Fast computation of kernel descriptors
US9330332B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 4, 2013 |
| Grant date | May 3, 2016 |
| Priority date | — |
| Expiry date | Jan 11, 2034 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F18/2135
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An approach to computation of kernel descriptors is accelerated using precomputed tables. In one aspect, a fast algorithm for kernel descriptor computation that takes O(1) operations per pixel in each patch, based on pre-computed kernel values. This speeds up the kernel descriptor features under consideration, to levels that are comparable with D-SIFT and color SIFT, and two orders of magnitude faster than STIP and HoG3D. In some examples, kernel descriptors are applied to extract gradient, flow and texture based features for video analysis. In tests of the approach on a large database of internet videos used in the TRECVID MED 2011 evaluations, the flow based kernel descriptors are up to two orders of magnitude faster than STIP and HoG3D, and also produce significant performance improvements. Further, using features from multiple color planes produces small but consistent gains.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.