Skip to main content
ARS Home » Southeast Area » Athens, Georgia » U.S. National Poultry Research Center » Egg and Poultry Production Safety Research Unit » Research » Publications at this Location » Publication #401186
Research Project: Reduction of Foodborne Pathogens and Antimicrobial Resistance in Poultry Production Environments

Location: Egg and Poultry Production Safety Research Unit

Title: Detecting broiler chickens on litter floor with the YOLOv5-CBAM deep learning model

Author
item GUO, YANGYANG - Anhui Jianzhu University
item AGGREY, SAMUEL - University Of Georgia
item Oladeinde, Adelumola - Ade
item QIAO, YONGLIANG - University Of Sydney
item CHAI, LILONG - University Of Georgia

Submitted to: Artificial Intelligence in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 8/8/2023
Publication Date: 8/9/2023
Citation: Guo, Y., Aggrey, S.E., Oladeinde, A.A., Qiao, Y., Chai, L. 2023. Detecting broiler chickens on litter floor with the YOLOv5-CBAM deep learning model. Artificial Intelligence in Agriculture. 9 (2023) 36-45.

Interpretive Summary: Broiler meat provides a valuable source of proteins but face a number of challenges worldwide. Among the many challenges is the welfare concerns of the broiler chickens under intensive management systems. Due to the large number of chickens reared at any given time in a barn, accurate and efficient monitoring of birds can improve their health and welfare status. Currently, most broiler houses are monitored manually, however, this approach could be both laborious and erroneous. Therefore, there is a need for an automatic broiler monitoring system that could collect individual bird data within a flock and provide critical information to aid in the digital management of a broiler flock. In this study, we developed a vision-based broiler detection model to monitor broilers at different ages, raised on different litter types and in multiple pens.

Technical Abstract: For commercial broiler production, about 20,000 – 30,000 birds are raised in each confined house, which has caused growing public concerns on animal welfare. Currently, daily evaluation of broiler wellbeing and growth is conducted manually, which is labor intensive and subjective to human errors. Therefore, there is a need for an automatic tool to detect and analyze the behaviors of chickens and predict their welfare status. In this study, we developed a YOLOv5-CBAM-broiler model and tested its performance for tracking broilers on litter floor. The proposed model consisted of two parts: (1) basic YOLOv5 model for bird or broiler feature extraction and target detection; and (2) the convolutional block attention module (CBAM) to improve the feature extraction ability of the network and the problem of missed detection of occluded targets and small targets. A complex dataset of broiler chicken images at different ages, multiple pens and scenes (fresh litter versus reused litter) was constructed to evaluate the effectiveness of the new model. In addition, the model was compared to the Faster R-CNN, SSD and YOLOv5 models. The results demonstrate that the proposed approach achieved a precision of 97.3%, a recall of 92.3%, an F1 score of 94.7%, and an mAP@0.5 of 96.5%, which outperformed Faster R-CNN, SSD and YOLOv5. In addition, comparing the detection effects in different scenes, the YOLOv5-CBAM model was still better than the comparison method. Overall, the proposed deep learning-based broiler detection approach can achieve real-time accurate and fast target detection and provide technical support for the management and monitoring of birds in commercial broiler houses.