GEO-REGISTERING AN AERIAL IMAGE BY AN OBJECT DETECTION MODEL USING MACHINE LEARNING
Patent №
US 10,691,944
Granted
2020-06-23
Filed 2018
Owner
THE BOEING COMPANY
Lab
—
AI components
3
ml · vision · planning
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
15984906
A method of obtaining and geo-registering an aerial image of an object of interest is provided. The method includes obtaining an aerial image by a camera onboard an aircraft. The method includes accessing an object detection model trained using a machine learning algorithm and a training set of aerial images of an object of interest, and using the object detection model to detect the object of interest in the aerial image. The object detection includes a prediction of a boundary of the object of interest depicted in the aerial image based on the defined boundary of the object of interest. The method includes accessing a data store including a geographic location of the object of interest. And the method includes geo-registering the aerial image including the prediction of the boundary of the object of interest with the geographic location of the object of interest.
AI classification
Ownership
THE BOEING COMPANY
assignment · 458620742
Assignors
YANG, YAN
On an employer assignment, the assignors are typically the inventors.