GEO DATA

Data Article

KOMPSAT-3/3A Image-text Dataset for Training Large Multimodal Models: Han Oh, Dong-Bin Shin, Dae-Won Chung; Received February 6, 2025 Accepted February 28, 2025 Published online March 19, 2025; DOI: https://doi.org/10.22761/GD.2025.0003 [Epub ahead of print]

9 View
1 Download

Abstract PDF: This study aims to improve the accuracy and interpretability of large multimodal models (LMMs) specialized in satellite image analysis by constructing an image-text dataset based on KOMPSAT-3/3A imagery and presenting the results of training using this dataset. Conventional LMMs are primarily trained on general images, limiting their ability to effectively interpret the specific characteristics of satellite imagery, such as spectral bands, spatial resolution, and viewing angles. To address this limitation, we developed an image-text dataset, divided into pretraining and finetuning stages, based on the existing KOMPSAT object detection dataset. The pretraining dataset consists of captions summarizing the overall theme and key information of each image. The fine-tuning dataset integrates metadata -including acquisition time, sensor type, and coordinates- with detailed object detection labels to generate six types of question-answer pairs: detailed descriptions, conversations with varying answer lengths, bounding box identification, multiple choice questions, and complex reasoning. This structured dataset enables the model to learn not only the general context of satellite images but also fine-grained details such as object quantity, location, and geographic attributes. Training with the new KOMPSAT-based dataset significantly improved the model’s accuracy in recognizing regional information and object characteristics in satellite imagery. Finetuned models achieved substantially higher accuracy than previous models, surpassing even the GPT-4o model and demonstrating the effectiveness of a domain-specific dataset. The findings of this study are expected to contribute to various remote sensing applications, including automated satellite image analysis, change detection, and object detection.

Original Paper

GeoAI Dataset for Industrial Park and Quarry Classification from KOMPSAT-3/3A Optical Satellite Imagery: Che-Won Park, Hyung-Sup Jung, Won-Jin Lee, Kwang-Jae Lee, Kwan-Young Oh, Jae-Young Chang, Moung-jin Lee, Geun-Hyouk Han, Il-Hoon Choi; GEO DATA. 2023;5(4):238-243. Published online December 28, 2023; DOI: https://doi.org/10.22761/GD.2023.0052

1,381 View
73 Download
1 Citations

Air pollution is a serious problem in the world, and it is necessary to monitor air pollution emission sources in other neighboring countries to respond to the problem of air pollution spreading across borders. In this study, we utilized domestic and international optical images from KOMPSAT-3/3A satellites to build an AI training dataset for classifying industrial parks and quarries, which are representative sources of air pollution emissions. The data can be used to identify the distribution of air pollution emission sources located at home and abroad along with various state-of-the-art models in the image segmentation field, and is expected to contribute to the preservation of Korea’s air environment as a basis for establishing air-related policies.

Citations

Citations to this article as recorded by

Performance Comparison of Water Body Detection from Sentinel-1 SAR and Sentinel-2 Optical Imagery Using Attention U-Net Model
Il-Hoon Choi, Eu-Ru Lee, Hyung-Sup Jung
Korean Journal of Remote Sensing.2024; 40(5-1): 507. CrossRef

First
Prev
Page of 1
Next
Last

Search