Granted Patent B1

US 12,358,451 · App. 17/164,390 · Granted Jul 15, 2025

Inventors: Aaron Scott Chan (San Jose, CA); Kenneth J. Sanchez (San Francisco, CA)

Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

B60R21/0156B60N2/0027B60R21/0136B60R21/01538B60R21/01542B60R21/01544B60R21/01562B60N2210/24B60R2021/0027B60R2021/01315

Abstract

Claims (48)

1. A system comprising:

one or more image sensors configured to detect a posture of an occupant within a vehicle;

one or more audio sensors configured to detect audio data associated with the vehicle;

one or more computing devices of a remote computing system located remotely from the vehicle and communicatively coupled to the vehicle; and

a non-transitory computer-readable memory coupled to the one or more computing devices and storing thereon instructions that, when executed by the one or more computing devices, cause the one or more computing devices to:

receive real-time information indicative of the posture of the occupant within the vehicle, wherein the real-time information indicative of the posture comprises two-dimensional or three-dimensional image data detected in real-time by the one or more image sensors coupled to the vehicle during operation of the vehicle prior to a change in momentum associated with the vehicle;

receive, via a further one or more sensors of the vehicle, information indicative of the change in momentum associated with the vehicle, the change in momentum involving the vehicle physically contacting another entity;

receive, via the one or more audio sensors of the vehicle, information indicative of damage to one or more glass panes of the vehicle, the information indicative of damage to the one or more glass panes being based on an identification of a frequency in the audio data indicating the damage to the one or more glass panes;

responsive to receiving the information indicative of the change in momentum, determine the posture the occupant prior to the change in momentum by analyzing a subset of the two-dimensional or three-dimensional image data from a time prior to the change in momentum, with respect to two-dimensional or three-dimensional image data indicative of various levels of risk of occupant vehicle ejection;

determine the change in momentum of the vehicle by at least one of (i) determining a mass or speed of the another entity, or (ii) comparing the change in momentum to other similar vehicle contact scenarios involving entities similar to the another entity;

determine whether one or more conditions corresponding to an increased likelihood of ejection of the occupant are present, the one or more conditions include (i) the change in momentum, (ii) the damage to the one or more glass panes, and (iii) the posture of the occupant prior to the change in momentum; and

in response to determining that the one or more conditions corresponding to the increased likelihood of ejection of the occupant are present, automatically generate and provide a visual notification to a device of a responder in real time to cause the device of the responder to automatically display the visual notification upon the visual notification being provided to the device of the responder, wherein the visual notification indicates (i) that the increased likelihood of ejection of the occupant is present, (ii) a location of the occupant, and (iii) a radial distance of the occupant from the vehicle to the location of the occupant based upon a trajectory of the occupant.

2. The system of claim 1 , wherein the instructions that cause the one or more computing devices to determine whether the one or more conditions corresponding to the increased likelihood of ejection of the occupant are present further include instructions to:

determine one or more locations corresponding to the damage to the one or more glass panes;

determine the location of the occupant based on the one or more locations corresponding to the damage to the one or more glass panes; and

based on the location of the occupant, determine whether one or more further conditions corresponding to increased likelihood of ejection of the occupant are present.

3. The system of claim 1 , wherein the instructions that cause the one or more computing devices to determine whether the one or more conditions corresponding to the increased likelihood of ejection of the occupant are present further include instructions to:

receive information indicative of seatbelt restraint associated with the occupant prior to the change in momentum, wherein the information indicative of the seatbelt restraint is based on data captured by the further one or more sensors of the vehicle; and

determine whether one or more further conditions corresponding to increased likelihood of ejection of the occupant are present, based upon the information indicative of seatbelt restraint.

4. The system of claim 1 , wherein the instructions that cause the one or more computing devices to determine whether the one or more conditions corresponding to the increased likelihood of ejection of the occupant are present further include instructions to:

compare the posture of the occupant to one or more postures associated with a predetermined likelihood of vehicle ejection; and

based on a match of the posture of the occupant to at least one of the one or more postures, determine that at least one of the one or more conditions corresponding to the increased likelihood of ejection of the occupant are present.

5. The system of claim 1 , wherein the instructions to determine the change in momentum include instructions to determine a magnitude of the change in momentum by at least one of (i) determining the mass or speed of the another entity, or (ii) comparing the change in momentum to other similar vehicle contact scenarios involving entities similar to the another entity, and wherein the one or more conditions corresponding to the increased likelihood of ejection include the magnitude of the change in momentum.

