Recurrent Super-Resolution Method for Enhancing Low Quality Thermal Facial Data

TL;DR

This paper introduces a novel deep learning-based multi-image super-resolution recurrent neural network designed to enhance low-resolution thermal facial images, significantly improving image quality for driver monitoring systems.

Contribution

The study develops and trains a new fully convolutional recurrent neural network specifically for thermal image super-resolution, demonstrating superior performance over traditional methods.

Findings

Achieved a mean PSNR of 39.24 for 4x super-resolution.

Outperformed bicubic interpolation in both quantitative and qualitative assessments.

Validated on thermal data from 30 subjects with testing on 6 subjects.

Abstract

The process of obtaining high-resolution images from single or multiple low-resolution images of the same scene is of great interest for real-world image and signal processing applications. This study is about exploring the potential usage of deep learning based image super-resolution algorithms on thermal data for producing high quality thermal imaging results for in-cabin vehicular driver monitoring systems. In this work we have proposed and developed a novel multi-image super-resolution recurrent neural network to enhance the resolution and improve the quality of low-resolution thermal imaging data captured from uncooled thermal cameras. The end-to-end fully convolutional neural network is trained from scratch on newly acquired thermal data of 30 different subjects in indoor environmental conditions. The effectiveness of the thermally tuned super-resolution network is validated quantitatively as well as qualitatively on test data of 6 distinct subjects. The network was able to achieve a mean peak signal to noise ratio of 39.24 on the validation dataset for 4x super-resolution, outperforming bicubic interpolation both quantitatively and qualitatively.