Pure convolutional neural network localization
US9619735B1 · kind B1 · utility
13Cited by
3References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jun 8, 2016 |
| Grant date | Apr 11, 2017 |
| Priority date | — |
| Expiry date | Jun 8, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30204
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An approach is provided in which a knowledge manager processes an image using a convolutional neural network. The knowledge manager generates a pixel-level heat map of the image that includes multiple decision points corresponding to multiple pixels of the image. The knowledge manager analyzes the pixel-level heat map and detects sets of decision points that correspond to target objects. In turn, the knowledge manager marks regions of the heat map corresponding to the detected sets of per-pixel decision points, each of the regions indicating a location of the target objects.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.