UC Riverside

Given an uncalibrated network of video cameras, we are tasked with the problem of building a 3D model of every person's face as they move within the network. The process of doing so requires overcoming many challenges including person detection, tracking, cross-camera correspondence (how to determine if a person in one camera is the same person in another), and the final 3D model reconstruction from multiple views in real-time or at near real-time speeds (efficient modeling and data fusion from multiple hardware sources). Towards this goal, a wireless camera network was designed and built from the ground up, a new tracking algorithm and a cross-camera human signature method was developed, and face modeling using multiple cameras in a real-world setting was performed.