草地学报

基于3DGS的饲用燕麦冠层结构参数提取与生物量预测

PDF下载

李秀婷, 卢茂金, 赵伊豪, 张亮, 钟志花, 赵嘉欣, 孙承星, 邓博偲田, 刘一菠, 马钰雯, 马紫晨, 马祥, 王亚芳, 刘敏国

草地学报 | 研究论文 2026,34(8): 2776-2786

收起

草地学报 |研究论文 2026 , 34 (8) : 2776 -2786

基于3DGS的饲用燕麦冠层结构参数提取与生物量预测

全屏

李秀婷, 卢茂金, 赵伊豪, 张亮, 钟志花, 赵嘉欣, 孙承星, 邓博偲田, 刘一菠, 马钰雯, 马紫晨, 马祥, 王亚芳, 刘敏国

作者信息

作者简介:

李秀婷(2002-),女,汉族,福建泉州人,硕士研究生,主要从事植物表型组技术研究,E-mail:lxt@nwafu.edu.cn

Oat Canopy Structural Parameter Extraction and Biomass Prediction Using 3D Gaussian Splatting

LI Xiu-ting, LU Mao-jin, ZHAO Yi-hao, ZHANG Liang, ZHONG Zhi-hua, ZHAO Jia-xin, SUN Cheng-xing, DENG Bo-si-tian, LIU Yi-bo, MA Yu-wen, MA Zi-chen, MA Xiang, WANG Ya-fang, LIU Min-guo

Affiliations

doi: 10.11733/j.issn.1007-0435.2026.08.003

文章导航

摘要

收起

作物田间表型测量是品种选育的基础。传统作物表型采集存在破坏性大、成本高、主观性强等问题，难以满足当前品种选育工作的要求。本研究提出一种基于智能手机视频采集与3D高斯泼溅（3D Gaussian Splatting，3DGS）技术的饲用燕麦单株表型分析方法。试验以187株乳熟期饲用燕麦为研究对象，利用智能手机获取多视角视频数据并生成3DGS点云模型，提取投影面积、最大冠幅及平均冠幅等冠层结构参数，分别采用凸包法和体素化法（体素大小0.01 m，0.005 m）计算冠层体积。结合随机森林与支持向量机算法，构建生物量（鲜重、干重）预测模型。结果表明：（1）3DGS技术能够高保真地还原燕麦叶片细长、茎秆纤细及自遮挡严重的复杂形态，在复杂形态还原上展现出相对传统重建方法的显著优势；（2）基于3DGS点云体积的生物量估测模型精度可靠，干重预测精度（Acc≈0.88）普遍优于鲜重，且高分辨率（体素大小0.005 m）的体素化方法在描述冠层实体结构方面略占优势。本研究构建的“手机视频采集—3DGS建模—表型参数提取”工作流具有低成本、高精度且非破坏性的特点，为田间作物高通量表型分析提供了有效的技术支撑。

关键词

高斯泼溅 / 饲用燕麦 / 生物量预测 / 机器学习 / 冠层体积 / 高通量表型

Abstract

收起

Field phenotyping is fundamental to crop variety evaluation. However， traditional data acquisition methods are often destructive， costly， and subjective， and conventional 3D reconstruction techniques struggle to capture fine plant structures. To address these challenges， this study proposed a high-throughput phenotyping method for individual oat plants based on smartphone video acquisition and 3D Gaussian Splatting （3DGS） technology. The experiment utilized 187 oat plants at the milky stage as tested materials. Multi-view video data captured by smartphones were used to generate 3DGS point cloud models， from which canopy structural parameters—including projected area， maximum canopy width， and average canopy width-were extracted. Canopy volume was calculated using both Convex Hull and Voxelization （voxel size 0.01 m and 0.005 m） methods. Furthermore， biomass （fresh and dry weight） prediction models based on canopy volume were constructed using Random Forest （RF） and Support Vector Machine （SVM） algorithms. The results showed that：（1） 3DGS technology achieved high-fidelity reconstruction of the complex morphology of oats， effectively resolving issues related to slender leaves， thin stems， and severe self-occlusion， thereby demonstrating significant advantages over traditional reconstruction methods in restoring intricate structural forms；（2） Biomass estimation models based on 3DGS point cloud volume were reliable， with dry weight prediction accuracy （Accuracy≈0.88） generally superior to that of fresh weight； notably， high-resolution voxelization （voxel size 0.005 m） demonstrated a slight advantage in accurately describing the physical canopy structure. The workflow established in this study-“Smartphone Video Acquisition-3DGS Modeling-Phenotypic Parameter Extraction”-offered a low-cost， high-precision， and non-destructive solution， providing effective technical support for high-throughput phenotypic analysis of fields.

