Consumer Depth Cameras for Computer Vision

This up-to-date and authoritative book surveys the most promising Kinect-based research activities, discussing current challenges to the adaptation of consumer depth cameras, and showcasing exciting applications that extend far beyond entertainment and gaming.

The potential of consumer depth cameras extends well beyond entertainment and gaming, to real-world commercial applications. This authoritative text reviews the scope and impact of this rapidly growing field, describing the most promising Kinect-based research activities, discussing significant current challenges, and showcasing exciting applications. Features: presents contributions from an international selection of preeminent authorities in their fields, from both academic and corporate research; addresses the classic problem of multi-view geometry of how to correlate images from different viewpoints to simultaneously estimate camera poses and world points; examines human pose estimation using video-rate depth images for gaming, motion capture, 3D human body scans, and hand pose recognition for sign language parsing; provides a review of approaches to various recognition problems, including category and instance learning of objects, and human activity recognition; with a Foreword by Dr. Jamie Shotton.

Describes a topic of computer vision that will be key in coming years With a broad appeal, bridging academic and corporate research Provides publicly-available code for many of the applications described Includes supplementary material: sn.pub/extras

Autorentext

Dr. Andrea Fossati and Dr. Helmut Grabner are post-doctoral researchers in the Computer Vision Laboratory at ETH Zurich, Switzerland.

Dr. Juergen Gall is a Senior Researcher at the Max Planck Institute for Intelligent Systems, Tübingen, Germany.

Dr. Xiaofeng Ren is a Research Scientist at the Intel Science and Technology Center for Pervasive Computing, Intel Labs, and an Affiliate Assistant Professor at the Department of Computer Science and Engineering of the University of Washington, Seattle, WA, USA.

Dr. Kurt Konolige is a Senior Researcher at Industrial Perception Inc., Palo Alto, CA, USA.

Klappentext

The launch of Microsoft's Kinect, the first high-resolution depth-sensing camera for the consumer market, generated considerable excitement not only among computer gamers, but also within the global community of computer vision researchers.

The potential of consumer depth cameras extends well beyond entertainment and gaming, to real-world commercial applications such virtual fitting rooms, training for athletes, and assistance for the elderly. This authoritative text/reference reviews the scope and impact of this rapidly growing field, describing the most promising Kinect-based research activities, discussing significant current challenges, and showcasing exciting applications.

Topics and features:

• Presents contributions from an international selection of preeminent authorities in their fields, from both academic and corporate research
• Addresses the classic problem of multi-view geometry of how to correlate images from different viewpoints to simultaneously estimate camera poses and world points
• Examines human pose estimation using video-rate depth images for gaming, motion capture, 3D human body scans, and hand pose recognition for sign language parsing
• Provides a review of approaches to various recognition problems, including category and instance learning of objects, and human activity recognition

• With a Foreword by Dr. Jamie Shotton of Microsoft Research, Cambridge, UK This broad-ranging overview is a must-read for researchers and graduate students of computer vision and robotics wishing to learn more about the state of the art of this increasingly hot topic.

  Inhalt

  Part I: 3D Registration and Reconstruction.- 3D with Kinect.- Real-Time RGB-D Mapping and 3-D Modeling on the GPU using the Random Ball Cover.- A Brute Force Approach to Depth Camera Odometry.- Part II: Human Body Analysis.- Key Developments in Human Pose Estimation for Kinect.- A Data-Driven Approach for Real-Time Full Body Pose Reconstruction from a Depth Camera.- Home 3D Body Scans from a Single Kinect.- Real-Time Hand Pose Estimation using Depth Sensors.- Part III: RGB-D Datasets.- A Category-Level 3D Object Dataset: Putting the Kinect to Work.- RGB-D Object Recognition: Features, Algorithms, and a Large Scale Benchmark.- RGBD-HuDaAct: A Color-Depth Video Database for Human Daily Activity Recognition.