Method for recovering a relative depth map from a single image or a sequence of still images

摘要

Method for recovering a relative depth map from a single image or a sequence of still images, comprising:- decomposing the image into sets Uλ, each formed by pixels whose intensity is in a predefined interval;- decomposing sets Uλ into connected components Ciλ, a subset of adjacent pixels according to a connectivity rule;- for each connected component Ciλ, computing membership measures indicative of the probability of each pixel x ∉ Ciλ to belong to it and being a function of:• the distance Ciλ) from the pixel x to said connected component Ciλ;• the curvature κx⁢Ciλ of the level line of the distance function Ciλ) from the pixel x to said connected component Ciλ;- for each pixel x of the image, compute a local depth feature Z(x) indicative of the probability of the pixel x belonging simultaneously to different connected components and which provides a relative depth order estimation at pixel x.