End-to-end pipeline for simultaneous temperature estimation and super resolution of low-cost uncooled infrared camera frames for precision agriculture applications

Download PDF
Open Webpage

Navot Oz, Nir A. Sochen, David Mendlovic, Iftach Klapp

Published: 2025, Last Modified: 14 Nov 2025Comput. Electron. Agric. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Deep learning estimates radiometry from low-cost uncooled infrared cameras.•Frame inference under one second supports real-time correction and superresolution.•Eliminates the need for constant recalibration across different uncooled infrared cameras.•Validated on real-world thermal imaging datasets.•Mean CWSI errors were 1.42% at two-times and 1.86% at four-times.