Method and system for three-dimensional obstacle mapping for navigation of autonomous vehicles

An obstacle detection and mapping system, comprising:

• an image capturing device configured to focus at a predetermined number of different specified distances to capture an image at each of the specified distances;
• a mapping module in operative communication with the image capturing device, wherein the mapping module has instructions to:
• identify which regions in each captured image are in focus;
• assign a corresponding lens-focus distance to each of the regions that are in focus;
• form a composite image based on each captured image, with each of the regions labeled with the corresponding lens-focus distance;
• and
• produce a three-dimensional obstacle map from the composite image, wherein the three-dimensional obstacle map has an x, y, z coordinate system, with x being proportional to pixel horizontal position, y being proportional to pixel vertical position, and z being the lens-focus distance;
• and
• an obstacle avoidance module in operative communication with the mapping module.

A computer readable medium having instructions stored thereon for a method of obstacle mapping for navigation of an autonomous vehicle, the method comprising:

• focusing an image capturing device at a predetermined number of different specified distances from an autonomous vehicle to capture an image at each of the specified distances;
• identifying which regions in each captured image are in focus;
• assigning a corresponding lens-focus distance to each of the regions that are in focus;
• forming a composite image based on each captured image, with each of the regions labeled with the corresponding lens-focus distance;
• and
• producing a three-dimensional obstacle map from the composite image, wherein the three-dimensional obstacle map has an x, y, z coordinate system, with x being proportional to pixel horizontal position, y being proportional to pixel vertical position, and z being the lens-focus distance.