Skip to main content
ARS Home » Northeast Area » Kearneysville, West Virginia » Appalachian Fruit Research Laboratory » Innovative Fruit Production, Improvement, and Protection » Research » Publications at this Location » Publication #252966

Title: Hyperspectral image analysis for plant stress detection

item Kim, James
item Glenn, David
item Park, Johnny - Purdue University
item Ngugi, Henry - Pennsylvania State University
item Lehman, Brian - Pennsylvania State University

Submitted to: Proceedings of the American Society of Agricultural and Biological Engineers International (ASABE)
Publication Type: Proceedings
Publication Acceptance Date: 4/25/2010
Publication Date: 5/17/2010
Citation: Kim, Y., Glenn, D.M., Park, J., Ngugi, H.K., Lehman, B.L. 2010. Hyperspectral image analysis for plant stress detection. Proceedings of the American Society of Agricultural and Biological Engineers International (ASABE). David L. Lawrence Convention Center, Pittsburgh, PA, June 20-23, 2010. ASABE Paper No. 10-09114.

Interpretive Summary:

Technical Abstract: Abiotic and disease-induced stress significantly reduces plant productivity. Automated on-the-go mapping of plant stress allows timely intervention and mitigating of the problem before critical thresholds are exceeded, thereby, maximizing productivity. A hyperspectral camera analyzed the spectral signature of plant leaves in order to identify the plant stress. Different levels of water and fire blight disease (caused by Erwinia amylovora) were created on young apple trees ('Buckeye Gala') in a greenhouse and continuously monitored with a hyperspectral camera. The hyperspectral cube images were processed for calibration with dark and white cubes. Each spectral image at a specific wavelength was extracted to estimate reflectance. Spectral profiles were generated on 400 nm – 1000 nm wavelength range for water and disease-stressed leaves compared to the healthy leaves. Various properties of spectral profiles were investigated and correlated to the stress levels to find the highest correlation index. The analyzed results deliver the decision support for plant stress detection and management.