US 12,222,206 B2
Image processing method and vehicle, and readable storage medium
Hao Li, Beijing (CN); and Beisheng Zeng, Beijing (CN)
Assigned to Xiaomi EV Technology Co., Ltd., Beijing (CN)
Filed by Xiaomi EV Technology Co., Ltd., Beijing (CN)
Filed on Jun. 29, 2022, as Appl. No. 17/852,772.
Claims priority of application No. 202210179315.1 (CN), filed on Feb. 25, 2022.
Prior Publication US 2023/0273028 A1, Aug. 31, 2023
Int. Cl. G06T 3/60 (2024.01); G01C 21/30 (2006.01); G06T 3/08 (2024.01); G06T 11/00 (2006.01); H04N 23/698 (2023.01); B60W 60/00 (2020.01)
CPC G01C 21/30 (2013.01) [G06T 3/08 (2024.01); G06T 3/60 (2013.01); G06T 11/001 (2013.01); H04N 23/698 (2023.01); B60W 60/001 (2020.02); B60W 2420/403 (2013.01)] 19 Claims
OG exemplary drawing
 
10. A vehicle, comprising: a vehicle body, and a memory and a processor arranged on the vehicle body, wherein
the memory is configured to store a computer program executable by the processor; and
the processor is configured to:
obtain a real-time pose of a vehicle, and obtaining a first number of initial texture images;
obtain a first texture image corresponding to each initial texture image according to the real-time pose and each initial texture image;
obtain second texture images by
converting the first texture images to a coordinate system in which the vehicle is positioned and obtaining an area corresponding to a bottom of the vehicle,
matching a bottom area of the vehicle in a first texture image, corresponding to each initial texture image, with a vehicle-bottom passing area by converting the first texture image to the coordinate system in which the vehicle is positioned, and
obtaining a first number of bottom area images by obtaining a bottom area image of the bottom area of the vehicle in each first texture image, and using the bottom area images as second texture images; and
obtain a target image, representing a scene of the bottom area of the vehicle, by performing hybrid rendering on the second texture images corresponding to the first number of initial texture images.