A new tool being developed by the University of Saskatchewan is using artificial intelligence to assess indicators of on farm animal welfare at the abattoir.
The University of Saskatchewan's Western College of Veterinary Medicine and Department of Electrical and Computer Engineering, with funding provided through the NSERC Industrial Research Chair in Swine Welfare research program, have developed an automated swine welfare assessment system consisting of a digital security camera linked to an artificial intelligence processor and placed in the abattoir.
Dr. Seokbum Ko, a professor in the Department of Electrical and Computer Engineering, explains the camera records pigs as they move along the processing line and condensed AI models extract and assess images indicative of animal welfare.
Quote-Dr. Seokbum Ko-University of Saskatchewan:
Our goal is autonomous detection of lesions categorizing them by type and severity and generating individual lesion reports.Data will produce the reports for both abattoirs and farms showing lesion prevalence in pig shipments.Regarding the technology's capability to evaluate lesions, we are witnessing increasing progress.
The AI models are displaying improved accuracy in identifying and categorizing lesions on pig carcasses.Yet several factors impact this ability.Firstly, the quality and quantity of data utilized for training significantly influences performance.A diverse dataset with ample images representing various lesion types and severity is crucial for effective training.
Secondly the complexity of lesions can pose challenges for accurate detection, especially subtle or irregularly shaped ones.More over environmental factors like lighting conditions in the abattoir can affect image quality and consequently lesion detection accuracy.Optimizing camera placement and lighting is essential to ensure clear and consistent images for analysis.
Dr. Ko says the next step is to refine the computer models to ensure the delivery of more precise results.
Source : Farmscape.ca