TRAFFIC SPEED ESTIMATION USING TEMPORAL AND SPATIAL SMOOTHING OF GPS SPEED DATA

• US 20150006068A1
• Filed: 07/01/2014
• Published: 01/01/2015
• Est. Priority Date: 07/01/2013
• Status: Active Grant

• Current Assignee: Iteris Incorporated
• Original Assignee: Iteris Incorporated
• Inventors: KWON, JAIMYOUNG, PETTY, KARL F., KURZHANSKIY, ALEX A., MOYLAN, ANDREW J.
• Granted Patent: US 9,129,522 B2
• Time in Patent Office: Days
• US Class Current: 701/119
• CPC Class Codes: G06G 7/76 for traffic
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/096716 where the received information does not generate an automatic action on the vehicle control
• CPC Class Codes: G08G 1/20 Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles

Abstract

Estimation of traffic speed includes applying data processing functions to determine missing speed information by smoothing spatial and temporal GPS data to achieve an accurate estimation of link speed over all links of a transportation network at all time periods. This estimation of traffic speed uses one link'"'"'s observed speed information to estimate neighboring links without observed speed information and therefore provides a system and method of processing collected GPS data to obtain a thorough understanding of traffic flow conditions for all represented links without further collection of GPS data. The present invention also provides a framework for analyzing and improving real-time collection of GPS speed data.

Claims

1. A method of determining real-time traffic speed over a plurality of links in a transportation network, comprising:

ingesting collected global positioning system (GPS) data from one or more sources and link data representing one or more links forming a transportation network;

processing the collected GPS data within a computing environment comprised of hardware and software components and a plurality of data processing functions executed by at least one processor and configured to fill in speed values missing from GPS data, by;

initiating a model of rescaled speed estimation by mapping the collected GPS data to the to one or more links comprising a transportation network, identifying a set of closest links neighboring those to which GPS data is mapped, and calculating an initial speed estimate;

building a first profile representing an estimate of free-flow speed from the collected GPS data mapped to the set of closest links, the first profile representing a free-flow speed estimate and enabling a rescaling of speed across all the links, and building a second profile of rescaled speed over a specified initial period by extrapolating observed speed data from the GPS data to the set of closest neighboring links to develop a rescaled speed value;

compressing the rescaled speed value with the first profile representing an estimate of free-flow speed to form the model of rescaled speed estimation from the collected GPS data mapped to the one or more links;

smoothing the collected GPS data and the model of re-scaled speed estimation to supply missing values among the collected GPS data, by applying a plurality of different values of rescaled speed and comparing the different values of rescaled speed with collected values relative to at least one link l and at least one time period u; and

estimating a link speed for all links in the transportation network at all time periods and generating output data representative of the link speed.

2. The method of claim 1, wherein the collected GPS data is processed probe data that reflects traffic speed on a transportation network.

3. The method of claim 1, wherein the identifying a set of closest links neighboring those represented in incoming GPS data sets further comprising performing a network neighbor calculation with a network distance limit to determine the closest links by degrees of separation by traversing a geographical area comprising the one or more links of the transportation network, locating all neighboring upstream and downstream links within a specified degree of separation of connectivity from a downstream node l, excluding links of different road classes from l, and maintaining a maximum length of closest neighboring link candidates.

4. The method of claim 1, wherein the identifying a set of closest links neighboring those represented in incoming GPS data sets further comprising performing a network neighbor calculation with a road distance limit to determine the closest links in the network within a fixed distance by traversing a geographical area comprising the one or more links of the transportation network, locating all neighboring upstream and downstream links within a specified maximum distance value from a current link l, and excluding links of different road classes from l.

5. The method of claim 1, wherein the smoothing the collected GPS data and the model of re-scaled speed estimation further comprises applying a Bayesian update by starting with a grand median of a rescaled speed value, and updating the grand median of the rescaled speed value based on a current observed value from current and neighboring links.

6. The method of claim 1, wherein the smoothing the collected GPS data and the model of re-scaled speed estimation further comprises examining a temporal median as a possible candidate for a missing speed value.

7. The method of claim 1, wherein the estimating a link speed for all links in the transportation network at all time periods and generating output data representative of the link speed further comprising re-scaling a resultant speed value back to the initial speed estimate to yield the final estimate of the link speed.

8. The method of claim 1, wherein the generating output data representative of the link speed further comprises providing link speed estimates to enable at least one of real-time dynamic routing of all aggregated traffic in a transportation network comprised of inter-connected road segments, performance of operational analytics for roadway infrastructure management, visualization of traffic data on a user interface.

