POLAR I is Increasing Scan Accuracy by 1,000X

Alan Bologlu, the CEO of POLAR I, Inc. recently introduced me to an exciting new approach that increases the accuracy of laser scanning by a factor of 1,000, using commercial off the shelf cameras and the POLAR I proprietary algorithm.

images of enhanced depth Polar I

MIT Media Lab

The POLAR I technology is from the MIT Media Lab (check out the 60 Minute story for a fascinating inside look at the people working at this important facility) . The principal researchers are Achuta Kadambi and Ramesh Raskar.

Polar I, Inc. has the core capability of enhancing the resolution of existing depth sensors by exploiting angles of polarization to recalculate surface normals, thereby providing ultra high resolution 3D depth maps. This is accomplished using COTS equipment and their proprietary algorithm.

The solution revolves around using multiple angles of polarization to enhance surface normals collected by a coarse depth sensor like lidar. A link with their ToF camera will follow. The resolution is about the same as lidar – good for detecting that something is there, very poor for determining what it is.

Polar I, Inc. is collecting angles of polarization using the new Sony 5mp IMX250MZR (mono) and the IMX250MYR (color) polarized cmos sensor. They use this sensor to collect angles of polarization and are therefore pixel agnostic, meaning when zoom functionality is enabled they do not lose resolution where as a normal image would get pixelated.

Cameras are available from various manufacturers and the solution will enhance the resolution of multiple coarse depth sensors including ToF, lidar, laser  and more.

The technique could lead to high-quality 3-D cameras built into cellphones, and perhaps to the ability to snap a photo of an object and then use a 3-D printer to produce a replica. An SDK is going to be available soon.

For more information click here.

Note – If you liked this post click here to stay informed of all of the 3D laser scanning, UAS, autonomous vehicle and Lidar News. If you have an informative 3D video that you would like us to promote, please forward to editor@lidarnews.com.

 

This entry was posted in 3D Modeling, artificial intelligence, computer vision, Data, Hardware, Research, Sensors and tagged , , , , , , , . Bookmark the permalink.

Leave a Reply

Your email address will not be published. Required fields are marked *

*

This site uses Akismet to reduce spam. Learn how your comment data is processed.