Method and device for following objects, particularly for traffic monitoring

• US 7,880,643 B2
• Filed: 12/19/2002
• Issued: 02/01/2011
• Est. Priority Date: 12/19/2001
• Status: Expired due to Fees

• Current Assignee: Logobject AG
• Original Assignee: Logobject AG
• Inventors: Brega, Roberto, Wullschleger, Felix H.
• Primary Examiner(s): Black; Thomas G
• Assistant Examiner(s): LOUIE, WAE LENNY
• Application Number:
  US10/499,202
• Publication Number:
  US 20050068198A1
• Time in Patent Office: 2,966 Days
• Field of Search: 340/933, 340/942, 340/935, 340/936, 340/941, 701/117
• US Class Current: 340/933
• CPC Class Codes: G01S 17/66 Tracking systems using electromagnetic waves other than radio waves
• CPC Class Codes: G01S 17/89 for mapping or imaging
• 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 1/017 identifying vehicles G08G1/015, G08G1/054 take precedence
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors

Abstract

A method for tracking objects, especially for monitoring traffic, wherein a sensor measuring in an essentially horizontal and radial manner detects metrical data on moving objects in the form of raw data and transmits said data to a computer unit. The raw data is processed in the computer in such a way that the objects are tracked and the geometric properties thereof are determined. The static background is autonomously recognized and adapted or updated if changes occur. Objects in a present scene are tracked and current parameters are determined and correlated with the parameters of the objects of previous scenes. The method is particularly suitable for the detection and recognition of non-static traffic infractions which can only be recognized by analyzing the tracking of an object. The invention can be used in conjunction with several sensors in existing traffic control systems. Also disclosed is a device for carrying out the above-mentioned method.

Claims

1. Method for simultaneously tracking a plurality of objects, wherein a substantially horizontal radially-measuring sensor detects metrical data of moving objects moving freely in a scene within a working region of the sensor, and static objects within the working region of the sensor wherein measurement points of said objects are acquired as raw data, and fed to a computer unit;

wherein the raw data are processed in the computer unit such that said moving objects are tracked and their geometrical properties are ascertained, and said static objects are used as references.

2. Method according to claim 1, wherein the static objects are autonomously detected and is adapted or updated when there are changes.

3. Method according to claim 1, wherein when moving objects in the present scene are tracked, present parameters are determined, and past scenes are correlated with the parameters of the moving and static objects.

4. Method according to claim 3, wherein the parameter of the tracked moving object is set to be available for introspection from present and past scenes.

5. Method according to claim 1, wherein moving objects which can no longer be found in a present scene are speculatively tracked further based on the known, already determined trajectory, up to a predetermined uncertainty threshold.

6. Method according to claim 1, wherein a simple and intuitive “

in the loop”

configuration is made available, the same set of sensors being used for the configuration, or parameterization, and for operation.

7. Method according to claim 1, wherein virtual induction loops are defined, or established, in order to realize monitoring and trigger functions.

8. Method according to claim 1, wherein the traffic flow and/or the speed are measured.

9. Method according to claim 1, wherein traffic objects are classified.

10. Method according to claim 1, wherein all traffic violations which are of a non-static nature, but can only be detected from the analysis of tracking the moving object, are detected and documented.

11. Method according to claim 10, wherein traffic violations include going through traffic signals, going over stop lines and safety lines, and disregarding pedestrians'"'"' precedence at pedestrian crossings.

12. Method according to claim 10, wherein disturbances of traffic flow, e.g. collisions, are detected and the measures for documentation (photographs) are activated based on the existing data.

13. Method according to claim 1, wherein surveillance mechanisms are controlled by the available object representations alone or in combination with a guidance system.

14. Method according to claim 13, wherein the surveillance mechanism is at least one of a camera and an alarm system.

15. Method according to claim 1, wherein safety mechanisms are controlled by the available object representations alone or in combination with a guidance system.

16. Method according to claim 15, wherein the safety mechanism is an automatic door.

17. Method according to claim 1, wherein traffic regulation is implemented with the available object representations.

18. Method according to claim 1, wherein the moving objects are followed and their geometrical properties are ascertained to monitor vehicular traffic in the working region of the sensor.

19. Device for performing the method according to claim 1, wherein a substantially horizontal radially-measuring sensor is provided for detecting metrical data of moving objects moving freely in a working region of the sensor, and is connected via an interface to a computer unit, wherein the computer unit is equipped with software, and this software is available for calculating object representations from the raw data of the sensor.

20. Device according to claim 19, wherein the sensor is present, installed such that its sensor plane is at least 25 cm and at most 75 cm from the street.

21. Device according to claim 19, wherein the calculation of the object representations takes place online and offline.

22. Device according to claim 19, wherein it is designed for mobile use.