Traffic volume estimation

• US 10,042,055 B2
• Filed: 04/20/2016
• Issued: 08/07/2018
• Est. Priority Date: 04/20/2016
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: Zhao, Yunjie, Giurgiu, Gavril, Anastassov, Anton
• Primary Examiner(s): Wong, Yuen H
• Application Number:
  US15/133,917
• Publication Number:
  US 20170309171A1
• Time in Patent Office: 839 Days
• CPC Class Codes: G01S 19/13 Receivers
• 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 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: G08G 1/096816 where the complete route is transmitted to the vehicle at once
• CPC Class Codes: G08G 1/096827 where the route is computed onboard
• CPC Class Codes: G08G 1/096838 where the user preferences are taken into account or the user selects one route out of a plurality
• CPC Class Codes: G08G 1/096844 where the complete route is dynamically recomputed based on new data

Abstract

Systems and methods for using a plurality of probe reports to augment a geographic database with traffic volume data. The plurality of probe reports are identified for a road segment for a time period. A probe value is determined for the road segment for the time period based on the plurality of probe reports. A probe probability value is calculated for the road segment for the time period based on the probe value. The probe probability value is adjusted using road attributes. The adjusted probe probability value is used to estimate traffic volume. The geographic database is augmented with the estimated traffic volume.

Claims

1. A method using a plurality of probe reports to estimate a quantity of vehicles on a road segment, the method comprising:

identifying, by a processor, the plurality of probe reports for the road segment in a roadway network acquired at increments over a time period, the roadway network comprising a plurality of road segments;

calculating, by the processor, a weighted probe value (n_ij) for the road segment as a function of the plurality of probe reports weighted by dividing the product of a probe speed and a probe cycle by a length of the road segment for each of the probe reports of the plurality of probe reports;

calculating, by the processor, a probe probability value (p_ij) for the road segment using another function;

2. The method of claim 1, wherein the plurality of probe reports are received from one or more probe vehicles.

3. The method of claim 1, wherein determining the weighted probe value further comprises:

identifying, by the processor, a probe session identifier for each of the plurality of probe reports; and

counting, by the processor, the unique session identifiers for the road segment for the time period.

4. The method of claim 1, wherein the probe probability value is a two dimensional probability distribution function representing a probability for a vehicle to be on the road segment for the time period.

5. The method of claim 1, wherein the road segment is divided into one or more sub-segments and the probe probability value is calculated for the one or more sub-segments.

6. The method of claim 1, wherein the plurality of probe reports include positioning data derived from a GPS (global positioning system) system.

7. The method of claim 1, wherein the weighted probe value is only determined for vehicles over a threshold weight.

8. The method of claim 1, further comprising:

identifying, by the processor, one or more weather conditions related to the road segment; and

adjusting, by the processor, the estimate of the quantity of vehicles based on the one or more weather conditions.

9. The method of claim 1, wherein adjusting the estimate of the quantity of vehicles comprises:

adjusting, by the processor, the estimate of the quantity of vehicles using machine learning techniques.

10. The method of claim 1, wherein the ground truth data is generated from one or more roadside sensors for the road segment.

11. The method of claim 1, wherein the one or more road attributes include a number of lanes.

12. The method of claim 1, further comprising:

calculating, by the processor, the estimate of the quantity of vehicles for the plurality of road segments;

grouping, by the processor, the plurality of road segments into one or more regional tiles;

wherein the estimate of the quantity of vehicles is based on the probe probability values for the plurality of road segments; and

wherein the estimate of the quantity of vehicles is adjusted separately for each of the one more regional tiles.

13. The method of claim 1, further comprising:

generating, by the at least one processor, an estimate of flow rate of vehicles that are on the road segment during the time period, wherein the estimate of flow rate of vehicles is generated based on the probe probability value and one or more roadway attributes related to the road segment;

adjusting, by the at least one processor, the estimate of flow rate of vehicles based on ground truth data; and

controlling, by the at least one processor, traffic volume by transmitting routing instructions to one or more navigation devices based on the adjusted estimate of flow rate of vehicles.

14. A non-transitory computer readable medium including instructions, that when executed by at least one processor, cause the at least one processor to perform a method for using a plurality of probe reports to estimate a quantity of vehicles on a road segment, the method comprising:

receive a plurality of probe reports for a road segment in a roadway network for increments over a time period, the roadway network comprising a plurality of road segments;

weighing each probe report of the plurality of probe reports using a probe speed and a probe cycle for each of the probe reports and a length of the road segment;

determine a weighted probe value for the road segment for the time period based on the weighted plurality of probe reports;

generate a probability distribution function representing a probability value for a vehicle to be on the road segment for the time period using the function;

15. The non-transitory computer readable medium of claim 14, wherein the road segment is divided into one or more sub-segments and the probe probability value is calculated for the one or more sub-segments.

16. An apparatus for using a plurality of probe reports to estimate a quantity of vehicles on a road segment, the 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 configured to store the computer program code configured to, that when executed by the at least one processor, cause the apparatus to at least perform;

identifying the plurality of probe reports for a road segment in a roadway network acquired at increments over a time period, the roadway network comprising a plurality of road segments;

weighing each probe report of the plurality of probe reports using a probe speed and a probe cycle for each of the probe reports of the plurality of probe reports and a length of the road segment;

determining a weighted probe value for the road segment for the time period based on the weighted plurality of probe reports;

calculating a probe probability value for the road segment for the time period using the function;

17. The apparatus of claim 16, wherein the road segment is divided into one or more sub-segments and the probe probability value is calculated for the one or more sub-segments.