UAV-Based Multi-Sensor Fusion for Leaf Age Detection in Maize Inbred Line Population Seedlings
DOI:
https://doi.org/10.3991/itdaf.v4i2.60397Keywords:
Multi-source sensors, Plot segmentation, Automatic Machine Learning, Maize leaf age.Abstract
Accurate and rapid detection of maize seedling growth is critical in early breeding decisionmaking, smart management, and yield improvement. Traditional leaf age detection still relies heavily on labor-intensive and low-efficiency manual field surveys, underscoring the urgent need for high-throughput phenotyping. Integrating multisource sensor data from unmanned aerial vehicle (UAV) with measured information such as crop height can further enhance the estimation accuracy of crop phenotypic parameters. Accurate field plot segmentation is critical for field-scale phenotypic analysis. However, current approaches remain largely dependent on slow, manual segmentation. Automating this step would greatly reduce the workload of agronomists. This study used UAV RGB and multispectral imagery collected over maize inbred line population plots before the canopy closure stage to perform automatic plot segmentation on field orthophotos and combined measured plant height with relative flight dates to achieve high-throughput detection of leaf age during the maize seedling stage. First, this study proposed a maize plot automatic segmentation method based on orthophotos. Then, it extracted texture features, RGB, and multispectral vegetation indices of each plot. Combined with relative flight date and plant height, four datasets were constructed. Support vector regression (SVR), random forest regression (RFR), and automatic machine learning (AutoML) regression algorithms were used to build the leaf age detection model. The results showed that the orthomosaic from March 23 achieved the best plot-segmentation performance, with minimum intersection over union (IoU), mean IoU, and IoU standard deviation of 14.67%, 96.47%, and 8.65%, respectively. Incorporating relative flight dates and plant-height measurements improved model performance, and the AutoML demonstrated the greatest robustness, achieving a validation R2 of up to 0.862 and an RMSE as low as 0.715. This study proposed a leaf age estimation method that offers practical technical support for field-based maize seedling assessment and reduces manual labor demands.
References
[1] Y. Bai et al., "Estimating leaf age of maize seedlings using UAV-based RGB and multispectral images," Computers and Electronics in Agriculture, vol. 215, p. 108349, 2023/12/01/ 2023, doi: https://doi.org/10.1016/j.compag.2023.108349.
[2] W. Guo, Z. H. Li, and C. M. Guo, "Study on leaf age model of spring maize in Jilin Province based on Logistic curve," Jilin Agriculture, no. 7, pp. 81–82, 2016, doi: 10.14025/j.cnki.jlny.2016.07.025.
[3] G. Q. Zheng, S. F. Duan, S. B. Yan, and B. Q. Lyu, "Simulation model of maize leaf age and organ development," Journal of Maize Sciences, no. 4, pp. 63–66, 2003, doi: 10.13597/j.cnki.maize.science.2003.04.022.
[4] J. J. Du, J. Yuan, C. Y. Wang, and X. Y. Guo, "Modeling and application of leaf color during the whole growth period based on in-situ monitoring of maize canopy," Transactions of the Chinese Society of Agricultural Engineering (TSCAE), vol. 33, no. 16, pp. 188–195, 2017. [Online]. Available: https://kns.cnki.net/kcms2/article/abstract?v=f0DSObGwzqhgB1K9htxHNxIS0gEZhffAcB3FI05AuPFye3Wu8QOkMoukWoptrtzsNU80CW0SBKMqGplewKlTlfqkjsm1BrcHmMdFPIkUx8oZgX0CfTU3fqfbkyHsHAMN-jRve6e7cmUeUhaVvYRJhceUQ5D7F5KQsq-0lHp6DlP1LECM5SH7jbFI0fVBVpim&uniplatform=NZKPT&language=CHS.
[5] Y. L. Wang et al., "Response of rice leaf age change to short photoperiod," Journal of Jiangsu Agricultural Sciences, vol. 36, no. 2, pp. 265–270, 2020. [Online]. Available: https://kns.cnki.net/kcms2/article/abstract?v=f0DSObGwzqi2OF9JeXAMRIwZ21c8UEbRb3Ee1svZo3n0SZkB6R1Qb-I4dbeWqV6sdxTYx8IvRZCkln26KoNmTYF2LgtgWGBx6s2whbqMm4I4vyPOpAzSfA0l94RyVMuaSRXphsD30Yj9p6W3sBGTd2xX_X-bDjIjGaIX4_83h_Wk1Mw3f7lF6TxAawDk-jyK&uniplatform=NZKPT&language=CHS.
[6] J. Q. Luo, "Study on rice leaf age recognition based on semantic segmentation and shortest distance algorithm," M.S. thesis, Northeast Agricultural University, Harbin, China, 2023, doi: 10.27010/d.cnki.gdbnu.2023.001090. [Online]. Available: https://link.cnki.net/doi/10.27010/d.cnki.gdbnu.2023.001090.
[7] L. Z. Quan, B. Wu, and S. R. Mao, "Instance segmentation of farmland weeds and leaf age recognition method based on Mask R-CNN," Journal of Northeast Agricultural University, vol. 52, no. 4, pp. 65–76, 2021, doi: 10.19720/j.cnki.issn.1005-9369.2021.04.008.
[8] J. Zhang et al., "Rapeseed Stand Count Estimation at Leaf Development Stages With UAV Imagery and Convolutional Neural Networks," Front Plant Sci, vol. 11, p. 617, 2020, doi: 10.3389/fpls.2020.00617.
[9] S. Fei et al., "UAV-based multi-sensor data fusion and machine learning algorithm for yield prediction in wheat," Precision Agriculture, vol. 24, no. 1, pp. 187–212, 2023/02/01 2023, doi: 10.1007/s11119-022-09938-8.
