Deep Vision for Pest Detection in Corn Fields

Pest infestation detection is vital for crop health monitoring and precision agriculture. However, manual sampling can be tedious and ineffective in providing complete situational awareness. Various automatic pest detection and recognition solutions have been presented. However, most of these lack robustness due to the challenges present in unconstrained in-field environment that includes illumination variations, camouflage, background clutter, low resolution, shape deformations, sparse and dense population. To overcome these challenges, we propose a deep learning-based solution that employs YOLOv5 architecture to detect and classify three types of pests affecting corn crop. We evaluated the proposed system on images taken from a benchmark dataset AgriPest. To the best of our knowledge, the results obtained by our system are the highest amongst the state-of-the-art techniques reported on the same dataset, which shows the effectiveness of our proposed approach.