Apparatuses, systems and methods for classifying digital images

• US 10,565,460 B1
• Filed: 01/13/2016
• Issued: 02/18/2020
• Est. Priority Date: 01/13/2015
• Status: Active Grant

• Current Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Original Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Inventors: Chan, Aaron Scott, Sanchez, Kenneth Jason
• Primary Examiner(s): Azima, Shaghayegh
• Application Number:
  US14/994,308
• Time in Patent Office: 1,497 Days
• CPC Class Codes: B60R 21/01542 detecting passenger motion
• CPC Class Codes: B60R 21/01552 detecting position of specific human body parts, e.g. face, eyes or hands
• CPC Class Codes: B60R 2300/30 characterised by the type of image processing
• CPC Class Codes: B60R 2300/8006 for monitoring and displaying scenes of vehicle interior, e.g. for monitoring passengers or cargo
• CPC Class Codes: B60W 2040/0872 Driver physiology
• CPC Class Codes: B60W 2050/0095 Automatic control mode change
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2420/54 Audio sensitive means, e.g. ultrasound
• CPC Class Codes: B60W 2540/22 Psychological state; Stress level or workload
• CPC Class Codes: B60W 2540/223 Posture, e.g. hand, foot, or seat position, turned or inclined
• CPC Class Codes: B60W 2540/225 Direction of gaze
• CPC Class Codes: B60W 2540/229 Attention level, e.g. attentive to driving, reading or sleeping
• CPC Class Codes: B60W 2540/26 Incapacity
• CPC Class Codes: B60W 40/08 related to drivers or passengers
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: B60W 50/08 Interaction between the driver and the control system
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention
• CPC Class Codes: B60W 60/0053 from vehicle to occupant
• CPC Class Codes: B60W 60/0059 Estimation of the risk associated with autonomous or manual driving, e.g. situation too complex, sensor failure or driver incapacity
• CPC Class Codes: B60Y 2400/30 Sensors
• CPC Class Codes: B60Y 2400/3015 : Optical cameras
• CPC Class Codes: B60Y 2400/3017 : Radars
• CPC Class Codes: G01S 19/42 : Determining position
• CPC Class Codes: G05D 1/0061 : for transition from automatic pilot to manual pilot and vice versa
• CPC Class Codes: G06F 16/51 : Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 18/22 : Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/24 : Classification techniques
• CPC Class Codes: G06F 18/2413 : based on distances to training or reference patterns
• CPC Class Codes: G06T 15/005 : General purpose rendering architectures
• CPC Class Codes: G06T 2207/30196 : Human being; Person
• CPC Class Codes: G06T 2207/30268 : Vehicle interior
• CPC Class Codes: G06T 7/337 : involving reference images or patches
• CPC Class Codes: G06T 7/70 : Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/73 : using feature-based methods
• CPC Class Codes: G06V 20/59 : inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
• CPC Class Codes: G06V 20/593 : Recognising seat occupancy
• CPC Class Codes: G06V 20/597 : Recognising the driver's state or behaviour, e.g. attention or drowsiness
• CPC Class Codes: G06V 20/64 : Three-dimensional objects
• CPC Class Codes: G06V 40/10 : Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/11 : Hand-related biometrics; Hand pose recognition
• CPC Class Codes: H04N 19/17 : the unit being an image region, e.g. an object
• CPC Class Codes: H04N 19/423 : characterised by memory arrangements H04N19/433 takes precedence
• CPC Class Codes: H04N 23/45 : for generating image signals from two or more image sensors being of different type or operating in different modes, e.g. with a CMOS sensor for moving images in combination with a charge-coupled device [CCD] for still images

Abstract

The present disclosure is directed to apparatuses, systems and methods for automatically classifying images of occupants inside a vehicle. More particularly, the present disclosure is directed to apparatuses, systems and methods for automatically classifying images of occupants inside a vehicle by comparing current image feature data to previously classified image features.

