| 摘要 |
The present invention relates to automatic modeling of a physical scene. At least two images (I 1 , I 2 ) of the scene are received, which are taken from different angles and/or positions. A matching module (130) matches image objects in the first image (I 1 ) against image objects in the second image (I 2 ), by first loading pixel values for at least one first portion of the first image (I 1 ) into an artificial neural network (133). Then, the artificial neural network (133) scans the second image (I 2 ) in search of pixels representing a respective second portion corresponding to each of the at least one first portion; determines a position of the respective second portion upon fulfillment of a match criterion; and produces a representative matching result (M 12 ). Based on the matching result (M 12 ), a first calculation module (140) calculates a fundamental matrix (F 12 ), which defines a relationship between the first and second images (I 1 , I 2 ). Based on the fundamental matrix (F 12 ), in turn, a second calculation module (150) calculates a depth map (D 12 ), which describes distance differences between a set of image points in the first image (I 1 ) and a corresponding set of image points in the second image (I 2 ). Finally, the depth map (D 12 ) constitutes a basis for a synthetic model of the scene. |
