Method, device and apparatus for generating electronic map, storage medium, and acquisition entity

1. A method for generating an electronic map, comprising:

obtaining a first point cloud sequence and a second point cloud sequence for a preset region;

generating a first grid map for the first point cloud sequence and a second grid map for the second point cloud sequence, wherein a grid in each of the first grid map and the second grid map at least comprises reflection value information of a point cloud; and

optimizing the first point cloud sequence based on the first grid map and the second grid map.

2. The method according to claim 1 , wherein obtaining the first point cloud sequence and the second point cloud sequence for the preset region comprises:

obtaining the first point cloud sequence and the second point cloud sequence when a signal of a geolocation system is weak or missing.

3. The method according to claim 1 , wherein generating the first grid map for the first point cloud sequence comprises:

projecting the first point cloud sequence into a plurality of grids in the first grid map;

aggregating point cloud data in each of the plurality of grids; and

storing an attribute of each of the plurality of grids in the first grid map, wherein the attribute comprises: a number of laser points, a mean value and variance of reflection values of the laser points, a mean value and variance of height values of the laser points.

4. The method according to claim 1 , wherein optimizing the first point cloud sequence comprises:

performing a geometric transformation within a predetermined range on the first grid map, wherein the geometric transformation comprises at least one of translation and rotation;

determining a geometric transformation magnitude when a matching probability between the transformed first grid map and the second grid map is maximized as a first pose difference;

optimizing the first point cloud sequence based on the first pose difference.

5. The method according to claim 4 , wherein performing the geometric transformation within the predetermined range on the first grid map comprises:

performing a first geometric transformation on the first grid map in a first transformation unit in a first range;

performing a second geometric transformation on the first grid map in a second transformation unit in a second range, wherein the second range is less than the first range, and the second transformation unit is less than the first transformation unit.

6. The method according to claim 4 , wherein determining the first pose difference comprises:

determining a joint matching probability of a reflection value and a height value between the transformed first grid map and the second grid map.

7. The method according to claim 4 , wherein optimizing the first point cloud sequence comprises:

generating a third grid map based on a third point cloud sequence for the preset region;

determining a second pose difference between the second grid map and the third grid map; and

determining a third pose difference between the third grid map and the first grid map.

8. The method according to claim 7 , wherein optimizing the first point cloud sequence comprises:

determining a first pose of the first grid map, a second pose of the second grid map and a third pose of the third grid map based on the first pose difference, the second pose difference and the third pose difference; and

adjusting the first point cloud sequence based on the first pose.

9. A device for generating an electronic map, comprising:

one or more processors; and

a memory, configured to store one or more programs;

wherein when the one or more programs are executed by the one or more processors, causes the one or more processors to:

obtain a first point cloud sequence and a second point cloud sequence for a preset region;

generate a first grid map for the first point cloud sequence and a second grid map for the second point cloud sequence, wherein a grid in each of the first grid map and the second grid map at least comprises reflection value information of a point cloud; and

optimize the first point cloud sequence based on the first grid map and the second grid map.

10. The device according to claim 9 , wherein the one or more processors are further configured to:

obtain the first point cloud sequence and the second point cloud sequence when a signal of a geolocation system is weak or missing.

11. The device according to claim 9 , wherein the one or more processors are further configured to:

project the first point cloud sequence into a plurality of grids in the first grid map;

aggregate point cloud data in each of the plurality of grids; and

store an attribute of each of the plurality of grids in the first grid map, wherein the attribute comprises: a number of laser points, a mean value and variance of reflection values of the laser points, a mean value and variance of height values of the laser points.

12. The device according to claim 9 , wherein the one or more processors are further configured to:

perform a geometric transformation within a predetermined range on the first grid map, wherein the geometric transformation comprises at least one of translation and rotation;

determine a geometric transformation magnitude when a matching probability between the transformed first grid map and the second grid map is maximized as a first pose difference;

optimize the first point cloud sequence based on the first pose difference.

13. The device according to claim 12 , wherein the one or more processors are further configured to:

perform a first geometric transformation on the first grid map in a first transformation unit in a first range;

perform a second geometric transformation on the first grid map in a second transformation unit in a second range, wherein the second range is less than the first range, and the second transformation unit is less than the first transformation unit.

14. The device according to claim 12 , wherein the one or more processors are further configured to:

determine a joint matching probability of a reflection value and a height value between the transformed first grid map and the second grid map.

15. The device according to claim 12 , wherein the one or more processors are further configured to:

generate a third grid map based on a third point cloud sequence for the preset region;

determine a second pose difference between the second grid map and the third grid map; and

determine a third pose difference between the third grid map and the first grid map.

16. The device according to claim 15 , wherein the one or more processors are further configured to:

determine a first pose of the first grid map, a second pose of the second grid map and a third pose of the third grid map based on the first pose difference, the second pose difference and the third pose difference; and

adjust the first point cloud sequence based on the first pose.

17. A non-transitory computer readable storage medium having stored thereon computer programs that, when executed by a processor, causes a method for generating an electronic map to be implemented, the method comprising:

obtaining a first point cloud sequence and a second point cloud sequence for a preset region;

generating a first grid map for the first point cloud sequence and a second grid map for the second point cloud sequence, wherein a grid in each of the first grid map and the second grid map at least comprises reflection value information of a point cloud; and

optimizing the first point cloud sequence based on the first grid map and the second grid map.