Method and system for modeling and processing vehicular traffic data and information and applying thereof

• US 20060111833A1
• Filed: 11/08/2005
• Published: 05/25/2006
• Est. Priority Date: 08/28/2000
• Status: Active Grant

• Current Assignee: Inrix Incorporated
• Original Assignee: Inrix Incorporated
• Inventors: Eshpar, Allon, Feldman, Israel, Meltzer, Yochai, Trinker, Arie, Lotem, Amnon
• Granted Patent: US 8,918,278 B2
• Time in Patent Office: Days
• US Class Current: 701/117
• CPC Class Codes: G08G 1/0104 Measuring and analyzing of parameters relative to traffic conditions
• CPC Class Codes: G08G 1/0125 Traffic data processing
• CPC Class Codes: H04W 12/02 Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII]

Abstract

A method and system for modeling and processing vehicular traffic data and information, comprising: (a) transforming a spatial representation of a road network into a network of spatially interdependent and interrelated oriented road sections, for forming an oriented road section network; (b) acquiring a variety of the vehicular traffic data and information associated with the oriented road section network, from a variety of sources; (c) prioritizing, filtering, and controlling, the vehicular traffic data and information acquired from each of the variety of sources; (d) calculating a mean normalized travel time (NTT) value for each oriented road section of said oriented road section network using the prioritized, filtered, and controlled, vehicular traffic data and information associated with each source, for forming a partial current vehicular traffic situation picture associated with each source; (e) fusing the partial current traffic situation picture associated with each source, for generating a single complete current vehicular traffic situation picture associated with entire oriented road section network; (f) predicting a future complete vehicular traffic situation picture associated with the entire oriented road section network; and (g) using the current vehicular traffic situation picture and the future vehicular traffic situation picture for providing a variety of vehicular traffic related service applications to end users.

Claims

1. A method for modeling and processing vehicular traffic data, comprising the steps of:

generating a representation of a road network associated with the vehicular traffic data, the road network comprising a plurality of road sections; and

acquiring vehicular traffic data associated with said road network from at least a plurality of mobile sensors in communication with a wireless telecommunication network, wherein gaps in a current traffic situation for a road section due to a lack of current data are filled by using prediction by using vehicular traffic behavior patterns and correlation rules based on historic vehicular traffic data.

2. The method of claim 1, wherein said behavior patterns of said road section network are time dependent.

3. The method of claim 1, wherein said correlation rules of said road section network are time dependent, and said time dependent correlation rule determines correlation and interrelation of between different road sections as a function of time.

4. The method of claim 1, wherein different behavior patterns are established for a road section at different times, days of the week, holidays and/or special events.

5. The method of claim 2, wherein a said time dependent behavior pattern of a road section describes regular changing of associated normalized travel time (NTT) values as a function of time.

6. The method of claim 2, wherein said time dependent correlation rule determines correlation and interrelation of each said single complete current vehicular traffic situation picture between different road sections as a function of time.

7. The method of claim 1, further comprising the step of:

predicting at least one future time vehicular traffic situation associated with at least a portion of said road section network.

8. The method of claim 7, wherein the current vehicular traffic situation serves as a baseline or starting point for predicting said at least one future time vehicular traffic situation.

9. The method of claim 7, wherein said predicting is performed at a pre-determined frequency in a range of from about once per every two minutes to about once per every ten minutes.

10. The method of claim 7, wherein said predicting includes using said time dependent behavior patterns of said road section network and time dependent correlation rules of said road section network.

11. The method of claim 7, wherein said predicting includes identifying unexpected vehicular traffic developments from a said current vehicular traffic situation by comparing said developments to regular time dependent behavior patterns of said road section network.

12. The method of claim 11, wherein said predicting includes predicting propagation of the affects of traffic developments identified in time along adjacent and non-adjacent road sections, using time dependent correlation rules of said road section network.

13. The method of claim 1, further comprising the step of providing a vehicular traffic related service application to an end user.

