드론 방제의 최적화를 위한 딥러닝 기반의 밀도맵 추정

초록

Global population growth has resulted in an increased demand for food production. Simultaneously, agingrural communities have led to a decrease in the workforce, thereby increasing the demand for automation inagriculture. Drones are particularly useful for unmanned pest control fields. However, the current method of uniformspraying leads to environmental damage due to overuse of pesticides and drift by wind. To address this issue, it isnecessary to enhance spraying performance through precise performance evaluation. Therefore, as a foundational studyaimed at optimizing drone-based pest control technologies, this research evaluated water-sensitive paper (WSP) viadensity map estimation using convolutional neural networks (CNN) with a encoder-decoder structure. To achieve moreaccurate estimation, this study implemented multi-task learning, incorporating an additional classifier for imagesegmentation alongside the density map estimation classifier. The proposed model in this study resulted in a R-squared(R²) of 0.976 for coverage area in the evaluation data set, demonstrating satisfactory performance in evaluating WSP atvarious density levels. Further research is needed to improve the accuracy of spray result estimations and develop areal-time assessment technology in the field.

키워드