Granted Patent B2

US 12,430,871 · App. 17/818,406 · Granted Sep 30, 2025

Inventor: Lele Jia (Beijing, CN)

Assignee: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

G06V10/457G06V10/46G06V10/72G06V10/762

Abstract

Claims (74)

1. An object association method, comprising:

extracting first description information of each of a plurality of first objects from real data, and extracting second description information of each of a plurality of second objects from high-definition map data;

determining, according to the first description information and the second description information, association probabilities between the first objects and the second objects;

determining, according to the association probabilities between the first objects and the second objects, an association result of the first objects and the second objects;

wherein the determining, according to the first description information and the second description information, the association probabilities between the first objects and the second objects comprises:

clustering, according to the first description information and the second description information, the plurality of first objects and the plurality of second objects to obtain a plurality of clustering results;

for each of the clustering results, determining, according to spatial distances between the first objects and the second objects comprised in the clustering result, the association probabilities between the first objects and the second objects comprised in the clustering result;

wherein the clustering, according to the first description information and the second description information, the plurality of first objects and the plurality of second objects to obtain the plurality of clustering results comprises:

performing, according to locations in the first description information and locations in the second description information, spatial clustering on the plurality of first objects and the plurality of second objects to obtain a plurality of initial clustering results;

performing, according to types in the first description information and types in the second description information, type clustering on the plurality of first objects and the plurality of second objects comprised in the initial clustering results to obtain the plurality of clustering results.

2. The method according to claim 1 , wherein for each of the clustering results, the determining, according to spatial distances between the first objects and the second objects comprised in the clustering results, the association probabilities between the first objects and the second objects comprised in the clustering result comprises:

for any first object among the plurality of first objects and any second object among the plurality of second objects:

determining, according to respective spatial distances between the first object and each of the second objects in the clustering result, a first association probability between the first object and the second object;

determining, according to respective spatial distances between the second object and each of the first objects in the clustering result, a second association probability between the second object and the first object;

determining, according to the first association probability and the second association probability, the association probability between the first object and the second object comprised in the clustering result.

3. The method according to claim 2 , wherein the determining, according to the association probabilities between the first objects and the second objects, the association result of the first objects and the second objects comprises:

traversing the plurality of first objects and the plurality of second objects respectively to obtain a plurality of association combinations between the plurality of first objects and the plurality of second objects;

determining, according to the association probabilities between the first objects and the second objects in a one-to-one correspondence in the association combinations, association rates corresponding to the association combinations;

determining, according to the respective association probabilities corresponding to the plurality of association combinations, the association result of the first objects and the second objects.

4. The method according to claim 2 , wherein the determining, according to the first association probability and the second association probability, the association probability between the first object and the second object comprises:

determining a first difference between a preset value and the first association probability, and determining a second difference between the preset value and the second association probability;

determining a product of the first difference and the second difference;

determining a third difference between the preset value and the product as the association probability between the first object and the second object.

5. The method according to claim 4 , wherein the determining, according to the association probabilities between the first objects and the second objects, the association result of the first objects and the second objects comprises:

traversing the plurality of first objects and the plurality of second objects respectively to obtain a plurality of association combinations between the plurality of first objects and the plurality of second objects;

determining, according to the association probabilities between the first objects and the second objects in a one-to-one correspondence in the association combinations, association rates corresponding to the association combinations;

determining, according to the respective association probabilities corresponding to the plurality of association combinations, the association result of the first objects and the second objects.

6. The method according to claim 1 , wherein the determining, according to the association probabilities between the first objects and the second objects, the association result of the first objects and the second objects comprises:

traversing the plurality of first objects and the plurality of second objects respectively to obtain a plurality of association combinations between the plurality of first objects and the plurality of second objects;

determining, according to the association probabilities between the first objects and the second objects in a one-to-one correspondence in the association combinations, association rates corresponding to the association combinations;

determining, according to the respective association probabilities corresponding to the plurality of association combinations, the association result of the first objects and the second objects.

7. The method according to claim 6 , wherein the determining, according to the respective association probabilities corresponding to the plurality of association combinations, the association result of the first objects and the second objects comprises:

determining an association combination corresponding to a maximum association probability as the association result of the first objects and the second objects.

