A Real-time Automatic Dengue Breeding Zone Detection and Prevention Scheme based on MobileNetV2 Enabled Autonomous Drone

Climate change is causing extreme weather conditions that have led to rapid transmission of one of the deadliest vector-borne diseases on earth, Dengue. The main form to combat this disease is to control the Aedes mosquito population by searching for and eliminating the potential mosquito breeding areas. Major challenges in this case are to locate, monitor, reach and spray insecticides in critical locations, such as out-of-sight spots in high-rise buildings, ponds, and side areas of large drains. One possible solution is to use a drone that can be controlled to reach such locations from above the ground. However, to handle the out-of-sight or unapproachable locations, it is extremely difficult to automatically identify the target locations and spray the insecticides. In this paper, a deep learning-based algorithm is incorporated in a proposed hexacopter drone-based effective method for automatic identification of mosquito breeding grounds from drone images. Due to a wide variation of the target locations, apart from existing datasets, a comprehensive dataset is created in this work. Moreover, the proposed design includes autonomous navigation to the target spot and spraying the insecticides to eliminate mosquito larvae. It is to be noted that the detected location data of these areas are also preserved for creating a better prediction model that can efficiently map the dengue risk zones. The proposed design is being implemented in an autonomous drone flying in real-time and the target zone identification performance is evaluated in different critical locations. From extensive experiments on several real-life areas, a very accurate location estimation and spraying is achieved.