Part-based multi-frame registration for estimation of the growth of cellular networks in plant roots

T.J. Roberts; S.J. McKenna; J. Hans; T.A. Valentine; A.G. Bengough

doi:10.1109/ICPR.2006.915

Part-based multi-frame registration for estimation of the growth of cellular networks in plant roots

T.J. Roberts, S.J. McKenna, J. Hans, T.A. Valentine, A.G. Bengough

Research output: Chapter in Book/Report/Conference proceeding › Chapter

8 Citations (Scopus)

Abstract

Motion estimation from confocal scanning laser micro-scope images of growing plant cell structures presents interesting challenges; motion exhibits multiple local discontinuities and noise is non-isotropic and non-Gaussian. A method is presented for estimating motion of cell networks based on a physically motivated, part-based model of cell boundary structure. Each part models the shape and appearance of a localised image region and can undergo constrained non-rigid deformation. This enables motion discontinuities between parts to be modelled. Parts are coupled in order to improve localisation and increase computational efficiency. Results from applying MCMC show accurate localisation of the structure across multiple frames. The form of the model assists biologists in interpreting growth.

Original language	English
Title of host publication	18th International Conference on Pattern Recognition
Subtitle of host publication	ICPR 2006; Hong Kong; China; 20 August 2006 through 24 August 2006
Place of Publication	California
Publisher	IEEE
Pages	378-381
Number of pages	4
Volume	2
ISBN (Print)	9780769525211
DOIs	https://doi.org/10.1109/ICPR.2006.915
Publication status	Published - 1 Jan 2006

Access to Document

10.1109/ICPR.2006.915

Cite this

Roberts, T. J., McKenna, S. J., Hans, J., Valentine, T. A., & Bengough, A. G. (2006). Part-based multi-frame registration for estimation of the growth of cellular networks in plant roots. In 18th International Conference on Pattern Recognition : ICPR 2006; Hong Kong; China; 20 August 2006 through 24 August 2006 (Vol. 2, pp. 378-381). IEEE. https://doi.org/10.1109/ICPR.2006.915

@inbook{633b5221dda040c98bd95833b3fd46d1,

title = "Part-based multi-frame registration for estimation of the growth of cellular networks in plant roots",

abstract = "Motion estimation from confocal scanning laser micro-scope images of growing plant cell structures presents interesting challenges; motion exhibits multiple local discontinuities and noise is non-isotropic and non-Gaussian. A method is presented for estimating motion of cell networks based on a physically motivated, part-based model of cell boundary structure. Each part models the shape and appearance of a localised image region and can undergo constrained non-rigid deformation. This enables motion discontinuities between parts to be modelled. Parts are coupled in order to improve localisation and increase computational efficiency. Results from applying MCMC show accurate localisation of the structure across multiple frames. The form of the model assists biologists in interpreting growth. ",

author = "T.J. Roberts and S.J. McKenna and J. Hans and T.A. Valentine and A.G. Bengough",

year = "2006",

month = jan,

day = "1",

doi = "10.1109/ICPR.2006.915",

language = "English",

isbn = "9780769525211",

volume = "2",

pages = "378--381",

booktitle = "18th International Conference on Pattern Recognition",

publisher = "IEEE",

}

Roberts, TJ, McKenna, SJ, Hans, J, Valentine, TA & Bengough, AG 2006, Part-based multi-frame registration for estimation of the growth of cellular networks in plant roots. in 18th International Conference on Pattern Recognition : ICPR 2006; Hong Kong; China; 20 August 2006 through 24 August 2006. vol. 2, IEEE, California, pp. 378-381. https://doi.org/10.1109/ICPR.2006.915

Part-based multi-frame registration for estimation of the growth of cellular networks in plant roots. / Roberts, T.J.; McKenna, S.J.; Hans, J. et al.
18th International Conference on Pattern Recognition : ICPR 2006; Hong Kong; China; 20 August 2006 through 24 August 2006. Vol. 2 California: IEEE, 2006. p. 378-381.

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - Part-based multi-frame registration for estimation of the growth of cellular networks in plant roots

AU - Roberts, T.J.

AU - McKenna, S.J.

AU - Hans, J.

AU - Valentine, T.A.

AU - Bengough, A.G.

PY - 2006/1/1

Y1 - 2006/1/1

N2 - Motion estimation from confocal scanning laser micro-scope images of growing plant cell structures presents interesting challenges; motion exhibits multiple local discontinuities and noise is non-isotropic and non-Gaussian. A method is presented for estimating motion of cell networks based on a physically motivated, part-based model of cell boundary structure. Each part models the shape and appearance of a localised image region and can undergo constrained non-rigid deformation. This enables motion discontinuities between parts to be modelled. Parts are coupled in order to improve localisation and increase computational efficiency. Results from applying MCMC show accurate localisation of the structure across multiple frames. The form of the model assists biologists in interpreting growth.

AB - Motion estimation from confocal scanning laser micro-scope images of growing plant cell structures presents interesting challenges; motion exhibits multiple local discontinuities and noise is non-isotropic and non-Gaussian. A method is presented for estimating motion of cell networks based on a physically motivated, part-based model of cell boundary structure. Each part models the shape and appearance of a localised image region and can undergo constrained non-rigid deformation. This enables motion discontinuities between parts to be modelled. Parts are coupled in order to improve localisation and increase computational efficiency. Results from applying MCMC show accurate localisation of the structure across multiple frames. The form of the model assists biologists in interpreting growth.

UR - http://www.scopus.com/inward/record.url?scp=34047222701&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2006.915

DO - 10.1109/ICPR.2006.915

M3 - Chapter

AN - SCOPUS:34047222701

SN - 9780769525211

VL - 2

SP - 378

EP - 381

BT - 18th International Conference on Pattern Recognition

PB - IEEE

CY - California

ER -

Part-based multi-frame registration for estimation of the growth of cellular networks in plant roots

Abstract

Access to Document

Other files and links

Fingerprint

Cite this