21. The method of claim 1, wherein acquiring vehicular traffic data comprises selecting a sample comprising vehicle-carried mobile sensors from the plurality of mobile sensors and tracking locations of mobile sensors of said sample for modelling and processing purposes.

35. The method of claim 21 wherein tracking locations of said mobile sensors comprises using location data and/or information provided by a server of a mobile wireless telecommunications network.

36. The method of claim 21, wherein said vehicle-carried mobile sensors are selected from the group consisting of:

computer devices;

cellular phone devices;

vehicle anti-theft devices; and

combinations thereof.

37. The method of claim 21, wherein locations of said vehicle-carried mobile sensors are obtained from said wireless telecommunication network in known time intervals, such that a path of each said vehicle is determined, said path being a sequence of connected road sections constituting a logical route to take between two points within said represented road network.

38. The method of claim 37, wherein normalized travel times (NTT) of said road sections of said determined path are calculated by using assumptions as to reasonable vehicle behavior and said tracked footprints of said mobile sensors.

39. The method of claim 38, wherein a mean normalized travel time (NTT) for a road section is calculated by statistically processing data from said mobile sensors traveling on said road section during a time period of an assessment cycle to indicate the possibility of different velocities on different lanes of said road section.

40. The method of claim 39, wherein said mean normalized travel time (NTT) values are calculated using a confidence factor.

41. The method of claim 40, wherein the confidence factor is a function of one or more of:

accuracy of said footprints;

amount of said footprints; and

, error rate of said footprints.

42. The method of claim 21, in which said vehicle-carried mobile sensors include one or more of:

computer devices;

cellular phone devices and combinations thereof; and

wherein selecting a sample comprising vehicle-carried mobile sensors from the plurality of mobile sensors includes the step of identifying said mobile sensors having a relatively fast movement indicating vehicular movement.

43. The method of claim 21, in which said vehicle-carried mobile sensors include one or more of:

computer devices;

cellular phone devices; and

combinations thereof; and

wherein selecting a sample comprising vehicle-carried mobile sensors from the plurality of mobile sensors includes identifying said mobile sensors connected to said wireless telecommunications network whose cell transition or handover rates indicate a relatively fast movement indicative of vehicular movement.

44. The method of claim 21, in which said vehicle-carried mobile sensors include anti-theft devices, and wherein selecting a sample comprising vehicle-carried mobile sensors from the plurality of mobile sensors includes identifying ignition activation for said mobile sensors comprising mobile vehicle anti-theft devices.

45. The method of claim 21, wherein said tracking is performed by polling said locations of said mobile sensors in known time intervals.

46. The method of claim 1, further comprising filtering out said mobile sensors that are recognized as noise.

47. The method of claim 1, further comprising filtering out said mobile sensors whose behaviour indicates they are not relevant.

48. The method of claim 21, further comprising preventing said tracking of said mobile sensors that stop moving for a predetermined time interval.

49. The method of claim 21, further comprising preventing said tracking of said mobile sensors that go beyond the bounds of a sensible travel route.

50. The method of claim 21, further comprising maintaining said tracking within the locating capacity of said wireless telecommunications network.

51. The method of claim 1, comprising acquiring vehicular traffic data by a procedure selected from the group consisting of:

a push procedure;

a pull procedure; and

, combinations thereof;

wherein said push procedure is a mode of acquiring the vehicular traffic data initiated by said mobile sensors, and,

wherein said pull procedure is a mode of acquiring the vehicular traffic data initiated by a software module sampling said mobile sensors.

52. The method of claim 21, wherein said tracking is controlled according to a predefined policy selected from the group consisting of:

not to track too many said vehicles in a same region of said road network;

focus said tracking on a certain problematic region of said road network;

stop said tracking said vehicles that stopped for a pre-determined time interval;

collect the vehicular traffic data and information within a certain limited capacity of said wireless telecommunication networks; and

, combinations thereof.

53. The method of claim 21, further including a procedure for protecting privacy of individuals associated with said vehicle-carried mobile sensors.

