The company is currently working with farmers to use drones to identify and target wild dogs and feral pigs over large tracts of land in Queensland. Using footage from the Ninox drone, farmers can identify the location of pests and work with teams of hunters to trap or shoot the animals. The pests cost Australian farmers billions of dollars annually, and farmers in some areas have previously joined together to hire helicopters manned with hunters several times a year to fly over farms. Farmers hope that using the drones will bring the cost of eliminating the animals down significantly.
Now, Ninox is working to target a different type of pest: weeds. Using the same drones that can identify breathing targets, the company has developed machine learning algorithms to review footage, mapping and classifying weeds.
“We’re pretty close… really we just need to do more testing,” says Ninox tech director Daniel Vogelnest. “If the camera systems were to improve slightly, which they do every year… it would make it easier.” Vogelnest comments that more widespread testing should bring the system up quickly, as the machine learning algorithm requires a lot of data.
Ninox uses an Israeli military-grade drone developed by Bluebird Aero Systems. The drone has a three meter wingspan and dual camera system, allowing for both visual and thermal siting. The drone also has the capability to fly at night, which is an enormous advantage in tracking animal pests. Working with the Australian Civil Aviation Authority, Ninox has received special clearance to fly above the 400-foot ceiling and to fly at night; they are the first Australian company to receive this clearance.
Miriam McNabb is the Editor-in-Chief of DRONELIFE and CEO of JobForDrones, a professional drone services marketplace, and a fascinated observer of the emerging drone industry and the regulatory environment for drones. Miriam has a degree from the University of Chicago and over 20 years of experience in high tech sales and marketing for new technologies.
Subscribe to DroneLife here.