Monitoring traffic congestion

Patent metadata

Field	Value
Publication number	US-10163339-B2
Application number	US-201615378036-A
Country	US
Kind code	B2
Filing date	Dec 13, 2016
Priority date	Dec 13, 2016
Publication date	Dec 25, 2018
Grant date	Dec 25, 2018

Abstract

Described herein is a framework to monitor traffic congestion. In accordance with one aspect of the framework, the framework receives vehicle data from vehicle data sources located in a region of interest. The framework may determine a sample size and an average speed for an edge of the region of interest based on the vehicle data. Congestion probability may then be determined based on the sample size and average speed. A report may be presented based on the congestion probability.

First claim

The invention claimed is:

1. A computer system for monitoring traffic congestion, comprising:
a non-transitory memory device for storing computer-readable program code; and
a processor in communication with the non-transitory memory device, the processor being operative with the computer-readable program code to perform operations including:
receiving, by a congestion monitor of the computer system, vehicle data within a time slot from vehicle data sources located in a region of interest, each vehicle data source being located in a vehicle in the region of interest;
determining, by the congestion monitor, a sample size and an average speed for an edge of the region of interest based on the vehicle data, wherein the sample size corresponds to a number of vehicles located in the edge of the region of interest within the time slot and the edge of the region of interest is a predefined segment of a road network of the region of interest and wherein an inverse of a variance of the average speed is linearly related to the sample size when the sample size is less than a predetermined value,
determining, by the congestion monitor, a congestion probability based on the sample size and the average speed and by:
determining the congestion probability comprises determining the variance of the average speed,
determining a slope of a graph of the inverse of the variance against the sample size, and
modeling a distribution of true speed using a normal probability model, wherein a mean of the normal probability model is the average speed and a variance of the normal probability model is based on the slope, and
presenting a report in a graphical user interface based on the congestion probability of the edge of the region of interest.

2. The computer system of claim 1 wherein the vehicle data comprises sequential data records the vehicle data sources, wherein at least one of the sequential data records comprises a device identifier, localization data, speed, time, or a combination thereof.

3. The computer system of claim 1 wherein the vehicle data sources comprise onboard mobile devices capable of continuously streaming the vehicle data.

4. The computer system of claim 1 wherein the report comprises a map of the region of interest indicating different levels of congestion based on the corresponding congestion probabilities of a plurality of edges of the region of interest.

5. The system of claim 1 wherein the determining the slope of the graph further comprises determining the slope based on historical vehicle data.

6. The system of claim 1 wherein the determining the congestion probability comprises determining a cumulative distribution of the normal probability model.

7. The system of claim 6 wherein the determining the cumulative distribution Pr comprises determining

Pr
⁡

(

mi
≤
C

)

=

1
2

⁢

⌊

1
+

erf
(

Ni
2

⁢

C
-
vi

12.8

)

⌋

wherein v i is the average speed, N i is the sample size, erf is an error function, m i is a true speed and C is a congestion threshold speed.

8. The system of claim 7 wherein the congestion threshold speed is selected based on a standardized grade level of the edge.

9. The system of claim 1 wherein presenting the report based on the congestion probability comprises displaying a map of the region of interest indicating different levels of congestion based on the corresponding congestion probabilities of a plurality of edges of the region of interest and further comprising updating the map in real-time in response to receiving new vehicle data.

10. A method of monitoring traffic congestion, the method being implemented by at least one computing device and comprising:
receiving, by a congestion monitor of the at least one computing device, vehicle data within a time slot from vehicle data sources located in a region of interest; each vehicle data source being located in a vehicle in the region of interest;
determining, by the congestion monitor, a sample size and an average speed for an edge of the region of interest based on the vehicle data, wherein the sample size corresponds to a number of vehicles located in the edge of the region of interest within the time slot and the edge of the region of interest is a predefined segment of a road network of the region of interest and wherein an inverse of a variance of the average speed is linearly related to the sample size when the sample size is less than a predetermined value;
determining, by the congestion monitor, a congestion probability based on the sample size and the average speed and by:
determining the congestion probability comprises determining the variance of the average speed;
determining a slope of a graph of the inverse of the variance against the sample size; and
modeling a distribution of true speed using a normal probability model, wherein a mean of the normal probability model is the average speed and a variance of the normal probability model is based on the slope; and
presenting a report in a graphical user interface based on the congestion probability of the edge of the region of interest.

11. The method of claim 10 wherein the determining the slope of the graph comprises determining the slope based on historical vehicle data.

12. The method of claim 10 wherein the determining the congestion probability comprises determining a cumulative distribution of the normal probability model.

13. The method of claim 12 wherein the determining the cumulative distribution Pr comprises determining

Pr
⁡

(

m
i

≤
C

)

=

1
2

⁢

⌊

1
+

erf
(

N
i

2

Assignees

• Sap Se

Inventors

• Liu Jing
• Zhang Qiwei
• Liu Jun
• Ni Yinling

Classifications

• G08G1/0133 Primary

  for classifying traffic situation · CPC title

• G08G1/0112

  from the vehicle, e.g. floating car data [FCD] · CPC title

• G08G1/052

  with provision for determining speed or overspeed {(speed measuring in general G01P)} · CPC title