After a recent automobile crash, John Murray-Bruce wished he could have seen the opposite automobile coming. The crash reaffirmed the University of South Florida assistant professor of computer science and engineering’s mission to create a technology that might just do that: See around obstacles and ultimately expand one’s line of vision.
Using a single photograph, Murray-Bruce and his doctoral student, Robinson Czajkowski, created an algorithm that computes highly accurate, full-color three-dimensional reconstructions of areas behind obstacles — an idea that can’t only help prevent automobile crashes, but help law enforcement experts in hostage situations, search-and-rescue and strategic military efforts.
“We’re turning odd surfaces into mirrors to disclose regions, objects and rooms which might be outside our line of vision,” Murray-Bruce said. “We live in a 3D world, so obtaining a more complete 3D picture of a scenario will be critical in various situations and applications.”
As published in Nature Communications, Czajkowski and Murray-Bruce’s research is the first-of-its-kind to successfully reconstruct a hidden scene in 3D using an odd digital camera. The algorithm works by utilizing information from the photo of faint shadows solid on nearby surfaces to create a high-quality reconstruction of the scene. While it’s more technical for the common person, it could have broad applications.
“These shadows are throughout us,” Czajkowski said. “The actual fact we will not see them with our naked eye does not imply they don’t seem to be there.”
The concept of seeing around obstacles has been a subject of science-fiction movies and books for a long time. Murray-Bruce says this research takes significant strides in bringing that idea to life.
Prior to this work, researchers have only used odd cameras to create rough 2D reconstructions of small spaces. Essentially the most successful demonstrations of 3D imaging of hidden scene all required specialized, expensive equipment.
“Our work achieves an identical result using far less,” Czajkowski said. “You needn’t spend one million dollars on equipment for this anymore.”
Czajkowski and Murray-Bruce expect it is going to be 10 to twenty years before the technology is powerful enough to be adopted by law enforcement and automobile manufacturers. Straight away, they plan to proceed their research to further improve the technology’s speed and accuracy to expand its applications in the long run, including self-driving cars to enhance their safety and situational awareness.
“In only over a decade because the idea of seeing around corners emerged, there was remarkable progress and there may be accelerating interest and research activity in the world,” Murray-Bruce said. “This increased activity, together with access to higher, more sensitive cameras and faster computing power form the premise for my optimism on how soon this technology will grow to be practical for a wide selection of scenarios.”
While the algorithm continues to be in the event phase, it is accessible for other researchers to check and reproduce in their very own space.
