System and method for rare object localization and search in overhead imagery
US12249123B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 29, 2022 |
| Grant date | Mar 11, 2025 |
| Priority date | — |
| Expiry date | Aug 8, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/13
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A feature extractor and novel training objective are provided for content-based image retrieval. For example, a computer-implemented method includes applying a query image and a search image to a neural network of a feature extraction network of a computing device, the query image indicating an object to be searched for in the search image. The feature extraction network includes the neural network, a spatial feature neural network receiving a first output of the neural network pertaining to the search image, and an embedding network receiving a second output of the neural network pertaining to the query image. The method includes generating spatial search features from the spatial feature neural network, generating a query feature from the embedding network, applying the query feature to an artificial neural network (ANN) index, and determining an optimal matching result of an object in the search image based on an operation using the ANN index.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.