Method for generating simulated point cloud data, device, and storage medium

1. A method for generating simulated point cloud data, comprising:

acquiring at least one frame of point cloud data collected by a road collecting device in an actual environment without a dynamic obstacle as static scene point cloud data;

setting, according to set position association information, at least one dynamic obstacle in a coordinate system matching the static scene point cloud data;

simulating in the coordinate system, according to the static scene point cloud data, a plurality of simulated scanning lights emitted by a virtual scanner located at an origin of the coordinate system, comprising connecting the origin of the coordinate system to each point in the static scene point cloud data respectively to obtain a plurality of line segments as the plurality of simulated scanning lights; and

updating the static scene point cloud data according to intersections of the plurality of simulated scanning lights and the at least one dynamic obstacle to obtain the simulated point cloud data comprising point cloud data of the dynamic obstacle.

2. The method according to claim 1 , wherein, simulating in the coordinate system, according to the static scene point cloud data, the plurality of simulated scanning lights emitted by the virtual scanner located at the origin of the coordinate system comprises:

connecting the origin of the coordinate system to each point in the static scene point cloud data respectively to obtain a plurality of line segments as actual scanning lights;

simulating actual working parameters of the virtual scanner, and generating a plurality of rays starting from the origin as ideal scanning lights;

comparing, in the coordinate system, each of the ideal scanning lights with each of the actual scanning lights separately;

deleting an ideal scanning light with an angle between the ideal scanning light and an actual scanning light that is less than or equal to a first angle threshold; and

determining a combination of remaining ideal scanning lights and the actual scanning lights as the plurality of simulated scanning lights.

3. The method according to claim 1 , wherein, updating the static scene point cloud data according to intersections of the plurality of simulated scanning lights and the at least one dynamic obstacle to obtain the simulated point cloud data comprising point cloud data of the dynamic obstacle comprises:

obtaining a distance value between the origin of the coordinate system and an intersection of a first target simulated scanning light and a dynamic obstacle when the first target simulated scanning light is intersected with the dynamic obstacle;

adding the intersection to the static scene point cloud data directly when the first target simulated scanning light is a ray;

when the first target simulated scanning light is a line segment, comparing a length of the line segment with the distance value, and replacing an end point of the line segment in the static scene point cloud data by the intersection when the distance value is smaller than the length of the line segment.

4. The method according to claim 1 , wherein, updating the static scene point cloud data according to intersections of the plurality of simulated scanning lights and the at least one dynamic obstacle to obtain the simulated point cloud data comprising point cloud data of the dynamic obstacle comprises:

determining, according to position association information of the at least one dynamic obstacle in the coordinate system, depth maps of the dynamic obstacle projected on respective projection planes in a projection cube centered on the virtual scanner;

obtaining intersections of the plurality of simulated scanning lights with respective projection planes in the projection cube;

determining a type of a second target simulated scanning light when first depth information on a target intersection of the second target simulated scanning light and a target plane is greater than second depth information of a depth map of the dynamic obstacle corresponding to the target plane at the target intersection;

when the second target simulated scan light is a ray, constructing a new intersection according to the second target simulated scanning light and the second depth information, and adding the new intersection to the static scene point cloud data;

when the second target simulated scanning light is a line segment, constructing a new intersection according to the second target simulated scanning light and the second depth information, and replacing an end point of the line segment in the static scene point cloud data by the new intersection.

5. The method according to claim 1 , wherein the position association information comprises: position information and orientation information.

6. The method according to claim 1 , wherein after updating the static scene point cloud data according to intersections of the plurality of simulated scanning lights and the at least one dynamic obstacle to obtain the simulated point cloud data comprising point cloud data of the dynamic obstacle, the method further comprises at least one of:

adding a set noise to the simulated point cloud data, and, deleting point cloud data corresponding to the dynamic obstacle according to a set ratio.

