KAT4IA:K-Means Assisted Training for Image Analysis of Field-Grown Plant Phenotypes

作     者：Xingche Guo Yumou Qiu Dan Nettleton Cheng-Ting Yeh Zihao Zheng Stefan Hey Patrick SSchnable 

作者机构：Department of StatisticsIowa State UniversityIowaUSA Plant Sciences InstituteIowa State UniversityIowaUSA Department of AgronomyIowa State UniversityIowaUSA 

出 版 物：《Plant Phenomics》 (植物表型组学（英文）)

年 卷 期：2021年第3卷第1期

页      面：144-155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] 08[工学] 080203[工学-机械设计及理论] 0901[农学-作物学] 0802[工学-机械工程] 

基　　金：the US National Science Foundation under grant HDR:TRIPODS 19-34884 the United States Department of Agriculture National Institute of Food and Agriculture Hatch project IOW03617,the Office of Science(BER),U.S.Department of Energy,Grant no.DE-SC0020355 the Plant Sciences Institute,Iowa State University,Scholars Program 

主　　题：utilize preparing separating 

摘      要：High-throughput phenotyping enables the efficient collection of plant trait data at *** example involves using imaging systems over key phases of a crop growing *** the resulting images provide rich data for statistical analyses of plant phenotypes,image processing for trait extraction is required as a *** methods for trait extraction are mainly based on supervised learning with human labeled data or semisupervised learning with a mixture of human labeled data and unsupervised ***,preparing a sufficiently large training data is both time and *** describe a self-supervised pipeline(KAT4IA)that uses K-means clustering on greenhouse images to construct training data for extracting and analyzing plant traits from an image-based field phenotyping *** KAT4IA pipeline includes these main steps:self-supervised training set construction,plant segmentation from images of field-grown plants,automatic separation of target plants,calculation of plant traits,and functional curve fitting of the extracted *** deal with the challenge of separating target plants from noisy backgrounds in field images,we describe a novel approach using row-cuts and column-cuts on images segmented by transform domain neural network learning,which utilizes plant pixels identified from greenhouse images to train a segmentation model for field *** approach is efficient and does not require human *** results show that KAT4IA is able to accurately extract plant pixels and estimate plant heights.