Version 1
: Received: 9 October 2024 / Approved: 9 October 2024 / Online: 10 October 2024 (08:00:36 CEST)
How to cite:
Cao, Y.; Zhao, P.; Xu, B.; Liang, J. An Improved Random Forest Approach on GAN-Based Dataset Augmentation for Fog Observation. Preprints2024, 2024100725. https://doi.org/10.20944/preprints202410.0725.v1
Cao, Y.; Zhao, P.; Xu, B.; Liang, J. An Improved Random Forest Approach on GAN-Based Dataset Augmentation for Fog Observation. Preprints 2024, 2024100725. https://doi.org/10.20944/preprints202410.0725.v1
Cao, Y.; Zhao, P.; Xu, B.; Liang, J. An Improved Random Forest Approach on GAN-Based Dataset Augmentation for Fog Observation. Preprints2024, 2024100725. https://doi.org/10.20944/preprints202410.0725.v1
APA Style
Cao, Y., Zhao, P., Xu, B., & Liang, J. (2024). An Improved Random Forest Approach on GAN-Based Dataset Augmentation for Fog Observation. Preprints. https://doi.org/10.20944/preprints202410.0725.v1
Chicago/Turabian Style
Cao, Y., Balin Xu and Jingshu Liang. 2024 "An Improved Random Forest Approach on GAN-Based Dataset Augmentation for Fog Observation" Preprints. https://doi.org/10.20944/preprints202410.0725.v1
Abstract
The monitoring of fog density is of great importance in meteorology and its applications in environment, aviation and transportation. Nowadays, vision-based fog estimation from images taken with surveillance cameras has made a great supplementary contribution to the scarcely traditional meteorological fog observation. In this paper, we propose a new Random Forest (RF) approach for image-based fog estimation. In order to reduce the impact of data imbalance on recognition, the StyleGAN2-ADA (generative adversarial network with adaptive discriminator augmentation) algorithm is used to generate virtual images to expand the data of low proportions. Key image features related to fog are extracted, and an RF method, integrated with the hierarchical and k-medoids clustering, is deployed to estimate the fog density. The experiment conducted in Sichuan in February 2024 shows that the improved RF model has achieved an average accuracy of fog density observation to 93%, 6.4% higher than the RF model without data expansion, 3%-6% higher than the VGG16, the VGG19, the ResNet50, and the DenseNet169 with or without data expansion. What is more, the improved RF method exhibits a very good convergence as a cost-effective solution.
Keywords
Fog density; data augmentation; random forest; generative adversarial network; hierarchical clustering; fog-relevant features
Subject
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
