F3Net: Feature Filtering Fusing Network for Change Detection of Remote Sensing Images
Open Access
- 28 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 10621-10635
Abstract
Change Detection of remote sensing images is an essential method for observing changes on the Earth's surface. Deep learning can efficiently process remote sensing images. However, shallow features in remote sensing data from different time are inherently inconsistent. During the feature extraction stage, these shallow features are mapped onto different dimensional feature maps, giving rise to noise information. Existing algorithms are ineffective in dealing with noise effectively. This can lead to detection results being influenced by shallow features noise information, resulting in fake detections. To address this issue, Feature Filtering Fusing Network (F3Net) is proposed in this article. In F3Net, Feature Filtering and Aggregation Module (FFA) is designed to integrate bi-temporal remote sensing features, which initially filters out noise information from different temporal domains. Additionally, the Channel Feature Difference Fusion Module (CFDF) is introduced to fuse high-dimensional features. Within CFDF, Channel Information Filtering Convolution (CIFConv) is utilized to filter out noise information from high-dimensional feature channels across multiple receptive fields. In order to verify the performance of F3Net, comparative experiments were conducted on multiple public datasets with other state-of-the-art models, and F3Net achieved the best performance. The code of F3Net can be achieved from https://github.com/juncyan/f3net.git .Keywords
Funding Information
- Science and Technology Development Fund of Macau SAR (0045/2022/A)
- Macao Polytechnic University (RP/FCA-12/2022)
This publication has 52 references indexed in Scilit:
- Double U-Net (W-Net): A change detection network with two heads for remote sensing imageryInternational Journal of Applied Earth Observation and Geoinformation, 2023
- Cross-domain landslide mapping from large-scale remote sensing images using prototype-guided domain-aware progressive representation learningISPRS Journal of Photogrammetry and Remote Sensing, 2023
- Cosine Annealing, Mixnet and Swish Activation for Computer Go2022
- Encoder and decoder network with ResNet-50 and global average feature pooling for local change detectionComputer Vision and Image Understanding, 2022
- Remote Sensing for Assessing Landslides and Associated HazardsSurveys in Geophysics, 2020
- A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing imagesISPRS Journal of Photogrammetry and Remote Sensing, 2020
- Remote Sensing Techniques in Landslide Mapping and Monitoring, Keynote Lecture2017
- Urban development change detection based on Multi-Temporal Satellite Images as a fast tracking approach—a case study of Ahwaz County, southwestern IranEnvironmental Monitoring and Assessment, 2015
- Change detection from remotely sensed images: From pixel-based to object-based approachesISPRS Journal of Photogrammetry and Remote Sensing, 2013
- Deforestation in the Miombo woodlands: a pixel-based semi-automated change detection methodInternational Journal of Remote Sensing, 2011