METHOD, IMAGE PROCESSING APPARATUS, AND SYSTEM FOR  GENERATING ROAD IMAGE BY USING TWO-DIMENSIONAL MAP DATA

    公开(公告)号:US20240233370A9

    公开(公告)日:2024-07-11

    申请号:US18489264

    申请日:2023-10-18

    IPC分类号: G06V20/10 G01C21/00

    摘要: A method, an image processing apparatus, and a system for generating a road image by using two-dimensional map data are proposed. The method includes receiving, by an image processing apparatus, an input of the map data of a specific area, extracting, by the image processing apparatus, road geometry information and road attribute information of a road from the map data, determining, by the image processing apparatus, road object standard information matched with the road attribute information for at least one road element of the road, generating, by the image processing device, style information for the at least one road element on a basis of at least one of the road attribute information and the road object standard information, and applying, by the image processing apparatus, the style information to the road geometry information to generate a basic road image including the road and the at least one road element.

    METHOD AND DEVICE FOR GENERATING MAP DATA
    4.
    发明公开

    公开(公告)号:US20230304826A1

    公开(公告)日:2023-09-28

    申请号:US18020595

    申请日:2021-07-07

    摘要: A method for generating map data comprising training a generator neural network by acquiring training data elements and training a generative adversarial network, comprising training a generator neural network to generate, for a satellite image and a road usage image of a training data element, the map data image of the training data element and comprising generating map data for a geographical region by acquiring road usage information specifying which parts of a geographical area have been used for driving a vehicle, acquiring a satellite image of the geographical area, forming a road usage image of the geographical area which has pixels, each pixel corresponding to a respective part of the geographical area and having a value indicating whether its part of the geographical area is specified by the road usage information to have been used; and feeding the satellite image and the road usage image to the trained generator neural network.