Unsupervised Image Regression for Heterogeneous Change Detection

TL;DR

This paper introduces an unsupervised framework for detecting changes in heterogeneous satellite images by comparing affinity matrices and applying image regression, improving accuracy and efficiency in challenging remote sensing scenarios.

Contribution

The paper presents a novel unsupervised approach combining affinity matrix comparison and multiple regression methods for change detection in heterogeneous multitemporal satellite images.

Findings

Affinity matrix comparison alone can detect changes effectively.

Image regression enhances change detection accuracy.

Random forest regression offers a good balance of accuracy and computational efficiency.

Abstract

Change detection in heterogeneous multitemporal satellite images is an emerging and challenging topic in remote sensing. In particular, one of the main challenges is to tackle the problem in an unsupervised manner. In this paper we propose an unsupervised framework for bitemporal heterogeneous change detection based on the comparison of affinity matrices and image regression. First, our method quantifies the similarity of affinity matrices computed from co-located image patches in the two images. This is done to automatically identify pixels that are likely to be unchanged. With the identified pixels as pseudo-training data, we learn a transformation to map the first image to the domain of the other image, and vice versa. Four regression methods are selected to carry out the transformation: Gaussian process regression, support vector regression, random forest regression, and a recently proposed kernel regression method called homogeneous pixel transformation. To evaluate the potentials and limitations of our framework, and also the benefits and disadvantages of each regression method, we perform experiments on two real data sets. The results indicate that the comparison of the affinity matrices can already be considered a change detection method by itself. However, image regression is shown to improve the results obtained by the previous step alone and produces accurate change detection maps despite of the heterogeneity of the multitemporal input data. Notably, the random forest regression approach excels by achieving similar accuracy as the other methods, but with a significantly lower computational cost and with fast and robust tuning of hyperparameters.