Intelligent thermal image-based sensor for affordable measurement of crop canopy temperature

Abstract

Crop canopy temperature measurement is necessary for monitoring water stress indicators such as the Crop Water Stress Index (CWSI). Water stress indicators are very useful for irrigation strategies management in the precision agriculture context. For this purpose, one of the techniques used is thermography, which allows remote temperature measurement. However, the applicability of these techniques depends on being affordable, allowing continuous monitoring over multiple field measurement. In this article, the development of a sensor capable of automatically measuring the crop canopy temperature by means of a low-cost thermal camera and the implementation of artificial intelligence-based image segmentation models is presented. In addition, we provide results on almond trees comparing our system with a commercial thermal camera, in which an R-squared of 0.75 is obtained.

Code and data availability

The supplied blocks contain no public phenotype/trait datasets, thermal/visible image collections, author analysis code, or trained model checkpoints with availability statements or public URLs. The paper describes a low-cost canopy temperature sensor and segmentation models (SVM, deep learning) developed in MATLAB, K,

No evidence-backed public reproduction asset is currently recorded.