Method, apparatus, electronic device, computer program and computer-readable recording medium for detecting lane marking based on vehicle image

An electronic device located in a vehicle, comprising:

• a camera;
• a display;
• a head up display (HUD) for displaying a plurality of visual objects on a windshield of the vehicle;
• memory comprising one or more storage media, storing instructions;
• and
• at least one processor comprising processing circuitry,
• wherein the instructions, when executed by the at least one processor, cause the electronic device to:
• while displaying a first user interface on the display, identify an input on an executable icon configured to execute an augmented reality (AR) view mode, included in the first user interface,
• based on identifying the input on the executable icon,
• obtain, using the camera, a first image of a front view of the vehicle,
• generate, based on the first image, a second image of a top view of the vehicle,
• identify, based on the second image, a first element corresponding to a left lane marking and a second element corresponding to a right lane marking,
• identify, based on the first element and the second element, within the second image, a first point corresponding to an initial position of the first element, and a second point corresponding to an initial position of the second element,
• determine, based on the first point and the second point, first candidate areas and second candidate areas, wherein each first candidate area of the first candidate areas includes a plurality of blocks, and wherein each second candidate area of the second candidate areas includes a plurality of blocks,
• identify a plurality of third points related to the left lane marking within the first candidate areas by determining a block among a plurality of blocks included in each first candidate area, and identify a plurality of fourth points related to the right lane marking within the second candidate areas by determining a block among a plurality of blocks included in each second candidate area,
• identify, based on the plurality of third points and the plurality of fourth points, a plurality of fifth points, wherein each of the plurality of fifth points is a center point of one of the plurality of third points and one of the plurality of fourth in the second image, and
• display, via the HUD, on the windshield, a second user interface including a first visual object along a first line identified based on the plurality of third points, a second visual object along a second line identified based on the plurality of fourth points, and a third visual object for guiding a direction to a destination along a third line identified based on the plurality of fifth points, in the AR view mode,
• wherein the first visual object is overlaid on the windshield and is superimposed on the left lane marking visible through the windshield,
• wherein the second visual object is overlaid on the windshield and is superimposed on the right lane marking visible through the windshield, and
• wherein the third visual object is overlaid centrally between the left lane marking and the right lane marking visible through the windshield.