OPTIMUS: Observing Persistent Transformations in Multi-temporal Unlabeled Satellite-data

TL;DR

OPTIMUS is a self-supervised method that detects persistent changes in multi-temporal satellite images by analyzing the relative order of images over time, improving change detection accuracy without requiring labeled data.

Contribution

The paper introduces OPTIMUS, a novel self-supervised approach for detecting long-lasting changes in satellite imagery without labeled datasets, leveraging change point detection on model outputs.

Findings

Achieved AUROC of 87.6% in change detection.

Outperformed baseline methods significantly.

Effective in identifying persistent surface changes.

Abstract

In the face of pressing environmental issues in the 21st century, monitoring surface changes on Earth is more important than ever. Large-scale remote sensing, such as satellite imagery, is an important tool for this task. However, using supervised methods to detect changes is difficult because of the lack of satellite data annotated with change labels, especially for rare categories of change. Annotation proves challenging due to the sparse occurrence of changes in satellite images. Even within a vast collection of images, only a small fraction may exhibit persistent changes of interest. To address this challenge, we introduce OPTIMUS, a self-supervised learning method based on an intuitive principle: if a model can recover information about the relative order of images in the time series, then that implies that there are long-lasting changes in the images. OPTIMUS demonstrates this principle by using change point detection methods on model outputs in a time series. We demonstrate that OPTIMUS can directly detect interesting changes in satellite images, achieving an improvement in AUROC score from 56.3% to 87.6% at distinguishing changed time series from unchanged ones compared to baselines. Our code and dataset are available at https://huggingface.co/datasets/optimus-change/optimus-dataset/.