The assessment of animal welfare on-farm is important to ensure that current welfare standards are followed. The current manual assessment proposed by Welfare Quality^® (WQ), although being an essential tool, is only a point-estimate in time, is very time consuming to perform, only evaluates a subset of the animals, and is performed by the subjective human. Automation of the assessment through information technologies (ITs) could provide a continuous objective assessment in real-time on all animals. The aim of the current systematic review was to identify ITs developed for welfare monitoring within the pig production chain, evaluate the ITs developmental stage and evaluate how these ITs can be related to the WQ assessment protocol. The systematic literature search identified 101 publications investigating the development of ITs for welfare monitoring within the pig production chain. The systematic literature analysis revealed that the research field is still young with 97% being published within the last 20 years, and still growing with 63% being published between 2016 and mid-2020. In addition, most focus is still on the development of ITs (sensors) for the extraction and analysis of variables related to pig welfare; this being the first step in the development of a precision livestock farming system for welfare monitoring. The majority of the studies have used sensor technologies detached from the animals such as cameras and microphones, and most investigated animal biomarkers over environmental biomarkers with a clear focus on behavioural biomarkers over physiological biomarkers. ITs intended for many different welfare issues have been studied, although a high number of publications did not specify a welfare issue and instead studied a general biomarker such as activity, feeding behaviour and drinking behaviour. The ‘good feeding’ principle of the WQ assessment protocol was the best represented with ITs for real-time on-farm welfare assessment, while for the other principles only few of the included WQ measures are so far covered. No ITs have yet been developed for the ‘Comfort around resting’ and the ‘Good human-animal relationship’ criteria. Thus, the potential to develop ITs for welfare assessment within the pig production is high and much work is still needed to end up with a remote solution for welfare assessment on-farm and in real-time.

Heart rate (HR) is a vital bio-signal that is relatively easy to monitor with contact sensors and is related to a living organism’s state of health, stress and well-being. The objective of this study was to develop an algorithm to extract HR (in beats per minute) of an anesthetized and a resting pig from raw video data as a first step towards continuous monitoring of health and welfare of pigs. Data were obtained from two experiments, wherein the pigs were video recorded whilst wearing an electrocardiography (ECG) monitoring system as gold standard (GS). In order to develop the algorithm, this study used a bandpass filter to remove noise. Then, a short-time Fourier transform (STFT) method was tested by evaluating different window sizes and window functions to accurately identify the HR. The resulting algorithm was first tested on videos of an anesthetized pig that maintained a relatively constant HR. The GS HR measurements for the anesthetized pig had a mean value of 71.76 bpm and standard deviation (SD) of 3.57 bpm. The developed algorithm had 2.33 bpm in mean absolute error (MAE), 3.09 bpm in root mean square error (RMSE) and 67% in HR estimation error below 3.5 bpm (PE_3.5). The sensitivity of the algorithm was then tested on the video of a non-anaesthetized resting pig, as an animal in this state has more fluctuations in HR than an anaesthetized pig, while motion artefacts are still minimized due to resting. The GS HR measurements for the resting pig had a mean value of 161.43 bpm and SD of 10.11 bpm. The video-extracted HR showed a performance of 4.69 bpm in MAE, 6.43 bpm in RMSE and 57% in PE_3.5. The results showed that HR monitoring using only the green channel of the video signal was better than using three color channels, which reduces computing complexity. By comparing different regions of interest (ROI), the region around the abdomen was found physiologically better than the face and front leg parts. In summary, the developed algorithm based on video data has potential to be used for contactless HR measurement and may be applied on resting pigs for real-time monitoring of their health and welfare status, which is of significant interest for veterinarians and farmers.

Respiratory rate (RR) is an important indicator of the health and welfare status of dairy cows. In recent years, progress has been made in monitoring the RR of dairy cows using video data and learning methods. However, existing approaches often involve multiple processing modules, such as region of interest (ROI) detection and tracking, which can introduce errors that propagate through successive steps. The objective of this study was to develop an end-to-end computer vision method to predict RR of dairy cows continuously and automatically. The method leverages the capabilities of a state-of-the-art Transformer model, VideoMAE, which divides video frames into patches as input tokens, enabling the automated selection and featurization of relevant regions, such as a cow's abdomen, for predicting RR. The original encoder of VideoMAE was retained, and a classification head was added on top of it. Further, the weights of the first 11 layers of the pre-trained model were kept, while the weights of the final layer and classifier were fine-tuned using video data collected in a tie-stall barn from 6 dairy cows. Respiratory rates measured using a respiratory belt for individual cows were serving as the ground truth (GT). The evaluation of the developed model was conducted using multiple metrics, including mean absolute error (MAE) of 2.58 breaths per minute (bpm), root mean squared error (RMSE) of 3.52 bpm, root mean squared prediction error (RMSPE; as a proportion of observed mean) of 15.03%, and Pearson correlation (r) of 0.86. Compared with a conventional method involving multiple processing modules, the end-to-end approach performed better in terms of MAE, RMSE and RMSPE. These results suggest the potential to implement the developed computer vision method for an end-to-end solution, for monitoring RR of dairy cows automatically in a tie-stall setting. Future research on integrating this method with other behavioral detection and animal identification algorithms for animal monitoring in a free-stall dairy barn can be beneficial for a broader application.