J
John Oliensis
Researcher at Stevens Institute of Technology
Publications - 8
Citations - 286
John Oliensis is an academic researcher from Stevens Institute of Technology. The author has contributed to research in topics: Image segmentation & Motion estimation. The author has an hindex of 7, co-authored 8 publications receiving 282 citations.
Papers
More filters
Journal ArticleDOI
Iterative Extensions of the Sturm/Triggs Algorithm: Convergence and Nonconvergence
John Oliensis,Richard Hartley +1 more
TL;DR: The first complete theoretical convergence analysis for the iterative extensions of the Sturm/Triggs algorithm is given, showing that the simplest extension, SIESTA, converges to nonsense results and implies that CIESTA gives a reliable way of initializing other algorithms such as bundle adjustment.
Book ChapterDOI
Iterative extensions of the sturm/triggs algorithm: convergence and nonconvergence
John Oliensis,Richard Hartley +1 more
TL;DR: The first complete theoretical convergence analysis for the iterative extensions of the Sturm/Triggs algorithm is given, showing that the simplest extension, SIESTA, converges to nonsense results and implies that CIESTA gives a reliable way of initializing other algorithms such as bundle adjustment.
Journal ArticleDOI
Generalizing edge detection to contour detection for image segmentation
Hongzhi Wang,John Oliensis +1 more
TL;DR: This work adds a term to the objective function that seeks a sharp change in fitness with respect to the entire contour's position, generalizing from edge detection's search for sharp changes in local image brightness.
Book ChapterDOI
The least-squares error for structure from infinitesimal motion
TL;DR: The error for projective structure from motion is simpler but flatter than the error for calibrated images, and it is shown theoretically and experimentally that the error tends to have a simpler form when many points are tracked.
Journal ArticleDOI
Rigid Shape Matching by Segmentation Averaging
Hongzhi Wang,John Oliensis +1 more
TL;DR: This work uses segmentations to match images by shape to address the unreliability of segmentations computed bottom-up, and gives a closed form approximation to an average over all segmentations.