KAT4IA: K-Means Assisted Training for Image Analysis of Field-Grown Plant Phenotypes
Open Access
- 1 January 2021
- journal article
- research article
- Published by American Association for the Advancement of Science (AAAS) in Plant Phenomics
- Vol. 2021, 9805489
- https://doi.org/10.34133/2021/9805489
Abstract
High-throughput phenotyping enables the efficient collection of plant trait data at scale. One example involves using imaging systems over key phases of a crop growing season. Although the resulting images provide rich data for statistical analyses of plant phenotypes, image processing for trait extraction is required as a prerequisite. Current 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 data. Unfortunately, preparing a sufficiently large training data is both time and labor-intensive. We describe a self-supervised pipeline (KAT4IA) that uses -means clustering on greenhouse images to construct training data for extracting and analyzing plant traits from an image-based field phenotyping system. The 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 traits. To 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 images. This approach is efficient and does not require human intervention. Our results show that KAT4IA is able to accurately extract plant pixels and estimate plant heights.Keywords
Funding Information
- Plant Sciences Institute, Iowa State University
- U.S. Department of Energy (DE-SC0020355)
- United States Department of Agriculture National Institute of Food and Agriculture Hatch project (IOW03617)
- National Science Foundation (HDR:TRIPODS 19-34884)
This publication has 33 references indexed in Scilit:
- Lights, camera, action: high-throughput plant phenotyping is ready for a close-upCurrent Opinion in Plant Biology, 2015
- A Review of Imaging Techniques for Plant PhenotypingSensors, 2014
- Image-based phenotyping for non-destructive screening of different salinity tolerance traits in riceRice, 2014
- Integrated Analysis Platform: An Open-Source Information System for High-Throughput Plant PhenotypingPlant Physiology, 2014
- Field high-throughput phenotyping: the new crop breeding frontierTrends in Plant Science, 2014
- Applications of Image Processing in Agriculture: A SurveyInternational Journal of Computer Applications, 2012
- On the use of depth camera for 3D phenotyping of entire plantsComputers and Electronics in Agriculture, 2012
- Deep Learning via Semi-supervised EmbeddingLecture Notes in Computer Science, 2012
- HTPheno: An image analysis pipeline for high-throughput plant phenotypingBMC Bioinformatics, 2011
- A simple nonparametric estimator of a strictly monotone regression functionBernoulli, 2006