The goal of this study was to develop an automated monitoring system for the detection of pigs’ bodies, heads and tails. The aim in the first part of the study was to recognize individual pigs (in lying and standing positions) in groups and their body parts (head/ears, and tail) by using machine learning algorithms (feature pyramid network). In the second part of the study, the goal was to improve the detection of tail posture (tail straight and curled) during activity (standing/moving around) by the use of neural network analysis (YOLOv4). Our dataset (n = 583 images, 7579 pig posture) was annotated in Labelbox from 2D video recordings of groups (n = 12–15) of weaned pigs. The model recognized each individual pig’s body with a precision of 96% related to threshold intersection over union (IoU), whilst the precision for tails was 77% and for heads this was 66%, thereby already achieving human-level precision. The precision of pig detection in groups was the highest, while head and tail detection precision were lower. As the first study was relatively time-consuming, in the second part of the study, we performed a YOLOv4 neural network analysis using 30 annotated images of our dataset for detecting straight and curled tails. With this model, we were able to recognize tail postures with a high level of precision (90%).

Dairy goats are commonly housed at a space allowance of 0.7 – 0.8 m2/goat in commercial Norwegian goat herds, which is very low compared to regulations and recommendations in other European countries. One easy and cheap way to increase space allowance is to allow the animals’ access to outdoor area. The aim of this study was to investigate the effect of access to an outside enclosure and environmental enrichment for dairy goats kept in slatted floor pens with low space allowance on their activity pattern and social behaviour.

There are several environmental and ambient factors that can affect pig eliminative behaviour. The aim of this survey was to investigate factors related to the physical and ambient environment that have the strongest effects on pig and pen cleanliness and ammonia concentration. Data were collected from 87 pig farms and analysed using mixed (ammonia concentration) or generalized linear (pen and pig cleanliness) model in SAS. The pen was cleaner when pen partitions were open compared to closed (p = 0.010) and increased with increasing amount of litter (p = 0.002), using straw (p = 0.002) as rooting material. Pig cleanliness was higher when pen partitions in the eliminative area were open compared to closed (p = 0.007) and increased with increasing space per pig in the resting area (p < 0.001), with decreasing temperature (p < 0.001), and lowering of air velocity (p = 0.003). Other factors that increased cleanliness was using straw as rooting material (p = 0.028) and increasing amount of litter in the resting area (p = 0.002). Ammonia concentration was reduced with increasing floor space in the eliminative area (p < 0.001) and increasing amount of litter (p = 0.006). Our results pinpoint physical and ambient conditions affecting pen and pig cleanliness and air quality.

The objective of the present paper was to discuss the design of farrowing pens and present the first production results of the “SowComfort farrowing pen” (SOWCOMF). The biggest difference between this pen and the traditional pen (TRAD) presented in the study, is that SOWCOMF contains a nest area equipped with a rubber mattress, floor heating, a rack for straw and no separate creep area. It was predicted that SOWCOMF would result in lower piglet mortality compared to TRAD due to a more stimulating and comfortable environment, and that the use of rubber mats in SOWCOMF would reduce the incidence of carpal joint lesions of the piglets. Results from both farms showed that percent mortality of live born piglets was lower in SOWCOMF than TRAD (p = 0.004), especially due to starvation (p < 0.0001) and other causes (p < 0.0001). In contrast, percentage of overlying was higher in SOWCOMF (p < 0.0001). The lower incidence of starved piglets in SOWCOMF than TRAD can possibly be explained by more sow-initiated communication with the piglets (p < 0.001). Most causes of mortality declined over consecutive batches. Percentage of piglets per litter without carpal lesions were significantly higher in the SOWCOMF than in TRAD (p < 0.0001), showing that rubber mats provide more protection of carpal joints.