ASABE Technical Library - Abstract

Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, view access and subscription options

Beyond Vision: mmWave MIMO Radar for Pest Detection in Challenging Agricultural Environments    

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2026 ASABE Annual International Meeting  2600990.(doi:10.13031/aim.202600990)
Authors:   Prem Raj, Mike Ojo, Partho Ghose, Al Bashir, Bijaya Sapkota, Katerina Graham, Arash Kheirodin, Azlan Zahid
Keywords:   mmWave Radar, Pest Detection, Precision Agriculture, Machine Learning

Abstract.

Early detection of small-scale agricultural pests is critical for preventing yield loss and reducing excessive pesticide use. However, conventional computer vision–based pest monitoring systems often fail under challenging field conditions, including occlusion within dense crop canopies and adverse environmental factors such as low illumination, fog, and rain. Radar signals are not sensitive to these environmental conditions. This paper explores a radar-based sensing approach for detecting small pests, such as aphids, using a low-power mmWave MIMO radar array. The proposed system leverages range-FFT values from the MIMO configuration of the mmWave radar sensor to capture subtle variations in reflected signals from the pest-affected plant leaves. Experiments are conducted on pepper plant samples under controlled conditions, both with and without pest infestation, to evaluate the feasibility of the approach. The results demonstrate that mmWave MIMO radar sensing can reliably classify plant samples as pest-free or infested with pests with 80% accuracy. This highlights the potential of the mmWave radar sensors as a complementary, non-contact, and robust sensing modality for in-field pest monitoring in precision agriculture.

(Download PDF)    (Export to EndNotes)