US 11,954,835 B2
Methods, devices, apparatuses, and media for image fusion utilizing images and LiDAR point clouds
Jiawei Shan, Beijing (CN); Ruitong Zheng, Beijing (CN); Shiwei Wang, Beijing (CN); Luofeng Shen, Beijing (CN); and Hongpeng Li, Beijing (CN)
Assigned to Tanway Technology (Beijing) Co., Ltd., Beijing (CN)
Appl. No. 18/255,164
Filed by Tanway Technology (Beijing) Co., Ltd., Beijing (CN)
PCT Filed Apr. 21, 2022, PCT No. PCT/CN2022/088255
§ 371(c)(1), (2) Date May 31, 2023,
PCT Pub. No. WO2023/197351, PCT Pub. Date Oct. 19, 2023.
Claims priority of application No. 202210375538.5 (CN), filed on Apr. 11, 2022.
Prior Publication US 2024/0037707 A1, Feb. 1, 2024
Int. Cl. G06T 5/50 (2006.01); G01S 17/89 (2020.01); G06T 7/90 (2017.01); G06T 17/00 (2006.01); G06V 10/56 (2022.01)
CPC G06T 5/50 (2013.01) [G01S 17/89 (2013.01); G06T 7/90 (2017.01); G06T 17/00 (2013.01); G06V 10/56 (2022.01); G06T 2207/10024 (2013.01); G06T 2207/20221 (2013.01)] 19 Claims
OG exemplary drawing
 
1. An image fusion method based on image and LiDAR point cloud, comprising:
acquiring a first image and sparse point cloud data, wherein point cloud data in each channel of the sparse point cloud data corresponds to pixels in the first image respectively, and wherein the sparse point cloud data and the first image having space and time synchronicity;
obtaining a target gradient value corresponding to at least one target pixel in the first image according to the first image, wherein the target pixel being a non-edge pixel of the first image;
up-sampling the sparse point cloud data based on at least one target gradient value to obtain dense point cloud data, wherein the target gradient value is determined according to a corresponding target pixel between adjacent channels of the sparse point cloud data; and
obtaining a target fusion image based on the first image and the dense point cloud data.