54. The method of claim 53, wherein the mobiles sensors are in communication with a cellular telecommunications network and the procedure for protecting privacy of individuals associated with said vehicle-carried mobile sensors includes keeping the identities of relevant mobile sensors within said wireless cellular telecommunications network.

55. The method of claim 53, wherein the procedure for protecting privacy of individuals associated with said vehicle-carried mobile sensors includes deleting identities of said identified mobile sensors and/or deleting said locations of said tracked mobile sensors following processing.

56. The method of claim 1, wherein said road network is represented as a geographical information system (GIS) road network.

57. The method of claim 1, wherein each said road section of said road section network represents a road section having a single vehicular traffic continuation option.

58. The method of claim 57, wherein said single vehicular traffic continuation option is located at a head end road junction, said road section represents a unit featuring a plurality of consecutive road segments of said road network, said consecutive road segments positioned head-to-tail relative to each other are located between two road junctions, a tail end road junction and a said head end road junction, within said road network, and are characterized by similar vehicular traffic data and information, and, said single vehicular traffic continuation option refers to one of various vehicular traffic flow options said each vehicle may take within said road network.

59. The method of claim 58, wherein, when lanes in various said road segments within said road section network are assigned to turning traffic, respective said road sections may yield different vehicular traffic data and information.

60. The method of claim 57, wherein said vehicular traffic continuation option is selected from the group consisting of:

continuing to travel straight;

taking a right turn; and

, taking a left turn;

from a said road segment joined or linked to a said head end road junction.

61. The method of claim 13, wherein said vehicular traffic data is used to provide one or more vehicular traffic related service applications selected from:

responding to traffic oriented queries;

finding optimal routes between given points of said road network;

finding alternative routes between given points of said road network;

estimating travel times between given points of said road network;

initiating alerts and route alterations when unexpected traffic events change said current vehicular traffic situation; and

combinations thereof.

62. The method of claim 1, additionally processing data and/or information from a variety of sources selected from the group consisting of:

fixed sensors;

traffic reports by police;

radio broadcasts of the vehicular traffic data and information;

historical and event related vehicular traffic data and information;

other sources of the vehicular traffic data and information; and

combinations thereof.

14. A method for modeling and processing vehicular traffic data, comprising the steps of:

generating a representation of a road network associated with the vehicular traffic data, the road network comprising a plurality of road sections; and

acquiring vehicular traffic data associated with said road network from at least a plurality of sensors and predicting a future traffic situation, wherein predicting a traffic situation comprises predicting normalized travel times over a plurality of road sections based on time dependent vehicle behavior patterns, such that the predicted traffic parameter for a particular road section takes into account the time of passage of that road section.

22. The method of claim 14, wherein acquiring vehicular traffic data comprises tracking locations of a sample of said sensors for modelling a current vehicular situation.

15. A method for modeling and processing vehicular traffic data, comprising the steps of:

generating a representation of a road network associated with the vehicular traffic data, the road network comprising a plurality of road sections; and

acquiring vehicular traffic data associated with said road network from at least a plurality of mobile sensors in communication with a wireless telecommunication network and predicting a future traffic situation, wherein predicting a future traffic situation comprises predicting travel times over a plurality of road sections based on time dependent vehicle behavior patterns, the method being further operable to compare detected traffic developments to regular time dependent behavior patterns of said road section network, and to identify discrepancies from said regular time dependent behavior patterns, whereby propagation in time along adjacent and non-adjacent road sections of traffic events identified by discrepancies from said time dependent behavior patterns can be determined using time dependent correlation rules of said road section network.

23. The method of claim 15, wherein acquiring vehicular traffic data comprises tracking locations of a sample of said mobile sensors for modelling a current vehicular situation.

