System for monitoring the interior of a vehicle

• US 20040176891A1
• Filed: 01/12/2004
• Published: 09/09/2004
• Est. Priority Date: 07/10/2001
• Status: Active Grant

• Current Assignee: Continental Automotive GmbH (Continental AG)
• Original Assignee: Siemens AG
• Inventors: Kohler, Thorsten, Zittlau, Dirk, Ertl, Ludwig, Christl, Markus
• Granted Patent: US 7,124,007 B2
• Time in Patent Office: Days
• US Class Current: 701/45
• CPC Class Codes: B60N 2/002 Seats provided with an occupancy detection means mounted therein or thereon detection means responsive to presence or absence of children B60N2/266
• CPC Class Codes: B60R 21/01512 Passenger detection systems
• CPC Class Codes: B60R 21/01556 Child-seat detection systems

Abstract

The invention relates to a system for monitoring the interior of a vehicle, wherein changes occurring in the occupancy of a seat, e.g. with a person P, a child seat K, an empty seat L, or an occupancy in another occupancy category, are effected in a computer unit by means of transitional probabilities which are externally specified to the monitoring system and which reflect the rapid speed at which a change in occupancy is taken into account by said monitoring system. As a result, an associated airbag or another safety device is activated or de-activated accordingly.

Claims

1. A system for monitoring the interior of a vehicle having a device for detecting data representing the occupancy state of a location in the interior of a vehicle and having a computing unit for obtaining association probabilities with respect to occupancy classes for a selected location in the interior of a vehicle with the aid of features representing the occupancy state of a location in the interior of a vehicle from-measurement data of the device, characterized

in that the computing unit is connected to a memory in which are stored transitional probabilities between the occupancy classes in accordance with which transitions occur between the occupancy classes.

2. The monitoring system as claimed in claim 1, characterized

in that a threshold value is defined, and in that the features are allocated to an occupancy class only when they lie above the threshold value.

3. The monitoring system as claimed in claim 1 or 2, characterized in that the monitoring system is equipped with a switch or sensor for detecting the opening state of at least one door of the vehicle, in that the computing unit is connected to the switch or the sensor via a data line, and in that data of the switch or of the sensor can be evaluated in the computing unit.

4. The monitoring system as claimed in claim 3, characterized in that the transitional probabilities between the occupancy classes can be set in a manner dependent on the opening state of the door by the computing unit by means of an algorithm.

5. The monitoring system as claimed in one of claims 1 to 4, characterized in that the transitional probabilities are stored in the memory as matrix elements.

6. The monitoring system as claimed in one of claims 1 to 5, characterized in that the transitional probabilities are numerical values which embody the number of classification cycles after which a change in an occupancy state from one occupancy class to another occupancy class is deemed to have occurred.

7. A method for monitoring the interior of a vehicle, data representing the occupancy state of a location in the interior of a vehicle being measured, and association probabilities with respect to occupancy classes for a selected location in the interior of a vehicle being obtained with the aid of features representing the occupancy state of a location in the interior of a vehicle from measured data, characterized

in that transitional probabilities between the occupancy classes in accordance with which transitions occur between the occupancy classes are determined.

8. The method as claimed in claim 7, characterized in that the transitional probabilities are defined according to how probable the transition is considered to be.

9. The method as claimed in claim 7 or 8, characterized in that the transitional probabilities are defined according to how reliably the association probabilities are obtained.

10. The method as claimed in one of claims 7 to 9, characterized in that the transitional probabilities are defined according to how relevant they are to the safety of a person.

11. The method as claimed in one of claims 7 to 10, characterized in that the transitional probabilities are varied in a manner dependent on time or the movement state of the vehicle.

12. The method as claimed in one of claims 7 to 11, characterized in that the values for the association probabilities are smoothed with respect to time by averaging.

13. The method as claimed in claim 12, characterized in that by a weighting of association probabilities which is referred to a period of time is carried out.

14. The method as claimed in claim 13, characterized in that current association probabilities are weighted more strongly in comparison with association probabilities determined earlier.

15. The method as claimed in one of claims 7 to 14, characterized in that the transitional probabilities are defined in a manner dependent on the opening state of a door of the vehicle.

16. The method as claimed in claim 15, characterized in that, while the door is open, a safety device for protecting persons and/or objects in the interior of a vehicle remains deactivated.

17. The method as claimed in claim 15 or 16, characterized in that an airbag remains deactivated as long as the door is open.

18. The method as claimed in one of claims 15 to 17, in that, after the closing of the door, high transitional probabilities are permitted for transitions between the occupancy classes, and in that the transitional probabilities are lowered over the course of time.

19. The method as claimed in claim 18, characterized in that an averaging is performed over results of classifications of an occupancy state with respect to occupancy classes of the seat per occupancy class, the number of results which have an influence on the averaging being increased over the course of time.

20. The method as claimed in claim 18, characterized in that an averaging is performed over results of a classification of an occupancy state with respect to the occupancy class “

person sitting normally”

, and in that, if an assignment to the occupancy class “

person sitting normally”

is not performed over a predetermined period of time with a high association probability, the seat is allocated the occupancy class “

child seated”

.

21. The method as claimed in claim 18, characterized in that the transitional probabilities between occupancy classes are adapted in a manner dependent on fluctuations in the association probabilities.