Deep Evidential Remote Sensing Landslide Image Classification With a New Divergence, Multiscale Saliency and an Improved Three-Branched Fusion
Open Access
- 19 January 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) , 3799-3820
Abstract
Hitherto, image-level classification on remote sensing landslide images has been paid attention to, but the accuracy of traditional deep learning-based methods still have room for improvement. The evidence theory is found efficient to boost the accuracy of neural networks, however, the present study argues three challenges that hinder the lead-in of this theory in deep landslide image classification. Aiming at the three problems, this study makes three improvements. For the interpretability and decision-invariance losses of three previous divergences, we propose a belief Jensen–Renyi divergence with properties proven. To couple the evidence theory with deep remote sensing landslide image classification, a channelwise multiscale visual saliency fusion is developed. We additionally find that the channelwise fusion is capable to reduce false recognition of networks as compared with original RGB images. To avoid decision failures in evidence-theoretic fusion process, we design an interpretability improved three-branched fusion. Experiments on Bijie Landslide dataset corroborate the synergistic benefits of the three improvements, where the proposal is compared with state-of-the-art image classification backbone networks, remote sensing image scene classifiers, evidence fusion algorithms, and versatile evidence-theoretic deep learning classifiers. We also evaluated the new method with two sort of image degradation, as well as an actual scenario in Luding County, China, whose data is publicly available.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities (2572023DJ04)
This publication has 96 references indexed in Scilit:
- A survey of uncertainty in deep neural networksArtificial Intelligence Review, 2023
- An improved belief Hellinger divergence for Dempster-Shafer theory and its application in multi-source information fusionApplied Intelligence, 2023
- Evidence Fusion with Contextual Discounting for Multi-modality Medical Image Segmentation2022
- A belief Rényi divergence for multi-source information fusion and its application in pattern recognitionApplied Intelligence, 2022
- A novel belief χ2 ${\chi }^{2}$ divergence for multisource information fusion and its application in pattern classificationInternational Journal of Intelligent Systems, 2022
- Landslide detection using deep learning and object-based image analysisLandslides, 2022
- A novel divergence measure of mass function for conflict managementInternational Journal of Intelligent Systems, 2021
- Fusion of Evidential CNN Classifiers for Image Classification2021
- Review on remote sensing methods for landslide detection using machine and deep learningTransactions on Emerging Telecommunications Technologies, 2020
- Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networksLandslides, 2020