US 12,488,549 B2
Positioning model optimization method, positioning method, and positioning device
Linjie Luo, Los Angeles, CA (US); Jing Liu, Los Angeles, CA (US); Zhili Chen, Los Angeles, CA (US); Guohui Wang, Los Angeles, CA (US); Xiao Yang, Los Angeles, CA (US); Jianchao Yang, Los Angeles, CA (US); and Xiaochen Lian, Los Angeles, CA (US)
Assigned to BYTEDANCE INC., Los Angeles, CA (US)
Appl. No. 18/040,463
Filed by BYTEDANCE INC., Los Angeles, CA (US)
PCT Filed Jul. 22, 2021, PCT No. PCT/CN2021/107976
§ 371(c)(1), (2) Date Feb. 3, 2023,
PCT Pub. No. WO2022/028254, PCT Pub. Date Feb. 10, 2022.
Claims priority of application No. 202010767049.5 (CN), filed on Aug. 3, 2020.
Prior Publication US 2023/0290094 A1, Sep. 14, 2023
Int. Cl. G06T 19/20 (2011.01); G06T 7/70 (2017.01)
CPC G06T 19/20 (2013.01) [G06T 7/70 (2017.01); G06T 2207/30241 (2013.01); G06T 2219/2004 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A positioning model optimization method, comprising:
inputting a positioning model for a scene, the positioning model comprising a three-dimensional (3D) point cloud and a plurality of descriptors corresponding to each 3D point in the 3D point cloud;
calculating a significance of each 3D point in the 3D point cloud, and if the significance is greater than a predetermined threshold, outputting the 3D point and the plurality of descriptors corresponding to the 3D point to an optimized positioning model for the scene; and
outputting the optimized positioning model for the scene,
wherein said calculating the significance of each 3D point in the 3D point cloud comprises:
determining a trajectory formed by two-dimensional (2D) feature points projected by the 3D point on different images of the scene; and
calculating a length of the trajectory as the significance of the 3D point.