Method and apparatus for determining matching relationship between point cloud data

1. A method for determining a matching relationship between point cloud data, the method comprising:

extracting a first characteristic associated with first point cloud data and a second characteristic associated with second point cloud data, the first point cloud data and the second point cloud data being acquired for a same object;

performing characteristic matching between the first characteristic and the second characteristic; and

determining, based on the characteristic matching, a matching relationship between the first point cloud data and the second point cloud data,

wherein the extracting the first characteristic and the second characteristic comprises:

determining first candidate columnar point cloud data from the first point cloud data, and determining the first characteristic based on the first candidate columnar point cloud data; and

determining second candidate columnar point cloud data from the second point cloud data, and determining the second characteristic based on the second candidate columnar point cloud data,

the determining the first characteristic based on the first candidate columnar point cloud data comprises:

clustering point cloud data having an angle between a main direction and a ground normal vector less than a threshold angle in the first candidate columnar point cloud data; and

determining, in response to a clustering result indicating that the first candidate columnar point cloud data comprising columnar point cloud data, a center point, a normal vector, and a radius of the columnar point cloud data as a characteristic point, a normal vector and a radius of the first characteristic,

wherein the method is performed by at least one processor.

2. The method according to claim 1 , wherein the second characteristic includes at least a characteristic point and a normal vector corresponding to the characteristic point.

3. The method according to claim 1 , wherein the extracting the first characteristic and the second characteristic comprises:

determining first ground point cloud data from the first point cloud data, and determining a center point of the first ground point cloud data and a corresponding normal vector as a second characteristic point and a second corresponding normal vector of the first characteristic; and

determining second ground point cloud data from the second point cloud data, and determining a center point of the second ground point cloud data and a corresponding normal vector as a characteristic point and a corresponding normal vector of the second characteristic.

4. The method according to claim 1 , wherein the extracting the first characteristic and the second characteristic comprises:

determining first candidate planar point cloud data from the first point cloud data, and determining the first characteristic based on the first candidate planar point cloud data; and

determining second candidate planar point cloud data from the second point cloud data, and determining the second characteristic based on the second candidate planar point cloud data.

5. The method according to claim 4 , wherein the determining the first characteristic based on the first candidate planar point cloud data comprises:

determining a breakpoint of a thread in the first candidate planar point cloud data;

segmenting the thread based on the breakpoint;

clustering the segmented thread; and

determining, in response to a clustering result indicating that the first candidate planar point cloud data comprising planar point cloud data, a center point of the planar point cloud data and a corresponding normal vector as a third characteristic point and a third corresponding normal vector of the first characteristic.

6. The method according to claim 3 , wherein the performing characteristic matching between the first characteristic and the second characteristic comprises:

converting the first characteristic and the second characteristic into a same coordinate system;

determining a distance between the characteristic point of the first characteristic and the characteristic point of the second characteristic;

determining a difference between the normal vector of the first characteristic and the normal vector of the second characteristic, in response to the distance being less than a threshold distance; and

determining the first characteristic matching the second characteristic, in response to the difference being less than a threshold difference.

7. The method according to claim 1 , wherein the performing characteristic matching between the first characteristic and the second characteristic comprises:

converting the first characteristic and the second characteristic into a same coordinate system;

determining a distance between the characteristic point of the first characteristic and a characteristic point of the second characteristic;

determining a difference between the normal vector and the radius of the first characteristic and a normal vector and a radius of the second characteristic, in response to the distance being less than a threshold distance; and

determining the first characteristic matching the second characteristic, in response to the difference being less than a threshold difference.

8. The method according to claim 1 , wherein the determining a matching relationship between the first point cloud data and the second point cloud data comprises:

determining the matching relationship between the first point cloud data and the second point cloud data, in response to the first point cloud data matching the second point cloud data.

9. An apparatus for determining a matching relationship between point cloud data, the apparatus comprising:

at least one processor; and

a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:

extracting a first characteristic associated with first point cloud data and a second characteristic associated with second point cloud data, the first point cloud data and the second point cloud data being acquired for a same object;

performing characteristic matching between the first characteristic and the second characteristic; and

determining, based on the characteristic matching, a matching relationship between the first point cloud data and the second point cloud data

wherein the extracting the first characteristic and the second characteristic comprises:

determining first candidate columnar point cloud data from the first point cloud data, and determining the first characteristic based on the first candidate columnar point cloud data; and

determining second candidate columnar point cloud data from the second point cloud data, and determining the second characteristic based on the second candidate columnar point cloud data, the determining the first characteristic based on the first candidate columnar point cloud data comprises:

clustering point cloud data having an angle between a main direction and a ground normal vector less than a threshold angle in the first candidate columnar point cloud data; and

determining, in response to a clustering result indicating that the first candidate columnar point cloud data comprising columnar point cloud data, a center point, a normal vector, and a radius of the columnar point cloud data as a characteristic point, a normal vector and a radius of the first characteristic.

