A Light-Weight Self-Supervised Infrared Image Perception Enhancement Method

Gardado en:
Detalles Bibliográficos
Publicado en:Electronics vol. 13, no. 18 (2024), p. 3695
Autor Principal: Xiao, Yifan
Outros autores: Zhang, Zhilong, Li, Zhouli
Publicado:
MDPI AG
Materias:
Acceso en liña:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Engadir etiqueta
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!
Descripción
Resumo:Convolutional Neural Networks (<inline-formula>CNNs</inline-formula>) have achieved remarkable results in the field of infrared image enhancement. However, the research on the visual perception mechanism and the objective evaluation indicators for enhanced infrared images is still not in-depth enough. To make the subjective and objective evaluation more consistent, this paper uses a perceptual metric to evaluate the enhancement effect of infrared images. The perceptual metric mimics the early conversion process of the human visual system and uses the normalized Laplacian pyramid distance (<inline-formula>NLPD</inline-formula>) between the enhanced image and the original scene radiance to evaluate the image enhancement effect. Based on this, this paper designs an infrared image-enhancement algorithm that is more conducive to human visual perception. The algorithm uses a lightweight Fully Convolutional Network (<inline-formula>FCN</inline-formula>), with <inline-formula>NLPD</inline-formula> as the similarity measure, and trains the network in a self-supervised manner by minimizing the <inline-formula>NLPD</inline-formula> between the enhanced image and the original scene radiance to achieve infrared image enhancement. The experimental results show that the infrared image enhancement method in this paper outperforms existing methods in terms of visual perception quality, and due to the use of a lightweight network, it is also the fastest enhancement method currently.
ISSN:2079-9292
DOI:10.3390/electronics13183695
Fonte:Advanced Technologies & Aerospace Database