Wheat-Net: An Automatic Dense Wheat Spike Segmentation Method Based on an Optimized Hybrid Task Cascade Model

doi:10.3389/fpls.2022.834938

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 互联网大数据与信息安全

	Wheat-Net: An Automatic Dense Wheat Spike Segmentation Method Based on an Optimized Hybrid Task Cascade Model
	Zhang, Jiajing1,2,3 ; Min, An 4; Steffenson, Brian J.5; Su, Wen-Hao 6; Hirsch, Cory D.5; Anderson, James 7; Wei, Jian 1; Ma, Qin 1; Yang, Ce 4
发表期刊	FRONTIERS IN PLANT SCIENCE
ISSN	1664-462X
	2022-02-10
卷号	13 页码:13
通讯作者	Ma, Qin(sockline@163.com) ; Yang, Ce(ceyang@umn.edu)
摘要	Precise segmentation of wheat spikes from a complex background is necessary for obtaining image-based phenotypic information of wheat traits such as yield estimation and spike morphology. A new instance segmentation method based on a Hybrid Task Cascade model was proposed to solve the wheat spike detection problem with improved detection results. In this study, wheat images were collected from fields where the environment varied both spatially and temporally. Res2Net50 was adopted as a backbone network, combined with multi-scale training, deformable convolutional networks, and Generic ROI Extractor for rich feature learning. The proposed methods were trained and validated, and the average precision (AP) obtained for the bounding box and mask was 0.904 and 0.907, respectively, and the accuracy for wheat spike counting was 99.29%. Comprehensive empirical analyses revealed that our method (Wheat-Net) performed well on challenging field-based datasets with mixed qualities, particularly those with various backgrounds and wheat spike adjacence/occlusion. These results provide evidence for dense wheat spike detection capabilities with masking, which is useful for not only wheat yield estimation but also spike morphology assessments.
关键词	wheat spike instance segmentation Hybrid Task Cascade model challenging dataset non-structural field
DOI	10.3389/fpls.2022.834938
关键词[WOS]	NETWORKS ; MACHINE
收录类别	SCI
语种	英语
资助项目	USDA-ARS United States Wheat and Barley Scab Initiative[59-0206-0-181] ; Lieberman-Okinow Endowment at the University of Minnesota ; State of Minnesota Small Grains Initiative ; Provincial Natural Science Foundation Project[ZR2021MC099]
项目资助者	USDA-ARS United States Wheat and Barley Scab Initiative ; Lieberman-Okinow Endowment at the University of Minnesota ; State of Minnesota Small Grains Initiative ; Provincial Natural Science Foundation Project
WOS研究方向	Plant Sciences
WOS类目	Plant Sciences
WOS记录号	WOS:000760819100001
出版者	FRONTIERS MEDIA SA
七大方向——子方向分类	目标检测、跟踪与识别
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/47895
专题	多模态人工智能系统全国重点实验室_互联网大数据与信息安全
通讯作者	Ma, Qin; Yang, Ce
作者单位	1.China Agr Univ, Coll Informat & Elect Engn, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 4.Univ Minnesota, Dept Bioprod & Biosyst Engn, St Paul, MN 55108 USA 5.Univ Minnesota, Dept Plant Pathol, St Paul, MN USA 6.China Agr Univ, Coll Engn, Beijing, Peoples R China 7.Univ Minnesota, Dept Agron & Plant Genet, St Paul, MN USA
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zhang, Jiajing,Min, An,Steffenson, Brian J.,et al. Wheat-Net: An Automatic Dense Wheat Spike Segmentation Method Based on an Optimized Hybrid Task Cascade Model[J]. FRONTIERS IN PLANT SCIENCE,2022,13:13.
APA	Zhang, Jiajing.,Min, An.,Steffenson, Brian J..,Su, Wen-Hao.,Hirsch, Cory D..,...&Yang, Ce.(2022).Wheat-Net: An Automatic Dense Wheat Spike Segmentation Method Based on an Optimized Hybrid Task Cascade Model.FRONTIERS IN PLANT SCIENCE,13,13.
MLA	Zhang, Jiajing,et al."Wheat-Net: An Automatic Dense Wheat Spike Segmentation Method Based on an Optimized Hybrid Task Cascade Model".FRONTIERS IN PLANT SCIENCE 13(2022):13.