Computer Vision-Based Characterization of Temporal Feeding Dynamic in Group-Housed Dairy Goats
Open Access
Abstract
Feeding behavior is closely related to nutrient intake, health, and production performance, yet its temporal dynamics are difficult to quantify in group-housed dairy goats. We developed a computer vision-based framework to characterize feeding dynamics under commercial farm conditions. Video data were collected from 550 Guanzhong dairy goats housed in five pens over three consecutive days. YOLO11, RF-DETR, and RT-DETR were compared for feeding-area goat detection, and temporal feeding features were analyzed to characterize high feeding activity (HFA) and low feeding activity (LFA). In a subsequent recording phase, head-down feeding behavior was assessed in 150 goats originating from the classified source pens. A total of 24 of these goats (12 HFA and 12 LFA) were selected for exploratory milk-production and serum comparisons. RF-DETR showed the best overall detection performance, with a precision (P) of 87.39%, recall (R) of 84.00%, F1-score of 85.66%, mean average precision (mAP)@0.5 of 90.38%, and mAP@0.5:0.95 of 53.30%. Goats exhibited a “rapid entry–peak aggregation–gradual departure” feeding pattern after feed delivery. Among the temporal features, rise time of feeding-area goat count (RTFGC), fall time of feeding-area goat count (FTFGC), and feeding-area goat count increase rate (FGCIR) were the most informative features for distinguishing HFA from LFA. HFA goats reached peak feeding-area occupancy earlier, entered the feeding area at a higher rate, and maintained feeding activity for longer than LFA goats. HFA goats also showed higher head-down feeding proportions, greater average daily dry matter intake (DMI), and higher milk yield, as well as distinct serum immune, antioxidant, and neuroendocrine-related profiles. These findings indicate that feeding dynamics derived from video observations can provide a quantitative digital behavioral phenotype for characterizing individual differences in dairy goat feeding activity and their associations with production and physiological status.Keywords
Funding Information
- Talent Project in the Field of Science and Technology Innovation of Hohhot (2022RC-Industrial Research Institute-4)
- Basic Scientific Research Operating Expenses Project for Higher Education Institutions Directly under the Inner Mongolia Autonomous Region (BR261003)
- Inner Mongolia Agriculture and Animal Husbandry Research System Project (IMAHRS-16)
- Inner Mongolia Autonomous Region “Yingcai Xingmeng” Engineering Team Project (2025TYL10)
This publication has 47 references indexed in Scilit:
- Automated dairy cow identification and feeding behaviour analysis using a computer vision model based on YOLOv8Smart Agricultural Technology, 2025
- Computer vision in precision livestock farming: benchmarking YOLOv9, YOLOv10, YOLOv11, and YOLOv12 for individual cattle identificationSmart Agricultural Technology, 2025
- Livestock feeding behaviour: A review on automated systems for ruminant monitoringBiosystems Engineering, 2024
- Application of deep learning for livestock behaviour recognition: A systematic literature reviewComputers and Electronics in Agriculture, 2024
- Dairy sheep and goats sort for particle size and protein in mixed rationsApplied Animal Behaviour Science, 2023
- Non-contact sensing technology enables precision livestock farming in smart farmsComputers and Electronics in Agriculture, 2023
- Dairy goats adjust their meal patterns to the fibre content of the dietAnimal, 2021
- Inter- and intra-individual variability of feeding behaviour in group housed dairy goatsApplied Animal Behaviour Science, 2021
- Serotonin controlling feeding and satietyBehavioural Brain Research, 2015
- Feed intake and social interactions in dairy goats—The effects of feeding space and type of roughageApplied Animal Behaviour Science, 2007