Constrained parametric curve detection using clustering on Hough curves over a sequence of images
US9030559B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 28, 2012 |
| Grant date | May 12, 2015 |
| Priority date | — |
| Expiry date | Dec 13, 2033 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N7/181
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
A method for automatically detecting a constrained curve over a set of images includes: obtaining a set of one or more binary images of a scene wherein pixels thereof are designated as an edge pixel or not; and, processing at least one of the images. The processing includes: applying a Hough transform to the image to generate an accumulator array; determining Hough peaks from the accumulator array; selecting Hough peaks subject to a set of constraints; determining Hough curve segments for the selected Hough peaks; grouping the Hough curve segments into clusters; selecting from the clusters a cluster having a greatest number of Hough curve segments; and fitting a curve to the Hough curve segments grouped in the selected cluster.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.