16. A system for modeling and processing vehicular traffic data, comprising:

a mechanism for representing a road network associated with the vehicular traffic data and information, the road network comprising a plurality of road sections; and

software for acquiring vehicular traffic data associated with said road network from a plurality of mobile sensors in communication with a wireless telecommunications network, the system further comprising a module for filling in gaps in a current vehicular traffic data by predictions by using time dependent correlation rules based on time dependent vehicular patterns derived from historic data, such that a predicted traffic parameter for a particular road section takes into account the time of passage of that road section.

17. The system of claim 16, wherein different behavior patterns are established for a road section at days of the week, holidays and/or special events.

24. The system of claim 16, wherein the vehicular traffic data associated with the said network is taken from a sample of the plurality of mobile sensors, and the software comprising instructions for selecting said sample and for tracking locations of mobile sensors of said sample over the road network.

63. The system of claim 16, comprising an interface for receiving location data and/or information provided by a server of a mobile wireless telecommunications network.

64. The system of claim 16, wherein said mobile sensors are vehicle-carried mobile sensors and are selected from the group consisting of:

computer devices;

cellular phone devices;

vehicle anti-theft devices; and

combinations thereof.

65. The system of claim 16, wherein said software obtains locations of said mobile sensors from said wireless communications system in known time intervals.

66. The system of claim 16, wherein a path of a vehicle on the road network is determined in terms of a plurality of said road sections.

67. The system of claim 16, further capable of identifying said mobile sensors having a relatively fast movement indicating vehicular movement.

68. The system of claim 16, wherein said mobile sensors include cellular mobile telephones and/or computers in communication with a wireless cellular telecommunications network, and wherein software identifies said mobile cellular devices whose cell transition and/or handover rates indicate a relatively fast movement indicative of vehicular movement.

69. The system of claim 16, wherein said mobiles sensors include mobile vehicle anti-theft devices and wherein said software identifies said mobile vehicle anti-theft devices indicating ignition activation potentially indicating vehicular movement.

70. The system of claim 24, wherein said tracking is performed by polling said locations of said mobile sensors in known time intervals.

71. The system of claim 16, wherein said software further performs the step of filtering out said mobile sensors that are recognized as noise.

72. The system of claim 24, wherein said software further performs the step of preventing said tracking of said mobile sensors that stop moving for a predetermined time interval.

73. The system of claim 24, wherein said software further performs the step of preventing said tracking of said mobile sensors that have travelled beyond the bounds of a sensible route.

74. The system of claim 24, wherein said software maintains said tracking within locating capacity of said wireless telecommunications network.

75. The system of claim 16, wherein said software acquires the vehicular traffic data by a procedure selected from the group consisting of:

a push procedure;

a pull procedure; and

, combinations thereof;

said push procedure is a mode of said acquiring the vehicular traffic data and information initiated by said mobile sensors, and, said pull procedure is a mode of said acquiring the vehicular traffic data and information initiated by a software module sampling said mobile sensors.

76. The system of claim 24, wherein said tracking is controlled according to a predefined and updated policy selected from the group consisting of:

not to track too many said vehicles in a same region of said road network;

focus said tracking on a certain problematic region of said road network;

stop said tracking said vehicles that stopped for a pre-determined time interval;

collect the vehicular traffic data and information within a certain limited capacity of a said wireless telecommunications network; and

, combinations thereof.

77. The system of claim 16, wherein said software further performs a procedure for protecting privacy of individuals associated with said vehicle-carried mobile sensors.

78. The system of claim 16, wherein said road network is represented as a geographical information system (GIS) road network.

79. The System of claim 16, wherein each said road section of said road network represents a road section having a single vehicular traffic continuation option located at a head end road junction, said road section represents a unit featuring a plurality of consecutive road segments of said road network, said consecutive road segments positioned head-to-tail relative to each other are located between two road junctions, a tail end road junction and a said head end road junction, within said road network, and are characterized by similar vehicular traffic data and information, and, said single vehicular traffic continuation option refers to one of various vehicular traffic flow options said each vehicle may take within said road network.

80. The system of claim 79, wherein said vehicular traffic continuation option is selected from the group consisting of continuing to travel straight, taking a right turn, and, taking a left turn, from a said road segment joined or linked to a said head end road junction.

