Free Standard AU & NZ Shipping For All Book Orders Over $80!
Register      Login
Animal Production Science Animal Production Science Society
Food, fibre and pharmaceuticals from animals
Shopping Cart: ( empty )
You are here: Home > Journals > AN > EA07404
RESEARCH ARTICLE
Contents Vol 48(7)

Using video image analysis to count hens in cages and reduce egg breakage on collection belts

G. M. Cronin A C E , S. S. Borg A and M. T. Dunn B D
+ Author Affiliations
- Author Affiliations

A Animal Welfare Science Centre, Department of Primary Industries, Werribee, Vic. 3030, Australia.

B National Centre for Engineering in Agriculture, University of Southern Queensland, Toowoomba, Qld 4350, Australia.

C Present address: Faculty of Veterinary Science, University of Sydney, 425 Werombi Road, Camden, NSW 2570, Australia.

D CSIRO Exploration & Mining Group, 1 Technology Court, Pullenvale, Qld 4069, Australia.

E Corresponding author. Email: g.cronin@usyd.edu.au

Australian Journal of Experimental Agriculture 48(7) 768-772 https://doi.org/10.1071/EA07404
Submitted: 10 December 2007  Accepted: 23 March 2008   Published: 20 June 2008

Abstract

Stock people working in modern cage layer sheds spend more than half their daily work time directly checking hens to monitor health and welfare. In addition, mechanical egg collection belts must be checked for potential blockages that may result in cracked or broken eggs during the collection process. These are important tasks in the profitable management of modern multi-tier cage systems. However, where the upper tiers of cages are above stockperson eye level, the effectiveness of humans to perform these tasks accurately may be questioned. We investigated whether video image analysis (VIA, the ability of a computer to ‘see’) could automatically perform two common tasks – that of counting the number of hens per cage and scanning the egg collection belt to identify foreign (non-egg) objects. Cameras were attached to the robotic feeder that moved along the front of the cages. Views of the interior of the cages and the egg collection belt were recorded on digital video as the robotic feeder moved. Two VIA prototypes were evaluated, initially at the research institute and subsequently at a commercial farm. Using the respective automatic detection algorithms that were developed for the research, 79% of targets (hen legs) in cages were correctly counted, while 95% of foreign objects on the egg collection belt were detected. The results demonstrate that VIA can be used to monitor egg belts for potential blockages, and has potential as technology to count hens.

Additional keywords: cage housing, egg production, laying hens, machine vision.


Acknowledgements

We are grateful to DPI Victoria and the Australian Poultry CRC for co-funding the research, Bruce Schirmer for assistance with care of the hens at DPI Werribee, Philip Szepe for allowing us to conduct the on-farm component at Kinross Farm and Dr John Barnett for his comments on this manuscript.


References


Anon. (2006) Big Dutchman. Egg detector for cages and aviaries. World Poultry 22(5), 27. open url image1

Bizeray D, Leterrier C, Constantin P, Picard M, Faure JM (2000) Early locomotor behaviour in genetic stocks of chickens with different growth rates. Applied Animal Behaviour Science 68, 231–242.
| Crossref | GoogleScholarGoogle Scholar | PubMed | open url image1

Brandl N (2003) Experiences of building a virtual library using a case study of applied image analysis in estimating the weight of a pig. The Pig Journal 52, 63–70. open url image1

Cupillard F, Thonnat M, Brémond F (2005) Automatic visual recognition for metro surveillance. In ‘Proceedings of Measuring Behavior 2005, 5th International Conference on Methods and Techniques in Behavioral Research, Wageningen, The Netherlands, 30 August–2 September 2005’. (Eds LPJJ Noldus, F Grieco, LWS Loijens, PH Zimmerman) pp. 167–171. (Noldus Information Technology: Wageningen, The Netherlands)

Dunn MT (2007) Applications of vision sensing in agriculture. PhD Thesis, University of Southern Queensland, Toowoomba.

Finch NA, Murray PJ, Dunn MT, Billingsley J (2006) Using machine vision classification to control access of animals to water. Australian Journal of Experimental Agriculture 46, 837–839.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Foresti GL, Micheloni C, Piciarelli C, Snidaro L (2005) A multi-sensor surveillance system for the detection of anomalous behaviours. In ‘Proceedings of Measuring Behavior 2005, 5th International Conference on Methods and Techniques in Behavioral Research, Wageningen, The Netherlands, 30 August–2 September 2005’. (Eds LPJJ Noldus, F Grieco, LWS Loijens, PH Zimmerman) pp. 180–183. (Noldus Information Technology: Wageningen, The Netherlands)

Genstat Committee (2000) ‘The guide to Genstat, Part 2: statistics.’ (Lawes Agricultural Trust: Rothamsted, UK)

Manning L, Chadd SA, Baines RN (2007a) Key health and welfare indicators for broiler production. World’s Poultry Science Journal 63, 46–62. open url image1

Manning L, Chadd SA, Baines RN (2007b) Water consumption in broiler chicken: a welfare indicator. World’s Poultry Science Journal 63, 63–69. open url image1

Negretti P, Bianconi G, Bartocci S, Terramoccia S, Verna M (2008) Determination of live weight and body condition score in lactating Mediterranean buffalo by visual image analysis. Livestock Science 113, 1–7.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Noldus LPJJ, Grieco F, Loijens LWS, Zimmerman PH (Eds) (2005) ‘Proceedings of Measuring Behavior 2005, 5th International Conference on Methods and Techniques in Behavioral Research, Wageningen, The Netherlands, 30 August–2 September 2005.’ (Noldus Information Technology: Wageningen, The Netherlands)

Patel VC, McClendon RW, Goodrum JW (1998) Color computer vision and artificial neural networks for the detection of defects in poultry eggs. Artificial Intelligence Review 12, 163–176.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Primary Industries Standing Committee (2001) ‘Model code of practice for the welfare of animals, domestic poultry.’ 4th edn. SCARM Report 83. (CSIRO Publishing: Melbourne)

Schofield CP, Wathes CM, Frost AR (2002) Integrated management systems for pigs – increasing production efficiency and welfare. Animal Production in Australia 24, 197–200. open url image1

Sergeant D, Boyle R, Forbes M (1998) Computer visual tracking of poultry. Computers and Electronics in Agriculture 21, 1–18.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Stafford JV (Ed.) (2005) ‘Precision Agriculture 05 – 5th Biennial Conference on Precision in Agriculture, Uppsala, Sweden.’ (Wageningen Academic Publishers: Dordrecht, The Netherlands)

Tillett RD, Onyango CM, Marchant JA (1997) Using model-based image processing to track animal movements. Computers and Electronics in Agriculture 17, 249–261.
| Crossref | GoogleScholarGoogle Scholar | open url image1

White DJ, Svellingen C, Strachan NJC (2006) Automated measurement of species and length by computer vision. Fisheries Research 80, 203–210.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Yang CC, Chao K, Chen YR, Kim MS, Chan DE (2006) Development of fuzzy logic based differentiation algorithm and fast line-scan imaging system for chicken inspection. Biosystems Engineering 95, 483–496.
| Crossref | GoogleScholarGoogle Scholar | open url image1

Zheng C, Sun D, Zheng L (2006) Recent developments and applications of image features for food quality evaluation and inspection – a review. Trends in Food Science & Technology 17, 642–655.
| Crossref | GoogleScholarGoogle Scholar | CAS | open url image1