Automated vision-based system for monitoring Asian citrus psyllid in orchards utilizing artificial intelligence

Abstract

Specialty crop growers face challenges from numerous diseases and pests. For example, the Asian citrus psyllid (ACP) is a key pest of citrus due to its role as vector of huanglongbing (HLB) (greening disease). There is no known cure for HLB, but vector management is critical, both for slowing spread and attenuating symptoms in infected trees. Therefore, monitoring ACP population, as well as other pest populations, is an essential management component for timing and assessment of control actions. Manual crop scouting is often labor intensive and time consuming. In this work, an automated system was developed and evaluated utilizing machine vision and artificial intelligence to monitor ACP in groves. This system comprised a tapping mechanism to collect insects from the tree’s branches and a board with a grid of cameras for image acquisition. A software was developed using two convolutional neural-networks to accurately detect and distinguish psyllids from other insects and debris fallen from the tree. A GPS was utilized to automatically record individual tree position to facilitate data assessment on large groves. A precision and recall of 80% and 95%, respectively, was obtained on detecting ACPs on a sample of 90 young citrus trees. The system proved a great potential to automate scouting procedures in citrus and to be extended to other crop insects.