GeoWATCH for Detecting Heavy Construction in Heterogeneous Time Series of Satellite Images

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Crall, Jon, Greenwell, Connor, Joy, David, Leotta, Matthew, Chaudhary, Aashish, Hoogs, Anthony
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914862636990464
author Crall, Jon
Greenwell, Connor
Joy, David
Leotta, Matthew
Chaudhary, Aashish
Hoogs, Anthony
author_facet Crall, Jon
Greenwell, Connor
Joy, David
Leotta, Matthew
Chaudhary, Aashish
Hoogs, Anthony
contents Learning from multiple sensors is challenging due to spatio-temporal misalignment and differences in resolution and captured spectra. To that end, we introduce GeoWATCH, a flexible framework for training models on long sequences of satellite images sourced from multiple sensor platforms, which is designed to handle image classification, activity recognition, object detection, or object tracking tasks. Our system includes a novel partial weight loading mechanism based on sub-graph isomorphism which allows for continually training and modifying a network over many training cycles. This has allowed us to train a lineage of models over a long period of time, which we have observed has improved performance as we adjust configurations while maintaining a core backbone.
format Preprint
id arxiv_https___arxiv_org_abs_2407_06337
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GeoWATCH for Detecting Heavy Construction in Heterogeneous Time Series of Satellite Images
Crall, Jon
Greenwell, Connor
Joy, David
Leotta, Matthew
Chaudhary, Aashish
Hoogs, Anthony
Computer Vision and Pattern Recognition
Learning from multiple sensors is challenging due to spatio-temporal misalignment and differences in resolution and captured spectra. To that end, we introduce GeoWATCH, a flexible framework for training models on long sequences of satellite images sourced from multiple sensor platforms, which is designed to handle image classification, activity recognition, object detection, or object tracking tasks. Our system includes a novel partial weight loading mechanism based on sub-graph isomorphism which allows for continually training and modifying a network over many training cycles. This has allowed us to train a lineage of models over a long period of time, which we have observed has improved performance as we adjust configurations while maintaining a core backbone.
title GeoWATCH for Detecting Heavy Construction in Heterogeneous Time Series of Satellite Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.06337