Non-registered change detection: a novel change detection task and baseline data Set

Total: 1

In this study, we propose a new remote sensing change detection task, registration-free change detection, to respond to the increasing number of emergencies such as natural disasters, anthropogenic accidents, and military strikes. First, in light of the limited discourse on the issue of non-logging change detection, we systematically propose eight scenarios that could arise in the real world and potentially contribute to the emergence of non-logging issues. Second, we develop distinct image transformation schemes suitable for various scenarios to convert the available registration change detection dataset into a registration-free version. Finally, we demonstrate that record-free change detection can cause catastrophic damage to state-of-the-art methods. Our code and dataset are available at https://github.com/ShanZard/NRCD.