Granted Patent B2

US 12,315,302 · App. 17/465,885 · Granted May 27, 2025

Inventors: Neslihan Kose Cihangir (Munich, DE); Nese Alyuz Civitci (Portland, OR); Rafael Rosales (Unterhaching, DE); Ignacio J. Alvarez (Portland, OR)

Assignee: Intel Corporation

G06V40/40B60R25/31G06F21/32G06V20/597G06V40/171G06V40/172G06V40/28G06V40/70

Abstract

Claims (118)

1. A device comprising:

a processor; and

an interface coupled to the processor, wherein the interface is configured to communicatively couple the processor to one or more input devices via an electrical or a radio connection;

wherein the processor is configured to:

receive, via the interface, first sensor data comprising information indicating a detection comprising a facial attribute of an occupant for a vehicle, second sensor data comprising information indicating a detection comprising a body attribute of the occupant for a period of time, and movement information representing kinematic forces that the vehicle experiences;

determine an identity for the occupant based on the first sensor data;

estimate a behavior for the occupant based on the second sensor data, wherein the behavior is estimated based on a detected action of the occupant;

determine a spoofing attempt result indicating whether the occupant attempts a spoofing based on the determined identity and the estimated behavior,

wherein the spoofing attempt result is determined to represent that the occupant attempts the spoofing if the detected action does not correspond to the information indicating the kinematic forces that the vehicle experiences.

2. The device of claim 1 ,

wherein the first sensor data comprises a first modality information indicating the detection of the facial attribute of the occupant based on a first modality and a second modality information indicating the detection of the facial attribute of the occupant based on a second modality,

wherein the first modality information comprises a near-infrared (NIR) image of the occupant, and the second modality information comprises a depth image of the occupant,

wherein the processor is further configured to determine the spoofing attempt result based on the first modality information and the second modality information.

3. The device of claim 2 ,

wherein the processor is further configured to:

generate a first spoofing attempt score based on the first modality information;

generate a second spoofing attempt score based on the second modality information;

combine the first spoofing attempt score and the second spoofing attempt score to determine the spoofing attempt result.

4. The device of claim 1 ,

wherein the processor is further configured to:

determine the identity for the occupant based on the first sensor data according to an occupant information comprising one or more occupant facial attributes.

5. The device of claim 1 ,

wherein the second sensor data comprises information indicating the detection of the body attribute of the occupant for a period of time, and wherein the processor is further configured to:

detect an action of the occupant spatiotemporally to obtain the detected action; and

estimate the behavior of the occupant based on the detected action of the occupant.

6. The device of claim 5 ,

wherein the processor is further configured to:

compare the detected action of the occupant and a predefined spoofing action; and

determine the spoofing attempt result based on the comparison of the detected action with the predefined spoofing action.

7. The device of claim 5 ,

wherein the detected action comprises a first action based on the second sensor data comprising information indicating the detection of the occupant for a first period of time,

wherein the processor is configured to:

detect a second action based on the second sensor data comprising information indicating a detection of the occupant for a second period of time;

determine the spoofing attempt result based on the first action and the second action;

compare the first action with the second action to obtain a difference score to determine the spoofing attempt result.

8. The device of claim 5 ,

wherein the processor is further configured to determine the spoofing attempt result based on the movement information indicating the movement of the vehicle on at least one time instance and the detected action.

9. The device of claim 1 ,

wherein the processor is further configured to:

determine the spoofing attempt result based on a third sensor data comprising information indicating detection of an attribute of a further occupant located in the vehicle;

detect a further occupant action for the further occupant based on the third sensor data; and

determine the spoofing attempt result based on the detected further occupant action.

10. The device of claim 4 ,

wherein the second sensor data comprises at least one image of at least a portion of the body of the occupant,

wherein the occupant information comprises information indicating a predefined behavior for the occupant,

wherein the processor is further configured to:

estimate a second identity by comparing the estimated behavior of the occupant and the occupant information;

determine a matching result indicating whether the first identity matches the second identity;

determine the spoofing attempt result based on the matching result.

11. The device of claim 1 ,

wherein the second sensor data comprising information indicating a detection of a second modality, the second modality comprises an interaction of the occupant with the vehicle using a hand.

12. The device of claim 10 ,

wherein the determined identity comprises a first identity,

wherein the occupant information comprises information indicating a predefined behavior for the occupant, and

wherein the processor is further configured to:

determine a second identity for the occupant based on the estimated behavior for the occupant according to the occupant information;

determine the second identity by comparing the estimated behavior of the occupant and the occupant information comprising a plurality of behaviors for a plurality of occupants.

