UAV-based aerial imaging and path optimization to combat mosquito-borne diseases.

The Aedes aegypti mosquito is the cause of the transmission of diseases such as Dengue, Chikungunya, Yellow fever, and Zika. Dengue is a viral illness and currently, there is no specific treatment for the disease. The best possible way to prevent this disease is to avoid the reproduction of mosquitoes. Reproduction of mosquitoes is avoided by identifying and treating the Possible Breeding Habitats (PBH) such as Stagnant water in Tires, water tanks, and Puddles. The PBH can be identified using Unmanned Aerial Vehicles (UAVs) better known as Drones which cover vast areas and are cost-effective. In this work, an aerial dataset containing the PBH is created which is obtained by UAV. Each image is annotated manually to identify the objects of interest. Automatic detection of objects is experimented with by using YOLOv8 and YOLOv11 algorithms of all variants where YOLOv11 outperformed YOLOv8 with the metrics of mAP50 as 0.97, mAP50-90 as 0.61, Precision as 0.96, and recall as 0.88. The Travelling Salesman Problem is used to optimize the path planning and spray the larvicides at every waypoint using UAVs by reducing energy and battery consumption. Our approach detects and treats mosquito habitats by using Unmanned Aerial Vehicles (UAVs).