Network and Dataset for Multiscale Remote Sensing Image Change Detection

Network and Dataset for Multiscale Remote Sensing Image Change Detection

Remote sensing image change detection (RSCD) aims to identify differences between remote sensing images of the same location at different times. However, due to the significant variations in the size and appearance of objects in real-world scenes, existing RSCD algorithms often lack strong capabilit...

Full description

Saved in:
Bibliographic Details
Main Authors: Shenbo Liu, Dongxue Zhao, Yuheng Zhou, Ying Tan, Huang He, Zhao Zhang, Lijun Tang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Attention mechanism
change detection dataset (CDD)
feature pyramid
multiscale change detection
remote sensing images
Online Access:https://ieeexplore.ieee.org/document/10813409/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Remote sensing image change detection (RSCD) aims to identify differences between remote sensing images of the same location at different times. However, due to the significant variations in the size and appearance of objects in real-world scenes, existing RSCD algorithms often lack strong capabilities in extracting multiscale features, thereby failing to fully capture the characteristics of changes. To address this issue, a multiscale remote sensing change detection network (MSNet) and a multiscale RSCD dataset (MSRS-CD) are proposed. A multiscale convolution module (MSCM) is investigated, and combined with MSCM, an encoder capable of capturing features of different sizes is designed to efficiently extract multiscale semantic change features. A global multiscale feature fusion module is designed to achieve global multiscale feature fusion and obtain multiscale high-level semantic change features. As existing RSCD datasets lack rich scale information and often focus on change targets of specific sizes, a new dataset, MSRS-CD, is constructed. This dataset consists of 842 pairs of images with a resolution of 1024 &#x00D7; 1024 pixels, featuring uniformly distributed change detection target sizes. Comparative experiments are conducted with 10 other state-of-the-art algorithms on the MSRS-CD dataset and another public dataset, LEVIR-CD. Experimental results demonstrate that MSNet achieves the best performance on both datasets, with an <italic>F</italic>1 score of 75.74&#x0025; on the MSRS-CD dataset and 91.41&#x0025; on the LEVIR-CD dataset.
ISSN:1939-1404
2151-1535

Similar Items