A Machine Learning Approach for Identifying Mosquito Breeding Sites via Drone Images

摘要: Dengue is one of the deadly and fast spreading diseases in Sri Lanka. The female Aedes mosquito dengue vector these mosquitoes breed clear non-flowing water. Public Health Inspectors (PHIs) are tasked with detecting eliminating such water collection areas. However, they face problem potential breeding sites hard-to-reach With technological development, drones come as most cost effective unmanned vehicles to access places that a man cannot access. This paper presents novel approach for identifying areas via drone images through distinct coloration those by applying Histogram Oriented Gradients (HOG) algorithm. Using HOG algorithm, we detect retention using images.