Segmenting Purple Rapeseed Leaves in the Field from UAV RGB Imagery Using Deep Learning as an Auxiliary Means for Nitrogen Stress Detection

Crop leaf purpling is a common phenotypic change when plants are subject to some biotic and abiotic stresses during their growth. The extraction of purple leaves can monitor crop stresses as an apparent trait and meanwhile contributes to crop phenotype analysis, monitoring, and yield estimation. Due...

Full description

Bibliographic Details
Main Authors: Jian Zhang, Tianjin Xie, Chenghai Yang, Huaibo Song, Zhao Jiang, Guangsheng Zhou, Dongyan Zhang, Hui Feng, Jing Xie
Format: Article
Language:English
Published: MDPI AG 2020-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/12/9/1403
_version_ 1827717827640950784
author Jian Zhang
Tianjin Xie
Chenghai Yang
Huaibo Song
Zhao Jiang
Guangsheng Zhou
Dongyan Zhang
Hui Feng
Jing Xie
author_facet Jian Zhang
Tianjin Xie
Chenghai Yang
Huaibo Song
Zhao Jiang
Guangsheng Zhou
Dongyan Zhang
Hui Feng
Jing Xie
author_sort Jian Zhang
collection DOAJ
description Crop leaf purpling is a common phenotypic change when plants are subject to some biotic and abiotic stresses during their growth. The extraction of purple leaves can monitor crop stresses as an apparent trait and meanwhile contributes to crop phenotype analysis, monitoring, and yield estimation. Due to 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) RGB 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 purple rapeseed leaf ratios 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 monitoring 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 nitrogen stress monitoring.
first_indexed 2024-03-10T20:09:53Z
format Article
id doaj.art-d5d07d4f46934f328e191abd6e49742f
institution Directory Open Access Journal
issn 2072-4292
language English
last_indexed 2024-03-10T20:09:53Z
publishDate 2020-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj.art-d5d07d4f46934f328e191abd6e49742f2023-11-19T23:01:23ZengMDPI AGRemote Sensing2072-42922020-04-01129140310.3390/rs12091403Segmenting Purple Rapeseed Leaves in the Field from UAV RGB Imagery Using Deep Learning as an Auxiliary Means for Nitrogen Stress DetectionJian Zhang0Tianjin Xie1Chenghai Yang2Huaibo Song3Zhao Jiang4Guangsheng Zhou5Dongyan Zhang6Hui Feng7Jing Xie8Macro Agriculture Research Institute, College of Resource and Environment, Huazhong Agricultural University, 1 Shizishan Street, Wuhan 430070, ChinaMacro Agriculture Research Institute, College of Resource and Environment, Huazhong Agricultural University, 1 Shizishan Street, Wuhan 430070, ChinaAerial Application Technology Research Unit, USDA-Agricultural Research Service, College Station, TX 77845, USACollege of Mechanical and Electronic Engineering, Northwest A&F University, 22 Xinong Road, Yangling 712100, ChinaMacro Agriculture Research Institute, College of Resource and Environment, Huazhong Agricultural University, 1 Shizishan Street, Wuhan 430070, ChinaCollege of Plant Science and Technology, Huazhong Agricultural University, Wuhan 430070, ChinaAnhui Engineering Laboratory of Agro-Ecological Big Data, Anhui University, 111 Jiulong Road, Hefei 230601, ChinaCollege of Informatics, Huazhong Agricultural University, Wuhan 430070, ChinaCollege of Science, Huazhong Agricultural University, Wuhan 430070, ChinaCrop leaf purpling is a common phenotypic change when plants are subject to some biotic and abiotic stresses during their growth. The extraction of purple leaves can monitor crop stresses as an apparent trait and meanwhile contributes to crop phenotype analysis, monitoring, and yield estimation. Due to 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) RGB 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 purple rapeseed leaf ratios 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 monitoring 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 nitrogen stress monitoring.https://www.mdpi.com/2072-4292/12/9/1403purple rapeseed leavesunmanned aerial vehicleU-Netplant segmentationnitrogen stress
spellingShingle Jian Zhang
Tianjin Xie
Chenghai Yang
Huaibo Song
Zhao Jiang
Guangsheng Zhou
Dongyan Zhang
Hui Feng
Jing Xie
Segmenting Purple Rapeseed Leaves in the Field from UAV RGB Imagery Using Deep Learning as an Auxiliary Means for Nitrogen Stress Detection
Remote Sensing
purple rapeseed leaves
unmanned aerial vehicle
U-Net
plant segmentation
nitrogen stress
title Segmenting Purple Rapeseed Leaves in the Field from UAV RGB Imagery Using Deep Learning as an Auxiliary Means for Nitrogen Stress Detection
title_full Segmenting Purple Rapeseed Leaves in the Field from UAV RGB Imagery Using Deep Learning as an Auxiliary Means for Nitrogen Stress Detection
title_fullStr Segmenting Purple Rapeseed Leaves in the Field from UAV RGB Imagery Using Deep Learning as an Auxiliary Means for Nitrogen Stress Detection
title_full_unstemmed Segmenting Purple Rapeseed Leaves in the Field from UAV RGB Imagery Using Deep Learning as an Auxiliary Means for Nitrogen Stress Detection
title_short Segmenting Purple Rapeseed Leaves in the Field from UAV RGB Imagery Using Deep Learning as an Auxiliary Means for Nitrogen Stress Detection
title_sort segmenting purple rapeseed leaves in the field from uav rgb imagery using deep learning as an auxiliary means for nitrogen stress detection
topic purple rapeseed leaves
unmanned aerial vehicle
U-Net
plant segmentation
nitrogen stress
url https://www.mdpi.com/2072-4292/12/9/1403
work_keys_str_mv AT jianzhang segmentingpurplerapeseedleavesinthefieldfromuavrgbimageryusingdeeplearningasanauxiliarymeansfornitrogenstressdetection
AT tianjinxie segmentingpurplerapeseedleavesinthefieldfromuavrgbimageryusingdeeplearningasanauxiliarymeansfornitrogenstressdetection
AT chenghaiyang segmentingpurplerapeseedleavesinthefieldfromuavrgbimageryusingdeeplearningasanauxiliarymeansfornitrogenstressdetection
AT huaibosong segmentingpurplerapeseedleavesinthefieldfromuavrgbimageryusingdeeplearningasanauxiliarymeansfornitrogenstressdetection
AT zhaojiang segmentingpurplerapeseedleavesinthefieldfromuavrgbimageryusingdeeplearningasanauxiliarymeansfornitrogenstressdetection
AT guangshengzhou segmentingpurplerapeseedleavesinthefieldfromuavrgbimageryusingdeeplearningasanauxiliarymeansfornitrogenstressdetection
AT dongyanzhang segmentingpurplerapeseedleavesinthefieldfromuavrgbimageryusingdeeplearningasanauxiliarymeansfornitrogenstressdetection
AT huifeng segmentingpurplerapeseedleavesinthefieldfromuavrgbimageryusingdeeplearningasanauxiliarymeansfornitrogenstressdetection
AT jingxie segmentingpurplerapeseedleavesinthefieldfromuavrgbimageryusingdeeplearningasanauxiliarymeansfornitrogenstressdetection