Data plays an important role in breeding to take gene expression to the next level. In addition to sharing and interpreting data from developments for the estimation of breeding values, technological means such as cameras offer more possibilities for objective observations and the creation of new phenotypes. In China, for example, facial recognition technology for pig identification has been underway for a few years. This has not yet resulted in systems that can be used in practice, partly because pigs differ little from each other in appearance.
Automatic image interpretation
However, the use of cameras and digital imaging still has the potential to have a significant impact at the pen and/or pig level. The biggest challenge lies in the automatic interpretation of the images and in drawing conclusions based on these images. Dr. Saskia Bloemhof is Director of Genetic Services at PIC. She says: “Digital selection is still in its infancy, but the possibilities are many. To better understand this, we started working with Professor Dr. Tomas Norton from the Catholic University (KU) of Leuven in Belgium in 2020. PIC currently employs two engineers who are solely focused on translating video images into usable data . The company now uses digital selection to determine leg scores for breeding gilts and boars.
She explains: “We have worked for decades with a leg score for how a pig stands on its front and hind legs. Employees are trained to score gilts on a scale of 1-10. Ideal front scores are 5-6, rear scores between 5-10. Good or bad feet and legs are easily identified, but the difference between a score of 4 and a score of 5, for example, can be subjective. Until now, the industry has remained dependent on the human eye.
But still, marking the leg remains important.
“The paw score has proven itself in breeding, and animals with a better score have better longevity; but that remains subjective. A gilt can always get a different score from different employees. Work efficiency also plays a role. Obtaining and retaining competent and trained employees is difficult. Of course, you can always correct a breeding value estimate, but you really don’t want to. By passing the gilts in front of a camera that records the angles of movement, a more objective assessment can be made.
Can you explain that?
“We had software built that evaluates the images from the camera. The software is based on the ratings of our top reviewer. We let the gilts walk past this camera at the end of the test period and the program automatically assesses their movements. The engineers also constantly update the program to optimize the score. It might sound a bit naive, but at first we assumed we needed a full screen image, so we adjusted a piece of fence near the camera to only have the animal in the video. And then the engineers told us that it was not necessary; because he is constantly in the video, the fencing can be filtered.
Now that you can mark legs automatically, what’s next?
“The leg score is linked to the longevity of sows. We want to link a gilt’s leg use and gait to longevity or retention across multiple parts in the herd. How do they walk and how long do these steps last? You want them to take great strides. In cows, you can see the shoulder and hip bone well, so you can easily determine stride length. In a pig, seeing is more difficult than mobility. We are currently measuring stride length and locomotion based on many recorded points on the body and hope to be able to predict a pig’s lifespan. Gilts that have been numerically scored on scores and leg movements are tracked throughout their productive life.
The next step is to include locomotion in the longevity prediction
Will you select lines for breeding or propagation based on this?
“It provides selection options based on those characteristics. Especially since robustness and longevity are so important. With this data, we can more accurately predict the longevity of sows and boars destined for artificial insemination (AI). The next step is to include locomotion in longevity predictions. We now have a direct estimate of a breeding gilt, much faster than that based on an F1 sow and her offspring or a particular boar, where it takes 2.5 to 3 years to get results. The generation interval is getting shorter.
How soon do you plan to introduce the mobility score?
“At the end of the year, we will replace the subjective score in the United States and Canada with an objective score based on this program. Next year we will apply this to the rest of the world. Eventually, every nucleus breeder will have a camera system in their coop. »
What else can digital selection be applied to?
“A second step can be behavior. Behavioral assessment remains extremely difficult. You can put someone in a department to see what the pigs are doing, but that takes a long time and is impossible in practice. This is only possible with camera and video technology. But that comes with challenges. You need to know who is who in a group of pigs. This could be done with radio frequency identification (RFID), but the big question then is how to tie RFID to video and for the duration of recordings. We are currently reading ear tags through the camera. The software is so precise that it can read numbers that we can’t see properly due to dirt or a hanging ear.
How does behavioral research work?
“We color-coded behavioral expressions and looked for patterns by connecting to animal numbers. For example, from the videos, it became clear that the pigs eat before 10 a.m. and rest after 10 p.m. This means you can fill a feeder in the evening, but they won’t eat after 10 p.m. »
I think with digital selection one can search for more details
What is the next?
“We can read lying behavior, for example if a pig is lying on its stomach or on its side. We also look at mutual behavior and what is desirable or undesirable behavior. When is a given action considered play and when is it actually stress? With the tail bite, you quickly find the victim, but the biter is harder to recognize. I think with digital selection we can search for more details.
Several companies are trying to use cameras for weight determination. Do you see opportunities for this?
“You can make animals walk on a ladder, but it disrupts their rhythm. When using cameras, you can assess the entire enclosure without disturbing them. We look at these types of developments from a genetic perspective, but there is also a lot to be gained for pig farmers from a management perspective. A camera can handle anything you can see with the naked eye, as long as you have the software for it. Then the possibilities are endless.
What stops that?
“Fresh. For us, as a farming company, such a large investment is possible because it can replace a certain number of people. But this does not apply to an individual farm.
#Saskia #Bloemhof #camera #records #pigs #humans