Combining convolution and deconvolution for object detection
US10628705B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 29, 2018 |
| Grant date | Apr 21, 2020 |
| Priority date | — |
| Expiry date | Aug 4, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V40/16
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Provided are systems, methods, and computer-readable medium for operating a neural network. In various implementations, the neural network can receive an input image that includes an object to be identified. The neural network can generate a plurality of initial feature maps using a convolution layers, wherein a first initial feature maps is generated using the input image. The neural network can generate an up-sampled feature map using a de-convolution layer that takes an initial feature map as input, where the up-sampled feature map has a same resolution as the previous initial feature map. The neural network can combine the up-sampled feature map and the previous initial feature map, and use the combined feature map to more accurate identify the object.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.