[10] W. Zhai et al., "CatBoost algorithm for estimating maize above-ground biomass using unmanned aerial vehicle-based multi-source sensor data and SPAD values," Computers and Electronics in Agriculture, vol. 214, p. 108306, 2023/11/01/ 2023, doi: https://doi.org/10.1016/j.compag.2023.108306.
[11] Y. Liu et al., "Evaluating how lodging affects maize yield estimation based on UAV observations," Frontiers in Plant Science, Original Research vol. Volume 13 - 2022, 2023–January–17 2023, doi: 10.3389/fpls.2022.979103.
[12] Z. Khan and S. J. Miklavcic, "An Automatic Field Plot Extraction Method From Aerial Orthomosaic Images," Frontiers in Plant Science, vol. 10, May 2019, doi: 10.3389/fpls.2019.00683.
[13] L. Tresch et al., "Easy MPE: Extraction of Quality Microplot Images for UAV-Based High-Throughput Field Phenotyping," Plant Phenomics, vol. 2019, p. 2591849, 2019/01/01/ 2019, doi: https://doi.org/10.34133/2019/2591849.
[14] M. X. Zheng et al., "Extraction of plot boundary from remote sensing images for UAV agricultural applications based on improved Mean Shift," Hubei Agricultural Sciences, vol. 60, no. 23, pp. 153–156, 2021, doi: 10.14088/j.cnki.issn0439-8114.2021.23.034.
[15] T. Ha, H. Duddu, A. Vandenberg, and S. Shirtliffe, "A semi-automatic workflow for plot boundary extraction of irregularly sized and spaced field plots from UAV imagery," The Plant Phenome Journal, vol. 5, no. 1, p. e20039, 2022, doi: https://doi.org/10.1002/ppj2.20039.
[16] S. Wu et al., "Extraction and Mapping of Cropland Parcels in Typical Regions of Southern China Using Unmanned Aerial Vehicle Multispectral Images and Deep Learning," Drones, vol. 7, no. 5, p. 285, 2023. [Online]. Available: https://www.mdpi.com/2504-446X/7/5/285.
[17] M. Kumar, B. K. Bhattacharya, M. R. Pandya, and B. K. Handique, "Machine learning based plot level rice lodging assessment using multi-spectral UAV remote sensing," Computers and Electronics in Agriculture, vol. 219, p. 108754, 2024/04/01/ 2024, doi: https://doi.org/10.1016/j.compag.2024.108754.
[18] D. Y. Zhang et al., "Estimation of winter wheat LAI based on feature fusion of multi-source UAV images," Transactions of the Chinese Society of Agricultural Engineering (TSCAE), vol. 38, no. 9, pp. 171–179, 2022. [Online]. Available: https://kns.cnki.net/kcms2/article/abstract?v=NitQnVYDOco--eBN-BExdTosW2DqRK-fD1lNEDvlC-A5RPvQTNnApYcqgIhc2uz9q5LjvrqhvT0ngPI90km3E7mN4b1X3L_M_VicXx4XUp6VNKju3CchAF-btApx3Tr9HqfgImgxk0ABQyGMQscJdaA0An0lpJqkh2rNvjf7CoxHOqrZiQEKlonU39zDsaD7&uniplatform=NZKPT&language=CHS.
[19] Y. Che et al., "High-quality images and data augmentation based on inverse projection transformation significantly improve the estimation accuracy of biomass and leaf area index," Computers and Electronics in Agriculture, vol. 212, p. 108144, 2023/09/01/ 2023, doi: https://doi.org/10.1016/j.compag.2023.108144.
[20] X. X. Han, "Monitoring of winter wheat growth and yield estimation based on multi-source UAV remote sensing images," M.S. thesis, Anhui University, Hefei, China, 2022, doi: 10.26917/d.cnki.ganhu.2022.000416. [Online]. Available: https://link.cnki.net/doi/10.26917/d.cnki.ganhu.2022.000416.
[21] H. Y. Fu et al., "Screening method of high-quality ramie germplasm resources based on UAV remote sensing phenotyping monitoring," Smart Agriculture (Chinese & English), vol. 4, no. 4, pp. 74–83, 2022. [Online]. Available: https://link.cnki.net/urlid/10.1681.S.20221130.1200.001.
[22] Y. Bai, "Remote sensing monitoring of maize seedling growth based on multi-source UAV images," M.S. thesis, Chinese Academy of Agricultural Sciences (CAAS), Beijing, China, 2022, doi: 10.27630/d.cnki.gznky.2022.000417. [Online]. Available: https://link.cnki.net/doi/10.27630/d.cnki.gznky.2022.000417.
[23] L. Meng et al., "Improved Crop Biomass Algorithm with Piecewise Function (iCBA-PF) for Maize Using Multi-Source UAV Data," Drones, vol. 7, p. 254, 04/08 2023, doi: 10.3390/drones7040254.
[24] Z. Li et al., "A hierarchical interannual wheat yield and grain protein prediction model using spectral vegetative indices and meteorological data," Field Crops Research, vol. 248, p. 107711, 2020/03/01/ 2020, doi: https://doi.org/10.1016/j.fcr.2019.107711.
[25] S. L. Anderson and S. C. Murray, "R/UAStools::plotshpcreate: Create Multi-Polygon Shapefiles for Extraction of Research Plot Scale Agriculture Remote Sensing Data," Frontiers in Plant Science, vol. 11, Sep. 2020, doi: 10.3389/fpls.2020.511768.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Yibo Wei, Dong Cai, Haoyu Wang, Xinyi Wang, Xiaohong Du, Jiangchuan Fan
This work is licensed under a Creative Commons Attribution 4.0 International License.
