AUTHOR=Wang Xuewei , Liu Jun , Liu Guoxu 

TITLE=Diseases Detection of Occlusion and Overlapping Tomato Leaves Based on Deep Learning

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 12 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2021.792244

DOI=10.3389/fpls.2021.792244

ISSN=1664-462X

ABSTRACT=Abstract: 
Background: In view of the existence of light shadow and branches occlusion and leaves overlapping conditions in the real natural environment, the problems such as slow detection speed, low detection accuracy, high missed detection rate and poor robustness in plant diseases and pests detection technology arise. 
Results: Based on YOLOv3-tiny network architecture, in order to reduce layer-by-layer loss of information during network transmission, learn from the idea of inverse-residual block, this study proposes a YOLOv3-tiny-IRB algorithm to optimize its feature extraction network, improve the gradient disappearance phenomenon during network deepening, avoid feature information loss, and realize network multi-layer feature multiplexing and fusion. The network is trained by the methods of expanding datasets and multi-scale strategies to obtain the optimal weight model.
Conclusion: The experimental results show that when the method is tested on the self-built tomato diseases and pests dataset, while ensuring the detection speed (206 FPS), the mAP under three conditions: a. deep separation, b. debris occlusion and c. leaves overlapping are 98.3%, 92.1% and 90.2%, respectively. Compared with the current mainstream object detection methods, the proposed method improves the detection accuracy of tomato diseases and pests under conditions of occlusion and overlapping in real natural environment.