Lightweight remote sensing change detection with progressive multi scale difference aggregation

Abstract Change detection (CD) is the process of acquiring changes in the ground surface by analyzing remotely sensed images of the same location at two different stages. Deep learning is becoming increasingly popular for change detection tasks in remote sensing due to its significant advantages in...

Full description

Saved in:
Bibliographic Details
Main Authors: Yinghua Fu, Haifeng Peng, Tingting Zhao, Yize Li, Jiansheng Peng, Dawei Zhang
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-10972-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226303095439360
author Yinghua Fu
Haifeng Peng
Tingting Zhao
Yize Li
Jiansheng Peng
Dawei Zhang
author_facet Yinghua Fu
Haifeng Peng
Tingting Zhao
Yize Li
Jiansheng Peng
Dawei Zhang
author_sort Yinghua Fu
collection DOAJ
description Abstract Change detection (CD) is the process of acquiring changes in the ground surface by analyzing remotely sensed images of the same location at two different stages. Deep learning is becoming increasingly popular for change detection tasks in remote sensing due to its significant advantages in deep feature representation and nonlinear problem modeling. However, many previous neural network-based approaches require a large number of parameters and computations and high-performance hardware, which makes their practical application in remote sensing challenging. Some lightweight change detection techniques are implemented by enhancing deep features and then extracting their difference information, which tends to ignore many shallow features. We propose a lightweight network MobileNetV2 as an encoder and a modified UNet as a decoder, where MobileNetV2 extracts features from bit-time images and UNet performs layer-by-layer fusion of different stages of difference images to enhance the representativeness of changes. Since MobileNetV2 is used as the encoder of UNet, the computation of the proposed method is greatly reduced. Experiments show that our method has the lowest computational cost (2.38G) and the fewest parameters (2.95M) compared to the current mainstream lightweight networks (FC-Siam-diff32, FC-Siam-conc, A2Net and BIT). Three remote sensing public datasets, SYSU-CD, BCDD and LEVIR-CD, are introduced to validate the proposed method in this paper, and the results show that the F1 of the method in this paper reaches 82.84%, 94.51% and 90.89% respectively. All code as well as detailed instructions are available at https://github.com/tawneydaylily/Mobile-CDNet .
format Article
id doaj-art-beecb8773b8e427f9f2da3543fbb883f
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-beecb8773b8e427f9f2da3543fbb883f2025-08-24T11:28:38ZengNature PortfolioScientific Reports2045-23222025-08-0115111810.1038/s41598-025-10972-5Lightweight remote sensing change detection with progressive multi scale difference aggregationYinghua Fu0Haifeng Peng1Tingting Zhao2Yize Li3Jiansheng Peng4Dawei Zhang5School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and TechnologySchool of Optical-Electrical and Computer Engineering, University of Shanghai for Science and TechnologySchool of Optical-Electrical and Computer Engineering, University of Shanghai for Science and TechnologySchool of Optical-Electrical and Computer Engineering, University of Shanghai for Science and TechnologyDepartment of Artificial Intelligence and Manufacturing, Hechi UniversitySchool of Optical-Electrical and Computer Engineering, University of Shanghai for Science and TechnologyAbstract Change detection (CD) is the process of acquiring changes in the ground surface by analyzing remotely sensed images of the same location at two different stages. Deep learning is becoming increasingly popular for change detection tasks in remote sensing due to its significant advantages in deep feature representation and nonlinear problem modeling. However, many previous neural network-based approaches require a large number of parameters and computations and high-performance hardware, which makes their practical application in remote sensing challenging. Some lightweight change detection techniques are implemented by enhancing deep features and then extracting their difference information, which tends to ignore many shallow features. We propose a lightweight network MobileNetV2 as an encoder and a modified UNet as a decoder, where MobileNetV2 extracts features from bit-time images and UNet performs layer-by-layer fusion of different stages of difference images to enhance the representativeness of changes. Since MobileNetV2 is used as the encoder of UNet, the computation of the proposed method is greatly reduced. Experiments show that our method has the lowest computational cost (2.38G) and the fewest parameters (2.95M) compared to the current mainstream lightweight networks (FC-Siam-diff32, FC-Siam-conc, A2Net and BIT). Three remote sensing public datasets, SYSU-CD, BCDD and LEVIR-CD, are introduced to validate the proposed method in this paper, and the results show that the F1 of the method in this paper reaches 82.84%, 94.51% and 90.89% respectively. All code as well as detailed instructions are available at https://github.com/tawneydaylily/Mobile-CDNet .https://doi.org/10.1038/s41598-025-10972-5
spellingShingle Yinghua Fu
Haifeng Peng
Tingting Zhao
Yize Li
Jiansheng Peng
Dawei Zhang
Lightweight remote sensing change detection with progressive multi scale difference aggregation
Scientific Reports
title Lightweight remote sensing change detection with progressive multi scale difference aggregation
title_full Lightweight remote sensing change detection with progressive multi scale difference aggregation
title_fullStr Lightweight remote sensing change detection with progressive multi scale difference aggregation
title_full_unstemmed Lightweight remote sensing change detection with progressive multi scale difference aggregation
title_short Lightweight remote sensing change detection with progressive multi scale difference aggregation
title_sort lightweight remote sensing change detection with progressive multi scale difference aggregation
url https://doi.org/10.1038/s41598-025-10972-5
work_keys_str_mv AT yinghuafu lightweightremotesensingchangedetectionwithprogressivemultiscaledifferenceaggregation
AT haifengpeng lightweightremotesensingchangedetectionwithprogressivemultiscaledifferenceaggregation
AT tingtingzhao lightweightremotesensingchangedetectionwithprogressivemultiscaledifferenceaggregation
AT yizeli lightweightremotesensingchangedetectionwithprogressivemultiscaledifferenceaggregation
AT jianshengpeng lightweightremotesensingchangedetectionwithprogressivemultiscaledifferenceaggregation
AT daweizhang lightweightremotesensingchangedetectionwithprogressivemultiscaledifferenceaggregation