Early Detection of Rice Blast Using a Semi-Supervised Contrastive Unpaired Translation Iterative Network Based on UAV Images.

Abstract

Rice blast has caused major production losses in rice, and thus the early detection of rice blast plays a crucial role in global food security. In this study, a semi-supervised contrastive unpaired translation iterative network is specifically designed based on unmanned aerial vehicle (UAV) images for rice blast detection. It incorporates multiple critic contrastive unpaired translation networks to generate fake images with different disease levels through an iterative process of data augmentation. These generated fake images, along with real images, are then used to establish a detection network called RiceBlastYolo. Notably, the RiceBlastYolo model integrates an improved fpn and a general soft labeling approach. The results show that the detection precision of RiceBlastYolo is 99.51% under intersection over union (IOU 0.5 ) conditions and the average precision is 98.75% under IOU 0.5-0.9 conditions. The precision and recall rates are respectively 98.23% and 99.99%, which are higher than those of common detection models (YOLO, YOLACT, YOLACT++, Mask R-CNN, and Faster R-CNN). Additionally, external data also verified the ability of the model. The findings demonstrate that our proposed model can accurately identify rice blast under field-scale conditions.

Plant phenotyping relevance

UAV画像からイネの病害状態を直接推定する検出ネットワークを開発し、精度比較と外部データ検証も行っており、病害フェノタイピング手法が中心です。

Code and data availability

The article describes UAV-collected rice blast images (1702 images) and a RiceBlastYolo model, but contains no data availability statement, no public dataset deposit, and no author code repository. The only URLs present are CC BY license text and citations to prior work (EfficientDet, SwinIR, PAFPN), which are not this

No evidence-backed public reproduction asset is currently recorded.