Abstract
Lameness is a serious problem in dairy farm management systems and has a significant impact on dairy product reduction. Image signal processing techniques have been developed to automatically detect lame cows in dairy farms. In this paper, we propose a method of artificial intelligence fusion in digital transformation techniques for detecting lameness scores in dairy cattle. Specifically, we investigate the use of Fourier Transformation and Moving Average Transformation in conjunction with Artificial Intelligence (AI) models to analyze image depth signals taken on individual cows as they walk from the milking station to resting areas. Our proposed method involves developing frequency signal variation measures of the collected image depth signals, using spectral analysis and Moving Average Transformation, and analyzing the frequency variation measures with AI models to detect cattle lameness scores. We present partial experimental results using self-collected real-life data, which showed that applying Fourier analysis to the backbone depth data for individual cows resulted in increased mean and standard deviations when the lame scores increased but decreased skewness and kurtosis. We also used Poincare graph representations to visualize and quantify the correlation between consecutive data points in a time series and found that wider intervals between peaks were associated with larger scores. These results demonstrate the potential of our proposed method for lameness detection in dairy cattle and highlight the importance of further research in this area.
