AF prototypes skin-sensing camera
- By Mark Pomerleau
- Feb 02, 2016
Researchers have developed an advanced sensing system that could better identify humans in surveillance videos or search and rescue operations by differentiating human skin from other materials in images.
Typical color-image based systems have high false detection rates, but the prototype camera system developed by the Sensors Exploitation Research Group at the Air Force Institute of Technology
uses a skin detection and color estimation approach that is more accurate and requires only a small number of spectral channels, Air Force officials said.
The system can assess skin color in real time by detecting the amount of melanin and water in skin, enabling it to differentiate between human skin and other materials -- such as grass, trees or buildings -- and to simultaneously filter out skin colors that are not of interest.
“Since melanin is the primary element contributing to skin's color, it's a valuable piece of information to extract," said Michael Mendenhall, an assistant professor at the Air Force Institute of Technology and leader of the Sensors Exploitation Research Group. “I can use our camera system to filter out skin types based on the details of the person of interest. We can show only fair-skinned people, only dark-skinned people, or anything in between,” he said. “This is particularly useful in speeding up the search process and improving an analyst's ability to locate persons of interest.”
Mendenhall's system is capable of real-time detection and color estimation at typical video speeds, at a much lower cost than traditional methods, Air Force officials said.
Currently, Mendenhall's team is looking to improve skin detection by incorporating the skin’s mirror-like reflections into their algorithms. In the future, they would like to account for the hair on the skin, so they can make additional improvements in estimating skin color.
Mark Pomerleau is a former editorial fellow with GCN and Defense Systems.