Current cameras are poor imitations of the human eye and close descen dants in their design of ideas and a technology that are more than a century old. People in computer vision have traditionally used off-the-shelf cameras that were not meant for the uses they were intended for by these researchers: off-the-shelf cameras are designed to capture images to be printed on paper or looked at on a television screen, not for guiding robots or making 3D models of the environment or even surveilling a large area where very large field of views, high geometric and photometric accuracies are necessary. Quite a significant part of the efforts in computer vision has been targeted at overcoming algorithmically these problems. The authors of this book convince us that it is possible to abandon the traditional route of using standard cameras and to follow the path of designing new cameras explicitly for solving the tasks at hand in computer vision applications. This leads to different design concepts and allows to alleviate many of the difficulties encountered in the processing of the images taken with the "traditional" cameras.
Author(s): Ryad Benosman, Sing Bing Kang (eds.)
Series: Monographs in Computer Science
Publisher: Springer
Year: 2001
Language: English
Pages: 463
Tags: Pattern Recognition; Image Processing and Computer Vision; Artificial Intelligence (incl. Robotics)
Front Matter....Pages i-xxiv
Introduction....Pages 1-4
A Brief Historical Perspective on Panorama....Pages 5-20
Front Matter....Pages 21-22
Development of Low-Cost Compact Omnidirectional Vision Sensors....Pages 23-38
Single Viewpoint Catadioptric Cameras....Pages 39-71
Epipolar Geometry of Central Panoramic Catadioptric Cameras....Pages 73-102
Folded Catadioptric Cameras....Pages 103-119
Front Matter....Pages 121-122
A Real-time Panoramic Stereo Imaging System and Its Applications....Pages 123-141
Panoramic Imaging with Horizontal Stereo....Pages 143-160
Panoramic Stereovision Sensor....Pages 161-168
Calibration of the Stereovision Panoramic Sensor....Pages 169-180
Matching Linear Stereoscopic Images....Pages 181-199
Front Matter....Pages 201-203
Characterization of Errors in Compositing Cylindrical Panoramic Images....Pages 205-226
Construction of Panoramic Image Mosaics with Global and Local Alignment....Pages 227-268
Self-Calibration of Zooming Cameras from a Single Viewpoint....Pages 269-289
360 x 360 Mosaics: Regular and Stereoscopic....Pages 291-307
Mosaicing with Strips on Adaptive Manifolds....Pages 309-325
Front Matter....Pages 327-328
3D Environment Modeling from Multiple Cylindrical Panoramic Images....Pages 329-358
N-Ocular Stereo for Real-Time Human Tracking....Pages 359-375
Identifying and Localizing Robots with Omnidirectional Vision Sensors....Pages 377-391
Video Representation and Manipulations Using Mosaics....Pages 393-424
Back Matter....Pages 425-449
