AUTHOR=Yu Jun , Cheng Tao , Cai Ning , Lin Fenfang , Zhou Xin-Gen , Du Shizhou , Zhang Dongyan , Zhang Gan , Liang Dong 

TITLE=Wheat lodging extraction using Improved_Unet network

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.1009835

DOI=10.3389/fpls.2022.1009835

ISSN=1664-462X

ABSTRACT=The accurate extraction of wheat lodging areas can provide important technical support for post-disaster yield loss assessment and lodging-resistant wheat breeding. At present, wheat lodging assessment is facing the contradiction between timeliness and accuracy, and there is also a lack of effective lodging extraction methods. This study aims to propose a wheat lodging assessment method applicable to multiple flight heights. The quadrotor UAV was used to collect high-definition images of wheat canopy at the grain filling and maturity stages, and the Unet network was improved based on the Involution operator, and the results were compared with Segnet, Unet and DeeplabV3+ networks. The performance of the improved Unet network (Improved_Unet) was evaluated using the data collected from different flight heights, and the robustness of the improved network was verified with data from different years and different locations. The experimental results show that (1) The Improved_Unet network was better than other networks in terms of segmentation accuracy, and was more effective in extracting wheat lodging areas at the maturity stage. The four evaluation indicators, Precision, Dice, Recall, and Accuracy, were all the highest, which were 0.907, 0.929, 0.884, and 0.933, respectively; (2) The Improved_Unet network had the strongest robustness, and its Precision, Dice, Recall, and Accuracy reached 0.851, 0.892, 0.844, and 0.885, respectively, at the verification stage of using lodging data from other wheat production areas; and (3) The flight height had an influence on the lodging segmentation accuracy. The verification results of 20 m, 40 m, 80 m and 120 m show that the 20-m flight height had the best performance, and the segmentation accuracy decreased with the increase of the flight height. The Precision, Dice, Recall, and Accuracy of Improved_Unet changed from 0.907 to 0.845, from 0.929 to 0.864, from 0.884 to 0.841, and from 0.933 to 0.881, respectively. In conclusion, the deep learning network proposed in this study can effectively extract the areas of wheat lodging, and the different height fusion models developed from this study can provide a more comprehensive reference for the automatic extraction of wheat lodging.