| CPC G01C 21/3632 (2013.01) [G01C 21/3623 (2013.01); G06V 10/751 (2022.01); G06V 20/586 (2022.01); B60W 30/06 (2013.01); B60W 2420/403 (2013.01)] | 7 Claims |

|
1. A vehicle positioning method for a fixed parking scenario, the method comprising:
a marker detection step of detecting markers and identifying a pair of markers, proceeding to a pose matching step if vehicle position information of a vehicle in the fixed parking scenario has been obtained, or skipping to a non-pose matching step if the vehicle position information in the fixed parking scenario has not been obtained, wherein the vehicle position information comprises a point on an axle of the vehicle in a known fixed scenario coordinate system;
the pose matching step of performing pose matching based on the obtained vehicle position information and the identified pair of markers, and skipping to a position update step if latest vehicle position information is obtained based on pose matching, otherwise proceeding to the non-pose matching step;
the non-pose matching step of performing non-pose matching based on the identified pair of markers, to obtain the latest vehicle position information;
the position update step of updating current vehicle position information based on the latest vehicle position information obtained in the pose matching step or the non-pose matching step; and
a parking control step of controlling automatic parking for the vehicle using the updated current vehicle position information,
wherein the vehicle position information in the marker detection step refers to vehicle location information that has been obtained by performing the vehicle positioning method in a previous time sequence,
wherein the marker detection step comprises filtering out duplicate pairs of markers from stored marker information, to obtain the identified pair of markers in a ground coordinate system, and
wherein the non-pose matching step comprises:
a coarse matching sub-step of matching the identified pair of markers in the ground coordinate system with pairs of actual markers in the known fixed scenario coordinate system, and performing a coordinate system transformation matrix by solving an ICP algorithm by means of SVD decomposition, to obtain a first transformation matrix and a first error;
a fine matching sub-step of performing an inverse operation on the first transformation matrix obtained in the coarse matching sub-step, to find corresponding pairs of virtual markers, in the ground coordinate system, of the pairs of actual markers in the known fixed scenario coordinate system, filtering out matched pairs of virtual markers from the corresponding pairs of virtual markers, and computing another transformation matrix for other unmatched pairs of virtual markers and matched pairs of markers in the ground coordinate system, to obtain a second transformation matrix and a second error; and
a selection sub-step of selecting, based on the first transformation matrix and the first error that are obtained in the coarse matching sub-step and the second transformation matrix and the second error that are obtained in the fine matching sub-step, a pair of markers from the transformation matrix with a small error as a matched pair of markers, and obtaining, based on the matched pair of markers, vehicle position information in the fixed scenario coordinate system as the latest vehicle position information.
|