Implementation of Computer-Vision-Based Farrowing Prediction in Pens with Temporary Sow Confinement

SIMPLE SUMMARY: The automated detection of the beginning and ending of nest-building behavior in sows might support the implementation of new management strategies in farrowing pens, i.e., temporary sow confinement in crates. This might improve sows’ welfare and reduce piglet mortality by limiting sow confinement in crates to only a critical period of piglets’ lives. The objective of this study was to predict farrowing with computer vision techniques to optimize the timing of sow confinement. In this study, we developed a computer-vision-based method for the automated detection of the beginning and ending of nest-building behavior in sows. The study included 71 Austrian Large White and Landrace × Large White crossbred sows and four types of farrowing pens. The beginning of nest-building behavior was detected with a median of 12 h 51 min and ending with a median of 2 h 38 min before the beginning of farrowing. It was possible to predict farrowing for 29 out of 44 animals. The developed method could be applied to warn the farmer when nest-building behavior starts and then to confine the sow in a crate when the end of nest-building behavior is detected. This could reduce labor costs otherwise required for the regular control of sows in farrowing compartments. ABSTRACT: The adoption of temporary sow confinement could improve animal welfare during farrowing for both the sow and the piglets. An important challenge related to the implementation of temporary sow confinement is the optimal timing of confinement in crates, considering sow welfare and piglet survival. The objective of this study was to predict farrowing with computer vision techniques to optimize the timing of sow confinement. In total, 71 Austrian Large White and Landrace × Large White crossbred sows and four types of farrowing pens were included in the observational study. We applied computer vision model You Only Look Once X to detect sow locations, the calculated activity level of sows based on detected locations and detected changes in sow activity trends with Kalman filtering and the fixed interval smoothing algorithm. The results indicated the beginning of nest-building behavior with a median of 12 h 51 min and ending with a median of 2 h 38 min before the beginning of farrowing with the YOLOX-large object detection model. It was possible to predict farrowing for 29 out of 44 sows. The developed method could reduce labor costs otherwise required for the regular control of sows in farrowing compartments.