13. A non-transitory computer-readable medium including one or more instructions that when executed on a processor communicatively coupled through an interface to one or more input devices via an electrical or a radio connection, cause the processor to:

receive, via the interface, first sensor data comprising information indicating a detection comprising a facial attribute of an occupant for a vehicle, second sensor data comprising information indicating a detection comprising a body attribute of the occupant for a period of time, and movement information representing kinematic forces that the vehicle experiences;

determine an identity for the occupant of the vehicle based on the first sensor data;

estimate a behavior for the occupant based on the second sensor data, wherein the behavior is estimated based on a detected action of the occupant;

determine a spoofing attempt result indicating whether the occupant attempts a spoofing based on the determined identity and the estimated behavior,

wherein the spoofing attempt result is determined to represent that the occupant attempts the spoofing if the detected action does not correspond to the information indicating the kinematic forces that the vehicle experiences.

14. The non-transitory computer-readable medium of claim 13 , wherein the one or more instructions further cause the processor to:

generate an output, wherein the output comprises at least one of the following:

authentication result indicating a decision to authenticate or not authenticate the occupant based on a matching result;

an adjustment result indicating to adjust a setting of the vehicle based on the at least one setting for an authenticated occupant;

an alertness result indicating a determined alertness score of the occupant based on at least one of the first sensor data and/or the second sensor data;

an encoded message indicating the spoofing attempt result;

a display information to be displayed to the occupant, wherein the display information comprises information indicating an entry for a username and/or password for the occupant; or information indicating a predetermined question for the occupant.

15. The non-transitory computer-readable medium of claim 13 ,

wherein the first sensor data comprises a first modality information indicating the detection of the facial attribute of the occupant based on a first modality and a second modality information indicating the detection of the facial attribute of the occupant based on a second modality,

wherein the first modality information comprises a near-infrared (NIR) image of the occupant, and the second modality information comprises a depth image of the occupant,

wherein the instructions are further configured to cause the processor to determine the spoofing attempt result based on the first modality information and the second modality information.

16. The non-transitory computer-readable medium of claim 15 ,

wherein the instructions are further configured to cause the processor to:

generate a first spoofing attempt score based on the first modality information;

generate a second spoofing attempt score based on the second modality information;

combine the first spoofing attempt score and the second spoofing attempt score to determine the spoofing attempt result.

17. The non-transitory computer-readable medium of claim 13 ,

wherein the instructions are further configured to cause the processor to determine the identity for the occupant based on the first sensor data according to an occupant information comprising one or more occupant facial attributes.

18. The non-transitory computer-readable medium of claim 13 ,

wherein the second sensor data comprises information indicating the detection of the body attribute of the occupant for a period of time, and

wherein the instructions are further configured to cause the processor to:

detect an action of the occupant spatiotemporally to obtain the detected action; and

estimate the behavior of the occupant based on the detected action of the occupant.

19. The non-transitory computer-readable medium of claim 13 ,

wherein the instructions are further configured to cause the processor to:

compare the detected action of the occupant and a predefined spoofing action; and

determine the spoofing attempt result based on the comparison of the detected action with the predefined spoofing action.

20. The non-transitory computer-readable medium of claim 13 ,

wherein the detected action comprises a first action based on the second sensor data comprising information indicating the detection of the occupant for a first period of time,

wherein the instructions are further configured to cause the processor to:

detect a second action based on the second sensor data comprising information indicating a detection of the occupant for a second period of time;

determine the spoofing attempt result based on the first action and the second action;

compare the first action with the second action to obtain a difference score to determine the spoofing attempt result.

21. The non-transitory computer-readable medium of claim 13 ,

wherein the instructions are further configured to cause the processor to determine the spoofing attempt result based on the movement information indicating the movement of the vehicle on at least one time instance and the detected action.

22. The non-transitory computer-readable medium of claim 13 ,

wherein the instructions are further configured to cause the processor to:

determine the spoofing attempt result based on a third sensor data comprising information indicating detection of an attribute of a further occupant located in the vehicle;

detect a further occupant action for the further occupant based on the third sensor data; and

determine the spoofing attempt result based on the detected further occupant action.

23. The non-transitory computer-readable medium of claim 17 ,

wherein the second sensor data comprises at least one image of at least a portion of the body of the occupant,

wherein the occupant information comprises information indicating a predefined behavior for the occupant,

wherein the instructions are further configured to cause the processor to:

estimate a second identity by comparing the estimated behavior of the occupant and the occupant information;

determine a matching result indicating whether the first identity matches the second identity;

determine the spoofing attempt result based on the matching result.

24. The non-transitory computer-readable medium of claim 13 ,

wherein the second sensor data comprising information indicating a detection of a second modality, the second modality comprises an interaction of the occupant with the vehicle using a hand.

25. The non-transitory computer-readable medium of claim 23 ,

wherein the determined identity comprises a first identity,

wherein the occupant information comprises information indicating a predefined behavior for the occupant, and

wherein the instructions are further configured to cause the processor to:

determine a second identity for the occupant based on the estimated behavior for the occupant according to the occupant information;

determine the second identity by comparing the estimated behavior of the occupant and the occupant information comprising a plurality of behaviors for a plurality of occupants.

Assignments (2)

Continuity (1)

References Cited (47)