Assessing Goats' Fecal Avoidance Using Image Analysis-Based Monitoring

The recent advances in sensor technologies and data analysis could improve our capacity to acquire long-term individual dataset on animal behavior. In livestock management, this is particularly interesting when behavioral be linked production performances, physiological or genetical information, with the objective of improving health welfare management. study, we proposed a framework, based computer vision deep learning, automatically estimate location within pasture discuss relationship risk gastrointestinal nematode (GIN) infection. We illustrated framework for monitoring goats allowed graze an experimental plot, where feces containing GIN infective larvae were previously dropped delimited areas. Four animals monitored, during two grazing weeks same (week 1 from April 12 19, 2021 week 2, June 28 July 5, 2021). Using different components behavior analyzed, infection was explored. First, average, 87.95% detected, detected individuals identified average sensitivity 94.9%, precision 94.8%. Second, ability avoid infected showed important temporal variability. Interestingly, avoidance 3 increased second (Wilcoxon rank sum, p -value < 0.05), level increase correlated (Pearson's correlation coefficient = 0.9). between time spent GIN-infested areas also studied, but no clear found. conclusion, due low number studied animals, biological results should interpreted caution; nevertheless, provided here new relevant tool explore ruminant parasitism studies.