Simple Multiscale UNet for Change Detection With Heterogeneous Remote Sensing Images

Zhiyong Lv, Haitao Huang, Lipeng Gao*, Jon Atli Benediktsson, Minghua Zhao, Cheng Shi

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)


Change detection with heterogeneous remote sensing images (HRSIs) is attractive for observing the Earth's surface when homogeneous images are unavailable. However, HRSIs cannot be compared directly because the imaging mechanisms for bitemporal HRSIs are different, and detecting change with HRSIs is challenging. In this letter, a simple yet effective deep learning approach based on the classical UNet is proposed. First, a pair of image patches are concatenated together to learn a shared abstract feature in both image patch domains. Then, a multiscale convolution module is embedded in a UNet backbone to cover the various sizes and shapes of ground targets in an image scene. Finally, a combined loss function, which incorporates the focal and dice losses with an adjustable parameter, was incorporated to alleviate the effect of the imbalanced quantity of positive and negative samples in the training progress. By comparisons with five state-of-the-art methods in three pairs of real HRSIs, the experimental results achieved by our proposed approach have the best overall accuracy (OA), average accuracy (AA), recall (RC), and F-Score that are more than 95%, 79%, 60%, and 61%, respectively. The quantitative results and visual performance indicated the feasibility and superiority of the proposed approach for detecting land cover change with HRSIs.

Original languageEnglish
Article number2504905
JournalIEEE Geoscience and Remote Sensing Letters
Publication statusPublished - 1 Jan 2022

Bibliographical note

Publisher Copyright:
© 2004-2012 IEEE.

Other keywords

  • Deep learning neural network
  • hetereogreous remote sensing images
  • land cover change detection
  • multi-scale feature


Dive into the research topics of 'Simple Multiscale UNet for Change Detection With Heterogeneous Remote Sensing Images'. Together they form a unique fingerprint.

Cite this