Exploring Autonomous Drones for Cattle Health Monitoring

At the University of Kentucky, a research project is underway to investigate how autonomous drones can monitor the health of cattle in pasture. This innovative approach utilizes unmanned air vehicles (UAVs) specifically designed to track and locate moving objects while flying in formation, which is the first step in creating a system that can monitor cattle out in the field.

Student researcher Zak LePay, pursuing a PhD in mechanical engineering, leads these drone test flights. When asked about the presence of a cow in the room, he explains that the team is working on a project that actually monitors cattle health using non-invasive methods with a UAV. The goal is to fly drones and formation around the cow to gather images, which will enable them to determine some health characteristics.

The drones used in this research work in sets of four, with an observer drone flying at altitudes between 90 to 270 feet above the herd. This drone uses downward-facing cameras to track motion and determine the location and orientation of each cow. The information relayed from the observer drone is then sent to three worker drones that fly below, taking the location information and using it to pinpoint a specific cow and gather health monitoring data such as volume weight or even body temperature.

The team utilizes drones that communicate with each other via Raspberry Pi and wireless connections. In the lab setup, multiple cameras replicate the observer drone, and there's also a model cow named Chuck used to represent cattle in this context. Currently, the focus of the team is on fully automating drone flights so that everything becomes completely autonomous. However, they have a fail-safe mechanism where pilots can take over if things become slightly unstable. Otherwise, Zak communicates with computer operators who send keystrokes on their keyboards at the ground station computer.

An additional piece of the puzzle in this cattle health monitoring system is creating image processing software capable of recognizing what a cow should look like. This requires taking images of a cow and building a 3D model. Michel Sama, an associate professor of Biosystems and agricultural engineering, is working on creating such a system. When asked about the project's image processing aspect, he explains that they are actually taking multiple images uniformly spaced all around the cow, which are then stitched together using photogrammetry to build a 3D model. In this example, they have all possible images from nine different flight paths, and their goal is to determine if fewer images can produce the same 3D model.

The team uses machine learning-based 3D modeling software for this purpose, which explains why they've built this pin to train it. Once trained, the system will be able to reliably identify cows in the pasture and subsequently recognize individual cows with facial recognition or other markings similar to those seen on drones used previously in lab research.

Following successful completion of their initial research steps, the team plans to visit a farm just outside of campus to see real cattle up close. They are test flying drones near the cattle to gauge the cows' reactions, using heart rate monitoring and behavioral changes to detect any signs of stress. The team performs five test flights per week over three days before giving the cows four days of rest each time. Each test flight lasts only five or ten minutes but helps them see how this system works in real life. So far, the cows haven't shown any signs of stress.

The next step for the team is to automate this entire process and add health monitoring and facial recognition capabilities to track each cow's vitals. According to Jessie Hogg, an associate professor in UK's Department of Mechanical Engineering who leads the project, the hope is that someday this technology will be applied by small herd cattle farms early in beef production processes where you may only have 50 cattle spread across a large plot of land.

By utilizing autonomous drones for monitoring cattle health, farmers can reduce their burden and increase efficiency. The team's researchers plan to continue working through 2021 despite not aiming to create a product for consumers. Instead, this project serves as a proof-of-concept that could significantly change the way cattle farmers work and manage their livestock.

