Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

BD-MSA: Body decouple VHR Remote Sensing Image Change Detection method guided by multi-scale feature information aggregation

Yonghui Tan, Xiaolong Li, Yishu Chen, Jinquan Ai

TL;DR

BD-MSA tackles remote sensing change detection in VHR imagery by jointly aggregating multi-scale global and local features and by decoupling the change region's body from its edges during training. The Overall Feature Aggregation Module (OFAM), the Feature Alignment (FA) module with MixFFN, and the Decouple Module collectively improve boundary clarity and overall detection accuracy. Empirical results on DSIFN-CD, S2Looking, and WHU-CD demonstrate state-of-the-art performance with a compact parameter footprint, and ablation/visualization studies highlight gains in edge fidelity and boundary localization. The work suggests strong practical potential for precise RSCD in varied imaging conditions and points toward semi-supervised extensions to reduce labeling needs.

Abstract

The purpose of remote sensing image change detection (RSCD) is to detect differences between bi-temporal images taken at the same place. Deep learning has been extensively used to RSCD tasks, yielding significant results in terms of result recognition. However, due to the shooting angle of the satellite, the impacts of thin clouds, and certain lighting conditions, the problem of fuzzy edges in the change region in some remote sensing photographs cannot be properly handled using current RSCD algorithms. To solve this issue, we proposed a Body Decouple Multi-Scale by fearure Aggregation change detection (BD-MSA), a novel model that collects both global and local feature map information in the channel and space dimensions of the feature map during the training and prediction phases. This approach allows us to successfully extract the change region's boundary information while also divorcing the change region's main body from its boundary. Numerous studies have shown that the assessment metrics and evaluation effects of the model described in this paper on the publicly available datasets DSIFN-CD, S2Looking and WHU-CD are the best when compared to other models.

BD-MSA: Body decouple VHR Remote Sensing Image Change Detection method guided by multi-scale feature information aggregation

TL;DR

BD-MSA tackles remote sensing change detection in VHR imagery by jointly aggregating multi-scale global and local features and by decoupling the change region's body from its edges during training. The Overall Feature Aggregation Module (OFAM), the Feature Alignment (FA) module with MixFFN, and the Decouple Module collectively improve boundary clarity and overall detection accuracy. Empirical results on DSIFN-CD, S2Looking, and WHU-CD demonstrate state-of-the-art performance with a compact parameter footprint, and ablation/visualization studies highlight gains in edge fidelity and boundary localization. The work suggests strong practical potential for precise RSCD in varied imaging conditions and points toward semi-supervised extensions to reduce labeling needs.

Abstract

The purpose of remote sensing image change detection (RSCD) is to detect differences between bi-temporal images taken at the same place. Deep learning has been extensively used to RSCD tasks, yielding significant results in terms of result recognition. However, due to the shooting angle of the satellite, the impacts of thin clouds, and certain lighting conditions, the problem of fuzzy edges in the change region in some remote sensing photographs cannot be properly handled using current RSCD algorithms. To solve this issue, we proposed a Body Decouple Multi-Scale by fearure Aggregation change detection (BD-MSA), a novel model that collects both global and local feature map information in the channel and space dimensions of the feature map during the training and prediction phases. This approach allows us to successfully extract the change region's boundary information while also divorcing the change region's main body from its boundary. Numerous studies have shown that the assessment metrics and evaluation effects of the model described in this paper on the publicly available datasets DSIFN-CD, S2Looking and WHU-CD are the best when compared to other models.
Paper Structure (22 sections, 15 equations, 15 figures, 9 tables, 1 algorithm)

This paper contains 22 sections, 15 equations, 15 figures, 9 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Pure Convolutional-based Model
  4. Attention Mechanism-based Model
  5. Transformer-based Model
  6. Methodology
  7. Overall Structure
  8. Overall Feature Aggregation Module (OFAM)
  9. FA Module
  10. Feature Decouple Module
  11. Experimental Results and Analysis
  12. Experimental Setup
  13. Implementation Details
  14. Comparison With SOTA Methods
  15. Main Results
  16. ...and 7 more sections

Figures (15)

  • Figure 1: A section of the images in the DSIFN-CD and S2Looking, with the first column representing the pre-change images, the second representing the post-change images, and the third representing the change mask. The photos in the figure's top row are from S2Looking, while those in the second and third rows are from DSIFN-CD.
  • Figure 2: Schematic diagram of BD-MSA.
  • Figure 3: The graphic depicts our OFAM, which is separated into three major portions, Channel Attention, Spatial Attention, and Fusion, which are distinguished by various colored backgrounds.
  • Figure 4: Parts (a), (b), (c), and (d) of the OFAM schematic diagrams depict Local Channel Attention, Global Channel Attention, Local Spatial Attention, and Global Spatial Attention, respectively, in Fig. \ref{['fig:OFAM']}.
  • Figure 5: A schematic representation of our FA Module, which is separated into two main portions, FDAF and MixFFN, which are distinguished by various colored backgrounds.
  • ...and 10 more figures