Systems and methods for deep learning-based subject persistence
US11232575B2 · kind B2 · utility
3Cited by
51References
33Claims
0Family size
Assignee
Inventor
Key dates
| Filing date | Apr 18, 2019 |
| Grant date | Jan 25, 2022 |
| Priority date | — |
| Expiry date | Jun 25, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30232
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and techniques are provided for tracking subjects in an area of real space. The system receives a plurality of sequences of images of corresponding fields of view in the real space. The system uses the sequences of images to locate subjects in the area of real space during identification intervals. The system compares a current set of located subjects from a current identification interval with previous sets of located subjects from a plurality of previous identification intervals to track locations of tracked subjects in the area.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.