M
Martin Urban
Researcher at Czech Technical University in Prague
Publications - 7
Citations - 6868
Martin Urban is an academic researcher from Czech Technical University in Prague. The author has contributed to research in topics: Epipolar geometry & Maximally stable extremal regions. The author has an hindex of 5, co-authored 6 publications receiving 6633 citations.
Papers
More filters
Journal ArticleDOI
Robust wide-baseline stereo from maximally stable extremal regions
TL;DR: The high utility of MSERs, multiple measurement regions and the robust metric is demonstrated in wide-baseline experiments on image pairs from both indoor and outdoor scenes.
Proceedings ArticleDOI
Robust wide baseline stereo from maximally stable extremal regions
TL;DR: The wide-baseline stereo problem, i.e. the problem of establishing correspondences between a pair of images taken from different viewpoints, is studied and an efficient and practically fast detection algorithm is presented for an affinely-invariant stable subset of extremal regions, the maximally stable extremal region (MSER).
Distinguished Regions for Wide-baseline Stereo
TL;DR: In experiments on indoor and outdoor image pairs, good estimates of epipolar geometry are obtained on challenging wide-baseline problems with the robustified matching algorithm operating on the output produced by the proposed detectors of distinguished regions.
Book ChapterDOI
Projective Reconstruction from N Views Having One View in Common
TL;DR: In this paper, a trifocal constraint concatenation is proposed for the projective reconstruction of 3D scene points from several projections in 2D images, which can be viewed as a generalization of Hartley's algorithm or as a particular application of Triggs' closure relations.
Proceedings Article
License Plate Recognition and Super-resolution from Low-Resolution Videos by Convolutional Neural Networks.
TL;DR: A CNN based super-resolution generator of LP images that converts input low-resolution LP image into its high-resolution counterpart which preserves the structure of the input and depicts a string that was previously recognized from video.