A Remote Sensing Image Change Detection Method Integrating Layer-Exchange and Channel-Spatial Differences

Change detection in remote sensing imagery is a crucial technique for Earth observation, primarily focusing on pixel-level segmentation of change regions between bitemporal images. The core of pixel-level change detection lies in determining whether corresponding pixels in bitemporal images have und...

Full description

Saved in:
Bibliographic Details
Main Authors: Sijun Dong, Fangcheng Zuo, Geng Chen, Siming Fu, Xiaoliang Meng
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11024553/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Change detection in remote sensing imagery is a crucial technique for Earth observation, primarily focusing on pixel-level segmentation of change regions between bitemporal images. The core of pixel-level change detection lies in determining whether corresponding pixels in bitemporal images have undergone changes. In deep learning, the spatial and channel dimensions of feature maps represent distinct types of information derived from the original images. In this study, we discovered that in change detection tasks, difference information can be computed not only from the spatial dimension of bitemporal features but also from the channel dimension. Based on this insight, we designed the channel-spatial difference weighting module, which serves as an aggregation-distribution mechanism for bitemporal features in change detection. This module enhances the sensitivity of the change detection model to difference features, thereby improving its overall performance. Furthermore, bitemporal images share the same geographic location and exhibit strong interimage correlations. To effectively capture and utilize these correlations, we designed a decoding structure based on the layer-exchange method, which enhances the interaction of bitemporal features. This approach allows the model to better leverage the temporal dependencies between the images, leading to more accurate change detection. To validate the effectiveness of our proposed method, we conducted comprehensive experiments on four widely used datasets: CLCD, PX-CLCD, LEVIR-CD, and S2Looking. The experimental results demonstrate that the proposed LENet model significantly outperforms existing methods in terms of change detection accuracy.
ISSN:1939-1404
2151-1535