Apparatus, systems and methods for classifying digital images
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.
1. A system for classifying image features associated with at least one occupant within an associated vehicle, the system comprising:
a module stored on a memory that, when executed by a processor, is configured to receive a signal from at least one vehicle interior sensor for acquiring vehicle interior data representative of at least one vehicle occupant;
a vehicle interior data normalization module stored on the memory that, when executed by the processor, causes the processor to generate normalized vehicle occupant data based on the vehicle interior data; and
a feature classification module stored on the memory that, when executed by the processor, causes the processor to classify three-dimensional coordinate spatial locations of at least a portion of the at least one vehicle occupant into a respective driver behavior, wherein classification of the three-dimensional coordinate spatial locations of at least the portion of the at least one vehicle occupant determines one of an approximate size and shape of an object in the vehicle occupant's hands, including whether a hand of the vehicle occupant is empty.
2. The system 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 system as in claim 1 , wherein the three-dimensional coordinate spatial locations of the at least the portion of at least one vehicle occupant within the vehicle interior are representative of at least one skeletal diagram.
4. The system as in claim 1 , further comprising a feature extraction module that, when executed by the processor, causes the processor to extract the three-dimensional coordinate spatial locations at least the portion of the at least one vehicle occupant.
5. The system as in claim 1 , wherein the vehicle interior 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 system as in claim 1 , wherein the normalized vehicle occupant data is representative of vehicle occupant postures normalized for a range of different drivers, and the vehicle occupant data representative of vehicle occupant postures includes one or more of a hand location/orientation, an arm location/orientation, an elbow location/orientation and a torso location/orientation of the vehicle occupant.
7. The system 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 current image feature data, at a processor, from at least one sensor, wherein the current image feature data is representative of current images of a vehicle interior;
generating normalized vehicle occupant data, based on the current image feature data, in response to the processor executing a vehicle interior data normalization module; and
classifying current image features, using the processor, based on the normalized vehicle occupant data and a comparison of the current image feature data with previously classified image features data, wherein classification of the current image features determines one of an approximate size and shape of an object in the vehicle occupant's hands, including whether the hand of the vehicle occupant is empty.
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 , further comprising receiving, at the processor, the 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, 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 one of: (1) a three-dimensional location of at least one vehicle occupant within the vehicle interior; and (2) an orientation of at least a portion of at least one vehicle occupant within the vehicle interior.
12. The method of claim 8 , wherein the normalized vehicle occupant data is representative of vehicle occupant postures normalized for a range of different drivers, and the vehicle occupant data representative of vehicle occupant postures includes one or more of a hand location/orientation, an arm location/orientation, an elbow location/orientation and a torso location/orientation.
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 current image data receiving module that, when executed by the processor, causes the processor to receive current image feature data from at least one sensor, wherein the current image feature 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 feature data; and
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 previously classified image features data, wherein classification of the current image features determines one of an approximate size and shape of an object in the vehicle occupant's hands, including whether a hand of the vehicle occupant is empty.
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.