000 04878nab|a22007577a|4500
001 69408
003 MX-TxCIM
005 20251016154349.0
008 20259s2025|||||xxu||p|op||||00||0|eng|dd
022 _a2643-6515
024 8 _ahttps://doi.org/10.1016/j.plaphe.2025.100084
040 _aMX-TxCIM
041 _aeng
100 0 _aZijian Wang
_940324
245 1 4 _aThe Global Wheat Full Semantic Organ Segmentation (GWFSS) dataset
260 _aUnited States of America :
_bElsevier B.V.,
_c2025.
500 _aPeer review
500 _aOpen Access
520 _aComputer vision is increasingly used in farmers' fields and agricultural experiments to quantify important traits. Imaging setups with a sub-millimeter ground sampling distance enable the detection and tracking of plant features, including size, shape, and colour. Although today's AI-driven foundation models segment almost any object in an image, they still fail for complex plant canopies. To improve model performance, the global wheat dataset consortium assembled a diverse set of images from experiments around the globe. After the head detection dataset (GWHD), the new dataset targets a full semantic segmentation (GWFSS) of organs (leaves, stems and spikes) covering all developmental stages. Images were collected by 11 institutions using a wide range of imaging setups. Two datasets are provided: i) a set of 1096 diverse images in which all organs were labelled at the pixel level, and (ii) a dataset of 52,078 images without annotations available for additional training. The labelled set was used to train segmentation models based on DeepLabV3Plus and Segformer. Our Segformer model performed slightly better than DeepLabV3Plus with a mIOU for leaves and spikes of ca. 90 %. However, the precision for stems with 54 % was rather lower. The major advantages over published models are: i) the exclusion of weeds from the wheat canopy, ii) the detection of all wheat features including necrotic and senescent tissues and its separation from crop residues. This facilitates further development in classifying healthy vs. unhealthy tissue to address the increasing need for accurate quantification of senescence and diseases in wheat canopies.
546 _aText in English
591 _aPerez-Olivera, I. : Not in IRS staff list but CIMMYT Affiliation
597 _dEuropean Commission (EC)
_dInternational Wheat Yield Partnership (IWYP)
_dHeat and Drought Wheat Improvement Consortium (HeDWIC)
_dAccelerating Genetic Gains in Maize and Wheat (AGG)
_dModernización Sustentable de la Agricultura Tradicional (MasAgro)
_dSecretaría de Agricultura y Desarrollo Rural (SADER)
_dFoundation for Food & Agriculture Research (FFAR)
_dSwiss National Science Foundation (SNSF)
_dAgence Nationale de la Recherche (ANR)
_dBiotechnology and Biological Sciences Research Council (BBSRC)
_dAnalytics for the Australian Grains Industry (AAGI)
_dFund for Scientific Research (FNRS)
_dNatural Sciences and Engineering Research Council of Canada (NSERC)
_dCanada First Research Excellence Fund (CFREF)
_dJapan Science and Technology Agency (JST)
650 7 _aWheat
_2AGROVOC
_91310
650 7 _aFields
_2AGROVOC
_97065
650 7 _aHigh-throughput phenotyping
_2AGROVOC
_930900
650 7 _aBreeding
_2AGROVOC
_91029
700 1 _aZenkl, R.
_940325
700 1 _aGreche, L.
_940326
700 _aDe Solan, B.
_910072
700 1 _aSamatan, L.B.
_940327
700 0 _aSafaa Ouahid
_940328
700 1 _aVisioni, A.
_940329
700 1 _aRobles-Zazueta, C.A.
_8001710187
_gGlobal Wheat Program
_923303
700 1 _aPinto Espinosa, F.
_8I1707012
_gFormerly Global Wheat Program
_94431
700 1 _aPerez-Olivera, I.
_940330
700 1 _aReynolds, M.P.
_gGlobal Wheat Program
_8INT1511
_9831
700 0 _aChen Zhu
_940383
700 _aShouyang Liu
_910189
700 1 _aD'argaignon, M.P.
_940331
700 1 _aLopez-Lozano, R.
_913779
700 _aWeiss, M.
_910250
700 1 _aMarzougui, A.
_930257
700 1 _aRoth, L.
_940332
700 1 _aDandrifosse, S.
_924311
700 1 _aCarlier, A.
_924312
700 1 _aDumont, B.
_91582
700 1 _aMercatoris, B.
_924313
700 1 _aFernandez, J.
_940333
700 1 _aChapman, S.
_9458
700 1 _aNajafian, K.
_940334
700 1 _aStavness, I.
_924318
700 0 _aHaozhou Wang
_924315
700 0 _aWei Guo
_98202
700 1 _aVirlet, N.
_940335
700 1 _aHawkesford, M.J.
_910302
700 0 _aZhi Chen
_940336
700 1 _aDavid, E.
_924303
700 1 _aGillet, J.
_913780
700 0 _aKamran Irfan
_940337
700 _aComar, A.
_910054
700 1 _aHund, A.
_921619
773 0 _tPlant Phenomics
_gv. 7, no. 3, art. 100084
_dUnited States of America : Elsevier B.V., 2025.
_x2643-6515
856 4 _yOpen Access through DSpace
_uhttps://hdl.handle.net/10883/35926
942 _cJA
_n0
_2ddc
999 _c69408
_d69400