An Approach for Rice Bacterial Leaf Streak Disease Segmentation and Disease Severity Estimation

Abstract

Rice bacterial leaf streak (BLS) is a serious disease in rice leaves and can seriously affect the quality and quantity of rice growth. Automatic estimation of disease severity is a crucial requirement in agricultural production. To address this, a new method (termed BLSNet) was proposed for rice and BLS leaf lesion recognition and segmentation based on a UNet network in semantic segmentation. An attention mechanism and multi-scale extraction integration were used in BLSNet to improve the accuracy of lesion segmentation. We compared the performance of the proposed network with that of DeepLabv3+ and UNet as benchmark models used in semantic segmentation. It was found that the proposed BLSNet model demonstrated higher segmentation and class accuracy. A preliminary investigation of BLS disease severity estimation was carried out based on our BLS segmentation results, and it was found that the proposed BLSNet method has strong potential to be a reliable automatic estimator of BLS disease severity.

High-throughput phenotyping of leaf discs infected with grapevine downy mildew using shallow convolutional neural networks

“…In a recent study this approach was demonstrated for black rot, black measles, leaf blight and mites on grapevine leaves [39]. Further studies have shown promising detection of leaf localized diseases using semantic segmentation for coffee and rice [40,41] However, the results obtained with the simple binary classification setup presented here clearly show a high correlation with standard scoring methods indicating its suitability for highthroughput phenotyping of leaf discs. Furthermore, it keeps the requirements in terms of computational resources and image training sets to a minimum allowing a fast adaptation to new plant-pathogen systems.…”

High-Throughput Phenotyping of Leaf Discs Infected with Grapevine Downy Mildew Using Shallow Convolutional Neural Networks

“…In a recent study this approach was demonstrated for black rot, black measles, leaf blight and mites on grapevine leaves [39]. Further studies have shown promising detection of leaf localized diseases using semantic segmentation for coffee and rice [40,41] However, the results obtained with the simple binary classification setup presented here clearly show a high correlation with standard scoring methods indicating its suitability for high-throughput phenotyping of leaf discs. Furthermore, it keeps the requirements in terms of computational resources and image training sets to a minimum allowing a fast adaptation to new plant-pathogen systems.…”

Autonomous Detection of Spodoptera frugiperda by Feeding Symptoms Directly from UAV RGB Imagery

“…Konstantinos et al developed CNN models to perform plant disease detection and diagnosis using simple leaves images of healthy and diseased plants through deep learning methodologies [23]. Chen et al used the UNet-based BLSNet to automatic identify and segment the diseased region of Rice bacterial leaf streak from the camera photos [24]. The appearance of the attention mechanism also further improves the performance of the network [22,25].…”