Saved in:
Bibliographic Details
Main Authors: Miranda, Mateus de Souza, Hänsch, Ronny, Júnior, Valdivino Alexandre de Santiago, Körting, Thales Sehn, Monteiro, Erison Carlos dos Santos
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.00083
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915132445032448
author Miranda, Mateus de Souza
Hänsch, Ronny
Júnior, Valdivino Alexandre de Santiago
Körting, Thales Sehn
Monteiro, Erison Carlos dos Santos
author_facet Miranda, Mateus de Souza
Hänsch, Ronny
Júnior, Valdivino Alexandre de Santiago
Körting, Thales Sehn
Monteiro, Erison Carlos dos Santos
contents The Cerrado faces increasing environmental pressures, necessitating accurate land use and land cover (LULC) mapping despite challenges such as class imbalance and visually similar categories. To address this, we present CerraData-4MM, a multimodal dataset combining Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 MultiSpectral Imagery (MSI) with 10m spatial resolution. The dataset includes two hierarchical classification levels with 7 and 14 classes, respectively, focusing on the diverse Bico do Papagaio ecoregion. We highlight CerraData-4MM's capacity to benchmark advanced semantic segmentation techniques by evaluating a standard U-Net and a more sophisticated Vision Transformer (ViT) model. The ViT achieves superior performance in multimodal scenarios, with the highest macro F1-score of 57.60% and a mean Intersection over Union (mIoU) of 49.05% at the first hierarchical level. Both models struggle with minority classes, particularly at the second hierarchical level, where U-Net's performance drops to an F1-score of 18.16%. Class balancing improves representation for underrepresented classes but reduces overall accuracy, underscoring the trade-off in weighted training. CerraData-4MM offers a challenging benchmark for advancing deep learning models to handle class imbalance and multimodal data fusion. Code, trained models, and data are publicly available at https://github.com/ai4luc/CerraData-4MM.
format Preprint
id arxiv_https___arxiv_org_abs_2502_00083
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CerraData-4MM: A multimodal benchmark dataset on Cerrado for land use and land cover classification
Miranda, Mateus de Souza
Hänsch, Ronny
Júnior, Valdivino Alexandre de Santiago
Körting, Thales Sehn
Monteiro, Erison Carlos dos Santos
Computer Vision and Pattern Recognition
Image and Video Processing
The Cerrado faces increasing environmental pressures, necessitating accurate land use and land cover (LULC) mapping despite challenges such as class imbalance and visually similar categories. To address this, we present CerraData-4MM, a multimodal dataset combining Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 MultiSpectral Imagery (MSI) with 10m spatial resolution. The dataset includes two hierarchical classification levels with 7 and 14 classes, respectively, focusing on the diverse Bico do Papagaio ecoregion. We highlight CerraData-4MM's capacity to benchmark advanced semantic segmentation techniques by evaluating a standard U-Net and a more sophisticated Vision Transformer (ViT) model. The ViT achieves superior performance in multimodal scenarios, with the highest macro F1-score of 57.60% and a mean Intersection over Union (mIoU) of 49.05% at the first hierarchical level. Both models struggle with minority classes, particularly at the second hierarchical level, where U-Net's performance drops to an F1-score of 18.16%. Class balancing improves representation for underrepresented classes but reduces overall accuracy, underscoring the trade-off in weighted training. CerraData-4MM offers a challenging benchmark for advancing deep learning models to handle class imbalance and multimodal data fusion. Code, trained models, and data are publicly available at https://github.com/ai4luc/CerraData-4MM.
title CerraData-4MM: A multimodal benchmark dataset on Cerrado for land use and land cover classification
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2502.00083