NON-CONTACT SENSING OF PLANT WATER STRESS BY 
IR THERMOMETRY AND IMAGE PROCESSING

M.Kacira, P.P. Ling, T.Short

This paper is a progress report on the research using infrared thermometry and image processing to detect plant water stress for controlled environment plant production. A theoretically driven crop water stress index (CWSI) was used to quantify the level of the water stress on New Guinea Impatiens. Furthermore, top projected canopy area (TPCA) information obtained from a CCD monochrome camera was also used to monitor plant growth and movement for well-watered and water-stressed plants to find the earliest time and corresponding CWSI value that the water stress can be detected. The results showed that as the transpiration rate decreased, the leaf temperature of the plant canopy increased resulting in higher values of CWSI. The detection of water stress by CWSI and TPCA was possible one day before it was visible to the human eye. Using the two techniques it was able to identify water-stressed plants when CWSI was 0.22 for New Guinea Impatiens used in this experiment.

Keywords: Water stress, CWSI, Image processing, IR, Evapotranspiration, Irrigation, Automatic control.