7. A device, comprising:

one or more processors;

a memory configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement a method for generating simulated point cloud data, in which the one or more processors are configured to:

acquire at least one frame of point cloud data collected by a road collecting device in an actual environment without a dynamic obstacle as static scene point cloud data;

set, according to set position association information, at least one dynamic obstacle in a coordinate system matching the static scene point cloud data;

simulate in the coordinate system, according to the static scene point cloud data, a plurality of simulated scanning lights emitted by a virtual scanner located at an origin of the coordinate system, comprising: connecting the origin of the coordinate system to each point in the static scene point cloud data respectively to obtain a plurality of line segments as the plurality of simulated scanning lights; and

update the static scene point cloud data according to intersections of the plurality of simulated scanning lights and the at least one dynamic obstacle to obtain the simulated point cloud data comprising point cloud data of the dynamic obstacle.

8. The device according to claim 7 , wherein, the one or more processors are configured to simulate, according to the static scene point cloud data, the plurality of simulated scanning lights emitted by the virtual scanner located at the origin of the coordinate system in the coordinate system by performing acts of:

connecting the origin of the coordinate system to each point in the static scene point cloud data respectively to obtain a plurality of line segments as actual scanning lights;

simulating actual working parameters of the virtual scanner, and generating a plurality of rays starting from the origin as ideal scanning lights;

comparing, in the coordinate system, each of the ideal scanning lights with each of the actual scanning lights separately;

deleting an ideal scanning light with an angle between the ideal scanning light and an actual scanning light that is less than or equal to a first angle threshold; and

determining a combination of remaining ideal scanning lights and the actual scanning lights as the plurality of simulated scanning lights.

9. The device according to claim 7 , wherein, the one or more processors are configured to update the static scene point cloud data according to intersections of the plurality of simulated scanning lights and the at least one dynamic obstacle to obtain the simulated point cloud data comprising point cloud data of the dynamic obstacle by performing acts of:

obtaining a distance value between the origin of the coordinate system and an intersection of a first target simulated scanning light and a dynamic obstacle when the first target simulated scanning light is intersected with the dynamic obstacle;

adding the intersection to the static scene point cloud data directly when the first target simulated scanning light is a ray;

when the first target simulated scanning light is a line segment, comparing a length of the line segment with the distance value, and replacing an end point of the line segment in the static scene point cloud data by the intersection when the distance value is smaller than the length of the line segment.

10. The device according to claim 7 , wherein, the one or more processors are configured to update the static scene point cloud data according to intersections of the plurality of simulated scanning lights and the at least one dynamic obstacle to obtain the simulated point cloud data comprising point cloud data of the dynamic obstacle by performing acts of:

determining, according to position association information of the at least one dynamic obstacle in the coordinate system, depth maps of the dynamic obstacle projected on respective projection planes in a projection cube centered on the virtual scanner;

obtaining intersections of the plurality of simulated scanning lights with respective projection planes in the projection cube;

determining a type of a second target simulated scanning light when first depth information on a target intersection of the second target simulated scanning light and a target plane is greater than second depth information of a depth map of the dynamic obstacle corresponding to the target plane at the target intersection;

when the second target simulated scan light is a ray, constructing a new intersection according to the second target simulated scanning light and the second depth information, and adding the new intersection to the static scene point cloud data;

when the second target simulated scanning light is a line segment, constructing a new intersection according to the second target simulated scanning light and the second depth information, and replacing an end point of the line segment in the static scene point cloud data by the new intersection.

11. The device according to claim 7 , wherein the position association information comprises: position information and orientation information.

12. The device according to claim 7 , wherein the one or more processors are configured to perform at least one act of:

adding a set noise to the simulated point cloud data, and, deleting point cloud data corresponding to the dynamic obstacle according to a set ratio.

13. A non-transitory computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement a method for generating simulated point cloud data, comprising: acquiring at least one frame of point cloud data collected by a road collecting device in an actual environment without a dynamic obstacle as static scene point cloud data; setting, according to set position association information, at least one dynamic obstacle in a coordinate system matching the static scene point cloud data; simulating in the coordinate system, according to the static scene point cloud data, a plurality of simulated scanning lights emitted by a virtual scanner located at an origin of the coordinate system, comprising: connecting the origin of the coordinate system to each point in the static scene point cloud data respectively to obtain a plurality of line segments as the plurality of simulated scanning lights; and updating the static scene point cloud data according to intersections of the plurality of simulated scanning lights and the at least one dynamic obstacle to obtain the simulated point cloud data comprising point cloud data of the dynamic obstacle.