Method and device for localization of autonomous vehicle for route planning by using attention-driven landmark detection

A device for detecting a location of a subject vehicle capable of an autonomous driving by using a landmark detection, comprising:

• at least one memory that stores instructions;
• and
• at least one processor configured to execute the instructions to perform processes of:
• (I) if at least one live feature map, which has been generated by processing at least one live image corresponding to a circumstance of the subject vehicle interworking with the computing device, is acquired, detecting each of feature map coordinates on the live feature map per each of one or more reference objects included in a subject data region corresponding to at least one location and at least one posture of the subject vehicle by which the live feature map has been acquired, by referring to (i) each of one or more reference feature maps corresponding to each of the reference objects, and (ii) the live feature map;
• (II) detecting each of image coordinates of each of the reference objects on the live image by referring to each of the feature map coordinates;
• and (III) detecting at least one optimized subject coordinate of the subject vehicle by referring to one or more 3-dimensional coordinates of the reference objects in a real world, the image coordinates, information on parameters of a camera which has acquired the live image, and information on said posture of the subject vehicle.