AUTHOR=Qiu Fasong , Zhai Zhiqiang , Li Yulin , Yang Jiankang , Wang Haiyuan , Zhang Ruoyu 

TITLE=UAV imaging and deep learning based method for predicting residual film in cotton field plough layer

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.1010474

DOI=10.3389/fpls.2022.1010474

ISSN=1664-462X

ABSTRACT=In this paper, a method for predicting residual film content in the cotton field plough layer based on UAV imaging and deep learning was proposed to solve the issues of high labour intensity, low efficiency, and high cost in residual film content monitoring in the cotton field plough layer. An aerial image of residual film on the cotton field surface was collected by UAV, and residual film content in the plough layer of the corresponding plot was obtained by the manual sampling method. Based on the three deep learning frameworks of LinkNet, FCN, and DeepLabv3, a segmentation model of residual film on the cotton field surface was built. After comparing the segmentation results, DeepLabv3 was determined to be the best model for segmenting residual film on the cotton field surface, and then the residual film area on the cotton field surface was obtained. In addition, a linear regression prediction model between the residual film coverage area on the cotton field surface and the residual film content in the plough layer was built. The results of the experiment show that the correlation coefficient (R2), root mean square error, and average relative error of the prediction of residual film content in the plough layer are 0.83, 0.48, and 11.06%, respectively. The results of the study show that a quick and accurate prediction of residual film content in the cotton field plough layer can be realized based on UAV imaging and deep learning, which can provide certain technical support for monitoring and evaluating residual film pollution in the cotton field plough layer.