Aerial monitoring system and method for identifying and locating object features
US10949676B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 9, 2018 |
| Grant date | Mar 16, 2021 |
| Priority date | — |
| Expiry date | Aug 10, 2038 |
Classification
- Technology area (CPC B)Performing Operations; Transporting
- CPC primaryB64U2101/30
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An aerial monitoring system and method for identification and location of object features is disclosed. The aerial monitoring system and method includes training an image processing engine to identify predefined object features in images. Training involves the image processing engine generating a model for identifying predefined object features in images. Identifying the predefined object features includes using a drone outfitted with a drone camera to capture and geotag monitoring images of target objects. The monitoring images are both infrared and non-infrared. The image processing engine applies the model to the monitoring images to determine whether the monitoring images include object features that fit within one of multiple categories. The image processing engine uses a fuzzy clustering process to group objects into cluster locations. The image processing system outputs the identification and location of the object features. The output is used for maintenance planning related to the objects.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.