Growth recorded automatically and continuously by a machine vision system for finisher pigs

Tscharke, M. and Banhazi, T. M. (2013) Growth recorded automatically and continuously by a machine vision system for finisher pigs. Australian Journal of Multi-disciplinary Engineering, 10 (1). pp. 70-80. ISSN 1448-8388

Abstract

Conventional livestock weighing methods require direct contact with the animals. This contact creates a physically demanding and hazardous situation for those undertaking the weighing activities. Alternatively, the weight of livestock can be estimated from their body measurements using non-invasive methods. This article presents recent improvements in the ongoing development of a completely automatic, two-dimensional machine vision system labelled the piGUI system, designed to obtain body measurements of pigs to estimate their live weight. Results comparing pig weights obtained by a weigh-scale and the vision-based method are reported for pigs in their finisher stage of growth. During offline testing of a video dataset, the piGUI system demonstrated that it was capable of estimating the average group weight within a 2.5% error relative to the actual group average weight. In addition, the weight deviation of the groups was estimated within a ±1 kg error of the actual group weight deviation. During on-farm testing the average group weight was accurate to 2.5% relative error and the estimated weight deviation was within a ±2 kg error of the actual weight deviation. Continuous recording of livestock growth is important as growth data can be used to measure animals’ responses to various factors such as the surrounding climate, housing environment and nutrition. Assessing the animals’ responses to these conditions is essential in improving the efficiency and welfare of livestock in both research and commercial settings.


Statistics for USQ ePrint 36772
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Additional Information: Files associated with this item cannot be displayed due to copyright restrictions.
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Civil Engineering and Surveying (1 July 2013 -)
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Civil Engineering and Surveying (1 July 2013 -)
Date Deposited: 09 Aug 2019 04:40
Last Modified: 09 Aug 2019 05:52
Uncontrolled Keywords: precision livestock farming, machine vision, pigs, weight estimation, growth
Fields of Research : 07 Agricultural and Veterinary Sciences > 0702 Animal Production > 070203 Animal Management
Socio-Economic Objective: E Expanding Knowledge > 97 Expanding Knowledge > 970107 Expanding Knowledge in the Agricultural and Veterinary Sciences
Identification Number or DOI: 10.7158/14488388.2013.11464866
URI: http://eprints.usq.edu.au/id/eprint/36772

Actions (login required)

View Item Archive Repository Staff Only