Whether you’re taking shaky photos of Coke cans or a continent, Microsoft Research has technology that can help you remove the motion blur from the picture.
In 2010, a team of Microsoft Researchers published a method of deblurring images that relied on hardware motion sensors attached to the camera. Now several years later, this technology is now being applied to satellite imagery to make online mapping clearer and cheaper.
As nearly a textbook example of applied research, Microsoft Research recently posted a fantastic recount of how the Bing Imagery Technologies team reached out to the researchers to see if they could transfer the technology from consumer photography to taking much bigger and much higher photographs – photographs of Earth.
The Global Ortho program employs several airplanes mounted with computing equipment and highly efficient digital aerial cameras. The planes fly at the same time, about five miles apart, shooting 220 megapixels every two seconds at 17,000 feet.
Schickler was interested in the approach Joshi’s team had taken of using sensor data to remove blur because the equipment in each plane also included a tracking platform that collected data from gyroscopes, altimeters, and other sensors.
“This data allowed them to detect when an image would have been blurry,” Joshi explains, “and told them they had to send up the planes again. But until they saw our work, I don’t think they had considered taking that next step to use the data to recover the image.”
After some time adjusting the software algorithms to accommodate the larger imagery sizes and scale with gigabytes of pixels, Bing were so impressed with the results they decided to make deblurring part of its satellite imagery processing pipeline. The end result is clearer aerial imagery for users (in US and Europe at least).
And you can’t complain about clearer pictures of the roof on your house.