DroneDeploy Releases Machine Learning-Driven Photogrammetry Software

By Mike Ball / 22 Aug 2018
Follow UST

DroneDeploy Map Engine

DroneDeploy, a drone software platform with the largest drone data repository in the world, has announced the release of Map Engine — a machine learning-driven photogrammetry software package. This release comes after a successful beta period during which the software processed 30K maps per month for more than 4,000 clients across 180 countries.

DroneDeploy’s Map Engine generates high-resolution maps and 3D models from drone imagery collected in the construction, energy, agriculture, and surveying sectors. The new processing engine leverages the latest cloud infrastructure and machine learning technology to deliver high-quality results and help customers reduce on-prem hardware and maintenance costs.

“Map Engine tracks billions of points in aerial images to simultaneously reconstruct 3D scenes and the trajectory of the drone,” said Nicholas Pilkington, DroneDeploy’s CTO. “We have brought together the latest advances in cloud computing, computer vision, and machine learning to build a best-in-class photogrammetry pipeline that delivers accurate results in record time—no matter your workflow.”

This release includes four major improvements over earlier beta versions:

Improved Speed: Map Engine now generates maps and models 30-50% faster. Scenes made up of hundreds of images can be processed in under an hour.
Improved Accuracy: Industry-specific accuracy improvements for Agriculture, Construction, and Solar generate higher-quality results.
Large Map Support: Maps of up to 10,000 images (100GB) can now be quickly and accurately processed (in beta).
Mobile Uploads: Customers can now wirelessly transfer images to the cloud with Mobile Uploads (in beta) for immediate processing.

The Map Engine codebase integration began with DroneDeploy’s acquisition of photogrammetry solution 3DN, which had already been in development for five years. Since launching in Beta, Map Engine has processed 100M gigapixels of drone imagery. Its machine learning capabilities enable customers to gather better data, drive faster insights, and automate time-consuming workflows—helping drones become an essential tool on every job site.

The next release of Map Engine is scheduled to be unveiled at DroneDeploy’s annual user conference in San Francisco. At that time, significant updates that integrate a broad set of AI tools into Map Engine will be announced.

Posted by Mike Ball Mike Ball is our resident technical editor here at Unmanned Systems Technology. Combining his passion for teaching, advanced engineering and all things unmanned, Mike keeps a watchful eye over everything related to the unmanned technical sector. With over 10 years’ experience in the unmanned field and a degree in engineering, Mike’s been heading up our technical team here for the last 8 years. Connect & Contact