9. A method of filling in speed values missing from GPS data for a determination real-time traffic speed over a plurality of links in a transportation network, comprising:

determining an initial link speed estimate from collected GPS data mapped to one or more links comprising a transportation network;

calculating at least one set of neighboring links using a network distance limit to identify the at least one set of neighboring links at least within a specified degree of separation and a road distance limit to identify the at least one set of neighboring links within a fixed distance along a link;

generating a model of re-scaled speed estimation from the collected GPS data mapped to the one or more links, by;

estimating a free-flow speed using the initial link speed estimate, and re-scaling the initial link speed estimate using the free-flow speed;

building a rescaled speed profile comprised of a link profile represented by an hourly median value over a specific period of time for a particular link, a global profile represented by a median value across all links in the one or more links;

extracting a representative profile by performing a cluster analysis on re-scaled speed profiles, by calculating a cluster median profile and building a median profile for each road class for profile-eligible links;

snapping known GPS data to the one or more links using the re-scaled speed value; and

smoothing the collected GPS data by mapping the model of the re-scaled speed estimation to the one or more links comprising the transportation infrastructure network by applying a plurality of different values of re-scaled speed estimation for each observation of a link l, and comparing those different values with collected GPS data relative to at least one link l and at least one time period u.

10. The method of claim 9, wherein the collected GPS data is processed probe data that reflects traffic speed on a transportation network.

11. The method of claim 9, wherein the network distance limit determines the closest links by degrees of separation by traversing a geographical area comprising the one or more links of the transportation network, locating all neighboring upstream and downstream links within a specified degree of separation of connectivity from a downstream node l, excluding links of different road classes from l, and maintaining a maximum length of closest neighboring link candidates.

12. The method of claim 9, wherein the road distance limit determines the closest links in the network within a fixed distance by traversing a geographical area comprising the one or more links of the transportation network, locating all neighboring upstream and downstream links within a specified maximum distance value from a current link l, and excluding links of different road classes from l.

13. The method of claim 9, wherein the extracting a representative profile by performing a cluster analysis on re-scaled speed profiles further comprises applying a road class median profile for non-profile-eligible links

14. The method of claim 9, wherein a profile-eligible link is a link with at least twelve hourly data points in its profile.

15. The method of claim 9, wherein the smoothing the collected GPS data and the model of re-scaled speed estimation further comprises applying a Bayesian update by starting with a grand median of a rescaled speed value, and updating the grand median of the rescaled speed value based on a current observed value from current and neighboring links.

16. The method of claim 9, wherein the smoothing the collected GPS data and the model of re-scaled speed estimation further comprises examining a temporal median as a possible candidate for a missing speed value.

25. The link speed estimation system of claim 12, wherein the GPS data is processed probe data that reflects traffic speed on a transportation network.

17. A link speed estimation system, comprising:

a plurality of input including collected GPS data mapped to one or more links comprising a transportation network;

a plurality of data processing modules, executed by at least one processor within a computing environment, and configured to supply missing speed values among the collected GPS data by utilizing observed information from one link to estimate neighboring links without observed information, the plurality of data processing modules including a preparation module configured to model a re-scaled speed estimation from the collected GPS data mapped to the one or more links by locating a set of closest neighboring links to the one or more links to which collected GPS data is mapped, build a profile of rescaled speed for collected GPS data over a specified initial period at a link and a time period, and perform a cluster analysis to extrapolate observed speed data from the collected GPS data to the set of closest neighboring links to develop a rescaled speed value, and a smoothing module configured to process the collected GPS data by mapping the model of the re-scaled speed estimation to the one or more links comprising the transportation infrastructure network, apply a plurality of different values of re-scaled speed estimation for each observation of a link l, and compare those different values with collected GPS values relative to at least one link l and at least one time period u; and

an estimation module configured to determine a link speed estimate for all links 1 in the transportation network at all time periods u,

wherein output data generated by the estimation module enables dynamic, real-time routing information for traffic across the one or more links of the transportation network.

18. The link speed estimation system of claim 17, wherein the dynamic, real-time routing information comprises at least one instruction for alternate routing of traffic across the transportation network in response to an increase or decrease in the link speed estimate for any link l at any time period u.

19. The link speed estimation system of claim 17, wherein the dynamic, real-time routing information is used to generate traffic flow data for visualization on an animated map.

20. The link speed estimation system of claim 17, wherein the output data is provided via a third-party application for visualization on in-vehicle telematics equipment.

21. The link speed estimation system of claim 17, wherein the output data is provided via a third-party application for visualization on a mobile device.

22. The link speed estimation system of claim 17, wherein the output data is provided via a third-party application for media distribution.

23. The link speed estimation system of claim 22, wherein the dynamic, real-time routing information is used for traffic planning and operational analytics for transportation infrastructure management encompassing the one or more links.

24. The link speed estimation system of claim 22, wherein transportation infrastructure management includes at least one of planning for congestion alleviation for the one or more links, and efficient operation of mass transit vehicles for the one or more links.