Convolutional neural network framework using reverse connections and objectness priors for object detection
US11188794B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 10, 2017 |
| Grant date | Nov 30, 2021 |
| Priority date | — |
| Expiry date | Nov 11, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A convolutional neural network framework is described that uses reverse connection and obviousness priors for object detection. A method includes performing a plurality of layers of convolutions and reverse connections on a received image to generate a plurality of feature maps, determining an objectness confidence for candidate bounding boxes based on outputs of an objectness prior, determining a joint loss function for each candidate bounding box by combining an objectness loss, a bounding box regression loss and a classification loss, calculating network gradients over positive boxes and negative boxes, updating network parameters within candidate bounding boxes using the joint loss function, repeating performing the convolutions through to updating network parameters until the training converges, and outputting network parameters for object detection based on the training images.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.