US 12,333,822 B2
Method and apparatus for vehicle positioning
Hao Li, Beijing (CN); Chi Zhang, Beijing (CN); Hao Liu, Beijing (CN); Kun Guo, Beijing (CN); Kuiyuan Yang, Beijing (CN); Rui Cai, Beijing (CN); and Zhiwei Li, Beijing (CN)
Assigned to BEIJING XIAOMI MOBILE SOFTWARE CO., LTD., Beijing (CN)
Filed by BEIJING XIAOMI MOBILE SOFTWARE CO., LTD., Beijing (CN)
Filed on Feb. 28, 2022, as Appl. No. 17/682,495.
Claims priority of application No. 202111076719.X (CN), filed on Sep. 14, 2021.
Prior Publication US 2023/0082656 A1, Mar. 16, 2023
Int. Cl. G06V 20/58 (2022.01); B60W 40/105 (2012.01); G06T 7/12 (2017.01); G06T 7/90 (2017.01); G06V 20/56 (2022.01)
CPC G06V 20/58 (2022.01) [B60W 40/105 (2013.01); G06T 7/12 (2017.01); G06T 7/90 (2017.01); G06V 20/588 (2022.01); B60W 2420/403 (2013.01); B60W 2552/53 (2020.02); B60W 2554/4041 (2020.02)] 13 Claims
OG exemplary drawing
 
1. A method for vehicle positioning, comprising:
acquiring a distance transformation image of a road marking object in a road image based on the road image of an environment where a vehicle is located at a current time point;
acquiring a vector subgraph of the road marking object from a global vector map; and
determining a target positioning posture of the vehicle based on the distance transformation image and the vector subgraph;
wherein, determining the target positioning posture of the vehicle based on the distance transformation image and the vector subgraph, comprises:
predicting state information of the vehicle at the current time point based on state information of the vehicle at a previous time point of the current time point and measured data of an inertial measurement unit (IMU) at the current time point;
acquiring an actual vehicle speed of the vehicle at the current time point;
determining a target constraint function of the vehicle based on the state information at the current time point and the previous time point, the distance transformation image and the vector subgraph, and the measured data of the IMU and the actual vehicle speed; and
optimizing the state information by taking the target constraint function being minimized as a constraint condition, to output the target positioning posture of the vehicle;
wherein determining the target constraint function of the vehicle based on the state information, the distance transformation image and the vector subgraph, and the measured data of the IMU and the actual vehicle speed comprises:
mapping the vector subgraph to the distance transformation image based on the state information at the current time point, and acquiring a first image coordinate of a first pixel of the vector subgraph on the distance transformation image; and
determining the target constraint function based on the first image coordinate, the state information, the measured data of the IMU and the actual vehicle speed;
wherein determining the target constraint function of the vehicle based on the first image coordinate, the state information, and the measured data of the IMU and the actual vehicle speed comprises:
acquiring a gray value of each of the pixels from the distance transformation image based on the first image coordinate, and generating a first constraint parameter based on the gray value;
converting the state information at the current time point to a world coordinate system, and generating a second constraint parameter based on the converted state information;
converting the measured vehicle speed in the measured data of the IMU to a vehicle body coordinate system, and generating a third constraint parameter based on the measured vehicle speed after conversion and the actual vehicle speed;
performing IMU pre-integration on the measured data of the IMU between the previous time point and the current time point, to acquire a calculation increment of the IMU between adjacent time points, and generating a fourth constraint parameter based on an actually measured increment of the IMU between the adjacent time points and the calculation increment of the IMU; and
generating the target constraint function of the vehicle based on the first constraint parameter, the second constraint parameter, the third constraint parameter and the fourth constraint parameter.