Patch-Level Unsupervised Planetary Change Detection

Abstract

Change detection (CD) is critical for analyzing data collected by planetary exploration missions, e.g., for identification of new impact craters. However, CD is still a relatively new topic in the context of planetary exploration. Sheer variation of planetary data makes CD much more challenging than in the case of Earth observation (EO). Unlike CD for EO, patch-level decision is preferred in planetary exploration as it is difficult to obtain perfect pixelwise alignment/co-registration between the bi-temporal planetary images. Lack of labeled bi-temporal data impedes supervised CD. To overcome these challenges, we propose an unsupervised CD method that exploits a pretrained feature extractor to obtain bi-temporal deep features that are further processed using global max-pooling to obtain patch-level feature description. Bi-temporal patch-level features are further analyzed based on difference to determine whether a patch is changed. Additionally, a self-supervised method is proposed to estimate the decision boundary between the changed and unchanged patches. Experimental results on three planetary CD datasets from two different planetary bodies (Mars and Moon) demonstrate that the proposed method often outperforms supervised planetary CD methods. Code is available at https://gitlab.lrz.de/ai4eo/cd/-/tree/main/planetaryCDUnsup.

Deep Learning-Based Change Detection in Remote Sensing Images: A Review

“…Despite significant differences in image quality, illumination, imaging sensors, surface properties, and co-registration, their proposed method can detect meaningful changes with high accuracy, using relatively small training datasets. Saha et al [184] proposed a patch-level unsupervised CD deep transfer-based method for planetary exploration. Their proposed method can determine whether a pair of bitemporal patches are changed and, furthermore, they proposed a technique using pseudounchanged pairs to determine the threshold for distinguishing changed and unchanged patches.…”

RaVÆn: unsupervised change detection of extreme events using ML on-board satellites

“…At inference, we can drop the decoder and use only the trained encoder network as a feature extractor to encode individual tiles in their compressed representation, with the advantage of improved robustness to noise and to slight misalignment between tiles 35 and reduced computational and memory requirements of storing images from previous passes, which is a critical in a constrained environment.…”

Self-Supervised Learning in Remote Sensing: A review

“…Hence for good performance in the application of object detection, an integrated representation learning pipeline deserves consideration [231]. In addition, patch-based change detection considers comparisons between tiles of images (change or no change) rather than pixels due to reasons like possible misalignment between time stamps [246], or the requirement of fast preprocessing to retrieve region of interest and limited bandwidth for data communication [247]. We note that patch-level change detection can also be classified into image-level tasks.…”