Spatial Context Awareness for Unsupervised Change Detection in Optical Satellite Images

TL;DR

SiROC is an unsupervised, spatial context-based change detection method for optical satellite images that models pixels using their neighbors, providing accurate, training-free predictions with uncertainty estimates, suitable for various resolutions.

Contribution

This paper introduces SiROC, a novel unsupervised change detection approach leveraging spatial context modeling and ensemble techniques for improved accuracy.

Findings

Competitive performance on Sentinel-2 and Planetscope datasets.

Provides well-calibrated uncertainty estimates.

Operates effectively without training data.

Abstract

Detecting changes on the ground in multitemporal Earth observation data is one of the key problems in remote sensing. In this paper, we introduce Sibling Regression for Optical Change detection (SiROC), an unsupervised method for change detection in optical satellite images with medium and high resolution. SiROC is a spatial context-based method that models a pixel as a linear combination of its distant neighbors. It uses this model to analyze differences in the pixel and its spatial context-based predictions in subsequent time periods for change detection. We combine this spatial context-based change detection with ensembling over mutually exclusive neighborhoods and transitioning from pixel to object-level changes with morphological operations. SiROC achieves competitive performance for change detection with medium-resolution Sentinel-2 and high-resolution Planetscope imagery on four datasets. Besides accurate predictions without the need for training, SiROC also provides a well-calibrated uncertainty of its predictions. This makes the method especially useful in conjunction with deep-learning based methods for applications such as pseudo-labeling.