A UAV-based sparse-view 3DGS framework for greenhouse strawberry reconstruction
4 affiliations
- 1College of Biosystems Engineering and Food Science, Key Laboratory of Spectroscopy, Ministry of Agriculture and Rural Affairs, Zhejiang University, Hangzhou, 310058, China
- 2School of Information Engineering, Huzhou University, Huzhou, 313000, China
- 3Institute of Biotechnology Research, Hangzhou Academy of Agricultural Sciences, Hangzhou, 310024, China
- 4College of Information Science and Technology, Shihezi University, Shihezi, 832003, China
Abstract
UAV-based multi-view reconstruction is an important approach for high-precision, non-destructive 3D crop phenotyping. However, in greenhouse environments, UAV image acquisition is often restricted to sparse viewpoints because of UAV-induced airflow disturbances and the structural complexity of the greenhouse, which severely hinders accurate 3D phenotyping. To address this challenge, this study develops a task-driven phenotyping framework for constrained UAV viewpoints in greenhouse environments, integrating a vision-triggered flight planning strategy with an improved sparse-view 3DGS pipeline, termed SparseBerry-3DGS, for multi-view image acquisition and 3D phenotyping of greenhouse strawberries in GNSS-denied environments. Specifically, 3D Gaussian Splatting (3DGS) is improved by incorporating flow-guided initialization, depth supervision, and an adaptive pruning strategy, which effectively alleviate geometric collapse and floating artifacts under sparse-view conditions. Furthermore, sequential semantic masks generated by SAM2 are utilized to guide the segmentation of strawberry point clouds, thereby reducing background interference and segmentation errors. Experimental results show that the vision-triggered flight strategy enables stable capture of 16 surrounding images for each target fruit. Under sparse-view conditions, SparseBerry-3DGS improves reconstruction stability, with the average peak signal-to-noise ratio (PSNR) reaching 18.25 dB, corresponding to an 18% improvement. The SAM2-based segmentation module achieves high accuracy, with the mean intersection over union (mIoU) above 0.95. Geometric evaluation based on strawberry longitudinal diameter yielded an R2 of 0.88, supporting the accuracy of fruit-scale geometric reconstruction. For weight estimation, five-fold cross-validation yielded an R2 of 0.90 and an RMSE of 3.62 g, showing better predictive performance than models based on 2D projected area and standard 3DGS point clouds. This study provides a new approach for high-throughput, non-invasive digital crop phenotyping in greenhouse horticulture.
Related
- OA-Recon: An Online Adaptive Reconstruction Framework for Sparse-View Multi-Energy CT
- Explainable fine-grained feature enhancement framework for strawberry diagnostic decision making
- Standardised framework for analysis of greenhouse performance using key performance indicators
- Top2All: Benchmarking sparse-to-transcriptome reconstruction from high-expression profiles across sex- and sex-steroid-defined conditions
- RoDPAA: A Robust Dissimilarity-Based Principal Angle Analysis Framework for Multi-View Microbiome Data Integration
BibTeX
@article{cai2026uavbased,
title = {{A UAV-based sparse-view 3DGS framework for greenhouse strawberry reconstruction}},
author = {Jiayi Cai and Zhenyu Huang and Yuzhen Wei and Wenfei Xiao and Hong Yu and Pan Gao and Xuping Feng and Yong He},
journal = {Plant phenomics (Washington, D.C.)},
year = {2026},
month = sep,
doi = {10.1016/j.plaphe.2026.100281},
url = {https://europepmc.org/article/PMC/PMC13718796},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - A UAV-based sparse-view 3DGS framework for greenhouse strawberry reconstruction
AU - Jiayi Cai
AU - Zhenyu Huang
AU - Yuzhen Wei
AU - Wenfei Xiao
AU - Hong Yu
AU - Pan Gao
AU - Xuping Feng
AU - Yong He
PY - 2026
DA - 2026/09/03
JO - Plant phenomics (Washington, D.C.)
DO - 10.1016/j.plaphe.2026.100281
UR - https://europepmc.org/article/PMC/PMC13718796
AB - UAV-based multi-view reconstruction is an important approach for high-precision, non-destructive 3D crop phenotyping. However, in greenhouse environments, UAV image acquisition is often restricted to sparse viewpoints because of UAV-induced airflow disturbances and the structural complexity of the greenhouse, which severely hinders accurate 3D phenotyping. To address this challenge, this study develops a task-driven phenotyping framework for constrained UAV viewpoints in greenhouse environments, integrating a vision-triggered flight planning strategy with an improved sparse-view 3DGS pipeline, termed SparseBerry-3DGS, for multi-view image acquisition and 3D phenotyping of greenhouse strawberries in GNSS-denied environments. Specifically, 3D Gaussian Splatting (3DGS) is improved by incorporating flow-guided initialization, depth supervision, and an adaptive pruning strategy, which effectively alleviate geometric collapse and floating artifacts under sparse-view conditions. Furthermore, sequential semantic masks generated by SAM2 are utilized to guide the segmentation of strawberry point clouds, thereby reducing background interference and segmentation errors. Experimental results show that the vision-triggered flight strategy enables stable capture of 16 surrounding images for each target fruit. Under sparse-view conditions, SparseBerry-3DGS improves reconstruction stability, with the average peak signal-to-noise ratio (PSNR) reaching 18.25 dB, corresponding to an 18% improvement. The SAM2-based segmentation module achieves high accuracy, with the mean intersection over union (mIoU) above 0.95. Geometric evaluation based on strawberry longitudinal diameter yielded an R2 of 0.88, supporting the accuracy of fruit-scale geometric reconstruction. For weight estimation, five-fold cross-validation yielded an R2 of 0.90 and an RMSE of 3.62 g, showing better predictive performance than models based on 2D projected area and standard 3DGS point clouds. This study provides a new approach for high-throughput, non-invasive digital crop phenotyping in greenhouse horticulture.
SN - 2643-6515
ER -