81. The system of claim 79, wherein, when lanes in various said road segments within said road section network are assigned to turning traffic, respective said road sections may yield different vehicular traffic data and information.

82. The system of claim 16, wherein a particular traffic situation or scenario characterizing a particular road section is interdependent and interrelated with other particular said traffic situations or scenarios characterizing other particular said road sections of said road section network.

83. The system of claim 16, wherein vehicular traffic data and information is sourced from a variety of sources, and wherein the variety of sources of the vehicular traffic data and information is selected from the group consisting of:

fixed sensors;

of mobile sensors;

traffic reports by police;

radio broadcasts of the vehicular traffic data and information;

historical and event related vehicular traffic data and information;

other sources of the vehicular traffic data and information; and

combinations thereof.

84. The system of claim 83, wherein each said source is characterized by a variable level of accuracy.

85. The system of claim 16, further comprising software for calculating normalized travel time (NTT) values.

86. The system of claim 85, further comprising software for calculating a mean normalized travel time (NTT) value from a plurality of normalized travel time (NTT) values of each of a plurality of vehicles.

87. The system of claim 85, wherein said normalized travel time (NTT) value of a road section is calculated by statistical processing.

88. The system of claim 87, wherein said plurality of normalized travel time (NTT) values of a road section is calculated by statistically processing said tracked locations and velocities of said mobile sensors traveled on said specific road section during a time period of an assessment cycle, for indicating possibility of different said velocities on different lanes of said specific road section.

89. The system of claim 85, wherein said software for calculating normalized travel times (NTT) deduces a path of said each vehicle from several consecutive readings of said tricked locations, said deduced path is a sequence of connected said road sections which join into a logical route to take between two points within said road section network representing said road network.

90. The system of claim 89, wherein a said plurality of normalized travel time (NTT) values on each said road section of said deduced path is calculated by using timings and said tracked locations of said footprints of said mobile sensors determined by using assumptions as to reasonable acceleration and velocity behaviors of vehicular drivers of said plurality of vehicles moving on said road network.

91. The system of claim 85, wherein said software for calculating normalized travel time (NTT) values uses a confidence factor.

92. The system of claim 91, wherein said confidence factor is a function of accuracy taking into account one or more of accuracy of said footprints;

amount of said footprints; and

, error rate of said footprints;

of said identified and tracked mobile sensors.

93. The system of claim 16, wherein said correlation rules describe interdependence, interrelation, and mutual correlation of vehicular traffic parameters among said road sections in a particular legion of said road network.

94. The system of claim 16, wherein one or more of said vehicular behavior patterns and said correlation rules, are time dependent.

95. The system of claim 94, wherein said vehicular behavior patterns are time dependent, and said time dependent vehicular behavior pattern describes regular changing travel times of a road as a function of time.

96. The system of claim 94, wherein said correlation rules are time dependent, and said time dependent correlation rule determines correlation and interrelation of between different road sections as a function of time.

97. The system of claim 94, wherein the system is further operable to compare detected developments to regular said time dependent behavior patterns of said road section network, using said normalized travel time values, and correcting said normalized travel time values according to discrepancies from said time dependent behavior patterns.

98. The system of claim 97, wherein the system further determines propagation in time along adjacent and non-adjacent said road sections, of traffic events identified by discrepancies from said time dependent behavior patterns of said road section network, using said time dependent correlation rules of said road section network.

99. The system of claim 16, arranged to provide input to a variety of vehicular traffic related Service applications selected from the group consisting of:

finding optimal routes between given points of said road network;

finding alternative routes between given points of said road network;

estimating travel times between given points of said road network;

initiating alerts and route alterations when unexpected traffic events change said current vehicular traffic situation picture; and

, combinations thereof.

