Grading of vegetative cuttings using computer vision

Citation
S. Singh et M. Montemerlo, Grading of vegetative cuttings using computer vision, ADV ROBOT, 12(5), 1999, pp. 551-564
Citations number
14
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
ADVANCED ROBOTICS
ISSN journal
01691864 → ACNP
Volume
12
Issue
5
Year of publication
1999
Pages
551 - 564
Database
ISI
SICI code
0169-1864(1999)12:5<551:GOVCUC>2.0.ZU;2-D
Abstract
This paper reports on recent progress in the development of system to group populations of vegetative cuttings. The system is required to assign a cla ssification to cuttings such that they appear uniform after a growing perio d using single two-dimensional monochrome images. We have developed a fast segmentation technique that is able to measure plant features and a supervi sed learning scheme that learns a mapping from the features to a scalar cla ssification. We report results based on segmentation of over 2000 geranium cuttings. The system is able to process images at 2 Hz and has an accuracy of over 90%. Both metrics exceed human performance.