Improved YOLOX-Tiny network for detection of tobacco brown spot disease

Jianwu Lin; Dianzhi Yu; Renyong Pan; Jitong Cai; Jiaming Liu; Licai Zhang; Xingtian Wen; Xishun Peng; Tomislav Cernava; Safa Oufensou; Quirico Migheli; Xiaoyulong Chen; Xin Zhang

doi:10.3389/fpls.2023.1135105

Improved YOLOX-Tiny network for detection of tobacco brown spot disease

Front Plant Sci. 2023 Feb 14:14:1135105. doi: 10.3389/fpls.2023.1135105. eCollection 2023.

Authors

Jianwu Lin^{1

2

3}, Dianzhi Yu^{1

2}, Renyong Pan^{1

2}, Jitong Cai^{1

2}, Jiaming Liu^{1

2}, Licai Zhang^{1

2}, Xingtian Wen^{1

2}, Xishun Peng^{1

2}, Tomislav Cernava⁴, Safa Oufensou⁵, Quirico Migheli⁵, Xiaoyulong Chen^{2

3}, Xin Zhang^{1

2}

Affiliations

¹ College of Big Data and Information Engineering, Guizhou University, Guiyang, China.
² Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University, Guizhou Provincial Science and Technology Department, Guiyang, China.
³ International Jointed Institute of Plant Microbial Ecology and Resource Management in Guizhou University, Ministry of Agriculture, China Association of Agricultural Science Societies, Guiyang, China.
⁴ Institute of Environmental Biotechnology, Graz University of Technology, Graz, Austria.
⁵ Dipartimento di Agraria and Nucleo di Ricerca sulla Desertificazione - NRD, Università degli Studi di Sassari, Sassari, Italy.

Abstract

Introduction: Tobacco brown spot disease caused by Alternaria fungal species is a major threat to tobacco growth and yield. Thus, accurate and rapid detection of tobacco brown spot disease is vital for disease prevention and chemical pesticide inputs.

Methods: Here, we propose an improved YOLOX-Tiny network, named YOLO-Tobacco, for the detection of tobacco brown spot disease under open-field scenarios. Aiming to excavate valuable disease features and enhance the integration of different levels of features, thereby improving the ability to detect dense disease spots at different scales, we introduced hierarchical mixed-scale units (HMUs) in the neck network for information interaction and feature refinement between channels. Furthermore, in order to enhance the detection of small disease spots and the robustness of the network, we also introduced convolutional block attention modules (CBAMs) into the neck network.

Results: As a result, the YOLO-Tobacco network achieved an average precision (AP) of 80.56% on the test set. The AP was 3.22%, 8.99%, and 12.03% higher than that obtained by the classic lightweight detection networks YOLOX-Tiny network, YOLOv5-S network, and YOLOv4-Tiny network, respectively. In addition, the YOLO-Tobacco network also had a fast detection speed of 69 frames per second (FPS).

Discussion: Therefore, the YOLO-Tobacco network satisfies both the advantages of high detection accuracy and fast detection speed. It will likely have a positive impact on early monitoring, disease control, and quality assessment in diseased tobacco plants.

Keywords: YOLOX-Tiny network; convolutional block attention modules; hierarchical mixed-scale units; object detection; tobacco brown spot disease.

Grants and funding

This study was supported by the National Key Research and Development Program of China (2021YFE0107700), the National Natural Science Foundation of China (31960555), Guizhou Provincial Science and Technology Program (2019-1410; HZJD[2022]001), Outstanding Young Scientist Program of Guizhou Province (KY2021-026), and Guizhou University Cultivation Project (2019-04). In addition, the study received support by the Program for Introducing Talents to Chinese Universities (111 Program, D20023).