Claims

1. A vehicle in-cabin imaging device for generating data representative of at least one skeletal diagram of at least one occupant within an associated vehicle, the vehicle in-cabin imaging device comprising:

at least one vehicle interior sensor for acquiring vehicle interior data, wherein the vehicle interior data is representative of at least one image sequence of at least one vehicle occupant;

a memory for storing the vehicle interior data, vehicle occupant skeletal diagram data relating to the vehicle interior data, a vehicle interior data receiving module, a vehicle interior data normalization module, a current image feature extraction module, and a skeletal diagram data generation module; and

a processor that is configured to generate skeletal diagram data by;

receiving vehicle interior data, from the at least one vehicle interior sensor in response to the processor executing the vehicle interior data receiving module;

generating normalized vehicle occupant data from the at least one sensor in response to the processor executing the vehicle interior data normalization module, wherein the normalized vehicle occupant data is representative of scaled and rotated vehicle occupant postures normalized for a range of different drivers;

creating a skeletal diagram record for the at least one vehicle occupant comprising the normalized vehicle occupant data of the at least one vehicle occupant;

extracting three-dimensional coordinate spatial locations of at least one vehicle occupant from the normalized vehicle occupant data, wherein the three-dimensional coordinate spatial locations of the at least one vehicle occupant are stored in the skeletal diagram record, and wherein the three-dimensional coordinate spatial locations of the at least one vehicle occupant are representative of whether at least one hand of the vehicle occupant is empty;

generating skeletal diagram data, based on the normalized vehicle occupant data, in response to the processor executing the skeletal diagram data generation module; and

automatically updating the skeletal diagram record with the skeletal diagram data.

2. The vehicle in-cabin imaging device as in claim 1, wherein the at least one vehicle interior sensor is selected from:

at least one digital image sensor, at least one ultra-sonic sensor, at least one radar-sensor, at least one infrared light sensor, or at least one laser light sensor.

3. The vehicle in-cabin imaging device as in claim 1, wherein the skeletal diagram data is representative of a three-dimensional location of at least one vehicle occupant within the vehicle interior.

4. The vehicle in-cabin imaging device as in claim 1, wherein the skeletal diagram data is representative of an orientation of at least a portion of at least one vehicle occupant within the vehicle interior.

5. The vehicle in-cabin imaging device as in claim 1, wherein the skeletal diagram data is representative of a three-dimensional location of at least a portion of at least one occupant within the vehicle interior and an orientation of the portion of the at least one vehicle occupant.

6. The vehicle in-cabin imaging device as in claim 1, wherein the skeletal diagram data is representative of at least one of:

a vehicle occupant head location/orientation, a vehicle occupant hand location/orientation, a vehicle occupant arm location/orientation, a vehicle occupant elbow location/orientation, a vehicle occupant torso location/orientation, or a vehicle occupant eye location/orientation.

7. The vehicle in-cabin imaging device as in claim 1, wherein the vehicle interior data is representative of at least one of:

a vehicle occupant head location/orientation, a vehicle occupant hand location/orientation, a vehicle occupant arm location/orientation, a vehicle occupant elbow location/orientation, a vehicle occupant torso location/orientation, a seat belt location, a cellular telephone location, a vehicle occupant eye location/orientation, or a vehicle seat location/orientation.

8. A computer-implemented method for automatically classifying images of a vehicle interior, the method comprising:

receiving, at the processor, previously classified image features data from a remote computing device, in response to the processor executing a previously classified image features data receiving module, wherein the previously classified image features data is representative of known image features of at least one vehicle interior;

receiving current image data, at the processor, from at least one sensor, wherein the current image data is representative of current images of a vehicle interior;

generating normalized vehicle occupant data, based on the current image data, in response to the processor executing a vehicle interior data normalization module, wherein the normalized vehicle occupant data is representative of scaled and rotated vehicle occupant postures normalized for a range of different drivers;

creating, using the processor, a classified image feature record for the at least one vehicle occupant comprising the normalized vehicle occupant data of the at least one vehicle occupant;

extracting three-dimensional coordinate spatial locations of at least one vehicle occupant from the normalized vehicle occupant data, the three-dimensional coordinate spatial locations of the at least one vehicle occupant are stored in the classified image feature record as current image feature data, wherein the current image feature data is representative of current image features of a vehicle interior, and wherein the three-dimensional coordinate spatial locations of the at least one vehicle occupant are representative of whether at least one hand of the vehicle occupant is empty;

classifying current image features, using the processor, based on the normalized vehicle occupant data and a comparison of the current image feature data with the previously classified image features data; and

automatically updating the classified image feature record with the classified current image features.

