Static Early Fusion Techniques for Visible and Thermal Images to Enhance Convolutional Neural Network Detection: A Performance Analysis

This paper presents a comparison of different image fusion methods for matching visible-spectrum images with thermal-spectrum (far-infrared) images, aimed at enhancing person detection using convolutional neural networks (CNNs). While object detection with RGB images is a well-developed area, it is...

Full description

Saved in:
Bibliographic Details
Main Authors: Enrique Heredia-Aguado, Juan José Cabrera, Luis Miguel Jiménez, David Valiente, Arturo Gil
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/6/1060
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850207716190978048
author Enrique Heredia-Aguado
Juan José Cabrera
Luis Miguel Jiménez
David Valiente
Arturo Gil
author_facet Enrique Heredia-Aguado
Juan José Cabrera
Luis Miguel Jiménez
David Valiente
Arturo Gil
author_sort Enrique Heredia-Aguado
collection DOAJ
description This paper presents a comparison of different image fusion methods for matching visible-spectrum images with thermal-spectrum (far-infrared) images, aimed at enhancing person detection using convolutional neural networks (CNNs). While object detection with RGB images is a well-developed area, it is still greatly limited by lighting conditions. This limitation poses a significant challenge in image detection playing a larger role in everyday technology, where illumination cannot always be controlled. Far-infrared images (which are partially invariant to lighting conditions) can serve as a valuable complement to RGB images in environments where illumination cannot be controlled and robust object detection is needed. In this work, various early and middle fusion techniques are presented and compared using different multispectral datasets, with the aim of addressing these limitations and improving detection performance.
format Article
id doaj-art-c408803f4dfa4827b2c1eb9eb841dc91
institution OA Journals
issn 2072-4292
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-c408803f4dfa4827b2c1eb9eb841dc912025-08-20T02:10:24ZengMDPI AGRemote Sensing2072-42922025-03-01176106010.3390/rs17061060Static Early Fusion Techniques for Visible and Thermal Images to Enhance Convolutional Neural Network Detection: A Performance AnalysisEnrique Heredia-Aguado0Juan José Cabrera1Luis Miguel Jiménez2David Valiente3Arturo Gil4University Institute for Engineering Research, Miguel Hernández University, Avda. de la Universidad s/n, 03202 Elche, Alicante, SpainUniversity Institute for Engineering Research, Miguel Hernández University, Avda. de la Universidad s/n, 03202 Elche, Alicante, SpainUniversity Institute for Engineering Research, Miguel Hernández University, Avda. de la Universidad s/n, 03202 Elche, Alicante, SpainUniversity Institute for Engineering Research, Miguel Hernández University, Avda. de la Universidad s/n, 03202 Elche, Alicante, SpainUniversity Institute for Engineering Research, Miguel Hernández University, Avda. de la Universidad s/n, 03202 Elche, Alicante, SpainThis paper presents a comparison of different image fusion methods for matching visible-spectrum images with thermal-spectrum (far-infrared) images, aimed at enhancing person detection using convolutional neural networks (CNNs). While object detection with RGB images is a well-developed area, it is still greatly limited by lighting conditions. This limitation poses a significant challenge in image detection playing a larger role in everyday technology, where illumination cannot always be controlled. Far-infrared images (which are partially invariant to lighting conditions) can serve as a valuable complement to RGB images in environments where illumination cannot be controlled and robust object detection is needed. In this work, various early and middle fusion techniques are presented and compared using different multispectral datasets, with the aim of addressing these limitations and improving detection performance.https://www.mdpi.com/2072-4292/17/6/1060thermal imagesperson detectionmultispectral image fusiondeep learningcomputer vision
spellingShingle Enrique Heredia-Aguado
Juan José Cabrera
Luis Miguel Jiménez
David Valiente
Arturo Gil
Static Early Fusion Techniques for Visible and Thermal Images to Enhance Convolutional Neural Network Detection: A Performance Analysis
Remote Sensing
thermal images
person detection
multispectral image fusion
deep learning
computer vision
title Static Early Fusion Techniques for Visible and Thermal Images to Enhance Convolutional Neural Network Detection: A Performance Analysis
title_full Static Early Fusion Techniques for Visible and Thermal Images to Enhance Convolutional Neural Network Detection: A Performance Analysis
title_fullStr Static Early Fusion Techniques for Visible and Thermal Images to Enhance Convolutional Neural Network Detection: A Performance Analysis
title_full_unstemmed Static Early Fusion Techniques for Visible and Thermal Images to Enhance Convolutional Neural Network Detection: A Performance Analysis
title_short Static Early Fusion Techniques for Visible and Thermal Images to Enhance Convolutional Neural Network Detection: A Performance Analysis
title_sort static early fusion techniques for visible and thermal images to enhance convolutional neural network detection a performance analysis
topic thermal images
person detection
multispectral image fusion
deep learning
computer vision
url https://www.mdpi.com/2072-4292/17/6/1060
work_keys_str_mv AT enriqueherediaaguado staticearlyfusiontechniquesforvisibleandthermalimagestoenhanceconvolutionalneuralnetworkdetectionaperformanceanalysis
AT juanjosecabrera staticearlyfusiontechniquesforvisibleandthermalimagestoenhanceconvolutionalneuralnetworkdetectionaperformanceanalysis
AT luismigueljimenez staticearlyfusiontechniquesforvisibleandthermalimagestoenhanceconvolutionalneuralnetworkdetectionaperformanceanalysis
AT davidvaliente staticearlyfusiontechniquesforvisibleandthermalimagestoenhanceconvolutionalneuralnetworkdetectionaperformanceanalysis
AT arturogil staticearlyfusiontechniquesforvisibleandthermalimagestoenhanceconvolutionalneuralnetworkdetectionaperformanceanalysis