Downy mildew disease poses a significant threat to Kimchi cabbage, a key agricultural product in Korea. Early detection is crucial for preventing the disease and mitigating its physical impact. Hyperspectral imaging can capture data across a broad spectrum, enabling early detection before visible symptoms manifest. Combining a hyperspectral camera with an unmanned aerial vehicle (UAV) can establish a non-destructive, field-scale disease detection system. This thesis presents two studies conducted in different kimchi cabbage fields, each analyzed using a distinct approach. The study, conducted in an autumn kimchi cabbage field, employed the SLIC algorithm to segment aerial hyperspectral images. This segmentation isolated hyperspectral patches of diseased kimchi cabbage leaves, which were then utilized to train a three-dimensional residual network (3D-ResNet) to detect early signs of disease and their locations in the field. The model achieved an overall accuracy of 87.6%. This study successfully detected downy mildew diseases using different methodologies. Future research should focus on leveraging the advantages of each approach to develop a more robust disease detection model.
|