Method and device for simulating a distribution of obstacles

1. A method for simulating a distribution of obstacles, comprising:

acquiring a plurality of point clouds of a plurality of frames, wherein each point cloud comprises a plurality of original obstacles;

acquiring real labeling data of an acquisition vehicle, and obtaining data of a simulation position of the acquisition vehicle based on the real labeling data of the acquisition vehicle and a movement rule of the acquisition vehicle, wherein the real labeling data of the acquisition vehicle is obtained through labeling the acquisition vehicle by absolute coordinates of the acquisition vehicle as vehicle labeled positions;

determining the number of obstacles to be simulated based on the data of the simulation position of the acquisition vehicle;

selecting the determined number of obstacles to be simulated, from a range with the simulation position of the acquisition vehicle as a center, wherein the range is less than or equal to a maximum scanning range of the acquisition vehicle; and

acquiring real labeling data of the selected obstacles, and obtaining a position distribution of the selected obstacles based on the real labeling data of the selected obstacles;

wherein the determining the number of obstacles to be simulated based on the data of the simulation position of the acquisition vehicle comprises:

searching for real labeling data of the acquisition vehicle, from the acquired real labeling data of the acquisition vehicle, corresponding to a vehicle labeled position identical with the simulation position of the acquisition vehicle; and if the real labeling data of the acquisition vehicle corresponding to the vehicle labeled position identical with the simulation position of the acquisition vehicle is not found, searching for real labeling data of the acquisition vehicle, from the acquired real labeling data of the acquisition vehicle, corresponding to the vehicle labeled position adjacent to the simulation position of the acquisition vehicle; and

retrieving a point cloud to which the searched real labeling data of the acquisition vehicle belongs, and determining the number of the obstacles in the retrieved point cloud as the number of the obstacles to be simulated.

2. The method of claim 1 , wherein the acquiring real labeling data of an acquisition vehicle comprises:

acquiring the absolute coordinates of the acquisition vehicle in a world coordinate system; and

labeling the acquisition vehicle by the absolute coordinates of the acquisition vehicle to obtain the real labeling data of the acquisition vehicle.

3. The method of claim 2 , wherein the acquiring real labeling data of the selected obstacles comprises:

calculating relative coordinates of the selected obstacles in a coordinate system of the point cloud;

calculating absolute coordinates of the selected obstacles based on the absolute coordinates of the acquisition vehicle and the relative coordinates of the selected obstacles; and

obtaining the real labeling data of the selected obstacles based on the absolute coordinates of the selected obstacles.

4. The method of claim 1 , wherein before the selecting the determined number of obstacles to be simulated, from a range with the simulation position of the acquisition vehicle as a center, the method further comprises:

determining real labeling data of candidate obstacles in the range;

selecting an obstacle model from an obstacle model library, based on the real labeling data of the candidate obstacles; and

determining whether adjacent candidate obstacles are overlapped by using the obstacle model; and deleting one of the overlapped candidate obstacles in a case that the adjacent candidate obstacles are overlapped.

5. A device for simulating a distribution of obstacles, comprising:

one or more processors;

a storage device for storing one or more programs; wherein

the one or more programs are executed by the one or more processors to enable the one or more processors to:

acquire a plurality of point clouds of a plurality of frames, wherein each point cloud comprises a plurality of original obstacles;

acquire real labeling data of an acquisition vehicle, and to obtain data of a simulation position of the acquisition vehicle based on the real labeling data of the acquisition vehicle and a movement rule of the acquisition vehicle, wherein the real labeling data of the acquisition vehicle is obtained through labeling the acquisition vehicle by absolute coordinates of the acquisition vehicle as vehicle labeled positions;

determine the number of obstacles to be simulated based on the data of the simulation position of the acquisition vehicle;

select the determined number of obstacles to be simulated, from a range with the simulation position of the acquisition vehicle as a center, wherein the range is less than or equal to a maximum scanning range of the acquisition vehicle; and

