Skip to Main Content
This paper presents the algorithm of stereo-faces detection in video sequences. A stereo-face is a face of a man presented by set of images obtained from different points of view. Such data can be used for faces structure estimation. Our algorithm is based on computationally effective method of face detection in mono image. Information about face positions is then combined using sparse stereo matching algorithm. Sparse means that stereo correspondence is estimated not for all scene points but only for points of interest. This allows obtaining the low computation cost of algorithm. We use few criteria to estimate correspondence. These are: epipolar constraint, size correspondence, 3D region of interest constraint and histogram correspondence. Object distance estimation method that does not use projective transformations of stereo planes is also considered.