3D Computer Vision. Efficient Methods and Applications.

Springer Verlag Berlin Heidelberg, August 2009.

Link to the Springer website

The book provides an introduction to the foundations of three-dimensional computer vision and describes recent contributions to the field. Geometric methods include 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. Photometric techniques evaluate the intensity information of the image to infer three-dimensional scene structure, while real-aperture approaches exploit the behaviour of the point spread function. It is shown how the integration of several methods increases reconstruction accuracy and robustness. The described application scenarios include industrial quality inspection, metrology, human-robot interaction, and lunar remote sensing, primarily based on the author's professional activities in the automobile industry.

Key Topics

• Providing a broad general overview of the current state of the art in the field of 3D computer vision. A unique unified description of photogrammetric and computer vision approaches.
• Recent contributions to the fields of 3D scene analysis and surface reconstruction, pose estimation, and motion analysis.
• A large variety of application scenarios in the domains of industrial quality inspection, metrology, human-robot interaction, and remote sensing.

Further publications

Back to main page