[ad_1]

After a recent car accident, John Murray Bruce wished he could have seen the other car coming. The accident validated the University of South Florida assistant professor of computer science and engineering’s mission to create a technology that could do just that: see around obstacles and ultimately expand one’s vision.

Using a single image, Murray-Bruce and his doctoral student, Robinson Czajkowski, created an algorithm that calculates highly accurate, full-color three-dimensional reconstructions of areas behind obstacles — a concept Who can not only help prevent car accidents, but law enforcement experts in hostage situations, search and rescue and strategic military efforts.

“We’re turning ordinary surfaces into mirrors to reveal areas, objects and rooms that are out of our line of sight,” said Murray Bros. “We live in a 3D world, so getting a more complete 3D picture of the scene can be important in many situations and applications.”

As I was published. Nature Communications, Czajkowski and Murray-Bruce’s research is the first of its kind to successfully reconstruct a hidden scene in 3D using an ordinary digital camera. The algorithm works by using information from an image of blurred shadows cast on nearby surfaces to reconstruct a high-quality scene. Although it is more technical for the average person, it can have wide applications.

“These shadows are all around us,” Czajkowski said. “The fact that we can’t see them with our naked eyes doesn’t mean they aren’t there.”

The idea of ​​seeing around obstacles has been a topic of science fiction movies and books for decades. Murray-Bruce says this research makes significant progress in bringing this concept to life.

Prior to this work, researchers have only used ordinary cameras for rough 2D reconstruction of small spaces. All the specialized, expensive equipment required for the most successful invisible-scene 3D imaging demonstrations.

“Our work achieves a similar result using much less,” Czajkowski said. “Now you don’t have to spend a million dollars on equipment for that.”

Czajkowski and Murray-Bruce expect it will take 10 to 20 years for the technology to be adopted by law enforcement agencies and car manufacturers. Now, he plans to continue his research to further improve the speed and accuracy of the technology to expand its future applications, including self-driving cars to improve their safety and situational awareness. could

“In the more than a decade since the idea of ​​looking around corners was first introduced, there has been remarkable progress and interest and research activity in this area is accelerating,” said Murray-Bruce. “With increased activity, access to better, more sensitive cameras and faster computing power, I am optimistic about how soon this technology will become practical for a wider range of scenarios.”

While the algorithm is still in the development phase, it is available for other researchers to test and reproduce in situ.

[ad_2]