9. The method of claim 8, wherein the current image feature data is representative of at least one of:

a vehicle occupant head location/orientation, a vehicle occupant hand location/orientation, a vehicle occupant arm location/orientation, a vehicle occupant elbow location/orientation, a vehicle occupant torso location/orientation, a seat belt location, a cellular telephone location, a vehicle occupant eye location/orientation, or a vehicle seat location/orientation.

10. The method of claim 8, wherein the previously classified image features data is representative of at least one of:

a vehicle occupant head location/orientation, a vehicle occupant hand location/orientation, a vehicle occupant arm location/orientation, a vehicle occupant elbow location/orientation, a vehicle occupant torso location/orientation, a seat belt location, a cellular telephone location, a vehicle occupant eye location/orientation, or a vehicle seat location/orientation.

11. The method of claim 8, wherein the current image feature data is representative of a three-dimensional location of at least one vehicle occupant within the vehicle interior.

12. The method of claim 8, wherein the current image feature data is representative of an orientation of at least a portion of at least one vehicle occupant within the vehicle interior.

13. The method of claim 8, wherein the current image feature data is representative of a three-dimensional location of at least a portion of at least one occupant within the vehicle interior and an orientation of the portion of the at least one vehicle occupant.

14. A non-transitory computer-readable medium storing computer-readable instruction that, when executed by a processor, cause the processor to automatically classify image features of an interior of a vehicle, the non-transitory computer-readable medium comprising:

a previously classified image features data receiving module that, when executed by the processor, causes the processor to receive previously classified image features data from a remote computing device, wherein the previously classified image features data is representative of known image features of at least one vehicle interior;

a current image data receiving module that, when executed by the processor, causes the processor to receive current image data from at least one sensor, wherein the current image data is representative of current image of a vehicle interior;

a vehicle interior data normalization module that, when executed by the processor, causes the processor to generate normalized vehicle occupant data based on the current image data, wherein the normalized vehicle occupant data is representative of scaled and rotated vehicle occupant postures normalized for a range of different drivers;

creating, using the processor, a classified image feature record for the at least one vehicle occupant comprising the normalized vehicle occupant data;

a current image feature data extraction module that, when executed by the processor, causes the processor to extract current image feature data from the normalized vehicle occupant data, wherein the current image feature data is representative of current image features of a vehicle interior, and wherein the current image feature data is representative of whether at least one hand of the vehicle occupant is empty;

a current image feature classification module that, when executed by the processor, causes the processor to classify current image features based on the normalized vehicle occupant data and a comparison of the current image feature data with the previously classified image features data; and

automatically updating the classified image feature record with the classified current image features.

15. The non-transitory computer-readable medium of claim 14, wherein the current image feature data is representative of a three-dimensional location of at least a portion of at least one occupant within the vehicle interior and an orientation of the portion of the at least one vehicle occupant.

16. The non-transitory computer-readable medium of claim 14, wherein the current image feature data is representative of an orientation of at least a portion of at least one vehicle occupant within the vehicle interior.

17. The non-transitory computer-readable medium of claim 14, wherein the current image feature data is representative of a three-dimensional location of at least one vehicle occupant within the vehicle interior.

18. The non-transitory computer-readable medium of claim 14, wherein the current image feature data is representative of at least one of:

a vehicle occupant head location/orientation, a vehicle occupant hand location/orientation, a vehicle occupant arm location/orientation, a vehicle occupant elbow location/orientation, a vehicle occupant torso location/orientation, a seat belt location, a cellular telephone location, a vehicle occupant eye location/orientation, or a vehicle seat location/orientation.

19. The non-transitory computer-readable medium of claim 14, wherein the previously classified image features data is representative of at least one of:

a vehicle occupant head location/orientation, a vehicle occupant hand location/orientation, a vehicle occupant arm location/orientation, a vehicle occupant elbow location/orientation, a vehicle occupant torso location/orientation, a seat belt location, a cellular telephone location, a vehicle occupant eye location/orientation, or a vehicle seat location/orientation.

20. The non-transitory computer-readable medium of claim 14, wherein the at least one sensor is selected from:

at least one digital image sensor, at least one ultra-sonic sensor, at least one radar-sensor, at least one infrared light sensor, or at least one laser light sensor.