By: Cassidy Delamarter, University Communications and Marketing
After a recent car crash, John Murray-Bruce wished he could have seen the other car coming. The crash reaffirmed the USF assistant professor of computer science and engineering鈥檚 mission to create a technology that could do just that: See around obstacles and ultimately expand one鈥檚 line of vision.
Czajkowski and Murray-Bruce
Using a single photograph, Murray-Bruce and his doctoral student, , created an algorithm that computes highly accurate, full-color three-dimensional reconstructions of areas behind obstacles 鈥� a concept that can not only help prevent car crashes, but help law enforcement experts in hostage situations, search-and-rescue and strategic military efforts.
鈥淲e鈥檙e turning ordinary surfaces into mirrors to reveal regions, objects and rooms that are outside our line of vision,鈥� Murray-Bruce said. 鈥淲e live in a 3D world, so obtaining a more complete 3D picture of a scenario can be critical in a number of situations and applications.鈥�
As published in , Czajkowski and Murray-Bruce鈥檚 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 the photo of faint shadows cast on nearby surfaces to create a high-quality reconstruction of the scene. While it is more technical for the average person, it could have broad applications.
鈥淭hese shadows are all around us,鈥� Czajkowski said. 鈥淭he fact we can鈥檛 see them with our naked eye doesn鈥檛 mean they鈥檙e not there.鈥�
The idea of seeing around obstacles has been a topic of science-fiction movies and books for decades. Murray-Bruce says this research takes significant strides in bringing that concept to life.
Prior to this work, researchers have only used ordinary cameras to create rough 2D reconstructions of small spaces. The most successful demonstrations of 3D imaging of hidden scene all required specialized, expensive equipment.
鈥淥ur work achieves a similar result using far less,鈥� Czajkowski said. 鈥淵ou don鈥檛 need to spend a million dollars on equipment for this anymore.鈥�
Czajkowski and Murray-Bruce expect it will be 10 to 20 years before the technology is robust enough to be adopted by law enforcement and car manufacturers. Right now, they plan to continue their research to further improve the technology鈥檚 speed and accuracy to expand its applications in the future, including self-driving cars to improve their safety and situational awareness.
鈥淚n just over a decade since the idea of seeing around corners emerged, there has been remarkable progress and there is accelerating interest and research activity in the area,鈥� Murray-Bruce said. 鈥淭his increased activity, along with access to better, more sensitive cameras and faster computing power form the basis for my optimism on how soon this technology will become practical for a wide range of scenarios.鈥�
While the algorithm is still in the development phase, it is for other researchers to test and reproduce in their own space.