Growth recorded automatically and continuously by a machine vision system for finisher pigs
Article
Article Title | Growth recorded automatically and continuously by a machine vision system for finisher pigs |
---|---|
ERA Journal ID | 3449 |
Article Category | Article |
Authors | Tscharke, M. (Author) and Banhazi, T. M. (Author) |
Journal Title | Australian Journal of Multi-Disciplinary Engineering |
Journal Citation | 10 (1), pp. 70-80 |
Number of Pages | 11 |
Year | 2013 |
Publisher | Taylor & Francis |
Place of Publication | Australia |
ISSN | 0812-3314 |
1441-6611 | |
1448-8388 | |
Digital Object Identifier (DOI) | https://doi.org/10.7158/14488388.2013.11464866 |
Web Address (URL) | https://www.tandfonline.com/doi/abs/10.7158/14488388.2013.11464866 |
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. |
Keywords | precision livestock farming, machine vision, pigs, weight estimation, growth |
ANZSRC Field of Research 2020 | 300302. Animal management |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | National Centre for Engineering in Agriculture |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q5532/growth-recorded-automatically-and-continuously-by-a-machine-vision-system-for-finisher-pigs
151
total views5
total downloads3
views this month0
downloads this month