Research on Segmentation Method of Maize Seedling Plant Instances Based on UAV Multispectral Remote Sensing Images
Plants · 04.07.2024 · 13 (13) · 1842
DOI: 10.3390/plants13131842 ↗Kurz gefasst
Fachartikel in der Zeitschrift Plants, online erschienen am 04.07.2024. Verfasst von Tingting Geng und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, China. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Laboratory of Mine Spatio-Temporal Information and Ecological Restoration, MNR.
Abstract (Originalsprache)
The accurate instance segmentation of individual crop plants is crucial for achieving a high-throughput phenotypic analysis of seedlings and smart field management in agriculture. Current crop monitoring techniques employing remote sensing predominantly focus on population analysis, thereby lacking precise estimations for individual plants. This study concentrates on maize, a critical staple crop, and leverages multispectral remote sensing data sourced from unmanned aerial vehicles (UAVs). A large-scale SAM image segmentation model is employed to efficiently annotate maize plant instances, thereby constructing a dataset for maize seedling instance segmentation. The study evaluates the experimental accuracy of six instance segmentation algorithms: Mask R-CNN, Cascade Mask R-CNN, PointRend, YOLOv5, Mask Scoring R-CNN, and YOLOv8, employing various combinations of multispectral bands for a comparative analysis. The experimental findings indicate that the YOLOv8 model exhibits exceptional segmentation accuracy, notably in the NRG band, with bbox_mAP50 and segm_mAP50 accuracies reaching 95.2% and 94%, respectively, surpassing other models. Furthermore, YOLOv8 demonstrates robust performance in generalization experiments, indicating its adaptability across diverse environments and conditions. Additionally, this study simulates and analyzes the impact of different resolutions on the model’s segmentation accuracy. The findings reveal that the YOLOv8 model sustains high segmentation accuracy even at reduced resolutions (1.333 cm/px), meeting the phenotypic analysis and field management criteria.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, China.
- Key Laboratory of Mine Spatio-Temporal Information and Ecological Restoration, Ministry of Natural Resources, Henan Polytechnic University, Jiaozuo 454000, China.
Förderung
- National Natural Science Foundation of China
- Laboratory of Mine Spatio-Temporal Information and Ecological Restoration, MNR
Zitieren
APA
Geng, T., Yu, H., Yuan, X., Ma, R., & Li, P. (2024). Research on Segmentation Method of Maize Seedling Plant Instances Based on UAV Multispectral Remote Sensing Images. Plants, 13(13), 1842. https://doi.org/10.3390/plants13131842
Vancouver
Geng T, Yu H, Yuan X, Ma R, Li P. Research on Segmentation Method of Maize Seedling Plant Instances Based on UAV Multispectral Remote Sensing Images. Plants. 2024;13(13):1842. doi:10.3390/plants13131842
BibTeX
@article{Geng2024,
author = {Geng, Tingting and Yu, Haiyang and Yuan, Xinru and Ma, Ruopu and Li, Pengao},
title = {Research on Segmentation Method of Maize Seedling Plant Instances Based on UAV Multispectral Remote Sensing Images},
journal = {Plants},
year = {2024},
volume = {13},
number = {13},
pages = {1842},
doi = {10.3390/plants13131842}
}
EUVIMED