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

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 of traditional methods for residual film content monitoring. Images of residual film on soil surface in the cotton field were collected by UAV, and residual film content in the plough layer was obtained by manual sampling. Based on the three deep learning frameworks of LinkNet, FCN, and DeepLabv3, a model for segmenting residual film from the cotton field image was built. After comparing the segmentation results, DeepLabv3 was determined to be the best model for segmenting residual film, and then the area of residual film 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 showed that the correlation coefficient (R2), root mean square error, and average relative error of the prediction of residual film content in the plough layer were 0.83, 0.48, and 11.06%, respectively. It indicates 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. This study provides certain technical support for monitoring and evaluating residual film pollution in the cotton field plough layer.

Evaluation of residual plastic film pollution in pre-sowing cotton field using UAV imaging and semantic segmentation.

To accurately evaluate residual plastic film pollution in pre-sowing cotton fields, a method based on modified U-Net model was proposed in this research. Images of pre-sowing cotton fields were collected using UAV imaging from different heights under different weather conditions. Residual films were manually labelled, and the degree of residual film pollution was defined based on the residual film coverage rate. The modified U-Net model for evaluating residual film pollution was built by simplifying the U-Net model framework and introducing the inception module, and the evaluation results were compared to those of the U-Net, SegNet, and FCN models. The segmentation results showed that the modified U-Net model had the best performance, with a mean intersection over union (MIOU) of 87.53%. The segmentation results on images of cloudy days were better than those on images of sunny days, with accuracy gradually decreasing with increasing image-acquiring height. The evaluation results of residual film pollution showed that the modified U-Net model outperformed the other models. The coefficient of determination(R2), root mean square error (RMSE), mean relative error (MRE) and average evaluation time per image of the modified U-Net model on the CPU were 0.9849, 0.0563, 5.33% and 4.85 s, respectively. The results indicate that UAV imaging combined with the modified U-Net model can accurately evaluate residual film pollution. This study provides technical support for the rapid and accurate evaluation of residual plastic film pollution in pre-sowing cotton fields.