MLANet: a multi-level attention-based change detection method for remote sensing images

Yuping Zhang; Wangze Lu; Wenchao Lv; Ai Gao; Runbo Xie; Guang Yang

doi:10.1117/12.3024453

21 February 2024 MLANet: a multi-level attention-based change detection method for remote sensing images

Yuping Zhang, Wangze Lu, Wenchao Lv, Ai Gao, Runbo Xie, Guang Yang

Author Affiliations +

Proceedings Volume 12988, Second International Conference on Environmental Remote Sensing and Geographic Information Technology (ERSGIT 2023); 129880H (2024) https://doi.org/10.1117/12.3024453
Event: Second International Conference on Environmental Remote Sensing and Geographic Information Technology (ERSGIT 2023), 2023, Xi’an, China

Abstract

Change detection of dual-temporal remote sensing images is widely employed in natural disaster monitoring and land resource planning. Recently, most change detection methods aim at combining the complementary features at different scales to enhance the detection accuracy. However, it is challenging to obtain the complete change regions due to the general differences between semantic concept information and location representation in different feature layers. In this letter, we propose a multi-level attention-based network for change detection of high-resolution optical satellite imagery, namely MLANet. It combines Siamese network in the encoding structure and integrates multi-level attention mechanism (MLAM) in the decoding structure to improve the UNet++. MLANet focuses on strengthening the natural aggregation and spatial matching in multi-layer feature information fusion, and utilizes MLAM to enhance the effective change features and alleviate the impact of interference factors to refine the feature mapping information. Experimental results on two representative change detection datasets demonstrate that the proposed method outperforms most of the state-of-the-art change detection methods.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yuping Zhang, Wangze Lu, Wenchao Lv, Ai Gao, Runbo Xie, and Guang Yang "MLANet: a multi-level attention-based change detection method for remote sensing images", Proc. SPIE 12988, Second International Conference on Environmental Remote Sensing and Geographic Information Technology (ERSGIT 2023), 129880H (21 February 2024); https://doi.org/10.1117/12.3024453

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Feature extraction

Remote sensing

Semantics

Feature fusion

Buildings

Convolution

Image fusion

Show All Keywords

Keywords/Phrases

Search In:

Publication Years