Systems and methods for mapping based on multi-journey data

Patent metadata

Field	Value
Publication number	US-10296812-B2
Application number	US-201715620167-A
Country	US
Kind code	B2
Filing date	Jun 12, 2017
Priority date	Jan 4, 2017
Publication date	May 21, 2019
Grant date	May 21, 2019

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 method performed by an apparatus, comprising:
receiving a first set of object data collected during a previously traveled first journey;
receiving a second set of object data collected during a previously traveled second journey;
determining a similarity metric between the first set of object data and the second set of object data, wherein 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;
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; and
producing map data based on the at least one object cluster.

2. The method of claim 1 , wherein the similarity metric is based on an object type.

3. The method of claim 2 , wherein the similarity metric is determined for a sign object type, and wherein the method further comprises determining a second similarity metric for a lane marker object type.

4. The method of claim 1 , wherein the first set of object data and the second set of object data comprise sign data, and wherein the similarity metric indicates the distance between points for a sign from different journeys.

5. The method of claim 1 , wherein the first set of object data and the second set of object data comprise lane marker data, and wherein the similarity metric indicates at least one of a minimum distance between the lane marker data from different journeys or between points of the lane marker data within an area.

6. The method of claim 1 , wherein clustering the first set of object data and the second set of object data comprises performing hierarchical clustering, wherein performing hierarchical clustering comprises performing multiple different steps of clustering.

7. The method of claim 6 , wherein a first step of clustering comprises clustering based on a first distance parameter and a second step of clustering comprises clustering based on a second distance parameter, wherein the second distance parameter is less than the first distance parameter.

8. The method of claim 1 , wherein clustering the first set of object data and the second set of object data comprises performing spectral clustering.

9. The method of claim 1 , further comprising performing bundle adjustment based on the at least one object cluster.

10. The method of claim 1 , wherein clustering is performed within each of one or more association tiles.

11. The method of claim 1 , wherein producing the map data includes refining map data based on the at least one object cluster.

12. The method of claim 1 , further comprising transmitting the produced map data to at least one vehicle.

13. The method of claim 1 , wherein the object data comprises object pose information.

14. An apparatus, comprising:
a memory;
a processor coupled to the memory, wherein the processor is configured to:
receive a first set of object data collected during a previously traveled first journey;
receive a second set of object data collected during a previously traveled second journey;
determine a similarity metric between the first set of object data and the second set of object data, wherein 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;
cluster 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; and
produce map data based on the at least one object cluster.

15. The apparatus of claim 14 , wherein the similarity metric is based on an object type.

16. The apparatus of claim 15 , wherein the processor is configured to determine the similarity metric for a sign object type, and wherein the processor is configured to determine a second similarity metric for a lane marker object type.

17. The apparatus of claim 14 , wherein the first set of object data and the second set of object data comprise sign data, and wherein the similarity metric indicates the distance between points for a sign from different journeys.

18. The apparatus of claim 14 , wherein the first set of object data and the second set of object data comprise lane marker data, and wherein the similarity metric indicates at least one of a minimum distance between the lane marker data from different journeys or between points of the lane marker data within an area.

19. The apparatus of claim 14 , wherein the processor is configured to cluster the first set of object data and the second set of object data by performing hierarchical clustering, wherein performing hierarchical clustering comprises performing multiple different steps of clustering.

20. The apparatus of claim 19 , wherein a first step of clustering comprises clustering based on a first distance parameter and a second step of clustering comprises clustering based on a second distance parameter, wherein the second distance parameter is less than the first distance parameter.

21. The apparatus of claim 14 , wherein the processor is configured to cluster the first set of object data and the second set of object data by performing spectral clustering.

22. The apparatus of claim 14 , wherein the processor is configured to perform bundle adjustment based on the at least one object cluster.

23. The apparatus of claim 14 , wherein the processor is configured to perform clustering within each of one or more association tiles.

24. The apparatus of claim 14 , wherein the processor is configured to produce the map data by refining map data based on the at least one object cluster.

25. The apparatus of claim 14 , wherein the processor is configured to transmit the produced map data to at least one vehicle.

26. The apparatus of claim 14 , wherein the object data comprises object pose information.

27. A non-transitory tangible computer-readable medium storing computer executable code, comprising:
code for causing an electronic device to receive a first set of object data collected during a previously traveled first journey;
code for causing the electronic device to receive a second set of object data collected during a previously traveled second journey;
code for causing the electronic device to determine a similarity metric between the first set of object data and the second set of object data, wherein 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;
code for causing the electronic device to cluster 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; and
code for causing the electronic device to produce map data based on the at least one object cluster.

28. The computer-readable medium of claim 27 , wherein the similarity metric is based on an object type.

29. An apparatus, comprising:
means for receiving a first set of object data collected during a previously traveled first journey;
means for receiving a second set of object data collected during a previously traveled second journey;
means for determining a similarity metric between the first set of object data and the second set of object data, wherein the similarity metric indicates a distanc

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