Phys.org March 5, 2019
Researchers at the University of Dayton has developed an artificial neural network system that can run in a computer onboard a drone. First the system processes the images to improve their clarity. The system can identify people in various positions from different viewing angles and in varying lighting conditions, compute three-dimensional models of people, detect an object without seeing the whole object. The system has a strategy to focus the search area to the most significant regions in the scene to obtain information about the shape, structure and texture of objects and flags it the location and collects GPS data about its location. The entire process takes about one-fifth of a second on the normal laptop computer that the drone carries, along with its high-resolution camera. The technology has applications in civilian and battlefield situations…read more.
Our system can spot people amid busy surroundings. Credit: University of Dayton Vision Lab, CC BY-ND