Method and system for detecting actions in videos
US10242266B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 2, 2016 |
| Grant date | Mar 26, 2019 |
| Priority date | — |
| Expiry date | Dec 19, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V2201/06
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method and system detects actions of an object in a scene by first acquiring a video of the scene as a sequence of images, wherein each image includes pixels, wherein the video is partitioned into chunks. The object in the video is tracked. For each object and each chunk of the video, trajectories of the pixels within a bounding box located over the object are tracked, and cropped trajectories and cropped images for one or more images in the chunk are produced using the bounding box. Then, the cropped trajectories and cropped images are passed to a recurrent neural network (RNN) that outputs a relative score for each action of interest.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.