Method and device for identifying traffic-relevant information

• US 8,346,706 B2
• Filed: 05/16/2008
• Issued: 01/01/2013
• Est. Priority Date: 05/25/2007
• Status: Active Grant

• Current Assignee: Continental Engineering Services GmbH (Continental AG), Continental Teves AG & Co. OHG (Continental AG), ADC GmbH (TE Connectivity Limited)
• Original Assignee: Continental Teves AG & Co. OHG (Continental AG), Contintental Engineering Service GmbH, ADC GmbH (TE Connectivity Limited)
• Inventors: Groitzsch, Stephan, Schorn, Matthias, Fechner, Thomas, Kressel, Ulrich
• Primary Examiner(s): Rivas, Omar Fernandez
• Assistant Examiner(s): HANCHAK, WALTER P
• Application Number:
  US12/601,062
• Publication Number:
  US 20100241605A1
• Time in Patent Office: 1,691 Days
• Field of Search: None
• US Class Current: 706/47
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G06V 20/582 of traffic signs
• CPC Class Codes: G08G 1/163 involving continuous checking

Abstract

A device is arranged to carry out a method for identifying traffic-relevant information in a moving vehicle, wherein image data of a visual sensor and map data of a navigation system are each pre-evaluated for the identification and the results of the pre-evaluation are combined and interpreted. The image and map data is scanned for traffic-relevant information and compacted to relevant image and map data in a first and second scene interpretations, and the relevant image and map data is supplied to a rule engine and to a state machine for interpreting the image and map data. The rule engine evaluates the image and map data and transmits an action to be executed to the state machine which carries out a transition in its state space including pre-defined states and outputs information which is assigned to the state or to the transition.

Claims

1. A method for identifying traffic-relevant information (I) in a moving vehicle comprising the steps of:

pre-evaluating image data (B) of a visual sensor and map data (K) of a navigation system for said identification;

combining and interpreting results of said pre-evaluation;

scanning the image data (B) for traffic-relevant information (I) contained in the image data (B);

compacting relevant image data (B_r) of the image data (B) in a first scene interpretation;

scanning the map data (K) for traffic-relevant information (I) contained in the map data (K);

compacting relevant map data (K_r) of the map data (K) in a second scene interpretation;

supplying the relevant image data (B_r) and the relevant map data (K_r) to a rule engine and to a state machine for interpreting the image and map data;

evaluating the image data (B_r) and the map data (K_r) in the rule engine;

transmitting an action (A) to be executed to the state machine;

carrying out a transition, in the state machine, within a state space of the state machine comprising pre-defined states (Z) as a response to the action (A) to be executed; and

outputting information (I), in the state machine, which is assigned to a state (Z) or to said transition.

2. A method according to claim 1 further comprising the step of interpreting the contents of the relevant image and map data (B_r, K_r) in the rule engine according to specific sets of rules and the action (A) specified by the rule engine parameterizes a behaviour which is prescribed by a rule that has been identified.

3. A method according to claim 1, wherein a matrix is used to represent the rule engine, which matrix can be evaluated by means of an algorithm.

4. A method according to claim 1, the state machine includes defined states (Z) which can be assumed by the vehicle and/or its surroundings, wherein the action (A) to be executed, which is specified by the rule engine, induces a transition from a defined state to a another defined state or back to the defined state in the state machine.

5. A method according to claim 1, wherein a transition in the state machine is accompanied by an output of information (I).

6. A method according to claim 1, wherein the state machine feeds back its state (Z) to the rule engine.

7. A method according to claim 1, wherein the state machine is divided into a main state machine and one or more surroundings state machines.

8. A method according to claim 1, wherein the first and second scene interpretations transmit a trigger signal (T) to a trigger control during the compacting step to relevant image or map data (B_r, K_r), which trigger control generates a total trigger signal (GT) for the rule engine and the state machine.

9. A method according to claim 8, wherein the trigger control forms an ‘

OR’

relation of the trigger signals (T) of the first and second scene interpretations to generate the total trigger signal (GT).

10. A method according to claim 9, wherein the ‘

OR’

relation is a delayed ‘

OR’

relation.

11. A method according to claim 9, wherein the trigger control activates a counter when a first trigger signal (T) from the first or the second scene interpretation is available and generates the total trigger signal (GT) either when a maximum counter value is reached or when a second trigger signal (T) is available.

12. A method according to claim 1 further comprising the step of selecting relevant image and/or map data (B_r, K_r) according to pre-specified criteria in the first and/or second scene interpretation(s).

13. A method according to claim 1 further comprising the step of reducing the image data (B′

) of the visual sensor to a pre-selection of image data (B) to be analysed and camera status data (S) in a pre-processing step which is prior to the scene interpretation.

14. A method according to claim 1 further comprising the step of exchanging information between the first and second scene interpretations.

15. A method according to claim 1, wherein vehicle data (F) and/or camera status data (S) is available during identification of traffic-relevant information (I).

16. A device for identifying traffic-relevant information (I) in a moving vehicle having a connection to a system of a visual sensor for receiving image data (B, B′

), said device comprising;

a connection to a navigation system for receiving map data (K);

a connection to a display instrument for displaying or processing identification results, which device is configured to carry out the method according to claim 1; and

means for scene interpretation to compact the image data (B) received from the visual sensor and the map data (K) of the navigation system and to transmit the compacted image and map data (B_r, K_r) to a computing unit including a rule engine and a state machine,

wherein the rule engine is configured to evaluate the compacted image and map data (B_r, K_r) and to transmit an action (A) to be executed to the state machine, and

wherein the state machine is configured to use the action (A) to be executed to carry out a transition within a state space of the state machine comprising pre-defined states (Z) and to output information (I) which is assigned to a state (Z) or to said transition to the display instrument via said connection.

17. A device according to claim 16, wherein a trigger control for generating a total trigger signal (GT) is connected downstream of the means for scene interpretation.

18. A device according to claim 16, wherein the means for scene interpretation, the trigger control, the computing unit including the rule engine and the state machine are combined to form a fusion module.