Rear camera lane detection

A system comprising:

• a rearward facing camera of a vehicle;
• a source of perception data comprising a light detection and ranging (LIDAR) system of the vehicle;
• and
• a processor that is configurable to execute instructions stored in non-transitory computer readable storage media, the instructions comprising:
• receiving image data of a roadway from the rearward facing camera of the vehicle when the vehicle is moving forward on the roadway;
• receiving perception data measuring reflectivity of the roadway from the LIDAR system;
• determining whether there are lane markings on the roadway;
• in response to determining there are no lane markings, estimating a number of lanes on the roadway based on a location of shoulders of the roadway as determined only by the perception data;
• in response to determining there are lane markings, identifying in which lane the vehicle is located on the roadway by processing fused data using a neural network, wherein the fused data comprises the image data and the reflectivity of the roadway as determined by the perception data;
• and
• providing an indication of the number of lanes to an automated driving system or driving assistance system, whereby the automated driving system or driving assistance system actuates one or more vehicle controllers based on the indication of the number of lanes.

Non-transitory computer readable storage media storing instructions that, when executed by one or more processors, cause the one or more processors to:

• receive image data of a roadway from a rearward facing camera of a vehicle when the vehicle is moving forward on the roadway;
• receive perception data measuring reflectivity of the roadway from a source comprising a light detection and ranging (LIDAR) system;
• determine whether there are lane markings on the roadway;
• in response to determining there are no lane markings, estimate a number of lanes on the roadway based on a location of shoulders of the roadway as determined only by the perception data;
• in response to determining there are lane markings, identify in which lane the vehicle is located on the roadway by processing fused data using a neural network, wherein the fused data comprises the image data and the reflectivity of the roadway as determined by the perception data;
• and
• provide an indication of the number of lanes to an automated driving system or driving assistance system, whereby the automated driving system or driving assistance system actuates one or more vehicle controllers based on the indication of the number of lanes.