Model-based algorithms for phenotyping from 3D imaging of dense wheat crops
- Resource Type
- Authors
- Richard Dudley; Peter M. Harris; Imran Mohamed; Valerie Livina; Andrew Thompson
- Source
- 2019 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor).
- Subject
- Computer science
business.industry
Feature extraction
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Point cloud
Data analysis
Spike (software development)
Context (language use)
Cluster analysis
business
Automation
Remote sensing
Structured light
- Language
High-throughput phenotyping requires the automation of the process of extracting relevant quantitative information from crop images. We achieve this goal for dense wheat crops by applying model-based data analysis techniques (including clustering and data-fitting) to high-resolution 3D point clouds obtained from structured light laser scanners. By performing experiments comparing our estimates of crop height, spike height and spike width with manual measurements, we demonstrate that our approach is promising even in the challenging context of dense vegetation.