CPC G06V 20/46 (2022.01) [G06T 5/50 (2013.01); G06T 7/73 (2017.01); G06V 10/462 (2022.01); G06V 10/751 (2022.01); G06V 10/806 (2022.01); G06V 20/56 (2022.01); G06T 2207/20221 (2013.01)] | 19 Claims |
1. A map building apparatus, comprising a processor and a memory, wherein the memory is configured to store program instructions, and the processor coupled to the memory is configured to execute the program instructions to:
perform feature point matching on feature points at each of two map layers of a plurality of map layers useable to build a map, to obtain a plurality of feature point pairs, wherein each feature point pair of the plurality of feature point pairs comprises two feature points that are respectively from the two map layers and that match each other, each map layer comprises feature points in a plurality of frames of images, and each frame of the plurality of frames of images carries image information of a target environment, wherein the two map layers comprise a first map layer and a second map layer;
obtain a target displacement relationship between the two map layers based on map layer space coordinates, at a corresponding map layer, of each feature point in each feature point pair of the plurality of feature point pairs, wherein the map layer space coordinates are obtained based on image coordinates of the each feature point in a target image and a relative displacement between capture locations of each of two frames of target images, the relative displacement is obtained based on a motion parameter of an image capture component at the capture locations, the motion parameter is useable to indicate a motion status of the image capture component, and the target image is an image in which the each feature point is located;
perform map layer fusion on the each of two map layers based on the target displacement relationship between the each of two map layers, to obtain a map of the target environment;
determine at least one first projection plane based on map layer space coordinates of all feature points that are at the first map layer and that belong to the plurality of feature point pairs;
obtain, based on both a pixel value of any first to-be-matched feature point in a first image and a pixel value of each second to-be-matched feature point in a second image, a specified parameter corresponding to the second to-be-matched feature point, wherein the specified parameter is useable to indicate a difference between image information represented by the first to-be-matched feature point and the second to-be-matched feature point, the first image is any image in which the first to-be-matched feature point is located and that is in a first plurality of frames of images corresponding to the first map layer, and the second image is any image in which the second to-be-matched feature point is located and that is in a second plurality of frames of images corresponding to the second map layer; and
determine, as a feature point that matches the first to-be-matched feature point, a second to-be-matched feature point corresponding to a smallest specified parameter.
|