{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T01:52:32Z","timestamp":1784598752677,"version":"3.55.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>To accurately segment point clouds and quickly calculate leaf length and stem diameter, thereby enabling phenotypic analysis and variety selection of greenhouse tomato plants, this paper proposes a voxel grid downsampling (VGDS)\u2013PointNet++-based model for point cloud segmentation and trait calculation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The point clouds of the tomato canopy were acquired using a depth camera. After labeling, point cloud augmentation was performed, and the tomato point cloud dataset (TPCD) containing 1,552 sets of data was rebuilt. Voxel grid downsampling was applied to replace the original sampling strategy of PointNet++. Models of PointNet, PointNet++, VGDS-PointNet++, and Point Transformer were trained with the TPCD and compared on segmentation quality with accuracy and mean Intersection over Union (mIoU). After segmentation, skeletal morphology was fitted for non-occluded leaves by applying a series of surface fitting techniques. The leaf lengths and stem diameters were automatically calculated and compared with the manually measured values.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The validation results showed that the average runtime of voxel grid downsampling was 0.132 s, which was lower than under the same number of sampled points. Compared to the other three models, the proposed model had higher accuracy and mIoU, reaching up to 96.80% and 88.95%, respectively. The proposal\u2019s accuracy and mIoU increased by 3.9% and 4.45% over PointNet++, respectively. The determination coefficient\n                      <jats:italic>R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      between the automatic calculation and manual measurement values of leaf length and stem diameter was 0.93 and 0.87, respectively.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This can help extract phenotypic traits of tomatoes using depth cameras.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2026.1753706","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:45:30Z","timestamp":1776059130000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["VGDS-PointNet++ for organ segmentation and phenotypic trait estimation in greenhouse tomato seedlings"],"prefix":"10.3389","volume":"17","author":[{"given":"Feiyi","family":"Wang","sequence":"first","affiliation":[{"name":"College of Information Engineering, Northwest A&F University","place":["Xianyang, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University","place":["Xianyang, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lyuwen","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University","place":["Xianyang, Shaanxi, China"]},{"name":"Key Laboratory of Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs","place":["Xianyang, Shaanxi, China"]},{"name":"Shaanxi Engineering Research Center of Agricultural Information Intelligent Perception and Analysis, Northwest A&F University","place":["Yangling, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ce","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University","place":["Xianyang, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Horticulture, Northwest A&F University","place":["Xianyang, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenchong","family":"Min","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University","place":["Xianyang, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Horticulture, Northwest A&F University","place":["Xianyang, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Horticulture, Northwest A&F University","place":["Xianyang, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanming","family":"Nie","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University","place":["Xianyang, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"B1","first-page":"266","article-title":"Test-time adaptation in point clouds: Leveraging sampling variation with weight averaging","author":"Bahri","year":"2025"},{"key":"B2","first-page":"137","article-title":"ASAP: Attention-based state space abstraction for policy summarization","author":"Bekkemoen","year":"2024"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2025.102999","article-title":"Low-cost phone-based LiDAR scanning technology provides sub-centimeter accuracy when measuring the main dimensions of motor-manual tree felling cuts","volume":"85","author":"Borz","year":"2025","journal-title":"Ecol. Inf."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2024.115773","article-title":"An entropy-based approach for a robust least squares spline approximation","volume":"443","author":"Brugnano","year":"2024","journal-title":"J. Comput. Appl. Math."},{"key":"B5","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1093\/biomet\/asad024","article-title":"Populations of unlabelled networks: Graph space geometry and generalized geodesic principal components","volume":"111","author":"Calissano","year":"2024","journal-title":"Biometrika"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.scienta.2025.114178","article-title":"Mitigating cadmium and nickel uptake in lettuce through sulfur-enriched vermicompost: Impacts on soil fertility and sulfur compounds","volume":"346","author":"Chen","year":"2025","journal-title":"Sci. Hortic."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tgrs.2024.3353676","article-title":"3D terrain mapping and filtering from coarse-resolution data cubes extracted from real-aperture 94-GHz radar","volume":"62","author":"Harcourt","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102388","article-title":"mm-CasGAN: A cascaded adversarial neural framework for mmWave radar point cloud enhancement","volume":"108","author":"Hasan","year":"2024","journal-title":"Inf. Fus."},{"key":"B9","first-page":"1","article-title":"Pipeline defect detection based on matrix-array solid-state LiDAR","author":"Huang","year":"2025"},{"key":"B10","doi-asserted-by":"publisher","first-page":"100050","DOI":"10.1016\/j.plaphe.2025.100050","article-title":"A scalable and efficient UAV-based pipeline and deep learning framework for phenotyping sorghum panicle morphology from point clouds","volume":"7","author":"James","year":"2025","journal-title":"Plant Phenomics"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.scienta.2025.114136","article-title":"Evaluation of heat stress response in pepper (Capsicum annuum L.) seedlings under controlled environmental conditions using a high-throughput 3D multispectral phenotyping","volume":"345","author":"Jang","year":"2025","journal-title":"Sci. Hortic."