Video semantic segmentation method based on active learning
US11810359B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 21, 2021 |
| Grant date | Nov 7, 2023 |
| Priority date | — |
| Expiry date | Jul 18, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present invention belongs to the technical field of computer vision, and provides a video semantic segmentation method based on active learning, comprising an image semantic segmentation module, a data selection module based on the active learning and a label propagation module. The image semantic segmentation module is responsible for segmenting image results and extracting high-level features required by the data selection module; the data selection module selects a data subset with rich information at an image level, and selects pixel blocks to be labeled at a pixel level; and the label propagation module realizes migration from image to video tasks and completes the segmentation result of a video quickly to obtain weakly-supervised data. The present invention can rapidly generate weakly-supervised data sets, reduce the cost of manufacture of the data and optimize the performance of a semantic segmentation network.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.