Abstract
The present disclosure describes systems and methods that leverage one or more machine learning techniques or machine-learned models to identify large-scale churn using low-resolution geographic imagery. More particularly, a processing pipeline is provided that takes as input a low-resolution image corresponding to older existing imagery of a geographic area and a newer low-resolution image of the same geographic area. The pipeline can include a churn recognition neural network that compares the input images to identify churn, and output the result of the identification. Keywords associated with the present disclosure include: machine learning; neural network; deep learning; geographic imagery; satellite imagery; aerial imagery; churn; development; infrastructure; roads; automatic detection of change.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Manolides, Matthew, "Machine Learning to Automatically Detect Human Development from Satellite Imagery", Technical Disclosure Commons, (April 24, 2017)
https://www.tdcommons.org/dpubs_series/481