Skip to main content
ARS Home » Plains Area » Bushland, Texas » Conservation and Production Research Laboratory » Soil and Water Management Research » Research » Publications at this Location » Publication #294569
Title: Wireless computer vision system for crop stress detection

Author
item Casanova, Joaquin
item O`Shaughnessy, Susan
item Evett, Steven - Steve

Submitted to: ASA-CSSA-SSSA Annual Meeting Abstracts
Publication Type: Abstract Only
Publication Acceptance Date: 8/19/2013
Publication Date: 11/3/2013
Citation: Casanova, J.J., Oshaughnessy, S.A., Evett, S.R. 2013. Wireless computer vision system for crop stress detection [abstract]. ASA-CSSA-SSSA Annual Meeting Abstracts. Session 196-7, p.123.

Interpretive Summary: Plants can suffer stress from disease or lack of water. Diseased plants may not be able to use water efficiently or produce profitable yields. Therefore, withholding irrigation from diseased plants may save water. However, it is difficult to separate diseased and water stressed plants from healthy plants in a large size field. One method to aide in the detection of plant stress due to water or disease is with a computer vision instrument. This device acquires digital images, and separates information about the image into percent healthy and stressed plant. This information could be used by farmers to improve crop management. ARS scientists from Bushland programmed the computer vision algorithm onto a wireless microcomputer with a small digital camera, and temperature sensor that could be used in the field for irrigation control. The device analyzed digital images of diseased and healthy wheat throughout a growing season. Results showed that there was significant effect of crop stress on color derived from the images.

Technical Abstract: Knowledge of soil water deficits, crop water stress, and biotic stress from disease or insects is important for optimal irrigation scheduling and water management. Crop spectral reflectances provide a means to quantify visible and near infrared thermal crop stress, but in-situ measurements can be cumbersome, expensive, and affected by the amount of vegetation cover. Computer vision, the algorithmic analysis of digital images, offers an inexpensive way to remotely detect crop stress. In this study, wheat irrigated at full and deficit levels was inoculated with wheat streak mosaic virus at different times during the season. Digital images taken of the crop over time were segmented into shadow, soil, and vegetation pixels using hue and value thresholds determined by expectation maximization (EM). The mean hue of the vegetation pixels was used to determine whether or not the crop was water or disease stressed. Results showed that the vegetation hue determined by the EM algorithm showed significant effects from irrigation level and infection status. While the image analysis for the 2011 and 2012 seasons was primarily done with relatively large images taken in the field and processed later on a PC, it was also demonstrated that near real-time image analysis could be accomplished with a portable wireless computer vision system using inexpensive microcontrollers during the 2013 season. Additionally, the wireless system included a measurement of surface temperature by an infrared sensor which can help disambiguate water and disease stressed crops. Such a system could be used in the future for irrigation scheduling applications. This study shows that vegetation hue obtained through computer vision is a viable option for determining crop stress in irrigation scheduling.