The Global Wheat Head Detection(GWHD)dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4700 RGB images acquired from various acquisition platforms and 7 countries/institutions.With an ass...The Global Wheat Head Detection(GWHD)dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4700 RGB images acquired from various acquisition platforms and 7 countries/institutions.With an associated competition hosted in Kaggle,GWHD_2020 has successfully attracted attention from both the computer vision and agricultural science communities.From this first experience,a few avenues for improvements have been identified regarding data size,head diversity,and label reliability.To address these issues,the 2020 dataset has been reexamined,relabeled,and complemented by adding 1722 images from 5 additional countries,allowing for 81,553 additional wheat heads.We now release in 2021 a new version of the Global Wheat Head Detection dataset,which is bigger,more diverse,and less noisy than the GWHD_2020 version.展开更多
The application of spectral reflectance indices(SRIs) as proxies to screen for yield potential(YP) and heat stress(HS) is emerging in crop breeding programs.Thus, a comparison of SRIs and their associations with grain...The application of spectral reflectance indices(SRIs) as proxies to screen for yield potential(YP) and heat stress(HS) is emerging in crop breeding programs.Thus, a comparison of SRIs and their associations with grain yield(GY) under YP and HS conditions is important.In this study, we assessed the usefulness of 27 SRIs for indirect selection for agronomic traits by evaluating an elite spring wheat association mapping initiative(WAMI) population comprising 287 elite lines under YP and HS conditions.Genetic and phenotypic analysis identified 11 and 9 SRIs in different developmental stages as efficient indirect selection indices for yield in YP and HS conditions,respectively.We identified enhanced vegetation index(EVI) as the common SRI associated with GY under YP at booting, heading and late heading stages, whereas photochemical reflectance index(PRI) and normalized difference vegetation index(NDVI) were the common SRIs under booting and heading stages in HS.Genomewide association study(GWAS) using 18704 single nucleotide polymorphisms(SNPs) from Illumina i Select90 K identified 280 and 43 marker-trait associations for efficient SRIs at different developmental stages under YP and HS, respectively.Common genomic regions for multiple SRIs were identified in 14 regions in 9 chromosomes: 1 B(60–62 cM), 3 A(15, 85–90, 101–105 cM), 3 B(132–134 cM), 4 A(47–51 cM), 4 B(71–75 cM), 5 A(43–49, 56–60, 89–93 cM), 5 B(124–125 cM),6 A(80–85 cM), and 6 B(57–59, 71 cM).Among them,SNPs in chromosome 5 A(89–93 cM) and 6 A(80–85 cM)were co-located for yield and yield related traits.Overall,this study highlights the utility of SRIs as proxies for GY under YP and HS.High heritability estimates and identification of marker-trait associations indicate that SRIs are useful tools for understanding the genetic basis of agronomic and physiological traits.展开更多
基金the French National Research Agency under the Investments for the Future Program,referred as ANR-16-CONV-0004 PIA#Digitag.Institut Convergences Agriculture Numérique,Hiphen supported the organization of the competition.Japan:Kubota supported the organization of the competi-tion.Australia:Grains Research and Development Corpora-tion(UOQ2002-008RTX machine learning applied to high-throughput feature extraction from imagery to map spatial variability and UOQ2003-011RTX INVITA-a technology and analytics platform for improving variety selection)sup-ported competition.
文摘The Global Wheat Head Detection(GWHD)dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4700 RGB images acquired from various acquisition platforms and 7 countries/institutions.With an associated competition hosted in Kaggle,GWHD_2020 has successfully attracted attention from both the computer vision and agricultural science communities.From this first experience,a few avenues for improvements have been identified regarding data size,head diversity,and label reliability.To address these issues,the 2020 dataset has been reexamined,relabeled,and complemented by adding 1722 images from 5 additional countries,allowing for 81,553 additional wheat heads.We now release in 2021 a new version of the Global Wheat Head Detection dataset,which is bigger,more diverse,and less noisy than the GWHD_2020 version.
基金implemented by the CIMMYT as part of the projects ARCADIA and Mas Agro Trigo in collaboration with the CIMMYT, made possible by the generous support of SAGARPA Mas Agro Trigo and ARCADIAsponsored by the China Scholarship Council (CSC)–CIMMYT scholarship
文摘The application of spectral reflectance indices(SRIs) as proxies to screen for yield potential(YP) and heat stress(HS) is emerging in crop breeding programs.Thus, a comparison of SRIs and their associations with grain yield(GY) under YP and HS conditions is important.In this study, we assessed the usefulness of 27 SRIs for indirect selection for agronomic traits by evaluating an elite spring wheat association mapping initiative(WAMI) population comprising 287 elite lines under YP and HS conditions.Genetic and phenotypic analysis identified 11 and 9 SRIs in different developmental stages as efficient indirect selection indices for yield in YP and HS conditions,respectively.We identified enhanced vegetation index(EVI) as the common SRI associated with GY under YP at booting, heading and late heading stages, whereas photochemical reflectance index(PRI) and normalized difference vegetation index(NDVI) were the common SRIs under booting and heading stages in HS.Genomewide association study(GWAS) using 18704 single nucleotide polymorphisms(SNPs) from Illumina i Select90 K identified 280 and 43 marker-trait associations for efficient SRIs at different developmental stages under YP and HS, respectively.Common genomic regions for multiple SRIs were identified in 14 regions in 9 chromosomes: 1 B(60–62 cM), 3 A(15, 85–90, 101–105 cM), 3 B(132–134 cM), 4 A(47–51 cM), 4 B(71–75 cM), 5 A(43–49, 56–60, 89–93 cM), 5 B(124–125 cM),6 A(80–85 cM), and 6 B(57–59, 71 cM).Among them,SNPs in chromosome 5 A(89–93 cM) and 6 A(80–85 cM)were co-located for yield and yield related traits.Overall,this study highlights the utility of SRIs as proxies for GY under YP and HS.High heritability estimates and identification of marker-trait associations indicate that SRIs are useful tools for understanding the genetic basis of agronomic and physiological traits.