Segmenting purple rapeseed leaves in the field from UAV RGB imagery using deep learning as an auxiliary means for nitrogen stress detection

Authors: ZHANG, JIAN - Huazhong Agricultural University; XIE, TIANJIN - Huazhong Agricultural University; Yang, Chenghai; SONG, HUAIBO - Northwest A&f University; JIANG, ZHAO - Huazhong Agricultural University; ZHOU, GUANGSHENG - Huazhong Agricultural University; ZHANG, DONGYUAN - Anhui Agricultural University; FENG, HUI - Huazhong Agricultural University; XIE, JING - Huazhong Agricultural University

Submitted to: Remote Sensing
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 4/27/2020
Publication Date: 4/29/2020
Citation: Zhang, J., Xie, T., Yang, C., Song, H., Jiang, Z., Zhou, G., Zhang, D., Feng, H., Xie, J. 2020. Segmenting purple rapeseed leaves in the field from UAV RGB imagery using deep learning as an auxiliary means for nitrogen stress detection. Remote Sensing. 12, 1403. https://doi.org/10.3390/rs12091403.
DOI: https://doi.org/10.3390/rs12091403

Interpretive Summary: Crop leaf purpling is a common phenotypic change when plants are subject to some biotic and abiotic stresses during their growth. The segmentation of purple leaves can assess crop stresses quantitatively. In this study, a deep learning model was used to segment purple rapeseed leaves during the seedling stage based on unmanned aerial vehicle imagery. The model was compared with four commonly used image segmentation methods and results showed that the deep learning model performed better than the conventional methods. Moreover, regression analysis between the area of the purple rapeseed leaves and the measured nitrogen content revealed that purple leaf area could be used as an auxiliary means for assessing crop nitrogen stress. Results from this study demonstrate that the deep learning model is a robust method for purple leaf segmentation and that the accurate segmentation of purple leaves provides a new method for crop stress monitoring.

Technical Abstract: Crop leaf purpling is a common phenotypic change when plants are subject to some biotic and abiotic stresses during their growth. The segmentation of purple leaves can assess crop stresses quantitatively and meanwhile contributes to crop phenotype analysis, monitoring, and yield estimation. Because of the complexity of the field environment as well as differences in size, shape, texture, and color gradation among the leaves, purple leaf segmentation is difficult. In this study, we used a U-Net model for segmenting purple rapeseed leaves during the seedling stage based on unmanned aerial vehicle (UAV) imagery at the pixel level. With the limited spatial resolution of rapeseed images acquired by UAV and small object size, the input patch size was carefully selected. Experiments showed that the U-Net model with the patch size of 256 × 256 pixels obtained better and more stable results with a F-measure of 90.29% and an Intersection of Union (IoU) of 82.41%. To further explore the influence of image spatial resolution, we evaluated the performance of the U-Net model with different image resolutions and patch sizes. The U-Net model performed better compared with four other commonly used image segmentation approaches comprising support vector machine, random forest, HSeg, and SegNet. Moreover, regression analysis was performed between the area of the purple rapeseed leaves and the measured N content. The negative exponential model had a coefficient of determination (R²) of 0.858, thereby explaining much of the rapeseed leaf purpling in this study. This purple leaf phenotype could be an auxiliary means for assessing crop growth status so that crops could be managed in a timely and effective manner when nitrogen stress occurs. Results demonstrate that the U-Net model is a robust method for purple rapeseed leaf segmentation and that the accurate segmentation of purple leaves provides a new method for crop stress monitoring.