"WEBVTTKind: captionsLanguage: enyou might not think of cows when you think of drones but here at the University of Kentucky one research project is exploring how autonomous drones can monitor the health of cattle in pasture let's check it out in this lab student researchers are test flying drones or unmanned air vehicles especially made to lock on to and track a moving object while flying in formation that's the first step in creating a system that can monitor cattle out in the field Zak lepay is pursuing a PhD in mechanical engineering and as the student researcher leading these drone test flights so Zak why is there a cow in the middle of this room so we're actually working on a project that's actually monitoring cattle health and the way we're trying to do that is using non non invasive method with a UAV and so what we're gonna try and do is basically fly these drones and formation around this cow to gather images so that way we can determine some health characteristics the drones work in a set of four an observer drone flies at the highest altitude between 90 to 270 feet above the herd this drone uses downward facing cameras to track motion and determine the location and orientation of each cow that information is relayed from the observer drone to three worker drones flying information below those worker drones take that location information and use it to pinpoint a specific cow and gather health monitoring data like volume weight or even body temperature the team is using drones that talk to each other with the help of Raspberry Pi and wireless connections the setup in this lab uses multiple cameras to replicate the observer drone and then there's Chuck the model cow used to represent the cattle right now the team is focused on fully automating the drone flights so everything is completely autonomous we have a fail-safe where the pilots are can take over if things go a little unstable but other than that basically what happens is is that I communicate with a computer operator who sends basically presses keystrokes on the keyboard on the ground station computer the other piece of the cattle monitoring puzzle is creating image processing software that can recognize what a cow should look like to do that they need to take images of a cow and build a 3d model Michel sama associate professor of Biosystems and agricultural engineering is working on creating a system to do just that okay nice so tell us a little bit about the image processing that's going into this project and how you're getting a good image of a cow sure yeah so what we're doing here is actually taking a bunch of images uniformly spaced all around the cow and then we're stitching it together using photogrammetry to try to build a 3d model and in this example we actually have all the possible images from nine different flight paths and what we're trying to do is figure out can we take less images and get the same model out of it the 3d modeling software this research project is using is machine learning based and that's why they've built this pin to train it they'll bring actual cattle in and capture a simultaneous image with these 40 cameras once the software has been trained to reliably identify a cow in the pasture the team can aim for recognizing each cow individually with facial recognition or other markings like the drones we saw in the first lab the photo pin and 3d modeling are still in development so the goal that lab research is to create a real-world application and to see that in action we're headed to a farm just outside of campus where we'll get to see some real cattle on the farm the team is test flying drones near the cattle to gauge the cows reactions they use heart rate monitoring and behavioral changes to watch for any signs of stress the team performs five test flights per week over three days then gives the cows four days of rest each test flight lasts only five or ten minutes but helps the team see how the system would work in real life so far the cows haven't shown signs of stress the next step is automating this entire process and evolving it to include health monitoring and facial recognition to keep track of each cow and its vitals Jessie Hogg associate professor in UK's Department of Mechanical Engineering is the lead researcher on this project where do you see this being applied out in the real world someday well the hope is that someday the technology we're developing in this project could be used by small herd cattle farms early in the beef production process where you may only have 50 cattle but those cattle are across a large plot of land and this would reduce the burden on the cattle producer by being able to do some autonomous health monitoring the teams researchers plan to continue through 2021 and although they won't be creating a product for consumers it's a proof-of-concept that can really change the way cattle farmers work and after our day on the farm it looks like the cows are more bothered by people than flying dronesyou might not think of cows when you think of drones but here at the University of Kentucky one research project is exploring how autonomous drones can monitor the health of cattle in pasture let's check it out in this lab student researchers are test flying drones or unmanned air vehicles especially made to lock on to and track a moving object while flying in formation that's the first step in creating a system that can monitor cattle out in the field Zak lepay is pursuing a PhD in mechanical engineering and as the student researcher leading these drone test flights so Zak why is there a cow in the middle of this room so we're actually working on a project that's actually monitoring cattle health and the way we're trying to do that is using non non invasive method with a UAV and so what we're gonna try and do is basically fly these drones and formation around this cow to gather images so that way we can determine some health characteristics the drones work in a set of four an observer drone flies at the highest altitude between 90 to 270 feet above the herd this drone uses downward facing cameras to track motion and determine the location and orientation of each cow that information is relayed from the observer drone to three worker drones flying information below those worker drones take that location information and use it to pinpoint a specific cow and gather health monitoring data like volume weight or even body temperature the team is using drones that talk to each other with the help of Raspberry Pi and wireless connections the setup in this lab uses multiple cameras to replicate the observer drone and then there's Chuck the model cow used to represent the cattle right now the team is focused on fully automating the drone flights so everything is completely autonomous we have a fail-safe where the pilots are can take over if things go a little unstable but other than that basically what happens is is that I communicate with a computer operator who sends basically presses keystrokes on the keyboard on the ground station computer the other piece of the cattle monitoring puzzle is creating image processing software that can recognize what a cow should look like to do that they need to take images of a cow and build a 3d model Michel sama associate professor of Biosystems and agricultural engineering is working on creating a system to do just that okay nice so tell us a little bit about the image processing that's going into this project and how you're getting a good image of a cow sure yeah so what we're doing here is actually taking a bunch of images uniformly spaced all around the cow and then we're stitching it together using photogrammetry to try to build a 3d model and in this example we actually have all the possible images from nine different flight paths and what we're trying to do is figure out can we take less images and get the same model out of it the 3d modeling software this research project is using is machine learning based and that's why they've built this pin to train it they'll bring actual cattle in and capture a simultaneous image with these 40 cameras once the software has been trained to reliably identify a cow in the pasture the team can aim for recognizing each cow individually with facial recognition or other markings like the drones we saw in the first lab the photo pin and 3d modeling are still in development so the goal that lab research is to create a real-world application and to see that in action we're headed to a farm just outside of campus where we'll get to see some real cattle on the farm the team is test flying drones near the cattle to gauge the cows reactions they use heart rate monitoring and behavioral changes to watch for any signs of stress the team performs five test flights per week over three days then gives the cows four days of rest each test flight lasts only five or ten minutes but helps the team see how the system would work in real life so far the cows haven't shown signs of stress the next step is automating this entire process and evolving it to include health monitoring and facial recognition to keep track of each cow and its vitals Jessie Hogg associate professor in UK's Department of Mechanical Engineering is the lead researcher on this project where do you see this being applied out in the real world someday well the hope is that someday the technology we're developing in this project could be used by small herd cattle farms early in the beef production process where you may only have 50 cattle but those cattle are across a large plot of land and this would reduce the burden on the cattle producer by being able to do some autonomous health monitoring the teams researchers plan to continue through 2021 and although they won't be creating a product for consumers it's a proof-of-concept that can really change the way cattle farmers work and after our day on the farm it looks like the cows are more bothered by people than flying drones\n"