T-UNet: Triplet UNet for Change Detection in High-Resolution Remote Sensing Images

TL;DR

This paper introduces T-UNet, a triplet encoder-based neural network with attention mechanisms for more accurate change detection in high-resolution remote sensing images, addressing limitations of existing Siamese and early fusion methods.

Contribution

The paper proposes a novel Triplet UNet architecture with multi-branch attention modules for improved change detection accuracy in remote sensing images.

Findings

Enhanced detection accuracy over existing methods

Effective extraction of change and object features

Better edge delineation of changed objects

Abstract

Remote sensing image change detection aims to identify the differences between images acquired at different times in the same area. It is widely used in land management, environmental monitoring, disaster assessment and other fields. Currently, most change detection methods are based on Siamese network structure or early fusion structure. Siamese structure focuses on extracting object features at different times but lacks attention to change information, which leads to false alarms and missed detections. Early fusion (EF) structure focuses on extracting features after the fusion of images of different phases but ignores the significance of object features at different times for detecting change details, making it difficult to accurately discern the edges of changed objects. To address these issues and obtain more accurate results, we propose a novel network, Triplet UNet(T-UNet), based on a three-branch encoder, which is capable to simultaneously extract the object features and the change features between the pre- and post-time-phase images through triplet encoder. To effectively interact and fuse the features extracted from the three branches of triplet encoder, we propose a multi-branch spatial-spectral cross-attention module (MBSSCA). In the decoder stage, we introduce the channel attention mechanism (CAM) and spatial attention mechanism (SAM) to fully mine and integrate detailed textures information at the shallow layer and semantic localization information at the deep layer.