Systems, circuits, and methods for efficient hierarchical object recognition based on clustered invariant features
US9204112B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 7, 2013 |
| Grant date | Dec 1, 2015 |
| Priority date | — |
| Expiry date | Feb 7, 2033 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F2218/08
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
One embodiment is a method for selecting and grouping key points extracted by applying a feature detector on a scene being analyzed. The method includes grouping the extracted key points into clusters that enforce a geometric relation between members of a cluster, scoring and sorting the clusters, identifying and discarding clusters that are comprised of points which represent the background noise of the image, and sub-sampling the remaining clusters to provide a smaller number of key points for the scene.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.