Systems and methods for mapping based on multi-journey data

Patent metadata

Field	Value
Publication number	US-11120296-B2
Application number	US-201916375761-A
Country	US
Kind code	B2
Filing date	Apr 4, 2019
Priority date	Jan 4, 2017
Publication date	Sep 14, 2021
Grant date	Sep 14, 2021

Abstract

A method performed by an apparatus is described. The method includes receiving a first set of object data corresponding to a first journey. The method also includes receiving a second set of object data corresponding to a second journey. The method further includes determining a similarity metric between the first set of object data and the second set of object data. The similarity metric indicates a distance between the first set of object data and the second set of object data for at least one object. The method additionally includes clustering the first set of object data and the second set of object data for the at least one object based on the similarity metric to produce at least one object cluster. The method also includes producing map data based on the at least one object cluster.

First claim

What is claimed is:

1. A vehicle, comprising:
a memory;
a processor coupled to the memory, wherein the processor is configured to:
receive first object data collected by the vehicle during a first journey, wherein the first object data represents at least one object;
transmit the first object data;
receive map data based on a similarity metric between the at least one object in the first object data and the at least one object represented by an object cluster, wherein the object cluster is generated based on image data received from a plurality of different vehicles; and
localize the vehicle based on the received map data.

2. The vehicle of claim 1 , wherein the processor is configured to:
receive second object data collected by the vehicle during the first journey;
transmit the second object data; and
receive second map data based on the second object data and third object data, wherein the third object data is collected during a second journey traveled by the vehicle.

3. The vehicle of claim 1 , wherein the similarity metric is based on a type of the at least one object.

4. The vehicle of claim 3 , wherein the similarity metric is based on a sign object type, and wherein a second similarity metric is based on a lane marker object type, and wherein the similarity metric is different than the second similarity metric.

5. The vehicle of claim 1 , wherein the object cluster is based on feature points of the object.

6. The vehicle of claim 5 , wherein the map data is based on a bundle adjustment that is based on the at least one object cluster.

7. The vehicle of claim 5 , wherein the object cluster is based on each of one or more association tiles.

8. The vehicle of claim 5 , wherein the first object data comprises at least one of frames, object features, camera pose information, two-dimensional (2D) object location data, three-dimensional (3D) object position data, or 3D object orientation data.

9. The vehicle of claim 1 , wherein the map data comprises a map or a map update.

10. The vehicle of claim 8 , wherein the at least one object comprises a sign, a lane, a lane marker, or a spline.

11. The vehicle of claim 1 , wherein the map data is received after completion of the first journey.

12. The vehicle of claim 8 , wherein the map data corresponds to one or more tiles.

13. A method, comprising:
receiving first object data collected by a vehicle during a first journey, wherein the first object data represents at least one object;
transmitting the first object data;
receiving map data based on a similarity metric between the at least one object in the first object data and the at least one object represented by an object cluster wherein the object cluster is generated based on image data received from a plurality of different vehicles; and
localizing the vehicle based on the received map data.

14. The method of claim 13 , further comprising:
receiving second object data collected by the vehicle during the first journey;
transmitting the second object data; and
receiving second map data based on the second object data and third object data, wherein the third object data is collected during a second journey traveled by the vehicle.

15. The method of claim 13 , wherein the similarity metric is based on a type of the at least one object.

16. The method of claim 15 , wherein the similarity metric is based on a sign object type, and wherein a second similarity metric is based on a lane marker object type, and wherein the similarity metric is different than the second similarity metric.

17. The method of claim 13 , wherein the object cluster is based on feature points of the object.

18. The method of claim 17 , wherein the map data is based on a bundle adjustment that is based on the at least one object cluster.

19. The method of claim 17 , wherein the object cluster is based on each of one or more association tiles.

20. The method of claim 17 , wherein the first object data comprises at least one of frames, object features, camera pose information, two-dimensional (2D) object location data, three-dimensional (3D) object position data, or 3D object orientation data.

21. The method of claim 13 , wherein the map data comprises a map or a map update.

22. The method of claim 20 , wherein the at least one object comprises a sign, a lane, a lane marker, or a spline.

23. The method of claim 13 , wherein the map data is received after completion of the first journey.

24. The method of claim 20 , wherein the map data corresponds to one or more tiles.

25. An apparatus, comprising:
a memory;
a processor coupled to the memory, wherein the processor is configured to:
receive first object data from a vehicle, wherein the first object data is collected by the vehicle during a first journey, wherein the first object data represents at least one object; and
transmit map data based on a similarity metric between the at least one object in the first object data and the at least one object represented by an object cluster wherein the object cluster is generated based on image data received from a plurality of different vehicles.

26. The apparatus of claim 25 , wherein the processor is configured to:
receive, from the vehicle, second object data collected by the vehicle during the first journey; and
send second map data based on the second object data and third object data, wherein the third object data is collected during a second journey.

27. The apparatus of claim 25 , wherein the similarity metric is based on a type of the at least one object.

28. The apparatus of claim 27 , wherein the similarity metric is based on a sign object type, and wherein the processor is configured to determine a second similarity metric based on a lane marker object type, and wherein the similarity metric is different than the second similarity metric.

29. The apparatus of claim 25 , wherein the processor is configured to
generate the object cluster based on feature points of the object.

30. The apparatus of claim 29 , wherein the processor is configured to perform bundle adjustment based on the object cluster.

31. The apparatus of claim 29 , wherein the processor is configured to perform clustering within each of one or more association tiles.

32. The apparatus of claim 25 , wherein the first object data comprises at least one of frames, object features, camera pose information, two-dimensional (2D) object location data, three-dimensional (3D) object position data, or 3D object orientation data.

33. The apparatus of claim 25 , wherein the map data comprises a map or a map update.

34. The apparatus of claim 32 , wherein the at least one object comprises a sign, a lane, a lane marker, or a spline.

35. The apparatus of claim 25 , wherein the map data is transmitted after completion of the first journey.

36. The apparatus of claim 32 , wherein the map data corresponds to one or more tiles.

37. A method, comprising:
receiving first object data from a vehicle, wherein the first object data is collected by the vehicle during a first journey, wherein the first object data represents at least one object; and
transmitting map data based on a similarity metric between the at least one object in the

Assignees

• Qualcomm Inc

Inventors

• Dabeer Onkar Jayant
• Somasundaram Kiran
• Gowaikar Radhika Dilip
• Sukhavasi Ravi Teja

Classifications

• G06V10/7625

  Hierarchical techniques, i.e. dividing or merging patterns to obtain a tree-like representation; Dendograms · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G06V10/7715

  Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods · CPC title

• G06V10/763

  Non-hierarchical techniques, e.g. based on statistics of modelling distributions · CPC title

• G06F18/231

  Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram · CPC title