Back to search

BIONÆR-Bionæringsprogram

Genes2behave - Using vision-related behavioral traits in commercial breeding programs for pigs.

Alternative title: Genes2behave - Bruk av atferdsegenskaper basert på videoteknologi i avlsprogram for gris

Awarded: NOK 6.8 mill.

Poor economy and increased consumer demand for animal welfare friendly meat production has changed the framework for pig production. The farms are bigger with high animal turn-over. Manual work is automatized and the human-animal interactions are reduced. These factors are all creating the framework for the environment pigs are kept in. It is therefore crucial that breeding companies have information about behaviour to evolve the pig breeds to be calm, social and well-functioning in their social environment. This means to minimize antagonistic and damaging behaviours such as aggression and tail biting and stimulate to optimal behaviours such as play, positive interactions and exploration. Advances in vision technologies, artificial intelligence (AI) and machine learning (ML) have offered new opportunities to measure behavioural traits. In this project we aim to measure behavioural traits in pigs that influence animal welfare, production efficiency and product quality in order to establish a routine pipeline for implementation of behavioural traits in our breeding program. Currently, there are installed 12 cameras above 12 pens at Norsvin Delta. The image data are stored in a cloud solution. The project has started the work on annotating video images (1200 pictures). These annotated images are used to train models for segmentation, tracking and key point detection. The key points that are annotated are tail, back, shoulder, nose and right and left ear. Further, the project will add on meta data from feeding stations in to the models to identify the animals in a more accurate way. The work on identifying spesific behaviours recorded by cameras has started, and example videos has been reviewed. The work on finding proper technincal and biological definitions of the traits is on-going.

Poor economy and increased consumer demand for animal welfare friendly meat production has changed the framework for pig production. The farms are bigger with high animal turn-over. Manual work is automatized, the group sizes are increasing, and the human-animal interactions are reduced. These factors are all creating the framework for the environment pigs are kept in. It is therefore crucial that breeding companies have information about behaviour to evolve the pig breeds to be calm, social and well-functioning in their social environment. This means to minimize antagonistic and damaging behaviours such as aggression and tail biting and stimulate to optimal behaviours such as play, positive interactions and exploration. Advances in vision technologies, artificial intelligence (AI) and machine learning (ML) have offered new opportunities to measure behavioural traits. In this project we aim to measure behavioural traits in pigs that influence animal welfare, production efficiency and product quality in order to establish a routine pipeline for implementation of behavioural traits in our breeding program. This will be achieved using novel techniques within artificial intelligence, machine learning and digitization of pig behaviour through videos. From videos, the project shall identify novel behavioural traits relevant for genomic selection. The project will therefore develop models for efficient storage of informative images from video and develop models for predicting different behavioural traits. When the automated recording of behaviour is established and available - genomic analyses of the new traits will be performed to identify heritable traits relevant for implementation in the breeding program. Introducing a novel digital pipeline from video to breeding value for behavioural traits is essential in terms of improving the animal welfare and profit in pig production, but also our breeding programs and competetive advantage in an international market.

Funding scheme:

BIONÆR-Bionæringsprogram