Hostname: page-component-76fb5796d-5g6vh Total loading time: 0 Render date: 2024-04-28T22:18:07.368Z Has data issue: false hasContentIssue false
  • English
  • Français

Pig growth and conformation monitoring using image analysis

Published online by Cambridge University Press:  18 August 2016

J. A. Marchant ,
C. P. Schofield  and
R. P. White
J. A. Marchant
Affiliation:
BBSRC Silsoe Research Institute, Wrest Park, Silsoe, Bedford MK45 4HS
C. P. Schofield
Affiliation:
BBSRC Silsoe Research Institute, Wrest Park, Silsoe, Bedford MK45 4HS
R. P. White
Affiliation:
BBSRC Silsoe Research Institute, Wrest Park, Silsoe, Bedford MK45 4HS
Get access

Abstract

Machine vision can be used to collect images of pigs and analyse them to identify and measure specific areas and dimensions related to their growth, shape and hence conformation. This information could improve the stockman’s ability to maximize production efficiency and also to monitor health by detecting abnormalities in growth rates. This work introduces fully automated algorithms which find the plan view outline of animals in a normal housing situation, divide the outline into major body components and measure specified dimensions and areas. Special attention is paid to determining whether the results are sufficiently repeatable to be useful in estimating these parameters. Problems in compensating for changes in the optical geometry are outlined and methods proposed to deal with them. The repeatability of the image analysis process coupled with the subsequent signal processing for outlier rejection gives s.e. values on areas of < 0·005 and on linear dimensions of < 0·0025. For example, the plan view area less head and neck (A4) can be used to predict the weight of the group of pigs at 34 kg, 66 kg and 98 kg with standard errors of 0·25 kg, 0·17 kg and 0·39 kg respectively when using manual weighing results to calibrate the system. If an individual pig is weighed once at 75 days (e.g. 34 kg) to calibrate the A4-to-weight relationship, subsequent A4 measurements can be used to predict its weight when 125 days old (approx. 80 kg) to within 1 kg. This matches the accuracy of the manual weighing system used in the trials. The effect of pig gender on the area to weight relationships is not significant (P = 0·074), but there is a small yet significant gender effect with the linear dimensions.

Keywords

body weightdimensionsimagerymonitoringpigs
Type
Research Article
Information
Animal Science , Volume 68 , Issue 1 , February 1999 , pp. 141 - 150
Copyright
Copyright © British Society of Animal Science 1999

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

American Society of Agricultural Engineers. 1987. American Society of Agricultural Engineers handbook, pp. 391–398. ASAE, St Joseph.Google Scholar
Baxter, M. R. and Schwaller, C. E. 1983. Space requirements for sows in confinement. In Farm animal housing and welfare (ed. Baxter, S. H. Baxter, M. R. and MacCormack, J. A. D.) pp. 181–195. Martinus Nijhof, Boston.Google Scholar
Brandi, N. and Jorgensen, E. 1996. Determination of live weight of pigs from dimensions measured using image analysis. Computers and Electronics in Agriculture 15: 57–72.Google Scholar
Cohen, L. D. and Cohen, I. 1990. A finite element method applied to new active contour models and 3D reconstruction from cross sections. Proceedings of the third international conference on computer vision, IEEE Computer Society, Osaka, Japan, pp. 587–591.Google Scholar
Davies, E. R. 1990. Machine vision: theory, algorithms, practicalities. Academic Press, London.Google Scholar
Frost, A. R., Schofield, C. P., Beaulah, S. A., Mottram, T. T., Lines, J. A. and Wathes, C. M. 1997. A review of livestock monitoring and the need for integrated systems. Computers and Electronics in Agriculture 17: 139–157.Google Scholar
Kass, M., Witkin, A. and Terzopoulos, D. 1988. Snakes: active contour models. International Journal of Computer Vision 1: 321–331.Google Scholar
Marchant, J. A., Onyango, C. M. and Tillett, R. D. 1995. A compartmented snake for model-based boundary location. Proceedings of the conference ‘Current issues in statistical shape analysis’, Department of Statistics, University of Leeds, 5-7 April, pp. 100–107.Google Scholar
Minagawa, H. and Ichikawa, T. 1992. Measurements of pigs’ weights by an image analysis. Summer meeting of the American Society of Agricultural Engineers, Charlotte, USA, June 21-24, paper no. 927023. Google Scholar
Schofield, C. P. 1990. Evaluation of image analysis as a means of estimating the weight of pigs. Journal of Agricultural Engineering Research 47: 287–296.Google Scholar
Schofield, C. P. 1993. Image analysis for non-intrusive weight and activity monitoring. Proceedings of the fourth international symposium on livestock environment, ASAE, University of Warwick, pp. 503–510.Google Scholar
Schofield, C. P. and Marchant, J. A. 1990. Image analysis for estimating the weight of live animals. Proceedings of the conference ‘Optics in agriculture’, SPIE, Boston, MA, 7-8 November 1990, pp. 209–219.Google Scholar
Schofield, C. P. and Marchant, J. A. 1996. Measuring the size and shape of pigs using image analysis. Proceedings of Ag Eng 96, Madrid, 96G–035.Google Scholar
Stuyft, E. van der, Goedseels, V. and Geers, R. 1990. Digital restoration of distorted geometric features of pigs. Proceedings of the conference ‘Optics in agriculture’, SPIE, Boston, MA, 7-8 November 1990, pp. 189–200.Google Scholar
Stuyft, E. van der, Schofield, C. P., Randall, J. M., Wambacq, P. and Goedseels, V. 1991. Development and application of computer vision systems for use in livestock production. Computers and Electronics in Agriculture 6: 243–265.Google Scholar
Tsai, R. Y. 1986. An efficient and accurate camera calibration technique for 3D machine vision. Proceedings of the conference ‘Computer vision and pattern recognition’, IEEE Computer Society, Miami Beach, June 1986, pp. 364–374.Google Scholar