Alpine, Utah-based Loveland Innovations, a maker of advanced data analytics solutions and drone-based data gathering tools, has launched the beta version of IMGING Detect, a deep learning engine built specifically for unmanned inspections.
With the new deep learning framework, IMGING users will be able to inspect a roof or property with an automated drone, automatically find damage and materials, and create detailed estimates using one tool – all without ever stepping foot on a roof, the company explains.
Currently, IMGING Detect makes estimating much easier by automatically highlighting areas of damage on inspection images. The initial build can recognize wind-blown shingles and hail hits, including fringe hail, on composition rooftops, says Loveland.
Loveland explains that deep learning is an advanced approach to artificial intelligence (AI) that allows IMGING to “learn” as it gathers more data – which makes IMGING more sophisticated and accurate each time it’s used.
“It’s a common misconception that all AI is the same, but it’s not,” says Leif Larson, chief technology officer of Loveland Innovations. “Deep learning is built on a neural network capable of learning the same way a human brain learns. For instance, a true deep learning framework doesn’t just look for patterns in pixels that sort of look like hail damage – it’s trained to analyze images closely and determine with measurable confidence where hail damage is. We took our time to develop a deep learning framework because it gets smarter over time as we train it and because we can build so much more on top of it. It’s just a better way to analyze the data.”
IMGING Detect is a part of the IMGING Inspect solution and is included at no additional cost. Users can buy IMGING as a complete software + kit solution or as an app to run on their existing hardware. Those who already have a DJI Phantom 4 Pro drone and cellular-enabled iPad can buy the software or hardware they need to start improving their inspection and estimating process, the company says.
Jim Loveland, CEO and founder of Loveland Innovations, notes, “This release isn’t just about faster inspections and more accurate estimates – it’s about re-thinking the industry’s entire approach to inspections and estimating. Deep learning is dead center in that vision.”