With the development of agriculture, the illegal management of field compost, a non-point source of pollution, has become a growing concern as a source of water and environmental pollution. However, detection of field compost through field surveys is difficult and costly. Therefore, following the recent increase in research on the detection and management of field compost, this study aims to detect field compost using high-resolution satellite imagery. We collected satellite image data in the blue, green, red, and near-infrared (NIR) bands over agricultural fields in Gyeongsangnam-do. We labeled unmanaged field compost and evaluated the performance of field compost detection using deep learning models. A total of four models for field compost detection were presented: semantic segmentation detection using U-Net, object segmentation detection using Mask Region-based Convolutional Neural Network (R-CNN), object detection using Faster R-CNN, and a hybrid model combining Faster R-CNN and U-Net for semantic segmentation detection. In the accuracy evaluation based on pixel accuracy and mean Intersection-over-Union (mIoU), the object-based model was more reliable than other models, and the combined model proposed in this paper showed the highest mIoU of 0.68. Based on these results, it is expected that the cost advantage of satellite imagery and the high reliability of field compost detection through unmanned aerial vehicles can be utilized to solve the current problems of field compost detection. In future studies, if the methodology and the quality of satellite images can be improved, accurate field compost detection will be possible.



KeywordsField-compost, Deep learning, KOMPSAT-3, Instance segmentation