Methods for performing multi-view object detection by using homography attention module and devices using the same
US11514323B1 · kind B1 · utility
Assignee
Inventor
Key dates
| Filing date | Jun 10, 2022 |
| Grant date | Nov 29, 2022 |
| Priority date | — |
| Expiry date | Jun 10, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/82
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for training a homography attention module (HAM) to perform multi-view object detection includes steps of: generating, from an i-th feature map corresponding to each of multiple training images representing multi-views of a target space, a 1-st to a d-th channel attention map for determining channel attention scores each channel included in the i-th feature map has for each of a 1-st to a d-th height plane of the target space, generating a 1-st to a d-th channel refined feature map by referring to channels with top k channel attention scores for each height, element-wisely multiplying them with corresponding spatial attention map generated therefrom to produce a 1-st to a d-th spatial refined feature map, and then homographically transforming them onto corresponding height plane and aggregating them to generate a BEV occupancy heatmap, which is used with its GT for training.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.