Methods and systems to detect vehicle theft events

Patent metadata

Field	Value
Publication number	US-11919475-B2
Application number	US-202117304531-A
Country	US
Kind code	B2
Filing date	Jun 22, 2021
Priority date	Jun 22, 2021
Publication date	Mar 5, 2024
Grant date	Mar 5, 2024

Abstract

In an exemplary embodiment, a system is provided that includes a sensor, a computer memory, and a processor. The sensor is configured to be disposed on a vehicle, and is configured to obtain sound or vibration data for the vehicle. The computer memory is configured to store a plurality of known signatures pertaining to a plurality of different types of vehicle theft events. The processor is configured to: compare a signature of the data with the plurality of known signatures stored in the computer memory; and determine whether a vehicle theft event is occurring based on the comparing of the signature of the data with the plurality of known signatures.

First claim

What is claimed is:

1. A system comprising:
a sensor configured to be disposed on a vehicle and configured to obtain sound or vibration data for the vehicle, outside the vehicle, including a first combination of frequencies and locations of a first plurality of sounds or vibrations from the sound or vibration data outside the vehicle;
a computer memory configured to store a plurality of known signatures pertaining to a plurality of different types of vehicle theft events, the plurality of known signatures comprising a second combination of frequencies and locations corresponding to different sounds or vibrations, as to a plurality of types of events, including vehicle theft events; and
a processor configured to:
compare a signature of the sound or vibration data with the plurality of known signatures stored in the computer memory, by comparing the first combination of frequencies and locations of the first plurality of sounds or vibrations from the sound or vibration data outside the vehicle with the second combination of frequencies and locations of a second plurality of sounds or vibrations from the plurality of known signatures stored in the computer memory; and
determine whether a vehicle theft event is occurring based on the comparing of the signature of the sound or vibration data with the plurality of known signatures, including as to the comparing of the first combination of frequencies and locations of the first plurality of sounds or vibrations from the sound or vibration data outside the vehicle with the second combination of frequencies and locations of the second plurality of sounds or vibrations from the plurality of known signatures stored in the computer memory.

2. The system of claim 1 , wherein:
the sensor comprises a microphone; and
the sound or vibration data comprises sound data from the microphone.

3. The system of claim 1 , wherein:
the sensor comprises an ultrasonic sensor; and
the sound or vibration data comprises vibration data from the ultrasonic sensor.

4. The system of claim 1 , wherein the processor is configured to provide instructions for taking a responsive vehicle control action when it is determined that a vehicle theft act is occurring.

5. The system of claim 1 , wherein:
each of the plurality of known signatures comprises a different one of a plurality of tools that are known to be associated with different types of vehicle theft actions, wherein the plurality of tools include one or more cutting devices, one or more types of hydraulic equipment, or both; and
the processor is configured to determine a type of the vehicle theft event based on which particular one of the plurality of tools is associated with a corresponding one of the plurality of known signatures that matches the signature of the sound or vibration data.

6. The system of claim 1 , wherein the processor is further configured to generate the plurality of known signatures using machine learning in connection with the plurality of known signatures comprising the second combination of frequencies and locations corresponding to different sounds or vibrations, as to the plurality of types of events, including vehicle theft events, and further including enhanced learning as to ambient sounds that correspond to an environment surrounding the vehicle when no vehicle theft actions are occurring.

7. The system of claim 5 , wherein the plurality of tools include one or more saws.

8. The system of claim 5 , wherein the plurality of tools include the one or more types of hydraulic equipment.

9. The system of claim 6 , wherein the machine learning further includes enhanced learning as to the ambient sounds based on whether the environment surrounding the vehicle comprises a urban environment versus a rural environment.

10. The system of claim 6 , wherein the machine learning further includes enhanced learning as to the ambient sounds based on weather conditions associated with the environment surrounding the vehicle.

11. A vehicle comprising:
a body forming a cabin;
a sensor disposed on a portion of the body and configured to obtain sound or vibration data from outside the cabin, including a first combination of frequencies and locations of a first plurality of sounds or vibrations from the sound or vibration data outside the cabin;
a computer memory configured to store a plurality of known signatures pertaining to a plurality of different types of vehicle theft events, the plurality of known signatures comprising a second combination of frequencies and locations corresponding to different sounds or vibrations, as to a plurality of types of events, including vehicle theft events; and
a processor configured to:
compare a signature of the sound or vibration data with the plurality of known signatures stored in the computer memory, by comparing the first combination of frequencies and locations of the first plurality of sounds or vibrations from the sound or vibration data outside the vehicle with the second combination of frequencies and locations of a second plurality of sounds or vibrations from the plurality of known signatures stored in the computer memory; and
determine whether a vehicle theft event is occurring based on the comparing of the signature of the sound or vibration data with the plurality of known signatures, including as to the comparing of the first combination of frequencies and locations of the first plurality of sounds or vibrations from the sound or vibration data outside the vehicle with the second combination of frequencies and locations of the second plurality of sounds or vibrations from the plurality of known signatures stored in the computer memory.

12. The vehicle of claim 11 , wherein:
the sensor comprises a microphone; and
the sound or vibration data comprises sound data from the microphone.

13. The vehicle of claim 11 , wherein:
the sensor comprises an ultrasonic sensor; and
the sound or vibration data comprises vibration data from the ultrasonic sensor.

14. The vehicle of claim 11 , wherein:
each of the plurality of known signatures comprises a different one of a plurality of tools that are known to be associated with different types of vehicle theft actions, wherein the plurality of tools include one or more cutting devices, one or more types of hydraulic equipment, or both; and
the processor is configured to determine a type of the vehicle theft event based on which particular one of the plurality of tools is associated with a corresponding one of the plurality of known signatures that matches the signature of the sound or vibration data.

15. The vehicle of claim 11 , wherein the processor is configured to provide instructions for taking a responsive vehicle control action when it is determined that a vehicle theft act is occurring.

16. The vehicle of claim 11 , wherein the processor is further configured to update the plurality of known signatures via downloads obtained by the vehicle from a remote server.

17. The vehicle of claim 11 , wherein the processor is further configured to generate the plurality of known signatures using machine learning in connection with the plurality of known signatures comprising the second combination of frequencies and locations corresponding to different sounds or vibrations, as to the plurality of types of events, including vehicle theft events, and further including enhanced learning as to ambient sounds that correspond to an environment surrounding the vehicle when no vehicle theft actions are occurring.

18. A method comprising:
obtaining sound or vibration data for a vehicl

Assignees

• Gm Global Tech Operations Llc

Inventors

• Gilbert-Eyres Matthew Edward
• Patenaude Russell A
• Hosey Eric T

Classifications

• B60R25/1009 Primary

  Sonic sensors; Signal treatment therefor · CPC title

• G01S15/88

  Sonar systems specially adapted for specific applications (seismic or acoustic prospecting or detecting G01V1/00) · CPC title

• G06N20/00

  Machine learning · CPC title

• H04R1/222

  for microphones (H04R1/24, H04R1/26 take precedence) · CPC title

• B60R25/00 Primary

  Fittings or systems for preventing or indicating unauthorised use or theft of vehicles (locks for vehicles E05B77/00-E05B85/00) · CPC title