Real-time behavior detection and judgment of egg breeders based on YOLO v3
- 14 Downloads
In order to detect the behavior of egg breeders in self-breeding cages rapidly, a method of target location and behavior recognition based on visual images was proposed. In this study, Hy-Line Gray chickens were bred as objects. Through manual marking, the training set, validation set and test set were established, and YOLO v3 model was adopted to detect the collected images. The value of subdivision and batch size were determined by experiment. The learning rate was dynamically adjusted according to the change of loss value in the training model. Finally, the mean average precision of the trained model on the validation set was 92.09%. In this paper, the recognition rates of six kinds of behaviors in the morning and in the afternoon and under different densities were analyzed. Furthermore, a kind of welfare indicator was tested and abnormal behavior was evaluated. The results showed that: The mean precision rate of the six behaviors was followed by mating (94.72%), stand (94.57%), feed (93.10%), spread (92.02%), fight (88.67%) and drink (86.88%). The mean false rate ranged from low to high was spread (0.11%), mating (0.14%), fight (0.20%), drink (0.25%), feed (1.17%) and stand (8.62%). The mean missing rate ranged from low to high was mating (4.65%), stand (5.01%), feed (5.15%), spread (6.25%), fight (14.69%) and drink (15.79%). The method presented in this paper has a good effect on identifying the behavior of egg breeders, which can provide technical support for the promotion of the self-breeding mode.
KeywordsYOLO v3 Self-breeding Egg breeders Behavior recognition Mating rate Abnormal judgment
The authors would like to thank for the fund (2018YFD0500700) (19227213D), (16236605D-2 (2018)) and (HBCT2018150208).
Juan Wang contributed to methodology and wrote the original draft; Nan Wang performed data curation; Lihua Li performed formal analysis; Zhenhui Ren contributed to conceptualization and wrote the review.
This work was funded by the National Key R&D Program of China (2018YFD0500700), the Key Science and Technology Research and Development Program of Hebei Province (19227213D, 16236605D-2 (2018)) and the two-stage innovation team of the Modern Agricultural Industry Technology System in Hebei (HBCT2018150208).
Compliance with ethical standards
Conflict of interest
The authors declare no conflict of interest. No conflict of interest exists in the submission of this manuscript, and manuscript is approved by all authors for publication. We would like to declare that the work described was original research that has not been published previously and not under consideration for publication elsewhere, in whole or in part. All the authors listed have approved the manuscript that is enclosed.
- 11.Tullo E, Fontana I, Fernandez AP, Vranken E, Norton T, Berckmans D, Guarino M (2017) Association between environmental predisposing risk factors and leg disorders in broiler chickens. J Anim Sci 95(4):1512–1520Google Scholar
- 13.Fengdan LAO, Guanghui TENG, Jun LI, Ligen YU, Zhuo LI (2012) Behavior recognition method for individual laying hen based on computer vision. Trans Chin Soc Agric Eng (Trans CSAE) 28(24):157–163Google Scholar
- 14.Fengdan LAO, Guanghui TENG, Zhuo LI et al (2013) Recognition and conglutination separation of individual hens based on machine vision in complex environment. Trans Chin Soc Agric Mach 44(04):213–216 + 227Google Scholar
- 15.Fengdan LAO, Xiaodong DU, Guanghui TENG (2017) Automatic recognition method of laying hen behaviors based on depth image processing. Trans Chin Soc Agric Mach 48(01):155–162Google Scholar
- 20.Teresa C, Jose P (2019) Effect of conducive environment on the egg production of hen. Revis Cient 29(1):52–56Google Scholar
- 24.BI M, Zhang T, Zhuang X, Jiao P (2018) Recognition method of sick yellow feather chicken based on head features. Trans Chin Soc Agric Mach 49(01):51–57Google Scholar
- 25.Gao Y, Guo J, Li X, Lei M, Lu J, Tong Y (2019) Instance-level segmentation method for group pig images based on deep learning. Trans Chin Soc Agric Mach. http://kns.cnki.net/kcms/detail/11.1964.S.20190301.1632.004.html
- 27.Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. arXiv:1804.02767