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1457360","article-title":"DFMA: An improved DeepLabv3+ based on FasterNet, multi-receptive field, and attention mechanism for high-throughput phenotyping of seedlings","volume":"15","author":"Jia","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B13","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1186\/s13007-025-01375-8","article-title":"Mapping of cotton bolls and branches with high-granularity through point cloud segmentation","volume":"21","author":"Jiang","year":"2025","journal-title":"Plant Methods"},{"key":"B14","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s13007-025-01376-7","article-title":"Maui: Modular analytics of UAS imagery for specialty crop research","volume":"21","author":"Kanaley","year":"2025","journal-title":"Plant Methods"},{"key":"B15","first-page":"264","article-title":"Adaptive real-time lidar raw packet processing for dynamic environments","author":"Khajuria","year":"2025"},{"key":"B16","first-page":"62","article-title":"Stochastic gradient descent methods with step adaptation","author":"Krutikov","year":"2025"},{"key":"B17","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1186\/s12870-025-06307-1","article-title":"Climate change impacts on tomato production in high-tech soilless greenhouses in T\u00fcrkiye","volume":"25","author":"K\u00fcrkl\u00fc","year":"2025","journal-title":"BMC Plant Biol."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2026.111474","article-title":"A stem-leaf segmentation method of maize plant point cloud based on region growing and leaf phenotypic parameters measurement","volume":"244","author":"Liu","year":"2026","journal-title":"Comput. Electron. Agric."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.scienta.2024.113158","article-title":"PSTNet: Transformer for aggregating neighborhood features in 3D point cloud semantic segmentation of eggplant plants","volume":"331","author":"Ma","year":"2024","journal-title":"Sci. Hortic."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102371","article-title":"Efficient networks for textureless feature registration via free receptive field","volume":"108","author":"Ma","year":"2024","journal-title":"Inf. Fus."},{"key":"B21","first-page":"16949","article-title":"Fast point transformer","author":"Park","year":"2022"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108504","article-title":"Imaging spectroscopy for monitoring the crop status of tomato plants","volume":"216","author":"Polder","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1491170","article-title":"Plant stem and leaf segmentation and phenotypic parameter extraction using neural radiance fields and lightweight point cloud segmentation networks","volume":"16","author":"Qiao","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B24","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"R","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2025.121966","article-title":"Automatic liver tumor segmentation of CT and MRI volumes using ensemble ResUNet-InceptionV4 model","volume":"704","author":"Rahman","year":"2025","journal-title":"Inf. Sci."},{"key":"B26","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/tci.2023.3348758","article-title":"Simultaneous multifrequency demodulation for single-shot multiple-path ToF imaging","volume":"10","author":"Shahandashti","year":"2024","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"B27","first-page":"1","article-title":"A point cloud downsampling method balancing global and local shapes for 3D object classification","author":"Sugimoto","year":"2025"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110627","article-title":"Using 3D reconstruction from image motion to predict total leaf area in dwarf tomato plants","volume":"237","author":"Usenko","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.scienta.2024.112861","article-title":"Exogenous methyl jasmonate regulates endogenous hormone synthesis of soilless cultivated Chinese chive to promote growth physiology and photosynthesis","volume":"327","author":"Wang","year":"2024","journal-title":"Sci. Hortic."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy12030692","article-title":"Three-dimensional reconstruction of soybean canopy based on multivision technology for calculation of phenotypic traits","volume":"12","author":"Wang","year":"2022","journal-title":"Agron. (Basel)."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1508449","article-title":"Segmentation of tobacco shred point cloud and 3-D measurement based on improved PointNet++ network with DTC algorithm","volume":"15","author":"Wang","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2024.128669","article-title":"Randomized progressive iterative approximation for B-spline curve and surface fittings","volume":"473","author":"Wu","year":"2024","journal-title":"Appl. Math. Comput."},{"key":"B33","doi-asserted-by":"publisher","first-page":"100049","DOI":"10.1016\/j.plaphe.2025.100049","article-title":"Automated 3D segmentation of plant organs via the Plant-MAE: A self-supervised learning framework","volume":"7","author":"Xie","year":"2025","journal-title":"Plant Phenomics"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmecsci.2025.110088","article-title":"Customizing acoustic and electromagnetic unidirectional states in phoxonic topological insulators","volume":"290","author":"Xu","year":"2025","journal-title":"Int. J. Mech. Sci."},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1458962","article-title":"Research on the quantification and automatic classification method of Chinese cabbage plant type based on point cloud data and PointNet++","volume":"15","author":"Yang","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108512","article-title":"3D-based precise evaluation pipeline for maize ear rot using multi-view stereo reconstruction and point cloud semantic segmentation","volume":"216","author":"Yang","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.111380","article-title":"DRP-Net and clustering algorithm for stem-leaf segmentation and phenotypic trait extraction from tomato point clouds","volume":"243","author":"Yao","year":"2026","journal-title":"Comput. Electron. Agric."},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1654232","article-title":"Automated measurement of field crop phenotypic traits using UAV 3D point clouds and an improved PointNet++","volume":"16","author":"Yao","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111622","article-title":"Multi-scale learnable key-channel attention network for point cloud classification and segmentation","volume":"159","author":"Zhao","year":"2024","journal-title":"Appl. Soft. Comput."},{"key":"B40","doi-asserted-by":"publisher","first-page":"100064","DOI":"10.1016\/j.plaphe.2025.100064","article-title":"An unsupervised semantic segmentation network for wood-leaf separation from 3D point clouds","volume":"7","author":"Zhong","year":"2025","journal-title":"Plant Phenomics"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1753706\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:45:30Z","timestamp":1776059130000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1753706\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":40,"alternative-id":["10.3389\/fpls.2026.1753706"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1753706","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,13]]},"article-number":"1753706"}}