Yolov4 Based Rice Fields Classification from High-Resolution Images Taken by Drones.

In recent years, artificial intelligence (AI) technology has been used in computer vision to extract and analyze specific information from images. This research aims to apply AI in the field of agriculture. In this study, the you only look once version4 (YOLOv4) based on scaled-up feature fusion (YOLOv4-SUFF) has been implemented for rice fields detection from high-resolution images taken by an unmanned aerial vehicle (UAV). YOLOv4-SUFF consists of an extra layer which can extract special feature maps for the detector. This makes the proposed model YOLOv4-SUFF get more information during the stage of feature fusion. The experimental results show that the YOLOv4-SUFF has provided the best performance in terms of an average precision at 86.78% compared with other models.