Yolo-pest: an optimized YoloV8x for detection of small insect pests using smart traps

Abstract

Fruit flies and fall-armyworm are one of the major insect pest that adversely affect fruit and crops, whereas fall-armyworm is also a highly destructive pest in maize crop but also damage other economically important field crops and vegetables. Adults of both pests can fly, making it hard to monitor them in the field. This study focuses on fine-tuning the YoloV8x model for automated monitoring and identifying insect pests, like fruit flies and fall-armyworms, in open fields and closed environments using IoT-based Smart Traps. The conventional techniques for monitoring of these insect pests involve pheromone attractants and sticky traps that require regular farm visits. We developed an IoT-based device, called Smart Trap, that attracts insect pests with pheromones and captures real-time images using cameras and IoT sensors. Its main objective is automated pest monitoring in fields or indoor grain storage houses. Images captured by smart traps are transmitted to the server, where Yolo-pest, a fine-tuned YoloV8x model with customized hyperparameters performs in real time for object detection. The performance of the smart trap was evaluated in a mango orchard (Fruit Flies) and maize field (fall Armyworm) in an arid climate, achieving a 94% average detection accuracy. The validation process on grayscale and coloured images further confirmed the model's consistent accuracy in identifying insect pests in maze crop and mango orchards. The mobile application also enhances the practical utility as having a user-friendly interface for real time identification of insect pest. Farmers can easily acces the information and data remotely that empowering them for efficient pest maangment.