Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Computer Vision-Based Animal Preference Assessment – Do Laying Hen Chicks Prefer Light with UVA Radiation?

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  2018 ASABE Annual International Meeting  1800193.(doi:10.13031/aim.201800193)
Authors:   Kai Liu, Kailao Wang, Tao Fei, Lilong Chai, Hongwei Xin
Keywords:   Computer vision, Feeding behavior, Light preference, Poultry lighting, UVA light

Abstract. Poultry have a fourth retinal cone that allows them to see in the ultraviolet A (UVA) wavelength (315-400 nm) and may use UVA perception to modify various behavioral functions such as feeding, peer recognition, mate selection, and social encounters. As UVA perception is an essential part of poultry vision, it may be of socio-economic significance to provide certain amount of UVA light in poultry production facilities, particularly in most of modern facilities where artificial lighting is the only light source for the birds. However, there is limited scientific information regarding how to provide the UVA supplementation to birds as well as the behavioral responses of birds to UVA radiation. The objective of this study was to assess preference of W-36 chicks (day-old) for light-emitting diode (LED) light supplemented with or without various levels of UVA radiation (0%, 5%, 10%, and 15%), i.e., LED vs. LED+UVA. A total of 108 chicks (day-old) in 18 groups over nine successive batches were assessed for their choice via preference test. For each group (six chicks), each bird was individually identified with one of the six colored marks (yellow, green, blue, purple, pink, and orange) on the head. Each group of chicks involved an 8-day preference test, during which the birds could move freely between two inter-connected compartments that contained LED and LED+UVA, respectively. A real-time monitoring system was employed to record behaviors of chicks at a capture rate of 5 frames per second. Trajectory of each bird was tracked using automated computer vision based on color detection algorithms. Time spent and feed intake by the birds under each light condition were measured daily and analyzed with generalized linear mixed models. The following results were found. In the scenario of 0% vs. 5% UVA, the chicks spent significantly lower amount of time under LED+UVA than under LED (45.6% vs. 54.4%), but had comparable feed use under both light conditions. In the scenario of 0% vs. 10% UVA, the chicks showed similar amount of time spent and feed use. In the scenario of 0% vs. 15% UVA, the chicks spent significantly higher proportion of time (61.3% vs. 38.7%) and consumed significantly more feed (60.5% vs. 39.5%) under LED+UVA than under LED. The study demonstrates the attracting effect of UVA light at 15% inclusion rate under LED illumination on chicks in terms of time spent and feed use. A large-scale and long-term study to further verify the positive effects of UVA inclusion seems warranted.

(Download PDF)    (Export to EndNotes)