Smart farming

Background

Automated BW scoring: Accurate enough?

A lot of activities on a dairy farm can be automated such as milking and feeding. But can we also automate body weight measuring, and how accurate is it? Researchers in the Netherlands looked into this using a 3-D vision system.

Recent developments in sensor technology offer promising solutions to automate health monitoring by collecting daily information on the physical status of individual cows. An example of health monitoring includes monitoring of the body weight (BW) of dairy cows. And for large dairy farms it is key that BW of individual cows can be measured and monitored automatically to prevent additional labour input and to ensure farmers have time to maintain high quality and individual care.

Photo: Song et al
Photo: Song et al

3-D vision used

To find out how this can be done best, researchers from Wageningen University and Research Centre in the Netherlands set up a case study. In this study, an image acquisition setup was created in a cow selection box equipped with a top-view 3-D camera. Images taken in 3-D vision, in contrast to 2-D vision, show a clear depth difference between a cow and the background.

Morphological traits of hip height, hip width, and rump length were automatically extracted from the raw 3-D images taken of the rump area of dairy cows (n = 30). These traits combined with days in milk, age, and parity were used in multiple linear regression models to predict body weight.

Similar to manual methods

It was shown that among these variables, hip width, age, and parity showed significant linear relationships with the referential BW. Additionally, age and parity were highly correlated. Overall, the integrated system (including the image acquisition setup, image analysis, and the best prediction model) predicted the body weights with a performance similar to that achieved using semi-automated or manual methods. The variabilities of the automated (n = 9) and manual (n = 10) morphological trait measurements of a life-size model cow are listed in Table 1. Moreover, the variability of the simplified morphological trait measurement showed a negligible contribution to the uncertainty of body weight prediction.

Prediction should be improved

Although the prediction error is similar to those of other studies, the researchers address that an error of 41.2 kg is much larger than the cow’s average daily weight change caused by net energy intake, which is less than 1 kg. This is likely because this particular prediction model mainly contained variables that do not fluctuate on a daily basis. According to these results, this model is not yet suitable for monitoring short term BW variation or detecting anomalies in a cow’s health status. The researchers suggest that dairy cow body weight prediction can be improved by incorporating more predictive morphological traits and by improving the prediction model structure.

Or register to be able to comment.