Active Tracking Strategy for Monocular Depth Inference over Multiple Frames
IEEE Transactions on Pattern Analysis and Machine Intelligence
Artificial Intelligence
Techniques for disparity measurement
CVGIP: Image Understanding
Optimal discretization for stereo reconstruction
Pattern Recognition Letters
Optimal error discretization under depth and range constraints
Pattern Recognition Letters
What Tasks can be Performed with an Uncalibrated Stereo Vision System?
International Journal of Computer Vision
Robot Vision
Handbook of Image and Video Processing
Handbook of Image and Video Processing
Disparity estimation on log-polar images and vergence control
Computer Vision and Image Understanding
Camera Self-Calibration: Theory and Experiments
ECCV '92 Proceedings of the Second European Conference on Computer Vision
The Epipolar Geometry of the Log-Polar Image Plane
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Calibration of an active binocular head
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Foveated video compression with optimal rate control
IEEE Transactions on Image Processing
Embedded foveation image coding
IEEE Transactions on Image Processing
Nonlinearities in Stereoscopic Phase-Differencing
IEEE Transactions on Image Processing
Pattern Recognition Letters
Hi-index | 0.00 |
Biological vision systems have inspired and will continue to inspire the development of computer vision systems. One biological tendency that has never been exploited is the symbiotic relationship between foveation and uncalibrated active, binocular vision systems. The primary goal of any binocular vision system is the correspondence of the two retinal images. For calibrated binocular rigs the search for corresponding points can be restricted to epipolar lines. In an uncalibrated system the precise geometry is unknown. However, the set of possible geometries can be restricted to some reasonable range; and consequently, the search for matching points can be confined to regions delineated by the union of all possible epipolar lines over all possible geometries. We call these regions epipolar spaces. The accuracy and complexity of any correspondence algorithm is directly proportional to the size of these epipolar spaces. Consequently, the introduction of a spatially variant foveation strategy that reduces the average area per epipolar space is highly desirable. This paper provides a set of sampling theorems that offer a path for designing foveation strategies that are optimal with respect to average epipolar area.