Reliable seed yield estimation is an indispensable step in plant breeding programs geared towards cultivar development in major row crops.The objective of this study is to develop a machine learning(ML)approach adept ...Reliable seed yield estimation is an indispensable step in plant breeding programs geared towards cultivar development in major row crops.The objective of this study is to develop a machine learning(ML)approach adept at soybean(Glycine max L.(Merr.))pod counting to enable genotype seed yield rank prediction from in-field video data collected by a ground robot.To meet this goal,we developed a multiview image-based yield estimation framework utilizing deep learning architectures.Plant images captured from different angles were fused to estimate the yield and subsequently to rank soybean genotypes for application in breeding decisions.We used data from controlled imaging environment in field,as well as from plant breeding test plots in field to demonstrate the efficacy of our framework via comparing performance with manual pod counting and yield estimation.Our results demonstrate the promise of ML models in making breeding decisions with significant reduction of time and human effort and opening new breeding method avenues to develop cultivars.展开更多
基金the funding support from the Iowa Soybean Association(A.K.S.)USDA-NIFA Grants#2017-67007-26151(S.S.,A.K.S.,B.G.,A.S.),2017-67021-25965(S.B.,S.S.,B.G.,A.S.,A.K.S.),and 2019-67021-29938(A.S.,B.G.,S.S,A.K.S)+5 种基金NSF S&CC Grant#1952045NSF Grant#CNS-1954556Raymond F.Baker Center for Plant Breeding(A.K.S.)Bayer Chair in Soybean Breeding(A.K.S.)Plant Sciences Institute(S.S.,A.K.S.,B.G.)and USDA CRIS Project IOW04714(A.K.S.,A.S).M.E.C.was partly supported by a graduate assistantship through NSF NRT Predictive Plant Phenomics Project.
文摘Reliable seed yield estimation is an indispensable step in plant breeding programs geared towards cultivar development in major row crops.The objective of this study is to develop a machine learning(ML)approach adept at soybean(Glycine max L.(Merr.))pod counting to enable genotype seed yield rank prediction from in-field video data collected by a ground robot.To meet this goal,we developed a multiview image-based yield estimation framework utilizing deep learning architectures.Plant images captured from different angles were fused to estimate the yield and subsequently to rank soybean genotypes for application in breeding decisions.We used data from controlled imaging environment in field,as well as from plant breeding test plots in field to demonstrate the efficacy of our framework via comparing performance with manual pod counting and yield estimation.Our results demonstrate the promise of ML models in making breeding decisions with significant reduction of time and human effort and opening new breeding method avenues to develop cultivars.
