Filtering road traffic condition data obtained from mobile data sources

• US 9,449,508 B2
• Filed: 07/29/2011
• Issued: 09/20/2016
• Est. Priority Date: 03/03/2006
• Status: Active Grant

• Current Assignee: Inrix Incorporated
• Original Assignee: Inrix Incorporated
• Inventors: Chapman, Craig H., Downs, Oliver B., Barker, Alec, Burns, Mitchel A. Jr., Love, Scott R.
• Primary Examiner(s): MOYER, DALE S
• Application Number:
  US13/194,822
• Publication Number:
  US 20110288756A1
• Time in Patent Office: 1,880 Days
• Field of Search: 364/805, 701117-119, 701400-451, 340/539.2, 340/907, 340909-910, 340916-917, 340933-943, 3409951-996, 382104-105, 382/149, 342450-458, 342461-465, 3423572-35778, 348/149
• US Class Current: 1/1
• CPC Class Codes: G08G 1/0104 Measuring and analyzing of parameters relative to traffic conditions
• 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 1/052 with provision for determining speed or overspeed speed measuring in general G01P
• CPC Class Codes: G08G 1/056 with provision for distinguishing direction of travel
• CPC Class Codes: G08G 1/065 by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
• CPC Class Codes: H04W 88/02 Terminal devices

Abstract

Techniques are described for assessing road traffic conditions in various ways based on obtained traffic-related data, such as data samples from vehicles and other mobile data sources traveling on the roads, as well as in some situations data from one or more other sources (such as physical sensors near to or embedded in the roads). The assessment of road traffic conditions based on obtained data samples may include various filtering and/or conditioning of the data samples, and various inferences and probabilistic determinations of traffic-related characteristics from the data samples. In some situations, the filtering of the data samples includes identifying data samples that are inaccurate or otherwise unrepresentative of actual traffic condition characteristics, such as data samples that are not of interest based at least in part on roads with which the data samples are associated and/or that otherwise reflect vehicle locations or activities that are not of interest.

Claims

1. A computer-implemented method for assessing data samples representing vehicles traveling on roads, the method comprising:

receiving an indication of one or more segments of one or more roads, each road segment having multiple associated data samples that each are reported by one of multiple vehicles and indicate a reported location of the vehicle that corresponds to the road segment; and

for a first road segment of the one or more road segments,

automatically determining, by one or more configured computing systems, that the multiple data samples associated with the first road segment are not of interest based at least in part on identifying the first road segment as being of a functional road class that is not of interest; and

providing, by the one or more configured computing systems, one or more indications to exclude the multiple data samples associated with the first road segment from later use, to enable other data samples to be available for use in facilitating travel.

2. The method of claim 1 further comprising, for a second road segment of the one or more road segments that is distinct from the first road segment:

automatically analyzing, by the one or more configured computing systems, the multiple associated data samples for the second road segment to determine a subset of those data samples that are unrepresentative of actual vehicle travel on the second road segment, one or more of the data samples of the determined subset each indicating a reported location for an associated vehicle that does not correspond to the actual vehicle travel on the second road segment; and

providing, by the one or more configured computing systems, one or more indications to exclude the data samples of the determined subset from later use, so that the other data samples of the multiple associated data samples for second road segment are available for use in facilitating travel on the second road segment,

and wherein the determining of the subset of data samples for the second road segment includes determining that the reported vehicle locations for the one or more data samples of the subset correspond to a section of road that is not of interest for use in representing the actual vehicle travel on the second road segment.

3. The method of claim 2 wherein the section of road is a subset of lanes from multiple lanes that are part of the second road segment.

4. The method of claim 2 wherein the section of road is at least part of one or more of a ramp for the second road segment, a collector/distributor road associated with the road of the second road segment, a collector/distributor lane associated with the road of the second road segment, a feeder lane associated with the road of the second road segment, a shoulder of the road of the second road segment, and a breakdown area for the road of the second road segment.

5. The method of claim 2 wherein the determining of the subset of data samples from the multiple data samples associated with the second road segment includes selecting those data samples based on those data samples also being associated with one or more other distinct road segments.

6. The method of claim 2 wherein the determining of the subset of data samples includes comparing the data samples of the subset to at least some of other data samples of the multiple data samples associated with the second road segment.

7. The method of claim 2 wherein the determining of the subset of data samples includes identifying a subset of the actual vehicle travel on the second road segment that is of interest or that is not of interest, and determining whether the data samples of the determined subset correspond to the identified subset of the actual vehicle travel.

8. The method of claim 2 wherein the multiple associated data samples for the second road segment further include multiple data samples that each are reported from a traffic sensor monitoring the second road segment and each reflect one or more locations on the second road segment corresponding to the traffic sensor.

