Comparison of Deep Learning Frameworks For Rice Disease Mapping From UAV Multispectral Imaging
For agricultural researchers and practitioners, this work provides a benchmark for rice disease mapping using UAV imagery, though it is incremental as it applies existing architectures to a specific dataset.
The study compared CNN and transformer-based models for segmenting bacterial leaf blight severity in rice from UAV multispectral imagery, finding that U-Net++ with EfficientNet-B3 achieved the highest mean IoU of 97.62%, while transformer models showed lower accuracy. Lightweight CNNs were deemed more reliable for operational monitoring.
In this study, UAV multispectral imagery is used to segment the severity of bacterial leaf blight (BLB) in rice using convolutional neural networks (CNNs) and transformer-based models. The evaluated architectures include U-Net with a ResNet- 101 encoder, U-Net++ with EfficientNet-B3 and EfficientNetB7, DeepLabV3+, and SegFormer, all trained under a common pipeline with three input configurations (multispectral only, multispectral+NDVI, and multispectral+NDRE). Experiments are conducted using the publicly available BLB dataset with performance reported using mean IoU (mIoU), mean F1 (mF1), mean accuracy (mAcc), precision, and recall. U-Net++ with EfficientNet-B3 achieved the highest performance, with an mIoU of 97.62%. SegFormer obtained lower segmentation accuracy but comparable inference speed. Overall, the results indicate that lightweight CNN backbones remain more reliable for operational BLB monitoring while integration of vegetation indices provides small and consistent improvements. The study also highlights the value of standardised UAV datasets to compare disease mapping methods and encourages the use of CNN architectures for field implementation.