer vision techniques provide tools to support common human needs, such as mental functioning, personal mobility, sensory functions, daily living activities, image processing, pattern recognition, machine learning and how language processing and computer graphics cooperate with robotics to provide such tools. Users will learn about the emerging computer vision techniques for supporting mental functioning, algorithms for analyzing human behavior, and how smart interfaces and virtual reality tools lead to the development of advanced rehabilitation systems able to perform human action and activity recognition. In addition, the book covers the technology behind intelligent wheelchairs, how computer vision technologies have the potential to assist blind people, and about the computer vision-based solutions recently employed for safety and health monitoring. |
| Carrier Form: | 1 online resource(xxiii, 371 pages). |
| Bibliography: | Includes bibliographical references and index. |
| ISBN: |
9780128134467 0128134461 |
| Index Number: | R859 |
| CLC: | R319 |
| Contents: |
Front Cover; Computer Vision for Assistive Healthcare; Copyright; Contents; Contributors; About the Editors; Preface; 1 Computer Vision for Sight; 1.1 Introduction; 1.1.1 Problem Statement; 1.1.2 Important Considerations; 1.2 A Recommended Paradigm; 1.2.1 Environmental Modeling; 1.2.2 Localization Algorithms; 1.2.3 Assistive User Interfaces; 1.3 Related Work; 1.3.1 Omnidirectional-Vision-Based Indoor Localization; 1.3.2 Other Vision-Based Indoor Localization; 1.3.3 Assistive Technology and User Interfaces; 1.4 An Omnidirectional Vision Approach; 1.4.1 User Interfaces and System Consideration. 1.4.2 Path Planning for Scene Modeling1.4.2.1 Map Parsing and Path Planning; 1.4.2.2 Scene Modeling; 1.4.3 Machine Learning for Place Recognition; 1.4.3.1 Dataset; 1.4.3.2 Architecture; 1.4.3.3 Learning Process; 1.4.3.4 Results; 1.4.3.5 Discussions; 1.4.4 Initial Localization Using Image Retrieval; 1.4.4.1 Two-Dimensional Multiframe Aggregation Based on Candidates' Densities; 1.4.4.2 Localization in Wide Areas: Experimental Results; 1.4.5 Localization Re nement With 3D Estimation; 1.4.5.1 Geometric Constraints-Based Localization; 1.4.5.2 Experiment Using Multiview Omnidirectional Vision. 1.5 Conclusions and DiscussionsGlossary; Acknowledgments; References; 2 Computer Vision for Cognition; 2.1 Why Eyes Are Important for Human Communication; 2.1.1 Eyes in Nonverbal Communication; 2.1.2 Eye Movements; Spatial Movements; Temporal Movements; 2.2 Gaze Direction Recognition and Tracking; 2.2.1 Eye Tracking Metrics; 2.3 Eye Tracking and Cognitive Impairments; 2.4 Computer Vision Support for Diagnosis of Autism Spectrum Disorders; 2.4.1 Methods and Solutions; Using Saliency Models; Using Behavioral Models; 2.4.2 Results; 2.5 Computer Vision Support for the Identi cation of Dyslexia. 2.6 Computer Vision Support for Identi cation of Anxiety Disorders2.6.1 Assessing Phobias; 2.6.2 Studying PTSD; 2.7 Computer Vision Support for Identi cation of Depression and Dementia; 2.8 Conclusions and Discussion; Acknowledgments; References; 3 Real-Time 3D Tracker in Robot-Based Neurorehabilitation; 3.1 Introduction; 3.2 Tracking Module; 3.2.1 Two-Dimensional Preprocessing; 3.2.1.1 Coarse Depth Filtering; 3.2.1.2 Skin Removal; 3.2.2 Three-Dimensional Processing; 3.2.2.1 3D Filtering and Clustering; 3.2.2.2 Cylinder Recognition; Cylinder Segmentation; Cylinder Reconstruction. 3.2.2.3 Three-Dimensional TrackingFingerprint; Evaluation; Matching; Replacement; 3.2.3 Assessment; 3.2.3.1 Parameter Tuning; 3.2.3.2 Robustness; 3.2.3.3 Validation; 3.3 Robotic Devices; 3.3.1 Arm Light Exoskeleton; 3.3.2 Wrist Exoskeleton; 3.3.3 Hand Orthosis; 3.4 Overall System Experiments; 3.5 Discussion and Conclusion; References; 4 Computer Vision and Machine Learning for Surgical Instrument Tracking; 4.1 Introduction; 4.1.1 Potential Bene t of Surgical Instrument Tracking in Retinal Microsurgery; 4.1.2 Challenges of Computer Vision in Medical Applications. |