001022310 001__ 1022310
001022310 005__ 20240226075443.0
001022310 0247_ $$2datacite_doi$$a10.34734/FZJ-2024-01428
001022310 037__ $$aFZJ-2024-01428
001022310 1001_ $$0P:(DE-Juel1)185864$$aCherepashkin, Vsevolod$$b0$$ufzj
001022310 1112_ $$aICCV 2023$$cParis$$d2023-10-02 - 2023-10-06$$wFrance
001022310 245__ $$aDeep Learning Based 3d Reconstruction for Phenotyping of Wheat Seeds: a Dataset, Challenge, and Baseline Method
001022310 260__ $$c2023
001022310 300__ $$a561-571
001022310 3367_ $$2ORCID$$aCONFERENCE_PAPER
001022310 3367_ $$033$$2EndNote$$aConference Paper
001022310 3367_ $$2BibTeX$$aINPROCEEDINGS
001022310 3367_ $$2DRIVER$$aconferenceObject
001022310 3367_ $$2DataCite$$aOutput Types/Conference Paper
001022310 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1706794417_3610
001022310 520__ $$aWe present a new data set for 3d wheat seed reconstruction, propose a challenge, and provide baseline methods. Individual plant seed properties influence early development of plants and are thus of interest in plant phenotyping experiments. Seed shape can be measured reliably from images using volume carving, as done in robotic setups such as phenoSeeder. However, about 36 images are needed to obtain a suitably accurate 3d model, where image acquisition takes approximately 20 s. For large-scale experiments with thousands of seeds higher throughput is required limiting image acquisition time. We present a deep-learning model that reconstructs an approximate 3d point cloud from fewer images, even only a single view. It has a significantly lower error than linear regression, which has been actively used so far in similar tasks. Using three images reduces imaging time by a factor of 10, where relative errors of volume length, width, and height are all around 2%. Inference time from the neural network is negligibly short compared with imaging time which enables this method for real-time measurements and sorting.
001022310 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001022310 7001_ $$0P:(DE-Juel1)191034$$aYildiz, Erenus$$b1$$ufzj
001022310 7001_ $$0P:(DE-Juel1)129315$$aFischbach, Andreas$$b2$$ufzj
001022310 7001_ $$0P:(DE-HGF)0$$aKobbelt, Leif$$b3
001022310 7001_ $$0P:(DE-Juel1)129394$$aScharr, Hanno$$b4$$ufzj
001022310 8564_ $$uhttps://juser.fz-juelich.de/record/1022310/files/Deep%20Learning%20Based%203d%20Reconstruction%20for%20Phenotyping%20of%20Wheat%20Seeds%20a%20Dataset%2C%20Challenge%2C%20and%20Baseline%20Method%20-%20Cherepashkin_Deep_Learning_Based_3d_Reconstruction_for_Phenotyping_of_Wheat_Seeds_ICCVW_2023_paper.pdf$$yOpenAccess
001022310 8564_ $$uhttps://juser.fz-juelich.de/record/1022310/files/Deep%20Learning%20Based%203d%20Reconstruction%20for%20Phenotyping%20of%20Wheat%20Seeds%20a%20Dataset%2C%20Challenge%2C%20and%20Baseline%20Method%20-%20Cherepashkin_Deep_Learning_Based_3d_Reconstruction_for_Phenotyping_of_Wheat_Seeds_ICCVW_2023_paper.gif?subformat=icon$$xicon$$yOpenAccess
001022310 8564_ $$uhttps://juser.fz-juelich.de/record/1022310/files/Deep%20Learning%20Based%203d%20Reconstruction%20for%20Phenotyping%20of%20Wheat%20Seeds%20a%20Dataset%2C%20Challenge%2C%20and%20Baseline%20Method%20-%20Cherepashkin_Deep_Learning_Based_3d_Reconstruction_for_Phenotyping_of_Wheat_Seeds_ICCVW_2023_paper.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001022310 8564_ $$uhttps://juser.fz-juelich.de/record/1022310/files/Deep%20Learning%20Based%203d%20Reconstruction%20for%20Phenotyping%20of%20Wheat%20Seeds%20a%20Dataset%2C%20Challenge%2C%20and%20Baseline%20Method%20-%20Cherepashkin_Deep_Learning_Based_3d_Reconstruction_for_Phenotyping_of_Wheat_Seeds_ICCVW_2023_paper.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001022310 8564_ $$uhttps://juser.fz-juelich.de/record/1022310/files/Deep%20Learning%20Based%203d%20Reconstruction%20for%20Phenotyping%20of%20Wheat%20Seeds%20a%20Dataset%2C%20Challenge%2C%20and%20Baseline%20Method%20-%20Cherepashkin_Deep_Learning_Based_3d_Reconstruction_for_Phenotyping_of_Wheat_Seeds_ICCVW_2023_paper.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001022310 909CO $$ooai:juser.fz-juelich.de:1022310$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001022310 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)185864$$aForschungszentrum Jülich$$b0$$kFZJ
001022310 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)191034$$aForschungszentrum Jülich$$b1$$kFZJ
001022310 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129315$$aForschungszentrum Jülich$$b2$$kFZJ
001022310 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129394$$aForschungszentrum Jülich$$b4$$kFZJ
001022310 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001022310 9141_ $$y2023
001022310 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001022310 920__ $$lyes
001022310 9201_ $$0I:(DE-Juel1)IAS-8-20210421$$kIAS-8$$lDatenanalyse und Maschinenlernen$$x0
001022310 980__ $$acontrib
001022310 980__ $$aVDB
001022310 980__ $$aUNRESTRICTED
001022310 980__ $$aI:(DE-Juel1)IAS-8-20210421
001022310 9801_ $$aFullTexts