Early Warning System for Open-beaked Ratio, Spatial dispersion, and Movement of Chicken Using CNNs

Chicken is a major source of dietary protein worldwide. To meet the growing demand for chicken meat, chickens are usually raised using intensive farming approach, in which thousands of chickens are housed together. To ensure chicken production, it is essential to monitor the chickens. Typical monitoring indicators include open beak (OB) behavior, spatial dispersion, and movement of chickens. Conventionally, chicken monitoring was achieved in routinely patrol. However, manually monitoring a large flock of chickens is time-consuming and may not detect adverse events in real-time. Thus, this study proposes to monitor OB behavior, spatial dispersion, and movement of chickens on commercial farms using convolutional neural networks (CNNs). Embedded systems that comprise cameras were developed and installed on pillars and roof beams to acquire side-view and top-view videos, respectively, of chickens. The acquired videos were transmitted to a cloud server through 4G network and were converted into images. A You Only Look Once-version 7 tiny (YOLO v7-tiny), referred to as side-view YOLO v7-tiny, was trained to observe OB behaviors of chickens in the side-view images. Another YOLO v7-tiny, referred to as top-view YOLO v7-tiny, was trained to localize chickens in the top-view images. Spatial dispersion and movement of chickens were subsequently quantified using nearest neighbor algorithm and Bytetrack algorithm, respectively. The side-view YOLO v7-tiny model achieved an average precision of 91.3% in detecting chickens with OB behaviors. The top-view YOLO v7-tiny model achieved an average precision of 95.8% in localizing chickens. This research can provide an assistance for chicken farmers to more efficiently manage their farms.