Deep learning pose detection model for sow locomotion.

Lameness affects animal mobility, causing pain and discomfort. Lameness in early stages often goes undetected due to a lack of observation, precision, and reliability. Automated and non-invasive systems offer precision and detection ease and may improve animal welfare. This study was conducted to create a repository of images and videos of sows with different locomotion scores. Our goal is to develop a computer vision model for automatically identifying specific points on the sow's body. The automatic identification and ability to track specific body areas, will allow us to conduct kinematic studies with the aim of facilitating the detection of lameness using deep learning. The video database was collected on a pig farm with a scenario built to allow filming of sows in locomotion with different lameness scores. Two stereo cameras were used to record 2D videos images. Thirteen locomotion experts assessed the videos using the Locomotion Score System developed by Zinpro Corporation. From this annotated repository, computational models were trained and tested using the open-source deep learning-based animal pose tracking framework SLEAP (Social LEAP Estimates Animal Poses). The top-performing models were constructed using the LEAP architecture to accurately track 6 (lateral view) and 10 (dorsal view) skeleton keypoints. The architecture achieved average precisions values of 0.90 and 0.72, average distances of 6.83 and 11.37 in pixel, and similarities of 0.94 and 0.86 for the lateral and dorsal views, respectively. These computational models are proposed as a Precision Livestock Farming tool and method for identifying and estimating postures in pigs automatically and objectively. The 2D video image repository with different pig locomotion scores can be used as a tool for teaching and research. Based on our skeleton keypoint classification results, an automatic system could be developed. This could contribute to the objective assessment of locomotion scores in sows, improving their welfare.

Trade-offs in the externalities of pig production are not inevitable.

Farming externalities are believed to co-vary negatively, yet trade-offs have rarely been quantified systematically. Here we present data from UK and Brazilian pig production systems representative of most commercial systems across the world ranging from 'intensive' indoor systems through to extensive free range, Organic and woodland systems to explore co-variation among four major externality costs. We found that no specific farming type was consistently associated with good performance across all domains. Generally, systems with low land use have low greenhouse gas emissions but high antimicrobial use and poor animal welfare, and vice versa. Some individual systems performed well in all domains but were not exclusive to any particular type of farming system. Our findings suggest that trade-offs may be avoidable if mitigation focuses on lowering impacts within system types rather than simply changing types of farming.