Key words

Gaussian splatting / Oat / Biomass prediction / Machine learning / Canopy volume / High-throughput phenotyping

引用本文

李秀婷, 卢茂金, 赵伊豪, 张亮, 钟志花, 赵嘉欣, 孙承星, 邓博偲田, 刘一菠, 马钰雯, 马紫晨, 马祥, 王亚芳, 刘敏国. 基于3DGS的饲用燕麦冠层结构参数提取与生物量预测. 草地学报, 2026 , 34 (8) : 2776 -2786 . DOI: 10.11733/j.issn.1007-0435.2026.08.003

LI Xiu-ting, LU Mao-jin, ZHAO Yi-hao, ZHANG Liang, ZHONG Zhi-hua, ZHAO Jia-xin, SUN Cheng-xing, DENG Bo-si-tian, LIU Yi-bo, MA Yu-wen, MA Zi-chen, MA Xiang, WANG Ya-fang, LIU Min-guo. Oat Canopy Structural Parameter Extraction and Biomass Prediction Using 3D Gaussian Splatting[J]. Acta Agrestia Sinica, 2026 , 34 (8) : 2776 -2786 . DOI: 10.11733/j.issn.1007-0435.2026.08.003

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

DANILEVICZ M F，GILL M，ANDERSON R，et al. Plant genotype to phenotype prediction using machine learning[J]. Frontiers in Genetics，2022，13：822173
PIXLEY K V，CAIRNS J E，LOPEZ-RIDAURA S，et al. Redesigning crop varieties to win the race between climate change and food security[J]. Molecular Plant，2023，16（10）：1590-1611
NGUYEN H T，KHAN M A R，NGUYEN T T，et al. Advancing crop resilience through high-throughput phenotyping for crop improvement in the face of climate change[J]. Plants，2025，14（6）：907
SLATTERY R A，ORT D R. Perspectives on improving light distribution and light use efficiency in crop canopies[J]. Plant Physiology，2021，185（1）：34-48
DE OLIVEIRA G S，MARCATO JUNIOR J，POLIDORO C，et al. Convolutional neural networks to estimate dry matter yield in a Guineagrass breeding program using UAV Remote Sensing[J]. Sensors， 2021，21（12）：3971
YANG W Q，LIU T X，TANG X P，et al. Research progress on plant phenomics in the context of smart agriculture[J]. Journal of Henan Agricultural Sciences，2022，51（7）：1-12杨文庆，刘天霞，唐兴萍，等.智慧农业背景下的植物表型组学研究进展[J].河南农业科学，2022，51（7）：1-12
LI D L，QUAN C Q，SONG Z Y，et al. High-throughput plant phenotyping platform （HT3P） as a novel tool for estimating agronomic traits from the lab to the field[J]. Frontiers in Bioengineering and Biotechnology，2021，8：623705
OMIA E，PARK E，SEMYALO D，et al. Advancements in 3D field-crop phenotyping using point clouds： a comparative review of sensor technology， target traits， and challenges under controlled and field conditions[J]. Frontiers in Plant Science，2026，17：1731852
LIANG Y Q，GOU W B，WEN W L，et al. Comparison of three-dimensional data acquisition approaches for rail-driven field plant phenotyping platforms[J]. Smart Agricultural Technology，2025，12：101398
CHEN Y，HUANG X，LIAO F，et al. A low-cost framework for 3D phenotyping of sugarcane via instance segmentation and 3D Gaussian Splatting[J]. Agriculture，2026，16（3）：375
YANG X，LU X，XIE P，et al. PanicleNeRF： Low-cost， high-precision in-field phenotyping of rice panicles with smartphone[J]. Plant Phenomics，2024，6：0279
WU S X，HU C H，TIAN B Y，et al. A 3D reconstruction platform for complex plants using OB-NeRF[J]. Frontiers in Plant Science，2025（16）：1449626
KERBL B，KOPANAS G，LEIMKÜHLER T，et al. 3D Gaussian Splatting for real-time radiance field rendering[J]. ACM Transactions on Graphics，2023，42（4）：1-14
SHEN P，JING X Y，DENG W Z，et al. PlantGaussian： Exploring 3D Gaussian Splatting for cross-time， cross-scene， and realistic 3D plant visualization and beyond[J]. The Crop Journal，2025，13（2）：607-618
