3D Computer Vision: Efficient Methods and Applications

ISBN-13: 9781447141495 / Angielski / Twarda / 2012 / 382 str.

Christian W. Hler

Opis

This indispensable text introduces the foundations of three-dimensional computer vision and describes recent contributions to the field.Fully revised and updated, this much-anticipated new edition reviews a range of triangulation-based methods, including linear and bundle adjustment based approaches to scene reconstruction and camera calibration, stereo vision, point cloud segmentation, and pose estimation of rigid, articulated, and flexible objects. Also covered are intensity-based techniques that evaluate the pixel grey values in the image to infer three-dimensional scene structure, and point spread function based approaches that exploit the effect of the optical system. The text shows how methods which integrate these concepts are able to increase reconstruction accuracy and robustness, describing applications in industrial quality inspection and metrology, human-robot interaction, and remote sensing.Practitioners of computer vision, photogrammetry, optical metrology, robotics and planetary science will find the book an essential reference.Examines three-dimensional surface reconstruction of strongly non-Lambertian surfaces by the combination of photometric stereo and active range scanning, with applications to industrial metrology (NEW).Discusses pose estimation and tracking of human body parts, and subsequent recognition of actions performed in a complex industrial production environment, in the context of safe interaction between humans and industrial robots (NEW).Reviews the construction of high-resolution lunar digital elevation models based on orbital imagery in combination with laser altimetry data, including a discussion of the latest lunar spacecraft data sets (NEW).

Recenzje

"I do recommend serious consideration of this book for a one-semester advanced graduate course on methods for 3D scene reconstruction, based on the first five chapters. For graduate students pursuing PhDs in the field of computer vision, this is a book they won't want to miss." (Zhaoqiang Lai, ACM Computing Reviews, Mar 8 2013, Review # CR141001)

Spis treści

Part I: Methods of 3D Computer Vision

Triangulation-based Approaches to Three-dimensional Scene Reconstruction

Three-dimensional Pose Estimation and SegmentationMethods

Intensity-based and Polarisation-based Approaches

Point Spread Function Based Approaches to Three-dimensional Scene Reconstruction

Integrated Frameworks for Three-dimensional Scene Reconstruction

Part II: Application Scenarios

Applications to Industrial Quality Inspection

Applications to Safe Human–Robot Interaction

Applications to Lunar Remote Sensing

Conclusion

O autorze

Christian Wöhler is Professor of Image Analysis at the Department of Electrical Engineering and Information Technology of TU Dortmund, Germany. His scientific interests are in the domains of computer vision, photogrammetry, remote sensing, and pattern classification, with applications in various fields including machine vision, robotics, advanced driver assistance systems, and planetary science.

Blurb

This indispensable text introduces the foundations of three-dimensional computer vision and describes recent contributions to the field.

Fully revised and updated, this much-anticipated new edition reviews a range of triangulation-based methods, including linear and bundle adjustment based approaches to scene reconstruction and camera calibration, stereo vision, point cloud segmentation, and pose estimation of rigid, articulated, and flexible objects. Also covered are intensity-based techniques that evaluate the pixel grey values in the image to infer three-dimensional scene structure, and point spread function based approaches that exploit the effect of the optical system. The text shows how methods which integrate these concepts are able to increase reconstruction accuracy and robustness, describing applications in industrial quality inspection and metrology, human-robot interaction, and remote sensing.

Practitioners of computer vision, photogrammetry, optical metrology, robotics and planetary science will find the book an essential reference.

Key Topics

• Examines three-dimensional surface reconstruction of strongly non-Lambertian surfaces by the combination of photometric stereo and active range scanning, with applications to industrial metrology (NEW)
• Discusses pose estimation and tracking of human body parts, and subsequent recognition of actions performed in a complex industrial production environment, in the context of safe interaction between humans and industrial robots (NEW)
• Reviews the construction of high-resolution lunar digital elevation models based on orbital imagery in combination with laser altimetry data, including a discussion of the latest lunar spacecraft data sets (NEW)