Process and apparatus for monitoring a vehicle interior

• US 5,680,096 A
• Filed: 07/17/1995
• Issued: 10/21/1997
• Est. Priority Date: 07/16/1994
• Status: Expired due to Fees

• Current Assignee: Kiekert AG (Lingyun Industrial Corporation Limited)
• Original Assignee: Kiekert AG (Lingyun Industrial Corporation Limited)
• Inventors: Grasmann, Ulrich
• Primary Examiner(s): Hofsass, Jeffery
• Assistant Examiner(s): Lefkowitz, Edward
• Application Number:
  US08/502,419
• Time in Patent Office: 827 Days
• Field of Search: 340/426, 340/429, 340/541, 340/546, 340/566, 340/522, 340/552, 307/10.2, 180/287, 367/93, 367/906
• US Class Current: 340/426.27
• CPC Class Codes: B60R 25/1004 Alarm systems characterised by the type of sensor, e.g. current sensing means using door lock sensors B60R25/1001
• CPC Class Codes: B60R 25/1009 Sonic sensors; Signal treatment therefor
• CPC Class Codes: G01S 15/04 Systems determining presence of a target
• CPC Class Codes: G08B 13/1618 using ultrasonic detection means
• CPC Class Codes: G08B 13/1672 using sonic detecting means, e.g. a microphone operating in the audio frequency range
• CPC Class Codes: G08B 29/26 by updating and storing reference thresholds

Abstract

A monitoring of a vehicle interior is effected by detecting sound waves in a vehicle interior, either from an incursion source or as reflected as echo waves and decomposing the electrical signals representing those detected sound waves into measurement vectors which are compared with sample vectors in a neural network so that a correlation parameter is generated which triggers an alarm when the correlation parameter indicates incursion. The system can respond first to glass breakage before an echo system is used to then further establish the nature of the incursion.

Claims

1. A process for monitoring an interior of a vehicle against an incursion, said process comprising:

(a) detecting a sound wave in an interior of a vehicle;

(b) generating a time-dependent electrical measurement signal representing the detected sound wave;

(c) amplifying said time-dependent electrical measurement signal;

(d) feeding the amplified time-dependent electrical measurement signal to a computer and in said computer decomposing said amplified time-dependent electrical measurement signals into discrete measured-value signals and storing said discrete measured-value signals as respective individual vectors in a memory of said computer;

(e) applying each said vectors to an input of a neural network formed by said computer and processing said vector in said neural network by comparison with at least one sample vector to form a correlation parameter representing similarity of a measured-value signal vector and a sample vector; and

(f) activating an alarm device by said neural network in dependence upon said correlation parameter.

2. The process defined in claim 1 wherein said sample vector is formed from a measured signal in the course of an incursion into a vehicle interior and the alarm device is activated when said measured-value signal vector and a sample vector are sufficiently similar as determined by said correlation parameter.

3. The process defined in claim 1 wherein said sample vector is formed from a measured signal not in the course of an incursion into a vehicle interior and the alarm device is activated when said measured-value signal vector and a sample vector are sufficiently dissimilar as determined by said correlation parameter.

4. The process defined in claim 1 wherein said neural network is configured with the architecture of adaptive resonance theory as an ART network and the correlation parameter is an adaptive coefficient thereof.

5. The process defined in claim 1 wherein said neural network is configured with the architecture of an associative memory of the Hopfield network configuration and the correlation parameter is a Hamming distance.

6. The process defined in claim 1 wherein said computer is operated with fuzzy logic.

7. The process defined in claim 1, further comprising the step of rectifying and filtering said amplified time-dependent measuring signal to obtain an envelope curve measurement signal from which an envelope curve vector is formed in said computer and is compared with one or more envelope curve sample vectors in the computer.

8. The process defined in claim 1 wherein the amplified time-dependent measuring signal is spectrally analyzed in the computer by a fast-Fourier-transform algorithm to form a Fourier transform vector which is compared within the computer with at least one Fourier transform sample vector stored in the computer.

9. The process defined in claim 1 wherein said sample vector represents sound generated by breakage of a vehicle window.

10. The process defined in claim 1, further comprising at least one sound-wave generator communicating with said interior and generating primary sound wave pulses in said interior which are reflected and upon which other sound waves are superimposed, said detector picking up reflected superimposed sound waves and producing said time-dependent electrical measurement signal therefrom, said sample vector representing a signal containing components of reflected and superimposed waves.

11. The process defined in claim 1 wherein the comparison is effected alternately with a sample vector representing glass breakage and a sample vector representing a reflected wave in the interior upon which another sound wave is superimposed.

12. The process defined in claim 1 wherein the comparison is effected initially with a sample vector representing glass breakage and only thereafter with application of a primary sound wave pulse to said interior and comparison with a sample vector representing a reflected wave in the interior upon which another sound wave is superimposed.

13. The process defined in claim 1 wherein sound waves in said interior are picked up by a plurality of detectors with respective amplifiers, said process further comprising the step of multiplexing outputs of said amplifiers for input to said computer.

14. An apparatus for monitoring an interior of a vehicle against an incursion, comprising:

at least one detector in an interior of said vehicle for detecting a sound wave in said interior of said vehicle and generating a time-dependent electrical measurement signal representing the detected sound wave;

an amplifier connected to said detector for amplifying said time-dependent electrical measurement signal;

a computer connected to said amplifier and fed with the amplified time-dependent electrical measurement signal for decomposing said amplified time-dependent electrical measurement signals into discrete measured-value signals and storing said discrete measured-value signals as respective individual measurement vectors in a memory of said computer, said computer forming a neural network to inputs of which each of said vectors is applied for processing of said measurement vectors in said neural network by comparison with at least one sample vector to form a correlation parameter representing similarity of a measurement vector and a sample vector; and

an alarm device connected to said computer and activated by said neural network in dependence upon said correlation parameter.

15. The apparatus defined in claim 14, further comprising a sound generator in said interior controlled by said computer for generating primary sound wave pulses in said interior.

16. The apparatus defined in claim 14, further comprising a rectifier and a filter connected between said amplifier and said computer for producing an envelope curve measurement signal.

17. The apparatus defined in claim 14 wherein said computer includes an analog-digital converter for converting analog measurement signals to binary digital data sets.

18. The apparatus defined in claim 14 wherein a plurality of sound detectors are provided each having a respective amplifier, said apparatus further comprising a multiplexer having a plurality of inputs each connected to one of said amplifier and an output connected to said computer.