Synthetically generated cow (Bos taurus) provides data for gait analysis in feedlot

Analysis of bovine movement and behavior is crucial in detecting their motor disorders and maintaining their welfare. Quantitative gait analysis methods have been designed to facilitate this task, but the on-site subjective assessment of the gait pattern remains prominent and depends on human expertise. Gait pattern could be assessed in feedlot cattle using AI as a substitute for the absence of human diagnosis, but creating an AI diagnosis procedure requires substantial behavioral information for training the AI tool. One solution for obtaining behavioral information is to use AI-assisted tools for diagnosis based on recordings of cattle movement. In this study, we created a three-dimensional digital representation of walking cattle to generate the required information and compare its applicability to that of the actual gait patterns. We used video recordings of cattle walking and trotting, and then used them as reference to create three-dimensional pose representations. Then, we introduced variations to these representations by altering specific aspects of the original walking cow model and its environment. We then tested the combined representations against the real data to see if they can prove useful in training a deep neural network for detecting gait pattern and features. This method can compensate for the scarcity of behavioral data, provide information to create mathematical representations of specific behaviors and be used for the development of smart-phone-based diagnosis systems.

Authors

• Goldani, Ali
• University of Lethbridge. Faculty of Arts and Science

• bovine gait analysis
• lameness detection
• AI gait pattern analysis
• feedlot cattle health
• synthetic data generation
• dynamic systems theory
• bovine movement analysis

Identifier

hdl:10133/6685

OAI identifier oai:identifier

oai:opus.uleth.ca:10133/6685