Halyomorpha Halys Detection in Orchard from UAV Images Using Convolutional Neural Networks

Halyomorpha Halys, commonly known as the brown marmorated stink bug, is an invasive insect that causes significant damage in orchards. Neural networks have the potential to improve insect pest detection and classification in modern agriculture, which can lead to better pest management. The detection of these insects in orchards using drones imposes special problems because the images are taken from a limited distance and the foliage of the trees makes detection difficult. In this article, we studied the possibility of detecting the respective insects using the latest generation YOLOv8 neural networks and compared the results with the well-known YOLOv5 network. The results were obviously better for YOLOv8 (accuracy of 94.55%). However, satisfactory results were also obtained in the case of YOLOv5 (accuracy of 90.91%).