Interindividual distances and orientations of laying hens under 8 stocking densities measured by integrative deep learning techniques

Guoming Li; Baoming Li; Zhengxiang Shi; Guoyu Lu; Lilong Chai; Khaled M Rasheed; Prafulla Regmi; Ahmad Banakar

doi:10.1016/j.psj.2023.103076

Interindividual distances and orientations of laying hens under 8 stocking densities measured by integrative deep learning techniques

Poult Sci. 2023 Nov;102(11):103076. doi: 10.1016/j.psj.2023.103076. Epub 2023 Aug 30.

Authors

Guoming Li¹, Baoming Li², Zhengxiang Shi², Guoyu Lu³, Lilong Chai⁴, Khaled M Rasheed⁵, Prafulla Regmi⁶, Ahmad Banakar⁷

Affiliations

¹ Department of Poultry Science, The University of Georgia, Athens, GA 30602, USA; Institute for Artificial Intelligence, The University of Georgia, Athens, GA 30602, USA. Electronic address: gmli@uga.edu.
² College of Water Resources and Civil Engineering, China Agricultural University, Beijing 100083, China; Key Laboratory of Agricultural Engineering in Structure and Environment, Ministry of Agriculture and Rural Affairs, Beijing 100083, China.
³ Institute for Artificial Intelligence, The University of Georgia, Athens, GA 30602, USA; School of Electrical and Computer Engineering, The University of Georgia, Athens, GA 30602, USA.
⁴ Department of Poultry Science, The University of Georgia, Athens, GA 30602, USA.
⁵ Institute for Artificial Intelligence, The University of Georgia, Athens, GA 30602, USA.
⁶ Department of Poultry Science, The University of Georgia, Athens, GA 30602, USA; School of Computing, The University of Georgia, Athens, GA 30602, USA.
⁷ Biosystems Engineering Department, Tarbiat Modares University, Tehran 14117-13116, Iran.

Abstract

Interindividual distances and orientations of laying hens provide quantitative measures to calculate and optimize space allocations for bird flocks. However, these metrics were often measured manually and have not been examined for different stocking densities of laying hens. The objectives of this study were to 1) integrate and develop several deep learning techniques to detect interindividual distances and orientations of laying hens; and 2) examine the 2 metrics under 8 stocking densities via the developed techniques. Laying hens (Jingfen breed, a popular hen breed in China) at 35 wk of age were raised in experimental compartments at 8 different stocking densities of 3,840, 2,880, 2,304, 1,920, 1,646, 1,440, 1,280, and 1,152 cm²•bird^-1 (3-10 hens per compartment, respectively), and cameras on the top of the compartments recorded videos for further analysis. The designed deep learning image classifier achieved over 99% accuracy to classify bird's perching status and excluded frames with bird perching to ensure that all birds analyzed were on the same horizontal plane, reducing calculation errors. The YOLOv5m oriented object detection model achieved over 90% precision, recall, and F1 score in detecting birds in compartments and can output bird centroid coordinates and angles, from which interindividual distances and orientations were calculated based on pairs of birds. Laying hens maintained smaller minimum interindividual distances in higher stocking densities. They were in an intersecting relationship with conspecifics for over 90% of the time. The developed integrative deep learning techniques and behavior metrics provide animal-based measurement of space requirement for laying hens.

Keywords: animal welfare; artificial intelligence; oriented object detection; precision livestock farming; space allocation.