In the field of applied animal behaviour, video recordings of a scene of interest are often made and then evaluated by experts. This evaluation is based on different criteria (number of animals present, an occurrence of certain interactions, the proximity between animals and so forth) and aims to filter out video sequences that contain irrelevant information. However, such task requires a tremendous amount of time and resources, making manual approach ineffective. To reduce the amount of time the experts spend on watching the uninteresting video, this study introduces an automated watchdog system that can discard some of the recorded video material based on user-defined criteria. A pilot study on cows was made where a convolutional neural network detector was used to detect and count the number of cows in the scene as well as include distances and interactions between cows as filtering criteria. This approach removed 38% (50% for additional filter parameters) of the recordings while only losing 1% (4%) of the potentially interesting video frames.

References

1. 1)
  - 23. He, K., Zhang, X., Ren, S., et al: ‘Delving deep into rectifiers: surpassing human-level performance on imagenet classification’. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV) (ICCV '15). IEEE Computer Society, Washington, DC, USA, 2015, pp. 1026–1034. http://dx.doi.org/10.1109/ICCV.2015.123.
2. 2)
  - 20. Hartley, R.I., Zisserman, A.: ‘Multiple view geometry in computer vision’ (Cambridge University Press, Cambridge, UK, 2004, 2nd edn.), ISBN: 0521540518.
3. 3)
  - 22. Ioffe, S., Szegedy, C.: ‘Batch normalization: accelerating deep network training by reducing internal covariate shift’. 32nd International Conference on Machine Learning (ICML-15), JMLR Workshop and Conference Proceedings, 2015, pp. 448–456.
4. 4)
  - 13. Redmon, J., Farhadi, A.: ‘Yolo9000: better, faster, stronger’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), July 2017.
5. 5)
  - 15. He, S., Lau, R.W.H.: ‘Oriented object proposals’. The IEEE Int. Conf. Computer Vision (ICCV), December 2015.
6. 6)
  - 18. Zagoruyko, S., Lerer, A., Lin, T.-Y., et al: ‘A multipath network for object detection’. Proceedings of the British Machine Vision Conference (BMVC), September 2016, pp. 15.1–15.12.
7. 7)
  - 16. Pinheiro, P.H.O., Collobert, R., Dollár, P.: ‘Learning to segment object candidates’. Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2 (NIPS'15), Vol. 2, Cambridge, MA, USA, 1990–1998.
8. 8)
  - 11. Porto, S.M.C., Arcidiacono, C., Anguzza, U., et al: ‘The automatic detection of dairy cow feeding and standing behaviours in free-stall barns by a computer vision-based system’, Biosyst. Eng., 2015, 133, pp. 46–55.
9. 9)
  - 7. Polikarpus, A., Kaart, T., Mootse, H., et al: ‘Influences of various factors on cows’ entrance order into the milking parlour’, Appl. Anim. Behav. Sci., 2015, 166, pp. 20–24.
10. 10)
  - 4. Guzhva, O., Ardö, H., Herlin, A., et al: ‘Feasibility study for the implementation of an automatic system for the detection of social interactions in the waiting area of automatic milking stations by using a video surveillance system’, Comput. Electron. Agric., 2016, 127, pp. 506–509.
11. 11)
  - 21. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’, arXiv, 2014preprint arXiv:1409.1556.
12. 12)
  - 6. Kilgour, R.J.: ‘In pursuit of ‘normal’: a review of the behaviour of cattle at pasture’, Appl. Anim. Behav. Sci., 2012, 138, (1-2), pp. 1–11.
13. 13)
  - 8. Porto, S.M.C., Arcidiacono, C., Anguzza, U., et al: ‘Detecting cows at the feed barrier by means of an image analysis algorithm’. Int. Conf. RAGUSA SHWA 2012, Ragusa, Italy, September 3–6, 2012.
14. 14)
  - 14. Liu, W., Anguelov, D., Erhan, D., et al: ‘Ssd: single shot multibox detector’. European Conf. Computer Vision, 2016, pp. 21–37.
15. 15)
  - 17. Pinheiro, P.H.O., Lin, T.-Y., Collobert, R., et al: ‘Learning to refine object segments’, In: Leibe, B., Matas, J., Sebe, N., Welling, M. (Eds) ‘Computer Vision – ECCV 2016. ECCV 2016’ (LNCS, 9905). (Springer, Cham, 2016).
16. 16)
  - 9. Martinez-Ortiz, C.A., Everson, R.M., Mottram, T.: ‘Video tracking of dairy cows for assessing mobility scores’, 2013.
17. 17)
  - 10. Abdul Jabbar, K., Hansen, M.F., Smith, M., et al: ‘Locomotion traits of dairy cows from overhead three-dimensional video’. Visual Observation and Analysis of Vertebrate and Insect Behavior, Cancun, Mexico, 04 December 2016.
18. 18)
  - 3. DeVries, T. J., von Keyserlingk, M. A. G., Weary, D. M.: ‘Effect of feeding space on the inter-cow distance, aggression, and feeding behavior of free-stall housed lactating dairy cows’, J. Dairy Sci., 2004, 87, (5), pp. 1432–1438.
19. 19)
  - 2. Nadimi, E.S., Jörgensen, R.N., Blanes-Vidal, V., et al: ‘Monitoring and classifying animal behavior using ZigBee-based mobile ad hoc wireless sensor networks and artificial neural networks’, Comput. Electron. Agric., 2012, 82, pp. 44–54.
20. 20)
  - 5. Hemsworth, P.: ‘Human-animal interactions in livestock production’, Appl. Anim. Behav. Sci., 2003, 81, (3), pp. 185–198.
21. 21)
  - 1. Martin, P., Bateson, P.: ‘Measuring behaviour an introductory guide’ (Cambridge University Press, Cambridge, 2007).
22. 22)
  - 12. Redmon, J., Divvala, S., Girshick, R., et al: ‘You only look once: unified, real-time object detection’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), June 2016.
23. 23)
  - 19. Young, G., Householder, A. S.: ‘Discussion of a set of points in terms of their mutual distances’, Psychometrika, 1938, 3, (1), pp. 19–22.

Convolutional neural network-based cow interaction watchdog

References

Related content