Visual tracking for the recovery of multiple interacting plant root systems from X-ray μCT images

We propose a visual object tracking framework for the extraction of multiple interacting plant root systems from three-dimensional X-ray micro computed tomography images of plants grown in soil. Our method is based on a level set framework guided by a greyscale intensity distribution model to identi...

Full description

Bibliographic Details
Main Authors: Mairhofer, Stefan, Johnson, James, Sturrock, Craig, Bennett, Malcolm J., Mooney, Sacha J., Pridmore, Tony P.
Format: Article
Published: Springer Verlag 2015
Subjects:
Online Access:https://eprints.nottingham.ac.uk/32965/
_version_ 1848794530038415360
author Mairhofer, Stefan
Johnson, James
Sturrock, Craig
Bennett, Malcolm J.
Mooney, Sacha J.
Pridmore, Tony P.
author_facet Mairhofer, Stefan
Johnson, James
Sturrock, Craig
Bennett, Malcolm J.
Mooney, Sacha J.
Pridmore, Tony P.
author_sort Mairhofer, Stefan
building Nottingham Research Data Repository
collection Online Access
description We propose a visual object tracking framework for the extraction of multiple interacting plant root systems from three-dimensional X-ray micro computed tomography images of plants grown in soil. Our method is based on a level set framework guided by a greyscale intensity distribution model to identify object boundaries in image cross-sections. Root objects are followed through the data volume, while updating the tracker's appearance models to adapt to changing intensity values. In the presence of multiple root systems, multiple trackers can be used, but need to distinguish target objects from one another in order to correctly associate roots with their originating plants. Since root objects are expected to exhibit similar greyscale intensity distributions, shape information is used to constrain the evolving level set interfaces in order to lock trackers to their correct targets. The proposed method is tested on root systems of wheat plants grown in soil.
first_indexed 2025-11-14T19:17:39Z
format Article
id nottingham-32965
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:17:39Z
publishDate 2015
publisher Springer Verlag
recordtype eprints
repository_type Digital Repository
spelling nottingham-329652020-05-04T17:26:57Z https://eprints.nottingham.ac.uk/32965/ Visual tracking for the recovery of multiple interacting plant root systems from X-ray μCT images Mairhofer, Stefan Johnson, James Sturrock, Craig Bennett, Malcolm J. Mooney, Sacha J. Pridmore, Tony P. We propose a visual object tracking framework for the extraction of multiple interacting plant root systems from three-dimensional X-ray micro computed tomography images of plants grown in soil. Our method is based on a level set framework guided by a greyscale intensity distribution model to identify object boundaries in image cross-sections. Root objects are followed through the data volume, while updating the tracker's appearance models to adapt to changing intensity values. In the presence of multiple root systems, multiple trackers can be used, but need to distinguish target objects from one another in order to correctly associate roots with their originating plants. Since root objects are expected to exhibit similar greyscale intensity distributions, shape information is used to constrain the evolving level set interfaces in order to lock trackers to their correct targets. The proposed method is tested on root systems of wheat plants grown in soil. Springer Verlag 2015-12-12 Article PeerReviewed Mairhofer, Stefan, Johnson, James, Sturrock, Craig, Bennett, Malcolm J., Mooney, Sacha J. and Pridmore, Tony P. (2015) Visual tracking for the recovery of multiple interacting plant root systems from X-ray μCT images. Machine Vision and Applications . pp. 1-14. ISSN 1432-1769 Multiple object tracking Root system recovery Plant interaction X-ray micro computed tomography http://link.springer.com/article/10.1007/s00138-015-0733-7 doi:10.1007/s00138-015-0733-7 doi:10.1007/s00138-015-0733-7
spellingShingle Multiple object tracking
Root system recovery
Plant interaction
X-ray micro computed tomography
Mairhofer, Stefan
Johnson, James
Sturrock, Craig
Bennett, Malcolm J.
Mooney, Sacha J.
Pridmore, Tony P.
Visual tracking for the recovery of multiple interacting plant root systems from X-ray μCT images
title Visual tracking for the recovery of multiple interacting plant root systems from X-ray μCT images
title_full Visual tracking for the recovery of multiple interacting plant root systems from X-ray μCT images
title_fullStr Visual tracking for the recovery of multiple interacting plant root systems from X-ray μCT images
title_full_unstemmed Visual tracking for the recovery of multiple interacting plant root systems from X-ray μCT images
title_short Visual tracking for the recovery of multiple interacting plant root systems from X-ray μCT images
title_sort visual tracking for the recovery of multiple interacting plant root systems from x-ray μct images
topic Multiple object tracking
Root system recovery
Plant interaction
X-ray micro computed tomography
url https://eprints.nottingham.ac.uk/32965/
https://eprints.nottingham.ac.uk/32965/
https://eprints.nottingham.ac.uk/32965/