acquire real labeling data of the selected obstacles, and obtain a position distribution of the selected obstacles based on the real labeling data of the selected obstacles;

wherein the one or more programs are executed by the one or more processors to enable the one or more processors to:

search for real labeling data of the acquisition vehicle, from the acquired real labeling data of the acquisition vehicle, corresponding to a vehicle labeled position identical with the simulation position of the acquisition vehicle; and if the real labeling data of the acquisition vehicle corresponding to the vehicle labeled position identical with the simulation position of the acquisition vehicle is not found, search for real labeling data of the acquisition vehicle, from the acquired real labeling data of the acquisition vehicle, corresponding to the vehicle labeled position adjacent to the simulation position of the acquisition vehicle; and

retrieve a point cloud to which the searched real labeling data of the acquisition vehicle belongs, and determine the number of the obstacles in the retrieved point cloud as the number of the obstacles to be simulated.

6. The device of claim 5 , wherein the one or more programs are executed by the one or more processors to enable the one or more processors to:

acquire the absolute coordinates of the acquisition vehicle in a world coordinate system, and label the acquisition vehicle by the absolute coordinates of the acquisition vehicle to obtain the real labeling data of the acquisition vehicle.

7. The device of claim 6 , wherein the one or more programs are executed by the one or more processors to enable the one or more processors to:

calculate relative coordinates of the selected obstacles in a coordinate system of the point cloud, calculate absolute coordinates of the selected obstacles based on the absolute coordinates of the acquisition vehicle and the relative coordinates of the selected obstacles, and obtain the real labeling data of the selected obstacles based on the absolute coordinates of the selected obstacles.

8. The device of claim 5 , wherein the one or more programs are executed by the one or more processors to enable the one or more processors to:

determine real labeling data of candidate obstacles in the range, select an obstacle model from an obstacle model library, based on the real labeling data of the candidate obstacles, and determine whether adjacent candidate obstacles are overlapped by using the obstacle model; and delete one of the overlapped candidate obstacles in a case that the adjacent candidate obstacles are overlapped.

9. A non-transitory computer-readable storage medium having computer programs stored thereon, wherein the computer programs, when executed by a processor, cause the processor to perform operations of:

acquiring a plurality of point clouds of a plurality of frames, wherein each point cloud comprises a plurality of original obstacles;

acquiring real labeling data of an acquisition vehicle, and obtaining data of a simulation position of the acquisition vehicle based on the real labeling data of the acquisition vehicle and a movement rule of the acquisition vehicle; wherein the real labeling data of the acquisition vehicle is obtained through labeling the acquisition vehicle by absolute coordinates of the acquisition vehicle as vehicle labeled positions;

determining the number of obstacles to be simulated based on the data of the simulation position of the acquisition vehicle;

selecting the determined number of obstacles to be simulated, from a range with the simulation position of the acquisition vehicle as a center, wherein the range is less than or equal to a maximum scanning range of the acquisition vehicle; and

acquiring real labeling data of the selected obstacles, and obtaining a position distribution of the selected obstacles based on the real labeling data of the selected obstacles;

wherein when the computer programs, executed by a processor, cause the processor to determine the number of obstacles to be simulated based on the data of the simulation position of the acquisition vehicle, the computer programs, executed by a processor, cause the processor to perform operations of:

searching for real labeling data of the acquisition vehicle, from the acquired real labeling data of the acquisition vehicle, corresponding to a vehicle labeled position identical with the simulation position of the acquisition vehicle; and if the real labeling data of the acquisition vehicle corresponding to the vehicle labeled position identical with the simulation position of the acquisition vehicle is not found, searching for real labeling data of the acquisition vehicle, from the acquired real labeling data of the acquisition vehicle, corresponding to the vehicle labeled position adjacent to the simulation position of the acquisition vehicle; and

retrieving a point cloud to which the searched real labeling data of the acquisition vehicle belongs, and determining the number of the obstacles in the retrieved point cloud as the number of the obstacles to be simulated.