Software tool for thermographic inspection using multimodal fusing of thermal and visible images.

(Eng) Monocular cameras are commonly used in communication devices, entertainment, and industrial environments since they allow people to recognize rapidly scenes and objects. On the other hand, thermal cameras are mostly known in industrial environments to visualize the objects’ thermic radiance bu...

Full description

Autores:
Ospina, Rafael E.
Cardona, Sergio D.
Bacca Cortes, Eval Bladimir
Tipo de recurso:
Article of journal
Fecha de publicación:
2017
Institución:
Universidad del Valle
Repositorio:
Repositorio Digital Univalle
Idioma:
eng
OAI Identifier:
oai:bibliotecadigital.univalle.edu.co:10893/18225
Acceso en línea:
https://hdl.handle.net/10893/18225
Palabra clave:
Fusión de imágenes
Herramienta software de inspección
Termografía
Multimodal image fusion
Software inspection tool
Thermography
Rights
closedAccess
License
http://purl.org/coar/access_right/c_14cb
Description
Summary:(Eng) Monocular cameras are commonly used in communication devices, entertainment, and industrial environments since they allow people to recognize rapidly scenes and objects. On the other hand, thermal cameras are mostly known in industrial environments to visualize the objects’ thermic radiance but they lose their visual details. This work presents the design and implementation of a thermography inspection tool - INVIfusion - to fuse infrared and visual spectrum images. This tool includes three modules: image acquisition and calibration module, multimodal image fusion module, and report generation module. The main contribution of this work compared with other software inspection tools is INVIfusion supports cameras from different manufacturers (infrared and visible spectrum), having different field of view and spatial resolutions. To validate the suggested system’s functionality and accuracy, quantitative and qualitative tests were performed considering different camera configurations. In all cases the thermal camera was a FLIR E320. Quantitative tests were performed measuring the mean symmetric re-projection error obtaining a maximum error of 2.08 ± 1.8 pixels.