Method and device to generate virtual lane

A virtual lane generating device, comprising:

• a camera configured to obtain an image in front of a vehicle;
• and
• a processor configured to determine validity of lane detection information extracted from the image, and to generate a virtual lane based on an object in the image, in response to a determination that the lane detection information is not valid,
• wherein the determining of the validity of the lane detection information comprises extracting the lane detection information from the image, and determining whether a validity score of the lane detection information exceeds a threshold score.

A virtual lane generating method, comprising:

• determining validity of lane detection information extracted from an image in front a vehicle, the determining of the validity of the lane detection information comprising extracting the lane detection information from the image, and determining whether a validity score of the lane detection information exceeds a threshold score;
• generating at least one driving group by clustering objects present in the image, in response the lane detection information being invalid;
• estimating lane regions based on a region occupied by each of the at least one driving group, in response to the at least one driving group comprising a plurality of driving groups;
• generating a virtual lane boundary line between each of the estimated lane regions;
• and
• generating a virtual lane based on the virtual lane boundary lines.

A virtual lane generating apparatus comprising:

• a sensor configured to capture an image in front of a vehicle;
• a touch-sensitive display;
• a memory configured to store instructions;
• a processor configured to receive the image, and execute the instructions to determine validity of lane detection information extracted from the image, to generate a virtual lane based on an object in the image, in response to the lane detection information being invalid, and to output the virtual lane to the touch-sensitive display or an autonomous driving apparatus,
• wherein the processor is further configured to determine the validity of the lane detection information by extracting the lane detection information from the image, and determining whether a validity score of the lane detection information exceeds a threshold score.