Good health is a key element in pig welfare and steady weight gain is considered an indicator of good health and productivity. Many diseases such as diarrhoea cause a substantial reduction in food intake and weight gain in pigs. Therefore, continuous monitoring of weight is one of the essential methods to ensure pigs enjoy a good health. The purpose of this work was to investigate feasibility of an automated method to estimate weight of individual pigs by using image processing.
This study comprised measurements on four pens of grower pigs, and each consisting of 10 pigs. At the start of the experiments pigs weighed on average 23 ± 4.4 kg (mean ± SD) and 45 ± 6.5 kg at the end. Each pen was monitored by a top-view CCD camera. For validation purposes, the experiment was repeated once.
Individual pigs were automatically identified by their unique painting patterns using shape recognition techniques. The process of weight estimation was as follows: First, to localize pigs in the image, an ellipse fitting algorithm was employed. Second, the area the pig was occupying in the ellipse was calculated. Finally, using TF modelling the weight of pigs was estimated. The developed model was then validated by comparing the estimated weight against manual two weekly real live weight measurements of each individual. In addition, to monitor the weight of pigs individually, the pigs were marked with basic unique paint patterns and were identified automatically using shape recognition techniques. In this way, the weight of each individual pig could be estimated. This method can replace the regular weight measurements in farms that require repeated handling and thereby imposing stress on pigs.
Overall, video imaging of fattening pigs appeared promising for real-time weight and growth monitoring. In this study the weight could be estimated with an accuracy of 97.5% in a group level (standard error of 0.82 kg) and 96.2% individually (standard error of 1.23 kg).This is significant since the existing automated tools have currently a maximum accuracy of 95% (standard error of 2 kg) in practical setups and 97 % (standard error of 1 kg) in walk-through systems (when pigs are forced to pass a corridor one by one) on average.
Future work should focus on developing specific algorithms to account for the effect of gender and genotype on body surface area and body weight since these factors affect the model parameters for weight estimation.