It is commonly assumed that the goal of stereovision is computing explicit 3D scene reconstructions. We show that very accurate camera calibration is needed to support this, and that such accurate calibration is difficult to achieve and maintain. We argue that for tasks like recognition, figure/ground separation is more important than 3D depth reconstruction, and demonstrate a stereo algorithm that supports figure/ground separation without 3D reconstruction.
Why Stereo Vision is Not Always About 3D Reconstruction
1993
11 pages , 393745 byte , 520870 byte
Miscellaneous
Electronic Resource
English
Continuous Media and Machine Vision: Distributed Active Stereo Reconstruction
British Library Conference Proceedings | 1996
|ACCURACY ANALYSIS OF SURFACE NORMAL RECONSTRUCTION IN STEREO VISION
British Library Conference Proceedings | 2014
|Automotive engineering | 2000
|