Adaptive traffic control using object tracking and identity details

• US 10,636,298 B2
• Filed: 07/11/2018
• Issued: 04/28/2020
• Est. Priority Date: 08/11/2017
• Status: Active Grant

• Current Assignee: Cubic Corporation
• Original Assignee: Cubic Corporation
• Inventors: Malkes, William A., Overstreet, William S., Price, Jeffery R., Tourville, Michael J.
• Primary Examiner(s): Trivedi, Atul
• Application Number:
  US16/032,886
• Publication Number:
  US 20190051161A1
• Time in Patent Office: 657 Days
• Field of Search: 701117
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0145 for active traffic flow control
• CPC Class Codes: G08G 1/015 with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
• CPC Class Codes: G08G 1/08 according to detected number or speed of vehicles
• CPC Class Codes: G08G 1/081 Plural intersections under common control

Abstract

Systems and methods of adaptive traffic control based on detected anomalies in traffic conditions are disclosed. One aspect of the present disclosure is a method of adaptive traffic control that includes receiving traffic data at an intersection; determining statistics associated with traffic at the intersection based on the traffic data; detecting an anomaly in the traffic based on the statistics; determining an anomaly rule based on a portion of the statistics associated with the traffic at the intersection over at least one time interval prior to detection of the anomaly; and utilizing the anomaly rule to adaptively control the traffic at the intersection to prevent future occurrences of the anomaly at the intersection.

Claims

1. A method of adaptive traffic control, the method comprising:

receiving traffic data at an intersection;

determining statistics associated with traffic at the intersection based on the traffic data;

detecting an anomaly in the traffic based on the statistics;

responsive to detecting the anomaly, creating a new anomaly rule based on a portion of the statistics associated with the traffic at the intersection over at least one time interval prior to detection of the anomaly; and

utilizing the new anomaly rule to adaptively control the traffic at the intersection to prevent future occurrences of the anomaly at the intersection.

2. The method of claim 1, wherein determining the statistics comprises:

recording, for each of a plurality of time intervals, one or more of the statistics associated with the traffic, the one or more statistics including at least one of;

an average traffic flow rate at the intersection;

an average traffic flow rate at each identified zone of the intersection;

types of objects at each identified zone of the intersection;

or

a phase status of a traffic signal at each identified zone of the intersection.

3. The method of claim 2, further comprising:

determining a type of each object detected at the intersection, a type being one of a pedestrian, a car, a truck, a motor cycle or a bicycle.

4. The method of claim 2, wherein the anomaly is detected when the average traffic flow rate at the intersection is equal to or less than a predetermined threshold for at least two of the plurality of time intervals, consecutively.

5. The method of claim 4, wherein the portion of the statistics based on which the new anomaly rule is created corresponds to one or more of the statistics recorded over one or more of the plurality of time intervals preceding a first time interval over which the average traffic flow rate is equal to or less than the threshold.

6. The method of claim 1,

wherein the new anomaly rule has one or more traffic control settings to be applied to a traffic light at the intersection to prevent the future occurrences of the anomaly.

7. The method of claim 1, utilizing the new anomaly rule comprises:

subsequent to creating the new anomaly rule, monitoring traffic conditions at the intersection;

determining a traffic pattern at the intersection based on the monitoring;

determining if the traffic pattern matches an anomaly scenario stored in an anomaly scenario database, the anomaly scenario corresponding to the portion of the statistics for which the new anomaly rule is created; and

based on the determining, applying the new anomaly rule to a traffic light at the intersection.

8. The method of claim 1, wherein utilizing the new anomaly rule comprises:

receiving a query from a light controller for the new anomaly rule; and

sending the new anomaly rule and corresponding traffic control settings to the light controller to be applied to a traffic light for preventing the future occurrences of the anomaly.

9. A traffic controller comprising:

memory having computer-readable instructions stored thereon; and

one or more processors configured to execute the computer-readable instructions to;

receive traffic data at an intersection;

determine statistics associated with traffic at the intersection based on the traffic data;

detect an anomaly in the traffic based on the statistics;

responsive to detecting the anomaly, creating a new anomaly rule based on a portion of the statistics associated with the traffic at the intersection over at least one time interval prior to detection of the anomaly; and

utilize the new anomaly rule to adaptively control the traffic at the intersection to prevent future occurrences of the anomaly at the intersection.

10. The traffic controller of claim 9, wherein the one or more processors are configured to execute the computer-readable instructions to determine the statistics by:

recording, for each of a plurality of time intervals, one or more of the statistics associated with the traffic, the one or more statistics includes at least one of;

an average traffic flow rate at the intersection;

an average traffic flow rate at each identified zone of the intersection;

types of objects at each identified zone of the intersection;

or

a phase status of a traffic signal at each identified zone of the intersection.

11. The traffic controller of claim 10, wherein the one or more processors are configured to execute the computer-readable instructions to:

determine a type of each object detected at the intersection, a type being one of a pedestrian, a car, a truck, a motor cycle or a bicycle.

12. The traffic controller of claim 10, wherein the one or more processors are configured to execute the computer-readable instructions to detect the anomaly when the average traffic flow rate at the intersection is equal to or less than a threshold for at least two of the plurality of time intervals, consecutively.

13. The traffic controller of claim 12, wherein the portion of the statistics based on which the new anomaly rule is created corresponds to one or more of the statistics recorded over one or more of the plurality of time intervals preceding a first time interval over which the average traffic flow rate is equal to or less than the threshold.

14. The traffic controller of claim 9,

wherein the new anomaly rule has one or more traffic control settings to be applied to a traffic light at the intersection to prevent the future occurrences of the anomaly.

15. The traffic controller of claim 9, wherein the one or more processors are configured to execute the computer-readable instructions to transmit the new anomaly rule to a light controller configured to control traffic light settings at the intersection.

16. The traffic controller of claim 9, wherein the traffic data are captured via one or more sensors and include at least one of audio, video and image data corresponding to the traffic at the intersection.

17. One or more computer-readable medium having computer-readable instructions stored thereon, which when executed by one or more processors, cause the one or more processors to:

receive traffic data at an intersection;

determine, for each of a plurality of time intervals and based on the traffic data, corresponding statistics associated with traffic at the intersection based on the traffic data;

detect an anomaly in the traffic for at least two of the plurality of time intervals, consecutively;

generate an anomaly scenario based on statistics determined for at least one of the time intervals preceding a first one of the at least two of the plurality of time intervals, consecutively;

responsive to detecting the anomaly, create a new anomaly rule for the anomaly scenario; and

send the new anomaly rule to a light controller to adaptively control the traffic at the intersection to prevent future occurrences of the anomaly at the intersection.

18. The one or more computer-readable medium of claim 17, wherein the corresponding statistics of each of the plurality of time intervals includes at least one of:

an average traffic flow rate at the intersection;

an average traffic flow rate at each identified zone of the intersection;

types of objects at each identified zone of the intersection;

or

a phase status of a traffic signal at each identified zone of the intersection.

19. The one or more computer-readable medium of claim 18, wherein the execution of the computer-readable instructions cause the one or more processors to:

determine a type of each object detected at the intersection, a type being one of a pedestrian, a car, a truck, a motor cycle or a bicycle.

20. The one or more computer-readable medium of claim 17, wherein the execution of the computer-readable instructions cause the one or more processors to detect the anomaly when an average traffic flow rate at the intersection is equal to or less than a threshold for the at least two of the plurality of time intervals, consecutively.