8. The method according to claim 1 , wherein for each of the clustering results, the determining, according to spatial distances between the first objects and the second objects comprised in the clustering results, the association probabilities between the first objects and the second objects comprised in the clustering result comprises:

for any first object among the plurality of first objects and any second object among the plurality of second objects:

determining, according to respective spatial distances between the first object and each of the second objects in the clustering result, a first association probability between the first object and the second object;

determining, according to respective spatial distances between the second object and each of the first objects in the clustering result, a second association probability between the second object and the first object;

determining, according to the first association probability and the second association probability, the association probability between the first object and the second object comprised in the clustering result.

9. An object association apparatus, comprising:

at least one processor; and

a memory communicatively connected to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor is configured to:

extract first description information of each of a plurality of first objects from real data, and extract second description information of each of a plurality of second objects from high-definition map data;

determine, according to the first description information and the second description information, association probabilities between the first objects and the second objects;

determine, according to the association probabilities between the first objects and the second objects, an association result of the first objects and the second objects;

wherein the at least one processor is further configured to:

cluster, according to the first description information and the second description information, the plurality of first objects and the plurality of second objects to obtain a plurality of clustering results;

for each of the clustering results, determine, according to spatial distances between the first objects and the second objects comprised in the clustering result, the association probabilities between the first objects and the second objects comprised in the clustering result;

wherein the at least one processor is further configured to:

perform, according to locations in the first description information and locations in the second description information, spatial clustering on the plurality of first objects and the plurality of second objects to obtain a plurality of initial clustering results;

perform, according to types in the first description information and types in the second description information, type clustering on the plurality of first objects and the plurality of second objects comprised in the initial clustering results to obtain the plurality of clustering results.

10. The apparatus according to claim 9 , wherein the at least one processor is further configured to:

for any first object among the plurality of first objects and any second object among the plurality of second objects:

determine, according to respective spatial distances between the first object and each of second objects in the clustering results, a first association probability between the first object and the second object;

determine, according to respective spatial distances between the second object and each of the first objects in the clustering results, a second association probability between the second object and the first object;

determine, according to the first association probability and the second association probability, the association probability between the first object and the second object comprised in the clustering result.

11. The apparatus according to claim 10 , wherein the at least one processor is further configured to:

determine a first difference between a preset value and the first association probability, and determine a second difference between the preset value and the second association probability; determine a product of the first difference and the second difference; and determine a third difference between the preset value and the product as the association probability between the first object and the second object.

12. The apparatus according to claim 9 , wherein the at least one processor is further configured to:

traverse the plurality of first objects and the plurality of second objects respectively to obtain a plurality of association combinations between the plurality of first objects and the plurality of second objects;

determine, according to the association probabilities between the first objects and the second objects in a one-to-one correspondence in the association combinations, association rates corresponding to the association combinations;

determine, according to the respective association probabilities corresponding to the plurality of association combinations, the association result of the first objects and the second objects.

13. The apparatus according to claim 12 , wherein the at least one processor is further configured to:

determine an association combination corresponding to a maximum association probability as the association result of the first objects and the second objects.

14. A non-transitory computer-readable storage medium stored with computer instructions, wherein the computer instructions are configured to enable a computer to execute steps of:

extracting first description information of each of a plurality of first objects from real data, and extracting second description information of each of a plurality of second objects from high-definition map data;

determining, according to the first description information and the second description information, association probabilities between the first objects and the second objects;

determining, according to the association probabilities between the first objects and the second objects, an association result of the first objects and the second objects;

wherein the determining, according to the first description information and the second description information, the association probabilities between the first objects and the second objects comprises:

clustering, according to the first description information and the second description information, the plurality of first objects and the plurality of second objects to obtain a plurality of clustering results;

for each of the clustering results, determining, according to spatial distances between the first objects and the second objects comprised in the clustering result, the association probabilities between the first objects and the second objects comprised in the clustering result;

wherein the clustering, according to the first description information and the second description information, the plurality of first objects and the plurality of second objects to obtain the plurality of clustering results comprises:

performing, according to locations in the first description information and locations in the second description information, spatial clustering on the plurality of first objects and the plurality of second objects to obtain a plurality of initial clustering results;

performing, according to types in the first description information and types in the second description information, type clustering on the plurality of first objects and the plurality of second objects comprised in the initial clustering results to obtain the plurality of clustering results.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (14)