Assessment of Preference Behavior of Layer Hens under Different Light Colors and Temperature Environments in Long-Time Footage Using a Computer Vision System.

As for all birds, the behavior of chickens is largely determined by environmental conditions. In many production systems, light intensity is low and red feather strains have low contrast with the background, making it impossible to use conventional image segmentation techniques. On the other hand, studies of chicken behavior, even when using video camera resources, depend on human vision to extract the information of interest; and in this case, reduced samples are observed, due to the high cost of time and energy. Our work combined the use of advanced object detection techniques using YOLO v4 architecture to locate chickens in low-quality videos, and we automatically extracted information on the location of birds in more than 648 h of footage. We develop an automated system that allows the chickens to transition among three environments with different illuminations equipped with video cameras to monitor the presence of birds in each compartment, and we automatically count the number of birds in each compartment and determine their preference. Our chicken detection algorithm shows a mean average precision of 99.9%, and a manual inspection of the results showed an accuracy of 98.8%. Behavioral analysis results based on bird unrest index and permanence time indicate that chickens tend to prefer white light and disfavor green light, except in the presence of heat stress when no clear preference can be observed. This study demonstrates the potential of using computer vision techniques with low-resolution, low-cost cameras to monitor chickens in low-light conditions.

Degradabilidade ruminal in situ da matéria seca e proteína bruta do farelo e dos grãos de soja extrusados / In situ ruminal degradability of dry matter and crude protein from soybean meal and extruded whole soybean

Três novilhas mestiças Holandesas, dotadas de cânulas ruminais, foram utilizadas para comparar as taxas de degradabilidade ruminal da matéria seca e proteína bruta de três tratamentos: A) farelo de soja; B) grão de soja semi-integral extrusado; e C) grão de soja integral extrusado, através da técnica de sacos de náilon in situ. O delineamento utilizado foi inteiramente casualizado, considerando as variáveis tratamentos, animais e repetições. Os resultados mostraram que a degradabilidade ruminal dos grãos de soja integrais ou semi-integrais e extrusados foi menor do que a degradabilidade ruminal da matéria seca e proteína do farelo de soja. Também ficou evidente que a retirada prévia de parte de gordura dos grãos (grãos de soja semi-integrais) provocou diminuição na degradabilidade ruminal.

Ruminal degradability in dry and lactating cows, with 70% or 50% of roughage as dry matter diets / Degradabilidade ruminal de alimentos em vacas secas e lactantes, recebendo 70% ou 50% de MS das rações como volumosos

Four dry and four lactating Holstein heifers, received the following treatments to evaluate rumen degradabilities of soybean meal, rice meal, coast cross hay and sugar cane, through a dacron bag in situ technique: A = 70% roughage diet; dry cows; B = 70% roughage diet, lactating cows; C = 50% roughage diet, dry cows and D = 50% roughage diet, lactating cows. A randomized block design was used and the treatments had four repetitions in different times. Dry cows presented a higher degradability rate for soybean meal, coast cross hay and sugar cane than lactating females. Lactating cows consumed 40% more dry matter than the dry ones and presented higher rumen liquid turn-over. Coast cross hay and sugar cane were better digested with 70% roughage diets, than with the 50% roughage diets.

Oito novilhas holandesas, quatro secas e quatro em lactação, receberam os seguintes tratamentos, visando medir degradabilidade ruminal dos alimentos, farelo de soja, farelo de arroz, feno coast cross e cana-de-açúcar, pelo processo de sacos de nàilon in situ: A - 70% de volumosos; vacas secas; B - 70% de volumosos; vacas em lactação; C - 50% de volumosos, vacas secas e D - 50% de volumosos, vacas em lactação. O delineamento foi em blocos ao acaso e os tratamentos foram aplicados em quatro períodos consecutivos. Vacas secas degradaram melhor farelo de soja, feno coast cross e cana-de-açúcar que as em lactação. As fêmeas lactantes consumiram 40% mais matéria seca que as não- lactantes e apresentaram maior turn-over do líquido ruminal. Os alimentos feno de coast cross e cana-de-açúcar foram melhor degradados nas dietas com 70% de volumosos em relação às com 50%.