New traits in pigs based on 3D imaging technology

Offentlig prosjektsammendrag

As new tools within genomics has led to an increase in the precision of breeding, there is in parallel a high need for more precise registrations of the traits we want to improve on our livestock animals. Historically, scoring of an animals locomotion and conformation have been scored subjectively by trained technicians in pigs. This is manual work and leads to high costs as well as insufficient quality of data, which again leads to limited genetic gain for the traits of interest. In addition, the animals are taken out from their natural environment, which disturbs the natural behaviour of the animals and potentially compromising the evaluations. Increased precision on data recordings will highly improve the accuracy of selection of the best animals in the breeding program. Developing a methodology to transform 3D images and videos into high precision numeric phenotypes will substantially improve the genetic characteristic of pigs and cattle, in particular their functionality and longevity. Combining Radio frequency identification (RFID) with Camera technology and robot vision offers several new possibilities for livestock breeding. Proof of concept-studies have shown that e.g. 3D cameras developed for virtual reality and net communication can be used for precise recordings of animal locomotion and conformation. In this project, we are going to develop prototypes of combined RFID-readers with 3D cameras and implement them in relevant environments for data recording. We will build algorithms going through the images/videos and propose new, objective and accurate traits which will increase the genetic gain for robustness, production, functionality and longevity of pigs.