WSRD-Net: A Convolutional Neural Network-Based Arbitrary-Oriented Wheat Stripe Rust Detection Method

Haiyun Liu; Lin Jiao; Rujing Wang; Chengjun Xie; Jianming Du; Hongbo Chen; Rui Li

doi:10.3389/fpls.2022.876069

WSRD-Net: A Convolutional Neural Network-Based Arbitrary-Oriented Wheat Stripe Rust Detection Method

Front Plant Sci. 2022 May 24:13:876069. doi: 10.3389/fpls.2022.876069. eCollection 2022.

Authors

Haiyun Liu^{1

2}, Lin Jiao^{1

3}, Rujing Wang^{1

2

4}, Chengjun Xie^{1

2}, Jianming Du¹, Hongbo Chen^{1

2}, Rui Li¹

Affiliations

¹ Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Science, Hefei, China.
² Science Island Branch, University of Science and Technology of China, Hefei, China.
³ School of Internet, Anhui University, Hefei, China.
⁴ Institutes of Physical Science and Information Technology, Anhui University, Hefei, China.

Abstract

Wheat stripe rusts are responsible for the major reduction in production and economic losses in the wheat industry. Thus, accurate detection of wheat stripe rust is critical to improving wheat quality and the agricultural economy. At present, the results of existing wheat stripe rust detection methods based on convolutional neural network (CNN) are not satisfactory due to the arbitrary orientation of wheat stripe rust, with a large aspect ratio. To address these problems, a WSRD-Net method based on CNN for detecting wheat stripe rust is developed in this study. The model is a refined single-stage rotation detector based on the RetinaNet, by adding the feature refinement module (FRM) into the rotation RetinaNet network to solve the problem of feature misalignment of wheat stripe rust with a large aspect ratio. Furthermore, we have built an oriented annotation dataset of in-field wheat stripe rust images, called the wheat stripe rust dataset 2021 (WSRD2021). The performance of WSRD-Net is compared to that of the state-of-the-art oriented object detection models, and results show that WSRD-Net can obtain 60.8% AP and 73.8% Recall on the wheat stripe rust dataset, higher than the other four oriented object detection models. Furthermore, through the comparison with horizontal object detection models, it is found that WSRD-Net outperforms horizontal object detection models on localization for corresponding disease areas.

Keywords: arbitrary-oriented; convolutional neural network; deep learning; detection; wheat strip rust.