Method for representing surroundings

摘要

A method for environmental representation, in which two images of an environment (U) are taken respectively and a disparity image is determined by means of stereo image processing. An unobstructed free space (F) is identified in the disparity image, in that each pixel of the disparity image is allocated either to the unobstructed ground surface (B) or to one of several segments (S11 to Snu) depending on disparity values of the respective pixel. Segments (S11 to Snu) of the same width are formed from pixels of the same or similar distance to an image plane. An object (O1 to Ok) located outside of the free space (F) is modelled in the environment (U) using one segment (S11 to Snu) or several segments (S11 to Snu).

主权项

1. A method for environmental representation, in which two images of an environment (U) are taken respectively and a disparity image is determined by means of stereo image processing, comprising:
identifying in the disparity image, an unobstructed free space (F) in that each pixel of the disparity image is allocated to either an unobstructed ground surface (B) or one of several segments (S11 to Snu), wherein segments (S11 to Snu) of the same width are formed from pixels of the same or similar distances to an image modeling an object (O1 to Ok) located outside of the free space (F) in the environment (U) via a segment (S11 to Snu) or several segments (S11 to Snu), wherein several segments (S11 to Snu) are arranged on top of one another in one column of the disparity image respectively, if several objects (O1 to Ok) are depicted in different planes (E1 to E3) in one column of the disparity image.