5. Conclusion
In this research, a method based on Motion History Image was
used to calculate dynamic, local, temporal and spatial information
about the mean activity and occupation index in order to detect
aggressive interactions among pigs. The results revealed a classifi-
cation accuracy of 89.0%, a sensitivity of 88.7% and a specificity of
89.3% and proved that the two motion features can be successfully
used in order to discriminate between aggressive and not aggressive
interaction. This might be a first and very important step
towards the development of a fully automated system that can
detect aggressive interactions among pigs by analysing motion features
over time. Furthermore, the approach does not interfere with
or manipulate the animals. Consequently, this approach analysis
offers promising possibilities to continuously monitor pigs in a
fully automated way