ign language learning based on high-speed fringe projection profilometry employing defocused binary fringe

Abstract:

A high-speed fringe projection profilometry employing defocused binary fringe is presented to record the 3-D sign language, including gesture and mouth movement, to help people learn the sign language. It employs a number of advanced approaches, such as fringes binarization and defocus method, high precision phase calculation based on the phase-shifting method and the three pitches heterodyne unwrapping (TPHU) method, and how to combine multiple binary fringes into a 24-bit fringe. Experiments have shown that the proposed system can acquire and display high-quality 3D gesture and mouth movement at a speed of 500 frames per second.