6. A computer-implemented method comprising:

receiving, at a remote computing system including one or more processors and located remotely from a vehicle to which the remote computing system is communicatively coupled, real-time information indicative of a position of an occupant within a vehicle, wherein the real-time information indicative of the position comprises two-dimensional or three-dimensional image data detected in real-time by one or more image sensors coupled to the vehicle during operation of the vehicle prior to vehicle contact involving the occupant, the detected data being sent to the system in real-time via one or more computing devices coupled to the vehicle;

receiving, at the computing system, via a further one or more sensors of the vehicle, information indicative of the vehicle contact involving the occupant, the vehicle contact involving the vehicle physically contacting another entity and causing a change in momentum of the vehicle;

receiving, via one or more audio sensors of the vehicle, information indicative of damage to one or more glass panes of the vehicle, the information indicative of damage to the one or more glass panes being based on an identification of a frequency in the audio data indicating the damage to the one or more glass panes;

responsive to receiving the information indicative of the vehicle contact, determining the position of the occupant prior to the vehicle contact by analyzing a subset of the two-dimensional or three-dimensional image data from a time prior to the vehicle contact, with respect to two-dimensional or three-dimensional position data indicative of various levels of risk of occupant vehicle ejection;

determining the change in momentum by at least one of (i) determining a mass or speed of the another entity, or (ii) comparing the change in momentum to other similar vehicle contact scenarios involving entities similar to the another entity;

determining, by the one or more processors, whether one or more conditions corresponding to an increased likelihood of ejection of the occupant are present, the one or more conditions include (i) the information indicative of the vehicle contact, (ii) the position of the occupant prior to the vehicle contact, (iii) the change of momentum of the vehicle, and (iv) the damage to the one or more glass panes; and

in response to determining that at least one of the one or more conditions corresponding to the increased likelihood of ejection of the occupant are present:

determining, by the one or more processors, a location of the occupant subsequent to the vehicle contact according to the information indicative of the vehicle contact; and

automatically generating and providing, by the computing system, a visual notification to a device of a responder in real time to cause the device of the responder to automatically display the visual notification upon the visual notification being provided to the device of the responder, wherein the visual notification includes (i) the location of the occupant, and (ii) a radial distance of the occupant from the vehicle to the location of the occupant based upon a trajectory of the occupant.

7. The computer-implemented method of claim 6 , wherein determining whether the one or more conditions corresponding to the increased likelihood of ejection of the occupant are present further includes:

determining, by the one or more processors, one or more locations corresponding to the damage to the one or more glass panes of the vehicle;

determining, by the one or more processors, the location of the occupant based on the one or more locations corresponding to the damage to the one or more glass panes; and

based on the location of the occupant, determine whether one or more further conditions corresponding to increased likelihood of ejection of the occupant are present.

8. The computer-implemented method of claim 6 , wherein determining whether the one or more conditions corresponding to the increased likelihood of ejection of the occupant are present further includes:

receiving, at the computing system, information indicative of seatbelt restraint associated with the occupant prior to the vehicle contact; and

determine whether one or more further conditions corresponding to increased likelihood of ejection of the occupant are present, based upon the information indicative of seatbelt restraint.

9. The computer-implemented method of claim 6 , wherein determining the location of the occupant further includes:

receiving, at the computing system, information indicative of a location of a mobile device associated with the occupant; and

updating, by the computing system, the location of the occupant according to the location of the mobile device.

10. The computer-implemented method of claim 6 , wherein determining whether the one or more conditions corresponding to the increased likelihood of ejection of the occupant are present further includes:

comparing, by the computing system, the position of the occupant to one or more positions associated with a predetermined likelihood of vehicle ejection; and

based on a match of the position of the occupant to at least one of the one more positions, determining that at least one of the one or more conditions corresponding to the increased likelihood of ejection of the occupant are present.

11. The computer-implemented method of claim 10 , wherein the one or more positions associated with the predetermined likelihood of vehicle ejection include one or more recumbent positions within the vehicle.

12. The computer-implemented method of claim 6 , wherein determining the change in momentum includes determining a magnitude of the change in momentum by at least one of (i) determining the mass or speed of the another entity, or (ii) comparing the change in momentum to other similar vehicle contact scenarios involving entities similar to the another entity, and wherein the one or more conditions corresponding to the increased likelihood of ejection include the magnitude of the change in momentum.

Assignments (1)

Continuity (2)

References Cited (191)