• Español
Spanish Afrikaans English

Dataset: Far Infrared Images

Publication: 
Thermal Image SuperResolution through Deep Convolutional Neural Network
Authors: 
Rafael E. Rivadeneira, Patricia L. Suarez, Angel D. Sappa, Boris X. Vintimilla
Abstract: 

Due to the lack of thermal image datasets, a new dataset has been acquired for proposed a super-resolution approach using a Deep Convolution Neural Network schema. In order to achieve this image enhancement process, a new thermal images dataset is used. Different experiments have been carried out, firstly, the proposed architecture has been trained using only images of the visible spectrum, and later it has been trained with images of the thermal spectrum, the results showed that with the network trained with thermal images, better results are obtained in the process of enhancing the images, maintaining the image details and perspective.
 

Dataset description: 

Este dataset cuenta con 101 imágenes, con una resolución de 640x512. Capturadas de la manera especificada en [2].

Referencias
2. Rafael E. Rivadeneira, Patricia L. Suárez, Angel D. Sappa, Boris X. Vintimilla (2019). Thermal Image SuperResolution through Deep Convolutional Neural Network. In 2019, 16th International Conference on Image Analysis and Recognition (ICIAR 2019). (paper)

download: dataset
Bibtex: 

 

@article{,
title = "Thermal Image SuperResolution through Deep Convolutional Neutral Network ",
journal = "International Conference on Image Analysis and Recognition (ICIAR 2019)",
year = "2019",
url = "http://refbase.cidis.espol.edu.ec/files/rafaelerivadeneira/2019/103_RafaelE.Rivadeneira_etal2019.pdf",
author = "Rafael E. Rivadeneira, Patricia L. Suarez, Angel D. Sappa, Boris X. Vintimilla",
keywords = "Thermal Infrared Images, Thermal Cameras, Image Enhancement, Convolutional Neural Networks",
}