STUART L A G，WELLS D M，ATKINSON J A，et al. High-fidelity wheat plant reconstruction using 3D Gaussian Splatting and neural radiance fields[J]. GigaScience，2025（14）：1-18
GAO J，ZHU C，HU J，et al. Seed 3D phenotyping across multiple crops using 3D Gaussian Splatting[J]. Agriculture，2025，15（22）：2329
SIEBERS M H，FU P，BLAKELY B J，et al. Fast， nondestructive and precise biomass measurements are possible using lidar-based convex hull and voxelization algorithms[J]. Remote Sensing，2024（16）：2191
SIVAKUMAR M，PARTHASARATHY S，PADMAPRIYA T. Trade-off between training and testing ratio in machine learning for medical image processing[J]. PeerJ Computer Science，2024，10：e2245
MA H，WANG K，MA J，et al. Calculation method of canopy effective volume for fruit tree based on LiDAR point cloud data[J]. Frontiers in Plant Science，2025，16：1679027
WU Z，SONG S，KHOSLA A，et al. 3D ShapeNets： A deep representation for volumetric shapes[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. New York： IEEE， 2015：1912-1920
BIENERT A，HESS C，MAAS H G，et al. A voxel-based technique to estimate the volume of trees from terrestrial laser scanner data[C]//ISPRS Technical Commission V Symposium. Proceedings of the International Archives of the Photogrammetry， Remote Sensing and Spatial Information Sciences. Riva del Garda， Italy： ISPRS，2014，XL-5：101-106
LIU Y C，LI W K，LIU H L，et al. Three-dimensional forest reconstruction using rotational slice-based voxelization[J]. ACTA SCIENTIARUM NATURALIUM UNIVERSITATIS SUNYATSENI，2025，64（5）：84-99刘原池，李文楷，刘红良，等.基于旋转薄片体素化森林三维重构方法[J]. 中山大学学报（自然科学版中英文），2025，64（5）：84-99
LI Y，LIANG Z，LIU B，et al. Applications of 3D reconstruction techniques in crop canopy phenotyping： A review[J]. Agronomy，2025，15（11）：2518
MARAVEAS C. Image analysis artificial intelligence technologies for plant phenotyping： Current state of the art[J]. AgriEngineering，2024，6（3）：3375-3407
YAN X H，CHAI G Q，HAN X Y，et al. SA-Pmnet： Utilizing close-range photogrammetry combined with image enhancement and self-attention mechanisms for 3D reconstruction of forests[J]. Remote Sensing，2024，16（2）：416
ENTERKINE J， HOJATIMALEKSHAH A， VERMILLION M， et al. Voxel volumes and biomass： Estimating vegetation volume and litter accumulation of exotic annual grasses using automated ultra-high-resolution SfM and advanced classification techniques[J]. Ecology and Evolution，2025，15（1）：e70883
YAN X F，ZHAO W K，YANG S C，et al. Canopy porosity of masson pine based on terrestrial 3D Laser Scanning[J]. Remote Sensing Technology and Application，2023，38（4）：956-966严夏帆，赵文凯，杨舜成，等. 基于三维激光扫描技术的马尾松冠层孔隙度研究[J]. 遥感技术与应用，2023，38（4）：956-966
SHEIKH M，IQRA F，AMBREEN H，et al. Integrating artificial intelligence and high-throughput phenotyping for crop improvement[J]. Journal of Integrative Agriculture，2024，23（6）：1787-1802

2026年第34卷第8期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.11733/j.issn.1007-0435.2026.08.003

接收时间：2026-02-23
首发时间：2026-09-23

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2026-02-23
修回日期：2026-03-30

基金

作者信息

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/cdxb/CN/10.11733/j.issn.1007-0435.2026.08.003

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT