Self-supervised visual odometry framework using long-term modeling and incremental learning
US11321853B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 27, 2020 |
| Grant date | May 3, 2022 |
| Priority date | — |
| Expiry date | Nov 27, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30252
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computer-implemented method for implementing a self-supervised visual odometry framework using long-term modeling includes, within a pose network of the self-supervised visual odometry framework including a plurality of pose encoders, a convolution long short-term memory (ConvLSTM) module having a first-layer ConvLSTM and a second-layer ConvLSTM, and a pose prediction layer, performing a first stage of training over a first image sequence using photometric loss, depth smoothness loss and pose cycle consistency loss, and performing a second stage of training to finetune the second-layer ConvLSTM over a second image sequence longer than the first image sequence.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.