18. A system for modeling and processing vehicular traffic data, comprising:

a mechanism for representing a road network associated with the vehicular traffic data, the road network comprising a plurality of road sections; and

software for acquiring vehicular traffic data associated with said road network from a plurality of mobile sensors in communication with a wireless telecommunications network, the system further comprising software for filling in gaps in current vehicular traffic data by predictions based on time dependent vehicular patterns derived from historic data using time dependent correlation rules, wherein the system is further operable to compare detected developments to regular said time dependent behavior patterns of said road section network and to identify discrepancies from said regular time dependent behavior patterns.

25. The system of claim 18, wherein the vehicular traffic data associated with said network is from a sample of the plurality of mobile sensors, and the software comprising instructions for selecting said sample and for tracking locations of mobile sensors of said sample over the said network.

19. A system for modeling and processing vehicular traffic data, comprising:

a mechanism for representing a road network associated with the vehicular traffic data, the road network comprising a plurality of road sections; and

software for acquiring vehicular traffic data associated with said road network from a plurality of mobile sensors in communication with a wireless telecommunications network, the system further comprising a module to compare detected developments to regular said time dependent behavior patterns of said road section network and to identify discrepancies from said regular time dependent behavior patterns, whereby the system further determines propagation in time of traffic events identified by discrepancies from said time dependent behavior patterns of said road section network, using time dependent correlation rules and time dependent behavior patterns of said road section network.

26. The system of claim 19, wherein the vehicular traffic data associated with the network is from a sample of plurality of mobile sensors, and the software comprising instructions for selecting said sample and for tracking locations of mobile sensors of said sample over the road network.

20. A system for modeling and processing vehicular traffic data, comprising:

a mechanism for representing a road network associated with the vehicular traffic data, the road network comprising a plurality of road sections; and

software for acquiring vehicular traffic data associated with said road network from a plurality of mobile sensors in communication with a wireless telecommunications network, the system further comprising a module operable to compare detected developments to regular said time dependent behavior patterns of said road section network and to identify discrepancies from said regular time dependent behavior patterns, whereby the system further determines propagation in time along adjacent and non-adjacent said road sections, of traffic events identified by discrepancies from said time dependent behavior patterns of said road section network, using time dependent correlation rules of said road section network.

27. The system of claim 20, wherein the vehicular traffic data associated with the network is from a sample of the plurality of mobile sensors, and the software comprising instructions for selecting said sample and for tracking locations of mobile sensors of said sample over the road network.

28. A method for modelling and processing vehicular traffic data, comprising the steps of:

generating a representation of a road network associated with the vehicular traffic data, the road network comprising a plurality of road sections; and

acquiring vehicular traffic data associated with said road network from at least a plurality of mobile sensors in communication with a wireless telecommunication network, wherein gaps in a current traffic situation for a road section due to a lack of current data are filled by using prediction by using vehicular traffic behaviour patterns of said road section network are time dependent based on historic vehicular traffic data.

29. The method of claim 28, wherein gaps in the current traffic situation are filled by using vehicular traffic behaviour patterns and/or correlation rules based on historical vehicular traffic data.

30. The method of claim 28, wherein said correlation rules of said road section network are time dependent, and said time dependent correlation rule determines correlation and interrelation of between different road sections as a function of time.

31. A method for modeling and processing vehicular traffic data, comprising the steps of:

generating a representation of a road network associated with the vehicular traffic data, the road network comprising a plurality of road sections; and

acquiring vehicular traffic data associated with said road network from at least a plurality of mobile sensors in communication with a wireless telecommunication network, wherein gaps in a current traffic situation for a road section due to a lack of current data are filled by using prediction by using correlation rules based on historic vehicular traffic data.

32. The method of claim 31, wherein gaps in the current traffic situation are filled by using vehicular traffic behavior patterns and/or correlation rules based on historical vehicular traffic data.

33. The method of claim 31, wherein said behavior patterns of said road section network are time dependent, and said time dependent correlation rule determines correlation and interrelation of between different road sections as a function of time.

34. The method of claim 31, wherein said correlation rules of said road section network are time dependent, and said time dependent correlation rule determines correlation and interrelation of between different road sections as a function of time.