Detecting road condition changes from probe data

• US 9,361,797 B1
• Filed: 12/11/2014
• Issued: 06/07/2016
• Est. Priority Date: 12/11/2014
• Status: Active Grant

• Current Assignee: HERE Global B.V. (HERE Holding Corporation)
• Original Assignee: HERE Global B.V. (HERE Holding Corporation)
• Inventors: Chen, Xin, Zhukov, Vladimir
• Primary Examiner(s): Jeanglaud, Gertrude Arthur
• Application Number:
  US14/567,106
• Publication Number:
  US 20160171884A1
• Time in Patent Office: 544 Days
• Field of Search: 701/117, 701/301, 701/470, 340/436
• US Class Current: 1/1
• CPC Class Codes: G01C 7/04 involving a vehicle which moves along the profile to be traced
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0141 for traffic information dissemination

Abstract

Systems, methods, and apparatuses are disclosed for identifying anomalies or changes in road conditions on a roadway location. An initial low rank data matrix of initial vehicle probe data at a plurality of different times for a roadway location is provided, where the initial low rank data matrix represents a baseline of road conditions for the roadway location. A plurality of additional vehicle probe data from at least one vehicle at the roadway location is received. The additional vehicle probe data is added to the initial vehicle probe data of the initial low rank data matrix. The updated data matrix with the compiled probe data is decomposed into a low rank data matrix and a sparse data matrix. A change at the roadway location is identified based on the probe data in the sparse data matrix.

Claims

1. A method comprising:

providing an initial low rank data matrix of initial vehicle probe data at a plurality of different times for a roadway location, the initial low rank data matrix representing a baseline of road conditions for the roadway location;

receiving, using a processor, a plurality of additional vehicle probe data from at least one vehicle at the roadway location;

adding the additional vehicle probe data to the initial vehicle probe data of the initial low rank data matrix to provide an updated data matrix comprising compiled probe data;

decomposing the compiled probe data in the updated data matrix into a low rank data matrix and a sparse data matrix; and

identifying a change at the roadway location based on probe data in the sparse data matrix.

2. The method of claim 1, wherein the change is identified when a number of probe data in the sparse data matrix reaches a threshold.

3. The method of claim 2, further comprising:

determining that the change at the roadway location is permanent; and

updating the low rank data matrix with probe data representing the change.

4. The method of claim 3, wherein the low rank data matrix is updated through a decomposition of at least a portion of the data matrix into a new low rank data matrix and a new sparse data matrix, wherein the new low rank data matrix comprises probe data representing the change.

5. The method of claim 2, further comprising:

reporting the change in the roadway location to a navigation device.

6. The method of claim 1, wherein the initial vehicle probe data and the additional vehicle probe data comprise one or more of the following probe data characteristics:

speed, heading, geographic location, timestamp, acceleration or deceleration data, or vehicle identification.

7. The method of claim 1, wherein the initial vehicle probe data and the additional vehicle probe data comprise lane marking probe data.

8. The method of claim 7, wherein the vehicle sensor is a LIDAR sensor, a radar sensor, or a camera sensor.

9. The method of claim 1, wherein the determining is performed by the processor using a machine learning algorithm.

10. The method of claim 9, wherein the machine learning algorithm is a principal component analysis algorithm or a robust principal component analysis algorithm.

11. A method comprising:

providing an initial low rank data matrix of initial vehicle probe data at a plurality of different times for a roadway location, the initial low rank data matrix representing a baseline of road conditions for the roadway location;

receiving, using a processor, a plurality of additional vehicle probe data from at least one vehicle at the roadway location;

adding the additional vehicle probe data to the initial vehicle probe data of the initial low rank data matrix to provide an updated data matrix comprising compiled probe data;

decomposing, using a robust principal component analysis algorithm, the compiled probe data in the updated data matrix into a low rank data matrix and a sparse data matrix;

identifying a change at the roadway location based on probe data in the sparse data matrix when a number of probe data in the sparse data matrix reaches a threshold;

reporting the change in the roadway location to a navigation device; and

decomposing at least a portion of the data matrix into a new low rank data matrix and a new sparse data matrix, wherein the new low rank data matrix comprises probe data representing the change.

12. An apparatus comprising:

at least one processor; and

at least one memory including computer program code for one or more programs;

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to at least perform;

provide an initial low rank data matrix of initial vehicle probe data at a plurality of different times for a roadway location, the initial low rank data matrix representing a baseline of road conditions for the roadway location;

receive a plurality of additional vehicle probe data from at least one vehicle at the roadway location;

add the additional vehicle probe data to the initial vehicle probe data of the initial low rank data matrix to provide an updated data matrix comprising compiled probe data;

decompose the compiled probe data in the updated data matrix into a low rank data matrix and a sparse data matrix; and

identify a change at the roadway location based on probe data in the sparse data matrix.

13. The apparatus of claim 12, wherein the change is identified when a number of probe data in the sparse data matrix reaches a threshold.

14. The apparatus of claim 13, wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:

determine that the change at the roadway location is permanent; and

decompose at least a portion of the data matrix into a new low rank data matrix and a new sparse data matrix, wherein the new low rank data matrix comprises probe data representing the change.

15. The apparatus of claim 13, wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:

report the change in the roadway location to a navigation device.

16. The apparatus of claim 12, wherein the initial vehicle probe data and the additional vehicle probe data comprise one or more of the following probe data characteristics:

speed, heading, geographic location, timestamp, vehicle acceleration and deceleration, or vehicle identification.

17. The apparatus of claim 12, wherein the initial vehicle probe data and the additional vehicle probe data comprise lane marking probe data.

18. The apparatus of claim 17, wherein the vehicle sensor is a LIDAR sensor, a radar sensor, or a camera sensor.

19. The apparatus of claim 12, wherein the computer program code is a machine learning algorithm.

20. The apparatus of claim 19, wherein the machine learning algorithm is a principal component analysis algorithm or a robust principal component analysis algorithm.