Y-BGD: Broiler counting based on multi-object tracking

• Introducing Y-BGD framework for broiler counting in video with 98.131% accuracy. • Designing BGD algorithm to mitigate identity switching problem in MOT. • Constructing ChickenRun-2022 dataset with 144,001 frames in 283 videos. Automatic and accurate broiler counting plays a key role in the intelligent management of the cage-free broiler breeding industry. However, severe occlusion, similar appearance, variational posture and extremely crowded situation make it a very challenging task to accurately count cage-free broilers by applying the computer vision method. Currently, many broiler breeding enterprises have to count broilers manually, resulting in high management costs. To address these challenges, we propose a novel framework called YOLOX-Birth Growth Death (Y-BGD) for automatic and accurate cage-free broiler counting. The proposed method cooperated with improved multiple-object tracking algorithm to ease tracking loss and counting error by adopting BGD data association strategy. First, to evaluate the proposed framework, we constructed a large-scale dataset (namely ChickenRun-2022) that contains 283 videos, 343,657 label boxes, and over 144,000 frames with 14,373 chicken instances in total. Next, we conducted extensive experiments and analyses on this dataset and compared it with existing representative tracking algorithms to demonstrate the effectiveness of the proposed framework. Finally, the proposed framework yielded 98.131% counting accuracy, 0.1291 GEH, and 58.98 FPS speed on ChickenRun-2022. In conclusion, the proposed method provides an automatic approach to counting the number of cage-free broiler chickens in videos with higher speed and greater accuracy, which will benefit the broiler breeding industry and precision chicken management.