https://phaidra.vetmeduni.ac.at/o:4810 Supporting Information - Video S2 : Comparison of the automated monitoring of the sow activity in farrowing pens using video and accelerometer data Oczak, Maciej Maciej Oczak 0000-0003-1045-7568 Bayer, Florian Florian Bayer Vetter, Sebastian G. Sebastian G. Vetter 0000-0001-5374-5872 Maschat, Kristina Kristina Maschat 0000-0002-8295-9180 Baumgartner, Johannes Johannes Baumgartner 0000-0001-8555-1378 Elsevier B.V. video eng Patterns in pigs activity can be an indicator of health and welfare of the animals. This motivates researchers to develop Precision Livestock Farming (PLF) tools for automated monitoring of pig activity level. In this research we compared two important technologies that can be used for this purpose, ear tag accelerometer and computer vision. Additionally, we compared both technologies with gold standard based on human labelling. A state-of-the-art object detection algorithm RetinaNet was trained on 9969 images and validated on 4273 images to automatically detect head of a sow, body of a sow, left ear, right ear and a hay rack. It was possible to detect these objects with a performance of 0.26 mAP@0.5:0.95. Activity of 6 sows was derived from detected parts of animals’ bodies and compared with activity measurement based on ear tag accelerometer data. Dynamic relation between activity measurement based on both technologies was modelled with Transfer Function (TF) models. For all 6 animals activity of the body of a sow based on object detection was very similar to accelerometer based activity measurement (R² > 0.7). Similarly R² between activity of a head of a sow and accelerometer based activity was also very similar for most sows (R² > 0.7). Results of fitting of TF models to animal activity data based on ear tag accelerometer and output of object detection on body of sows and head of sows suggests that both technologies, the accelerometer and computer vision provide very similar information on activity level of animals. The presented computer vision method is limited to monitoring one animal under camera view as detected body parts cannot be associated with multiple individuals. Moreover, we expect that the method requires re-training the RetinaNet object detection algorithm with additional images collected on additional farms to achieve satisfactory performance in different environments. Application of computer vision approach might be advantageous in some PLF applications as it is non-invasive and might be less laborious than method based on ear tag accelerometer data. Supporting Information to the article Oczak, M, Bayer, F, Vetter, SG, Maschat, K, Baumgartner, J (2022) Comparison of the automated monitoring of the sow activity in farrowing pens using video and accelerometer data. Computers and Electronics in Agriculture, 192, 106517, DOI: doi.org/10.1016/j.compag.2021.106517. Video S2 - Performance of RetinaNet trained on 78 frames. Sow Activity Computer vision Accelerometer Automated monitoring Deep learning http://creativecommons.org/licenses/by/4.0/ https://phaidra.vetmeduni.ac.at/api/object/o:4810/download https://phaidra.vetmeduni.ac.at/o:4799 video/mp4 Computers and Electronics in Agriculture VoR Computers and Electronics in Agriculture 192 106517 222.72 MB 2022