Learning Lanes From Radar Sensors

A method comprising:

• receiving probe data from radar sensors of a plurality of vehicles at a road segment, the probe data comprising an identification of static objects in proximity to the respective vehicles at the road segment and geographic locations of the static objects;
• determining, using a processor, a first road boundary and a second, opposite road boundary at the road segment from the identified static objects received from the plurality of vehicles;
• computing a width of the road segment from the identified first and second road boundaries;
• estimating a number of lanes at the road segment by dividing the computed width of the road segment by a predetermined average lane width;
• and
• reporting the estimated number of lanes at the road segment to a vehicle navigation device over a connected network.

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:
• receive probe data from radar sensors of a plurality of vehicles at a road segment, the probe data comprising an identification of static objects in proximity to the respective vehicles at the road segment and geographic locations of the static objects;
• determine a first road boundary and a second, opposite road boundary at the road segment from the identified static objects;
• compute a width of the road segment from the identified first and second road boundaries;
• estimate a number of lanes at the road segment by dividing the computed width of the road segment by a predetermined average lane width;
• and
• update a map database with the estimated number of lanes at the road segment, or report the estimated number of lanes at the road segment to a vehicle navigation device over a connected network.