Computer vision using learnt lossy image compression representations
US10984560B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 29, 2019 |
| Grant date | Apr 20, 2021 |
| Priority date | — |
| Expiry date | Jun 20, 2039 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N19/91
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
Techniques for performing learnt image compression and object detection using compressed image data are described. A system may perform image compression using an image compression model that includes an encoder, an entropy model, and a decoder. The encoder, the entropy model, and the decoder may be jointly trained using machine learning based on training data. After training, the encoder and the decoder may be separated to encode image data to generate compressed image data or to decode compressed image data to generate reconstructed image data. In addition, the system may perform object detection using a compressed object detection model that processes compressed image data generated by the image compression model. For example, the compressed object detection model may perform partial decoding using a single layer of the decoder and perform compressed object detection on the partially decoded image data.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.