Method, apparatus, and system for a parametric representation of lane lines

A non-transitory computer-readable storage medium, carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to perform:

• segmenting, by a computer vision system, an input image into a plurality of grid cells, wherein each of the plurality of grid cells represents a portion of the input image;
• processing, by the computer vision system, portions of the input image in each of the plurality of grid cells to detect one or more lane lines in said each grid cell;
• for said each grid cell in which the one or more lane lines are detected, determining one or more intercepts of the one or more lane lines with one or more edges of said each grid cell, and one or more slopes of the one or more lane lines at the one or more intercepts;
• generating, by the computer vision system, a parametric representation of the one or more lane lines for said each grid cell, wherein the parametric representation encodes the one or more intercepts and the one or more slopes into a data structure for said each grid cell;
• and
• providing, by the computer vision system, an output parametric representation for the input image, wherein the output parametric representation aggregates the parametric representations of said each grid cell.

An apparatus comprising:

• at least one processor;
• and
• at least one memory including computer program code for one or more programs,
• the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,
• segment an input image into a plurality of grid cells, wherein each of the plurality of grid cells represents a portion of the input image;
• process portions of the input image in each of the plurality of grid cells to detect one or more lane lines in said each grid cell;
• for said each grid cell in which the one or more lane lines are detected, determine one or more intercepts of the one or more lane lines with one or more edges of said each grid cell, and one or more slopes of the one or more lane lines at the one or more intercepts;
• generate a parametric representation of the one or more lane lines for said each grid cell, wherein the parametric representation encodes the one or more intercepts and the one or more slopes into a data structure for said each grid cell;
• and
• provide an output parametric representation for the input image, wherein the output parametric representation aggregates the parametric representations of said each grid cell.