Apparatuses, systems and methods for generating data representative of vehicle occupant postures
AssigneeState Farm Mutual Automobile Insurance Company
InventorsAaron Scott Chan, Christina P. Mullen, Brian Mark Fields, Kenneth Jason Sanchez
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems and methods are provided for generating data representative of a vehicle operation mode. More particularly, apparatuses, systems and methods are provided for generating data representative of a vehicle operation mode based on vehicle interior image data. The vehicle interior data may be representative of a three-dimensional coordinate spatial location of at least one joint of a vehicle occupant. The three-dimensional coordinate spatial location of the at least one joint of the vehicle occupant may be tracked over time.
Claims20
A device for determining postures of vehicle occupants by tracking vehicle occupant postures using image recognition, the device comprising:
- at least one vehicle interior sensor for acquiring at least one image sequence of at least one vehicle occupant;
- a memory for storing the vehicle interior data, vehicle occupant posture data relating to the vehicle interior data, a three-dimensional coordinate spatial location extraction module, a vehicle interior data receiving module, a previously classified interior data receiving module, a skeletal pose data generation module, and a vehicle occupant posture determination module;
- and
- a processor that is configured to determine a vehicle operation mode 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, wherein the vehicle interior data is representative of three dimensional vehicle occupant postures;
- creating a vehicle occupant posture record for the at least one vehicle occupant comprising the vehicle interior data of the at least one vehicle occupant;
- extracting three-dimensional coordinate spatial locations of at least one joint location of the at least one vehicle occupant from the vehicle interior data in response to the processor executing the three-dimensional coordinate spatial location extraction module, wherein the three-dimensional coordinate spatial locations of at least one joint location of the at least one vehicle occupant are stored in the vehicle occupant posture record as vehicle occupant posture data relating to the vehicle interior data;
- receiving previously classified vehicle interior data in response to the processor executing a previously classified vehicle interior data receiving module, wherein the previously classified vehicle interior data is representative of known vehicle occupant postures;
- recognizing and tracking postures of the at least one vehicle occupant in the image sequence as vehicle occupant posture data by processing the three-dimensional coordinate spatial locations of at least one joint location of the at least one vehicle occupant and the previously classified interior data in response to the processor executing the stored skeletal pose data generation module and adding the vehicle occupant posture data to the vehicle occupant posture record;
- determining a vehicle occupant posture based on a comparison of the vehicle interior data with the previously classified vehicle interior data in response to the processor executing the vehicle occupant posture determination module;
- and
- automatically updating the vehicle occupant posture record with the vehicle posture data, wherein a first posture of the at least two vehicle occupant postures corresponds to a posture and an associated range of movement associated with the first posture that the vehicle occupant was oriented for a longest period of total time over at least two occurrences within a predetermined period of time, and wherein a second posture of the at least two vehicle occupant postures corresponds to a posture and an associated range of movement associated with the second posture that the vehicle occupant was oriented for a second longest period of total time within the predetermined period of time.
A computer-implemented method for determining a vehicle driver rating based on images that are representative of a known vehicle driver and vehicle operation by tracking vehicle occupant postures using image recognition, the method comprising:
- receiving, at a processor, vehicle interior data from at least one vehicle interior sensor, wherein the vehicle interior data is representative of three dimensional vehicle occupant postures;
- receiving, at the processor, previously classified vehicle interior data, wherein the previously classified vehicle interior data is representative of known vehicle occupant postures;
- creating a vehicle occupant posture record for the at least one vehicle occupant comprising the vehicle interior data of the at least one vehicle occupant;
- extracting three-dimensional coordinate spatial locations of at least one joint location of the at least one vehicle occupant from the vehicle interior data in response to the processor executing a three-dimensional coordinate spatial location extraction module, wherein the three-dimensional coordinate spatial locations of at least one joint location of the at least one vehicle occupant are stored in the vehicle occupant posture record as vehicle occupant posture data relating to the vehicle interior data;
- recognizing and tracking postures of the at least one vehicle occupant in the image sequence as vehicle occupant posture data by processing the three-dimensional coordinate spatial locations of at least one joint location of the at least one vehicle occupant and the previously classified interior data in response to the processor executing a skeletal pose data generation module and adding the vehicle occupant posture data to the vehicle occupant posture record;
- determining, using the processor, at least two vehicle occupant postures based on a comparison of the vehicle interior data with the previously classified vehicle interior data in response to the processor executing a vehicle occupant posture determination module;
- and
- automatically updating the vehicle occupant posture record with the vehicle posture data, wherein a first posture of the at least two vehicle occupant postures corresponds to a posture and an associated range of movement associated with the first posture that the vehicle occupant was oriented for a longest period of total time over at least two occurrences within a predetermined period of time, and wherein a second posture of the at least two vehicle occupant postures corresponds to a posture and an associated range of movement associated with the second posture that the vehicle occupant was oriented for a second longest period of total time within the predetermined period of time.
A non-transitory computer-readable medium storing computer-readable instructions that, when executed by a processor, cause the processor to determine a vehicle driver rating based on images that are representative of a known vehicle driver and vehicle operation by tracking vehicle occupant postures using image recognition, the non-transitory computer-readable medium comprising:
- a vehicle occupant posture record creation module that, when executed by a processor, causes the processor to create a vehicle occupant posture record for the at least one vehicle occupant comprising vehicle interior data of the at least one vehicle occupant;
- a three-dimensional coordinate spatial location extraction module that, when executed by a processor, causes the processor to extract three-dimensional coordinate spatial locations of at least one joint location of the at least one vehicle occupant from the vehicle interior data, the three-dimensional coordinate spatial locations of at least one joint location of the at least one vehicle occupant are stored in the vehicle occupant posture record as vehicle occupant posture data relating to the vehicle interior data;
- a vehicle interior data receiving module that, when executed by a processor, causes the processor to receive vehicle interior data from at least one vehicle interior sensor, wherein the vehicle interior data is representative of three dimensional coordinate spatial locations of at least one joint location of vehicle occupant postures;
- a previously classified vehicle interior data receiving module that, when executed by the processor, causes the processor to receive previously classified vehicle interior data, wherein the previously classified vehicle interior data is representative of known vehicle occupant postures;
- a posture recognizing and tracking module that, when executed by a processor, causes the processor to recognize and track postures of the at least one vehicle occupant in the image sequence as vehicle occupant posture data by processing the three-dimensional coordinate spatial locations of at least one joint location of the at least one vehicle occupant and the previously classified interior data in response to the processor executing a skeletal pose data generation module and adding the vehicle occupant posture data to the vehicle occupant posture record;
- a vehicle occupant posture determination module that, when executed by the processor, causes the processor to determine at least two vehicle occupant postures based on a comparison of the vehicle interior data with the previously classified vehicle interior data;
- and
- a vehicle occupant posture record updating module that, when executed by a processor causes the processor to automatically update the vehicle occupant posture record with the vehicle posture data, wherein a first posture of the at least two vehicle occupant postures corresponds to a posture and an associated range of movement associated with the first posture that the vehicle occupant was oriented for a longest period of total time over at least two occurrences within a predetermined period of time, and wherein a second posture of the at least two vehicle occupant postures corresponds to a posture and an associated range of movement associated with the second posture that the vehicle occupant was oriented for a second longest period of total time within the predetermined period of time.
Dependencies are inferred from the claim text.