An Exploration of Deep-Learning Based Phenotypic Analysis to Detect Spike Regions in Field Conditions for UK Bread Wheat

作     者：Tahani Alkhudaydi Daniel Reynolds Simon Griffiths Ji Zhou Beatriz de la Iglesia 

作者机构：University of East AngliaNorwich Research ParkNorwich NR47TJUK University of TabukFaculty of Computers&ITTabuk 71491Saudi Arabia Earlham InstituteNorwich Research ParkNorwich NR47UZUK John Innes CentreNorwich Research ParkNorwich NR47UHUK Plant Phenomics Research CenterChina-UK Plant Phenomics Research CentreNanjing Agricultural UniversityNanjing 210095China 

出 版 物：《Plant Phenomics》 (植物表型组学（英文）)

年 卷 期：2019年第1卷第1期

页      面：162-178页

核心收录：

学科分类：0501[文学-中国语言文学] 0303[法学-社会学] 0710[理学-生物学] 0502[文学-外国语言文学] 0601[历史学-考古学] 1302[艺术学-音乐与舞蹈学] 1301[艺术学-艺术学理论] 09[农学] 0901[农学-作物学] 

基　　金：Tahani Alkhudaydi was funded by University of Tabuk,scholarship program(37/052/75278) Ji Zhou,Daniel Reynolds,and Simon Griffiths were partially funded by UKRI Biotechnology Biological Sciences Research Council's(BBSRC)Designing Future Wheat Cross-Institute Strategic Programme(BB/P016855/1)to Prof.Graham Moore BBS/E/J/00OPR9781 to Simon Griffiths BBS/E/T/00OPR9785 to Ji Zhou Daniel Reynolds was partially supported by the Core Strategic Programme Grant(BB/CSP17270/l)at the Earlham Institute Beatriz de la Iglesiawas supported by ES/LO11859/1,from the Business and LocalGovernment Data Research Centre,funded by the Economicand Social Research Council 

主　　题：Wheat breeding crops 

摘      要：Wheat is one of the major crops in the world,with a global demand expected to reach 850 million tons by 2050 that is clearly outpacing current *** continual pressure to sustain wheat yield due to the world’s growing population under fluctuating climate conditions requires breeders to increase yield and yield stability across *** are working to integrate deep learning into field-based phenotypic analysis to assist breeders in this *** have utilised wheat images collected by distributed CropQuant phenotyping workstations deployed for multiyear field experiments of UK bread wheat *** on these image series,we have developed a deep-learning based analysis pipeline to segment spike regions from complicated *** a first step towards robust measurement of key yield traits in the field,we present a promising approach that employ Fully Convolutional Network(FCN)to performsemantic segmentation of images to segment wheat spike *** also demonstrate the benefits of transfer learning through the use of parameters obtained from other image *** found that the FCN architecture had achieved a Mean classification Accuracy(MA)82%on validation data and76%on test data and Mean Intersection over Union value(MIoU)73%on validation data and and64%on test *** this phenomics research,we trust our attempt is likely to form a sound foundation for extracting key yield-related traits such as spikes per unit area and spikelet number per spike,which can be used to assist yield-focused wheat breeding objectives in near future.