9. The method of claim 8 further comprising receiving one or more indications of a plurality of data samples that each are reported from one of multiple traffic sensors monitoring multiple road segments, and, for each of at least some of the plurality of data samples, associating the data sample with at least one of the road segments based at least in part on the one or more locations reflected by the data sample matching one or more locations associated with each of the at least one road segments.

10. The method of claim 2 wherein the determining of the subset of data samples includes identifying multiple data samples that are reported by a single vehicle traveling on the second road segment, and determining that the identified multiple data samples are unrepresentative based on combining information from the identified multiple data samples.

11. The method of claim 2 wherein the multiple associated data samples for the second road segment each further reflect a reported time at which the vehicle for the data sample is at the reported location, and wherein the automatic analyzing of the multiple associated data samples for the second road segment further corresponds to a predetermined period of time such that the actual vehicle travel on the second road segment is travel during the predetermined period of time.

12. The method of claim 1 further comprising automatically determining that the multiple data samples associated with a second road segment of the one or more road segments are not of interest based at least in part on a determination of an amount of actual vehicle traffic on the second road segment, and providing one or more indications to exclude the multiple data samples associated with the second road segment from later use.

13. The method of claim 1 further comprising automatically determining that the multiple data samples associated with a second road segment of the one or more road segments are not of interest based at least in part on a determination of an amount of variability of vehicle traffic on the second road segment, and providing one or more indications to exclude the multiple data samples associated with the second road segment from later use.

14. The method of claim 13 further comprising, before the determining that the multiple data samples associated with the second road segment are not of interest, assessing the variability of the vehicle traffic on the second road segment, and determining that the second road segment is not of interest based at least in part on the assessing.

15. The method of claim 14 wherein the assessing of the variability of the vehicle traffic on the second road segment is based on traffic during each of multiple time periods, and wherein a length of each of the multiple time periods is one of an hour, a day, and a week.

16. The method of claim 14 wherein the determining that the second road segment is not of interest is further based at least in part on an amount of the assessed variability being determined to be low.

17. The method of claim 13 wherein the determined amount of variability of vehicle traffic on the second road segment includes at least one of intra-day variability in the vehicle traffic and inter-day variability in the vehicle traffic.

18. The method of claim 1 further comprising automatically determining that the multiple data samples associated with a second road segment of the one or more road segments are not of interest based at least in part on a determination of an amount of actual traffic congestion on the second road segment, and providing one or more indications to exclude the multiple data samples associated with the second road segment from later use.

19. The method of claim 1 further comprising automatically determining that the multiple data samples associated with a second road segment of the one or more road segments are not of interest based at least in part on a determination of an amount of variability of traffic congestion on the second road segment, and providing one or more indications to exclude the multiple data samples associated with the second road segment from later use.

20. The method of claim 19 further comprising, before the determining that the multiple data samples associated with the second road segment are not of interest, assessing the variability of the traffic congestion on the second road segment, and determining that the second road segment is not of interest based at least in part on the assessing.

21. The method of claim 20 wherein the assessing of the variability of the traffic congestion on the second road segment is based on traffic during each of multiple time periods, and wherein a length of each of the multiple time periods is one of an hour, a day, and a week.

22. The method of claim 20 wherein the determining that the second road segment is not of interest is further based at least in part on an amount of the assessed variability being determined to be low.

23. The method of claim 19 wherein the determined amount of variability of traffic congestion on the second road segment includes at least one of intra-day variability in the traffic congestion and inter-day variability in the traffic congestion.

24. The method of claim 1 further comprising receiving one or more indications of a plurality of data samples that each indicate a reported location of a vehicle, and associating each of at least some of the plurality of data samples with at least one of the road segments based at least in part on the reported location of the data sample corresponding to one or more locations associated with each of the at least one road segments.

25. The method of claim 24 wherein each of the plurality of data samples has an associated heading of the vehicle for the data sample, and wherein the associating of a data sample with a road segment is further based at least in part on the associated heading of the vehicle for the data sample corresponding to one or more headings associated with the road segment.

26. A non-transitory computer-readable medium having stored contents that configure a computing device to assess data samples representing traveling vehicles, by performing a method comprising:

receiving, by the configured computing device, an indication of multiple data samples that reflect reported travel characteristics of multiple vehicles traveling on one or more roads, the reported travel characteristics for the multiple data samples reflecting locations of the multiple vehicles;

automatically determining, by the configured computing device, that a first road of the one or more roads is not of interest based at least in part on an amount of assessed variability in vehicle traffic on the first road during one or more days;

automatically determining, by the configured computing device, to exclude, from further use, a first group of one or more data samples of the multiple data samples as being unrepresentative of actual vehicle travel of interest on the one or more roads, the determining to exclude being based at least in part on the data samples of the first group corresponding to vehicle traffic on the first road; and

providing one or more indications that the data samples of the first group are unrepresentative of the actual vehicle travel of interest on the one or more roads, to enable other of the multiple data samples that are not in the first group to be available for use in facilitating travel on the one or more roads.

