Visible to the public A Comparative Analysis of Deep Learning based Super-Resolution Techniques for Thermal Videos

TitleA Comparative Analysis of Deep Learning based Super-Resolution Techniques for Thermal Videos
Publication TypeConference Paper
Year of Publication2020
AuthorsGautam, A., Singh, S.
Conference Name2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT)
Date PublishedAug. 2020
ISBN Number978-1-7281-5821-1
Keywordsauto-encoder, benchmark thermal datasets, Comparative Analysis, Databases, Deep Learning, deep neural networks, deep video, expensive optical sensors, healthcare, Image resolution, image sequences, Imaging, infrared imaging, law enforcement, learning (artificial intelligence), machine learning, Metrics, neural nets, Neural networks, object detection, optical precision, OSU color, pedestrian database, pedestrians, poor resolution, pubcrawl, resilience, Resiliency, Scalability, SRGAN, Super resolution, super resolution techniques, super-resolution algorithms, super-resolution techniques, Thermal analysis, thermal cameras, thermal frames, thermal imaging, thermal video dataset, thermal videos, video frame resolution, video signal processing, video streaming, video streams, Videos

Video streams acquired from thermal cameras are proven to be beneficial in diverse number of fields including military, healthcare, law enforcement, and security. Despite the hype, thermal imaging is increasingly affected by poor resolution, where it has expensive optical sensors and inability to attain optical precision. In recent years, deep learning based super-resolution algorithms are developed to enhance the video frame resolution at high accuracy. This paper presents a comparative analysis of super resolution (SR) techniques based on deep neural networks (DNN) that are applied on thermal video dataset. SRCNN, EDSR, Auto-encoder, and SRGAN are also discussed and investigated. Further the results on benchmark thermal datasets including FLIR, OSU thermal pedestrian database and OSU color thermal database are evaluated and analyzed. Based on the experimental results, it is concluded that, SRGAN has delivered a superior performance on thermal frames when compared to other techniques and improvements, which has the ability to provide state-of-the art performance in real time operations.

Citation Keygautam_comparative_2020