Advanced seatbelt interlock using video recognition
View Patent ↗Computing devices, methods, and systems for locking vehicle operations when an occupant is not wearing a correctly positioned seatbelt are disclosed. One example method for locking vehicle operations includes identifying an occupant position and a seatbelt position based on information relating to an occupant of the vehicle and a seatbelt associated with the occupant; determining whether the occupant is correctly wearing the seatbelt based at least in part on the occupant position, the seatbelt position, and a reference model; and locking one or more vehicle operations if the occupant is not correctly wearing the seatbelt. Example implementations include using depth-sensing cameras, rendering a three-dimensional model representing the occupant position and the seatbelt position, and comparing the three-dimensional model and the reference model. Examples of vehicle operations that may be locked include ignition operations, gear shift operations, and autonomous driving operations.
1. A computing device for a vehicle, comprising:
one or more processors for controlling the operations of the computing device; and
a memory for storing data and program instructions used by the one or more processors, wherein the one or more processors are configured to execute instructions stored in the memory to:
identify an occupant position and a seatbelt position based on information relating to an occupant of the vehicle and a seatbelt associated with the occupant;
determine whether the occupant is correctly wearing the seatbelt based at least in part on the occupant position, the seatbelt position, and a reference model including one or more skeletal models wearing seatbelts in correct and incorrect ways; and
lock one or more vehicle operations if the occupant is not correctly wearing the seatbelt.
2. The computing device of claim 1 , wherein the information relating to the occupant and the seatbelt are received from one or more optical sensors associated with the vehicle.
3. The computing device of claim 2 , wherein the one or more optical sensors are cameras.
4. The computing device of claim 2 , wherein the one or more optical sensors are depth-sensing cameras.
5. The computing device of claim 1 , wherein the one or more processors are further configured to render a three-dimensional model representing the occupant position and the seatbelt position.
6. The computing device of claim 5 , wherein the determining whether the occupant is correctly wearing the seatbelt is based at least in part on a comparison of the three-dimensional model and the reference model.
7. The computing device of claim 5 , wherein at least one of the three-dimensional model and the reference model comprise skeletal joint relationship information.
8. The computing device of claim 1 , wherein the reference model is received by the computing device from a remote source.
9. The computing device of claim 1 , wherein the one or more vehicle operations include at least one of an ignition operation and a gear shift operation.
10. The computing device of claim 1 , wherein the one or more processors are further configured to issue a warning before locking the one or more vehicle operations.
11. A computing device for a vehicle, comprising:
one or more processors for controlling the operations of the computing device; and
a memory for storing data and program instructions used by the one or more processors, wherein the one or more processors are configured to execute instructions stored in the memory to:
identify an occupant position and a seatbelt position based on information relating to an occupant of the vehicle and a seatbelt associated with the occupant;
determine whether the occupant is correctly wearing the seatbelt based at least in part on the occupant position, the seatbelt position, and a reference model including at least one of: one or more skeletal models, one or more seatbelt models, or one or more skeletal models wearing seatbelts in correct and incorrect ways; and
lock one or more vehicle operations if the occupant is not correctly wearing the seatbelt, the one or more vehicle operations including an autonomous driving operation.
12. A computing device for a vehicle, comprising:
one or more processors for controlling the operations of the computing device; and
a memory for storing data and program instructions used by the one or more processors, wherein the one or more processors are configured to execute instructions stored in the memory to:
identify an occupant position and a seatbelt position based on information relating to an occupant of the vehicle and a seatbelt associated with the occupant;
determine whether the occupant is correctly wearing the seatbelt based at least in part on the occupant position, the seatbelt position, and a reference model including at least one of: one or more skeletal models, one or more seatbelt models, or one or more skeletal models wearing seatbelts in correct and incorrect ways;
lock one or more vehicle operations if the occupant is not correctly wearing the seatbelt; and
issue one or more commands to one or more vehicle systems to autonomously divert the vehicle to a safe location.
13. A computer-implemented method for a vehicle, comprising:
identifying an occupant position and a seatbelt position based on information relating to an occupant of the vehicle and a seatbelt associated with the occupant;
determining whether the occupant is correctly wearing the seatbelt based at least in part on the occupant position, the seatbelt position, and a reference model including one or more skeletal models wearing seatbelts in correct and incorrect ways; and
locking one or more vehicle operations if the occupant is not correctly wearing the seatbelt.
14. The method of claim 13 , wherein the information relating to the occupant and the seatbelt is received from one or more optical sensors associated with the vehicle.
15. The method of claim 14 , wherein the one or more optical sensors are depth-sensing cameras.
16. The method of claim 13 , further comprising rendering a three-dimensional model representing the occupant position and the seatbelt position.
17. The method of claim 16 , wherein the determination whether the occupant is correctly wearing the seatbelt is based at least in part on a comparison of the three-dimensional model and the reference model.
18. The method of claim 16 , wherein at least one of the three-dimensional model and the reference model comprise skeletal joint relationship information.
19. The method of claim 13 , wherein the one or more vehicle operations includes at least one of an ignition operation, a gear shift operation, and an autonomous driving operation.
20. A system comprising:
one or more optical sensors associated with a vehicle;
a computing device in communication with the one or more optical sensors, the computing device comprising one or more processors for controlling the operations of the computing device and a memory for storing data and program instructions used by the one or more processors, wherein the one or more processors are configured to execute instructions stored in the memory to:
identify an occupant position and a seatbelt position based on information received from the one or more optical sensors relating to an occupant of the vehicle and a seatbelt associated with the occupant;
determine whether the occupant is correctly wearing the seatbelt based at least in part on the occupant position, the seatbelt position, and a reference model including one or more skeletal models wearing seatbelts in correct and incorrect ways; and
lock one or more vehicle operations if the occupant is not correctly wearing the seatbelt.