Automated detection and counting of broiler behaviors using a video recognition system

• Published in: Computers and electronics in agriculture Vol. 221; p. 108930
• Main Authors: Nasiri, Amin, Zhao, Yang, Gan, Hao
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.06.2024
• Subjects: agriculture; algorithms; automation; body size; Broiler; electronics; farms; Filtering mechanisms; head; neural networks; physical activity; physical health; poultry; Preening; Stretching; video recognition; video recognition; Filtering mechanisms; Preening; Broiler; Stretching
• ISSN: 0168-1699
• DOI: 10.1016/j.compag.2024.108930

•A video recognition-based pipeline was developed to detect and quantify the broilers’ behaviors.•The pipeline utilized three convolutional-based networks.•Filtering mechanisms were proposed to enhance the pipeline’s performance.•An average precision of 88.10% was attained in quantifying the broilers’ behaviors. Stretching and preening behaviors in broilers are linked to their comfort and overall welfare. These behaviors signal that broilers engage in natural behaviors and physical activity and that the environment is conducive to their needs. By examining the frequency of stretching and preening, valuable information can be gained regarding broilers' physical health and environmental circumstances. This study attempted to quantify stretching and preening among individual broilers in commercial farms, aiming to fill a gap in the literature on this subject. The proposed video recognition-based pipeline consisted of four main components: 1) identification of broilers using an encoder-decoder convolutional neural network, 2) tracking the identified broilers using the Euclidean distance algorithm, 3) utilizing a 3D convolutional network to recognize stretching and preening actions, and 4) detecting the heads of broilers using the YOLO model. Three separate filtering mechanisms, which involve assessing the broiler's movement, its body size, and the alignment of the head with the body, were implemented to improve the performance of the pipeline. To attain the goals of this research, 2500 labeled images and 1500 labeled videos obtained from a commercial broiler farm were used to train the CNN-based models. After assessing the proposed algorithm with eight 15-minute videos, the average per-class of its performance parameters − accuracy, precision, sensitivity, specificity, and AUC − was found to be 96.70%, 88.10%, 89.96%, 94.92%, and 92.44%, respectively. These findings support the feasibility of implementing the proposed algorithm as an automated tool in poultry farms.