27. The non-transitory computer-readable medium of claim 26 wherein the method further comprises determining that one or more other data samples of the multiple data samples that are not part of the first group are also unrepresentative of actual vehicle travel of interest on the one or more roads, the determining that one or more other data samples are also unrepresentative including identifying one or more activities in which one or more vehicles are engaged based on reported travel characteristics of the one or more other data samples, and including determining that the identified one or more activities are not of interest.

28. The non-transitory computer-readable medium of claim 26 wherein the method further comprises determining that one or more other data samples of the multiple data samples that are not part of the first group are also unrepresentative of actual vehicle travel of interest on the one or more roads, the determining that one or more other data samples are also unrepresentative being based at least in part on one or more associated vehicle speeds for the one or more other data samples relative to other vehicle speeds for actual vehicle travel on the one or more roads.

29. The non-transitory computer-readable medium of claim 26 wherein the stored contents are instructions that, when executed, program the configured computing device to perform the method, and wherein the computer-readable medium is a memory of the configured computing device.

30. The non-transitory computer-readable medium of claim 26 wherein the method further comprises, before the determining that the first road is not of interest, assessing the variability in the vehicle traffic on the first road during the one or more days.

31. The non-transitory computer-readable medium of claim 26 wherein the assessed variability in vehicle traffic on the first road during one or more days is intra-day variability in vehicle traffic on the first road.

32. The non-transitory computer-readable medium of claim 26 wherein the assessed variability in vehicle traffic on the first road during one or more days is inter-day variability in vehicle traffic on the first road.

33. The non-transitory computer-readable medium of claim 26 wherein the assessed variability in vehicle traffic on the first road during one or more days is based on variability in vehicle traffic volume on the first road.

34. The non-transitory computer-readable medium of claim 26 wherein the assessed variability in vehicle traffic on the first road during one or more days is based on variability in vehicle traffic congestion on the first road.

35. The non-transitory computer-readable medium of claim 26 wherein the assessed variability in vehicle traffic on the first road corresponds to an indicated road segment of the first road, and wherein the determining to exclude the first group of one or more data samples is further based on determining that the one or more data samples of the first group reflect locations associated with the indicated road segment.

36. A computing system configured to assess data samples representing traveling vehicles, comprising:

one or more processors;

a first component that is configured to, when executed by at least one of the one or more processors, and for each of multiple roads, receive an indication of multiple data samples for the road that have associated information, each of the multiple data samples being associated with one of multiple vehicles traveling near the road, the associated information for each of the multiple data samples reflecting a location near the road of the one associated vehicle for the data sample; and

a data sample filterer component that is configured to, when executed by at least one of the one or more processors,

for a first road of the multiple roads, automatically determine to exclude the multiple data samples for the first road from further use based at least in part on the first road being determined to not be of interest based on an amount of assessed variability of vehicle traffic on the first road during one or more days;

for a second road of the multiple roads, automatically determine to exclude a subset of the multiple data samples for the second road from further use based at least in part on the associated information for the multiple data samples for the second road, wherein the reflected vehicle locations for data samples of the subset do not correspond to vehicle travel of interest on the second road; and

provide one or more indications of the multiple data samples for the second road other than the data samples of the subset, to enable the indicated data samples to be used in facilitating travel on the second road.

37. The computing system of claim 36 wherein the determining to exclude the subset of data samples for the second road includes determining that the reflected vehicle locations of at least one of the data samples of the subset do not match predefined locations for the second road, and wherein the first component and the data sample filterer component each include software instructions for execution by at least one processor of the one or more processors.

38. The computing system of claim 36 further comprising one or more components configured to, before the determining to exclude the multiple data samples for the first road, assessing the variability of the vehicle traffic on the first road during the one or more days.

39. The computing system of claim 38 wherein the one or more components are further configured to, before the determining to exclude the multiple data samples for the first road, determining that the first road of the one or more roads is not of interest based on the assessing of the variability of the vehicle traffic on the first road during the one or more days.

40. The computing system of claim 36 wherein the assessed variability of vehicle traffic on the first road during the one or more days is intra-day variability in vehicle traffic on the first road.

41. The computing system of claim 36 wherein the assessed variability of vehicle traffic on the first road during the one or more days is inter-day variability in vehicle traffic on the first road.

42. The computing system of claim 36 wherein the assessed variability of vehicle traffic on the first road during the one or more days is based on variability in vehicle traffic volume on the first road.

43. The computing system of claim 36 wherein the assessed variability of vehicle traffic on the first road during the one or more days is based on variability in vehicle traffic congestion on the first road.

44. The computing system of claim 36 wherein the assessed variability of vehicle traffic on the first road corresponds to an indicated road segment of the first road, and wherein the amount of the assessed variability of the vehicle traffic on the first road corresponds to a low variability.