Attention-optimized DeepLab V3 + for automatic estimation of cucumber disease severity

Kaiyu Li; Lingxian Zhang; Bo Li; Shufei Li; Juncheng Ma

doi:10.1186/s13007-022-00941-8

Attention-optimized DeepLab V3 + for automatic estimation of cucumber disease severity

Plant Methods. 2022 Sep 6;18(1):109. doi: 10.1186/s13007-022-00941-8.

Authors

Kaiyu Li¹, Lingxian Zhang^{2

3}, Bo Li⁴, Shufei Li¹, Juncheng Ma⁵

Affiliations

¹ College of Information and Electrical Engineering, China Agricultural University, Beijing, 100083, China.
² College of Information and Electrical Engineering, China Agricultural University, Beijing, 100083, China. zhanglx@cau.edu.cn.
³ Key Laboratory of Agricultural Informationization Standardization, Ministry of Agriculture and Rural Affairs, Beijing, 100083, China. zhanglx@cau.edu.cn.
⁴ Beijing Information Science and Technology University, 100192, Beijing, China.
⁵ Institute of Environment and Sustainable Development in Agriculture, Chinese Academy of Agricultural Sciences, Beijing, 100081, China. majuncheng@caas.cn.

Abstract

Background: Automatic and accurate estimation of disease severity is critical for disease management and yield loss prediction. Conventional disease severity estimation is performed using images with simple backgrounds, which is limited in practical applications. Thus, there is an urgent need to develop a method for estimating the disease severity of plants based on leaf images captured in field conditions, which is very challenging since the intensity of sunlight is constantly changing, and the image background is complicated.

Results: This study developed a simple and accurate image-based disease severity estimation method using an optimized neural network. A hybrid attention and transfer learning optimized semantic segmentation model was proposed to obtain the disease segmentation map. The severity was calculated by the ratio of lesion pixels to leaf pixels. The proposed method was validated using cucumber downy mildew, and powdery mildew leaves collected under natural conditions. The results showed that hybrid attention with the interaction of spatial attention and channel attention can extract fine lesion and leaf features, and transfer learning can further improve the segmentation accuracy of the model. The proposed method can accurately segment healthy leaves and lesions (MIoU = 81.23%, FWIoU = 91.89%). In addition, the severity of cucumber leaf disease was accurately estimated (R² = 0.9578, RMSE = 1.1385). Moreover, the proposed model was compared with six different backbones and four semantic segmentation models. The results show that the proposed model outperforms the compared models under complex conditions, and can refine lesion segmentation and accurately estimate the disease severity.

Conclusions: The proposed method was an efficient tool for disease severity estimation in field conditions. This study can facilitate the implementation of artificial intelligence for rapid disease severity estimation and control in agriculture.

Keywords: Attention mechanism; DeepLab V3 +; Disease severity; Semantic segmentation; Transfer learning.