Semantic-Explicit Filtering Network for Remote Sensing Image Change Detection

doi:10.1109/TGRS.2024.3476992

Semantic-Explicit Filtering Network for Remote Sensing Image Change Detection

2024-01-01

2

PRE

AI

DOI：10.1109/TGRS.2024.3476992

Original

Original request for help

Save

Abstract

En 中文

Remote sensing image change detection (RSI-CD) aims to explore surface change information from aligned dual-phase images. However, RSI-CD currently encounters two major challenges. The first issue is the inadequate object-level semantic representation during the feature extraction in CD networks. The other issue is the spectral resolution of the RS image is limited, which leads to a mixture of pseudochange and real change. In order to explore the above-mentioned two challenges, we propose a semantic-explicit filtering network (SFNet) based on a neighborhood feature attention module (NFAM) and multiple-receptive-field semantic filtering mechanism (MSFM). First, the NFAM exploits the correlation of multiscale features and fuses features from the proximity layer to enhance the semantic-explicit representation of the object level. Then, the MSFM takes the weight map after the enhanced semantic representation as input and progressively refines the weight map through a multiple-receptive-field parallel convolution (MPC). This process filters out pseudochange from the predicted result while retaining the real-change information. The experiments on two benchmark datasets demonstrate that the proposed approach presents satisfactory performance over the existing methods.

Keywords:

Feature extraction

Semantics

Filtering

Attention mechanisms

Remote sensing

Convolutional neural networks

Decoding

Accuracy

Telecommunications

Measurement

Change detection (CD)

multiple receptive field (RF)

neighborhood feature attention

remote sensing (RS)

Semantic-Explicit Filtering Network for Remote Sensing Image Change Detection

Abstract

Journal

Organization