10. The apparatus according to claim 9 , wherein the first characteristic and the second characteristic each include at least a characteristic point and a normal vector corresponding to the characteristic point.

11. The apparatus according to claim 9 , wherein the extracting the first characteristic and the second characteristic comprises:

determining first ground point cloud data from the first point cloud data, and determining a center point of the first ground point cloud data and a corresponding normal vector as a second characteristic point and a second corresponding normal vector of the first characteristic; and

determining second ground point cloud data from the second point cloud data, and determining a center point of the second ground point cloud data and a corresponding normal vector as a characteristic point and a corresponding normal vector of the second characteristic.

12. The apparatus according to claim 9 , wherein the extracting the first characteristic and the second characteristic comprises:

determining first candidate planar point cloud data from the first point cloud data, and determining the first characteristic based on the first candidate planar point cloud data; and

determining second candidate planar point cloud data from the second point cloud data, and determining the second characteristic based on the second candidate planar point cloud data.

13. The apparatus according to claim 12 , wherein the determining the first characteristic based on the first candidate planar point cloud data comprises:

determining a breakpoint of a thread in the first candidate planar point cloud data;

segmenting the thread based on the breakpoint;

clustering the segmented thread; and

determining, in response to a clustering result indicating that the first candidate planar point cloud data comprising planar point cloud data, a center point of the planar point cloud data and a corresponding normal vector as a third characteristic point and a third corresponding normal vector of the first characteristic.

14. The apparatus according to claim 11 , wherein the performing characteristic matching between the first characteristic and the second characteristic comprises:

converting the first characteristic and the second characteristic into a same coordinate system;

determining a distance between the characteristic point of the first characteristic and the characteristic point of the second characteristic;

determining a difference between the normal vector of the first characteristic and the normal vector of the second characteristic, in response to the distance being less than a threshold distance; and

determining the first characteristic matching the second characteristic, in response to the difference being less than a threshold difference.

15. The apparatus according to claim 9 , wherein the performing characteristic matching between the first characteristic and the second characteristic comprises:

converting the first characteristic and the second characteristic into a same coordinate system;

determining a distance between the characteristic point of the first characteristic and a characteristic point of the second characteristic;

determining a difference between the normal vector and the radius of the first characteristic and a normal vector and a radius of the second characteristic, in response to the distance being less than a threshold distance; and

determining the first characteristic matching the second characteristic, in response to the difference being less than a threshold difference.

16. The apparatus according to claim 9 , wherein the determining a matching relationship between the first point cloud data and the second point cloud data comprises:

determining the matching relationship between the first point cloud data and the second point cloud data, in response to the first point cloud data matching the second point cloud data.

17. A non-transitory computer storage medium storing a computer program, the computer program when executed by one or more processors, causes the one or more processors to perform operations, the operations comprising:

extracting a first characteristic associated with first point cloud data and a second characteristic associated with second point cloud data, the first point cloud data and the second point cloud data being acquired for a same object;

performing characteristic matching between the first characteristic and the second characteristic; and

determining, based on the characteristic matching, a matching relationship between the first point cloud data and the second point cloud data

wherein the extracting the first characteristic and the second characteristic comprises:

determining first candidate columnar point cloud data from the first point cloud data, and determining the first characteristic based on the first candidate columnar point cloud data; and

determining second candidate columnar point cloud data from the second point cloud data, and determining the second characteristic based on the second candidate columnar point cloud data, the determining the first characteristic based on the first candidate columnar point cloud data comprises:

clustering point cloud data having an angle between a main direction and a ground normal vector less than a threshold angle in the first candidate columnar point cloud data; and

determining, in response to a clustering result indicating that the first candidate columnar point cloud data comprising columnar point cloud data, a center point, a normal vector, and a radius of the columnar point cloud data as a characteristic point, a normal vector and a radius of the first characteristic.