Estimating the Feeding Time of Individual Broilers via Convolutional Neural Network and Image Processing

SIMPLE SUMMARY: Using automated approaches to investigate feeding behavior in broilers provides accurate, non-invasive, and large-scale data collection, real-time monitoring capabilities, and opportunities for advanced data analysis that would not be possible with manual observations. These benefits contribute to a better understanding of broilers’ behavior for improving production efficiency and animal welfare, optimizing management practices, and promoting the profitability of poultry production. Hence, this study aimed to estimate the feeding time of individual broilers through an automated approach. First, the proposed algorithm detected the broilers’ heads. Then, a Euclidean distance-based tracking algorithm tracked the detected heads. The developed algorithm can estimate the broiler’s feeding time by identifying whether its head is inside the feeder area. The overall accuracy of each broiler’s feeding time per visit to the feeding pan was 87.3%. ABSTRACT: Feeding behavior is one of the critical welfare indicators of broilers. Hence, understanding feeding behavior can provide important information regarding the usage of poultry resources and insights into farm management. Monitoring poultry behaviors is typically performed based on visual human observation. Despite the successful applications of this method, its implementation in large poultry farms takes time and effort. Thus, there is a need for automated approaches to overcome these challenges. Consequently, this study aimed to evaluate the feeding time of individual broilers by a convolutional neural network-based model. To achieve the goal of this research, 1500 images collected from a poultry farm were labeled for training the You Only Look Once (YOLO) model to detect the broilers’ heads. A Euclidean distance-based tracking algorithm was developed to track the detected heads, as well. The developed algorithm estimated the broiler’s feeding time by recognizing whether its head is inside the feeder. Three 1-min labeled videos were applied to evaluate the proposed algorithm’s performance. The algorithm achieved an overall feeding time estimation accuracy of each broiler per visit to the feeding pan of 87.3%. In addition, the obtained results prove that the proposed algorithm can be used as a real-time tool in poultry farms.