부산대학교 도서관

This abstract describes about a system that uses Unmanned Aerial Vehicles (UAV) with high resolution cameras and deep learning algorithms to detect insects in agriculture. This device would make it possible to quickly and precisely detect insects in crops and determine their species and infestation degree . The same technology can also identify other problems affecting crops, like fertilizer shortages or water stress. The deep learning program can find patterns and signs of these problems by examining the images acquired by the UAV, enabling farmers to take appropriate action before serious damage happens. This method has the potential to greatly reduce the time and resources needed for manual crop scouting and monitoring, as well as enhance insect detection precision and lower the use of insecticides. An important factor of using deep learning is not only it detects insects but also classify them into useful and harmful category.