Continuous Cross-Resolution Remote Sensing Image Change Detection

Hao Chen

doi:10.1109/TGRS.2023.3325829

2023-01-01

DOI：10.1109/TGRS.2023.3325829

原文链接

原文求助

摘要

En 中文

Most contemporary supervised remote sensing (RS) image change detection (CD) approaches are customized for equal-resolution bitemporal images. Real-world applications raise the need for cross-resolution CD, a.k.a., CD based on bitemporal images with different spatial resolutions. Given training samples of a fixed bitemporal resolution difference (ratio) between the high-resolution (HR) image and the low-resolution (LR) one, current cross-resolution methods may fit a certain ratio but lack adaptation to other resolution differences. Toward continuous cross-resolution CD, we propose scale-invariant learning to enforce the model consistently predicting HR results given synthesized samples of varying resolution differences. Concretely, we synthesize blurred versions of the HR image by random downsampled reconstructions to reduce the gap between HR and LR images. We introduce coordinate-based representations to decode per-pixel predictions by feeding the coordinate query and corresponding multilevel embedding features into an MLP that implicitly learns the shape of land cover changes, therefore benefiting recognizing blurred objects in the LR image. Moreover, considering that spatial resolution mainly affects the local textures, we apply local-window self-attention to align bitemporal features during the early stages of the encoder. Extensive experiments on two synthesized and one real-world different-resolution CD datasets verify the effectiveness of the proposed method. Our method significantly outperforms several vanilla CD methods and two cross-resolution CD methods on the three datasets both in in-distribution and out-of-distribution settings. The empirical results suggest that our method could yield relatively consistent HR change predictions regardless of varying bitemporal resolution ratios. Our code will be public.

Keyword:

Attention mechanism

cross-resolution change detection (CD)

high-resolution (HR) remote sensing (RS) image

implicit neural representation (INR)

scale-invariant learning