Skip to main content
ARS Home » Southeast Area » Athens, Georgia » U.S. National Poultry Research Center » Bacterial Epidemiology & Antimicrobial Resistance Research » Research » Publications at this Location » Publication #379745

Research Project: Characterizing Antimicrobial Resistance in Poultry Production Environments

Location: Bacterial Epidemiology & Antimicrobial Resistance Research

Title: Application of Imaging Systems for Monitoring Poultry Well-being

Author
item CHAI, LILONG - UNIVERSITY OF GEORGIA
item GUO, YANGYANG - UNIVERSITY OF GEORGIA
item AGGREY, SAMUEL - UNIVERSITY OF GEORGIA
item Oladeinde, Adelumola - Ade
item RITZ, CASEY - UNIVERSITY OF GEORGIA

Submitted to: University of Georgia Research Report
Publication Type: Research Notes
Publication Acceptance Date: 10/26/2021
Publication Date: 10/22/2022
Citation: Chai, L., Guo, Y., Aggrey, S.E., Oladeinde, A.A., Ritz, C. 2022. Application of Imaging Systems for Monitoring Poultry Well-being. University of Georgia Research Report. UGA Cooperative Extension Circular 1256.

Interpretive Summary: In commercial poultry houses, animal floor uniformity and distribution in drinking, feeding, and resting zones are critical information for evaluating flock production, animal health, and wellbeing. Proper distribution of chickens in the house is an indication of a healthy flock. Currently, daily routine inspection of broiler flock distributions is done manually in commercial grow-out houses, which is labor intensive and time consuming. This task requires an efficient system that can monitor chickens' floor distributions and behaviors automatically to provide information for early detection of animal health and welfare. The objective of this extension article is to introduce a new method to likely end-users for monitoring floor distribution of chickens based on a deep-learning algorithm.

Technical Abstract: A research broiler house was used to raise Cobb-500 broiler chickens from d1 to d49. Each pen was monitored with a high definition camera mounted on the ceiling to capture video of grouped chickens. The broilers were raised antibiotic-free on reused litter made of pine shavings and the pen floor was virtually divided into drinking, feeding, and rest/exercise zones. Husbandry and management followed the standard industry protocols. A deep learning model first analyzed the total number of chickens in the pen and then quantified their distribution in each zone. This study provides the basis for devising a real-time evaluation tool to detect broiler chickens' floor distribution and behaviors in commercial facilities, because proper distribution of chickens in the house is an indication of a healthy flock.