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

TL;DR

GeoWATCH is a versatile framework that enables training models on long, multi-sensor satellite image sequences for various tasks, effectively handling data heterogeneity and improving performance over time.

Contribution

The paper introduces GeoWATCH, a novel framework with a partial weight loading mechanism for continual training on heterogeneous satellite data.

Findings

Improved model performance through iterative training and configuration adjustments.

Effective handling of multi-sensor, spatio-temporally misaligned satellite data.

Flexible application to classification, recognition, detection, and tracking tasks.

Abstract

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.