Method and system for seatbelt detection using determination of shadows
A method for detecting a position of a seatbelt in a vehicle includes: capturing, by a camera, a source image of an occupant in the vehicle; determining a pose of the occupant based on the source image; determining an occupant shadow based on the pose of the occupant; determining, based on the occupant shadow, a shadow overlying a region of interest (ROI) in the source image; and detecting, based on the shadow overlying the ROI, the seatbelt within the ROI. A system for detecting a position of a seatbelt is also provided. The system includes a camera and controller in communication with the camera and configured to: determine a pose of the occupant; determine an occupant shadow based on the pose of the occupant; determine, based on the occupant shadow, a shadow overlying the ROI; and detect, based on the shadow overlying the ROI, the seatbelt within the ROI.
1. A method for detecting a position of a seatbelt in a vehicle, comprising:
capturing, by a camera, a source image of an occupant in the vehicle, wherein the source image includes a plurality of pixels each having an associated brightness value having one of a range of different values;
executing, by a processor in communication with the camera, instructions to cause the processor to:
determine a pose of the occupant based on the source image;
determine an occupant shadow based on the pose of the occupant;
determine, based on the occupant shadow, whether a shadow overlies a region of interest in the source image; and
detect the seatbelt within the region of interest, wherein detecting the seatbelt within the region of interest includes at least one of:
using the source image to detect a plurality of transitions between bright segments and dark segments on the seatbelt based on the brightness values of the plurality of pixels and in response to determining the shadow overlying the region of interest, or
converting the source image to a black-and-white image and scanning across the black-and-white image to detect a plurality of transitions between bright segments and dark segments on the seatbelt and in response to determining the shadow not overlying the region of interest.
2. The method of claim 1 ,
wherein detecting the seatbelt within the region of interest includes using the source image to detect a plurality of transitions between bright segments and dark segments on the seatbelt based on the brightness values of the plurality of pixels and in response to determining the shadow overlying the region of interest.
3. The method of claim 1 , wherein the method includes converting the source image to a black-and-white image, and
wherein detecting the seatbelt within the region of interest includes scanning across the black-and-white image to detect a plurality of transitions between bright segments and dark segments on the seatbelt and in response to determining the shadow not overlying the region of interest.
4. The method of claim 1 , wherein capturing the image of the occupant includes capturing the image in near infrared (NIR).
5. The method of claim 1 , further comprising illuminating the occupant with a light source, and wherein determining the occupant shadow is also based on a location of the light source.
6. The method of claim 1 , further comprising determining an object shadow caused by an item in the vehicle; and
wherein determining the shadow overlying the region of interest is further based on the object shadow.
7. The method of claim 6 , further comprising fusing the occupant shadow with the object shadow to determine a fused shadow; and
wherein determining the shadow overlying the region of interest is based on the fused shadow.
8. The method of claim 6 , further comprising illuminating the occupant with a light source, and wherein determining the object shadow is also based on a location of the light source.
9. The method of claim 1 , wherein determining the shadow overlying the region of interest in the source image further comprises detecting an external shadow due to an external illumination source outside of the vehicle.
10. The method of claim 1 , wherein the shadow overlying the region of interest includes a boundary of the shadow overlying the region of interest.
11. A system for detecting a position of a seatbelt in a vehicle, comprising:
a camera configured to capture a source image of an occupant in the vehicle, wherein the source image includes a plurality of pixels each having an associated brightness value having one of a range of different values; and
a controller in communication with the camera and including a processor in communication with a memory containing instructions that, when executed by the processor, cause the controller to:
determine a pose of the occupant based on the source image;
determine an occupant shadow based on the pose of the occupant;
determine, based on the occupant shadow, whether a shadow overlies a region of interest in the source image;
detect the seatbelt within the region of interest, wherein detecting the seatbelt within the region of interest includes at least one of:
the controller using the source image to detect a plurality of transitions between bright segments and dark segments on the seatbelt based on the brightness values of the plurality of pixels and in response to determining the shadow overlying the region of interest, or
the controller converting the source image to a black-and-white image and scanning across the black-and-white image to detect a plurality of transitions between bright segments and dark segments on the seatbelt and in response to determining the shadow not overlying the region of interest.
12. The system of claim 11 ,
wherein detecting the seatbelt within the region of interest includes the controller using the source image to detect a plurality of transitions between bright segments and dark segments on the seatbelt based on the brightness values of the plurality of pixels and in response to determining the shadow overlying the region of interest.
13. The system of claim 11 , further comprising the controller being configured to convert the source image to a black-and-white image; and
wherein detecting the seatbelt within the region of interest includes the controller scanning across the black-and-white image to detect a plurality of transitions between bright segments and dark segments on the seatbelt and in response to determining the shadow not overlying the region of interest.
14. The system of claim 11 , wherein capturing the image of the occupant includes the camera capturing the image in near infrared (NIR).
15. The system of claim 11 , further comprising a light source configured to illuminate the occupant, and wherein determining the occupant shadow is also based on a location of the light source.
16. The system of claim 11 , further comprising determining an object shadow caused by an item in the vehicle; and
wherein determining the shadow overlying the region of interest is further based on the object shadow.
17. The system of claim 16 , further comprising fusing the occupant shadow with the object shadow to determine a fused shadow; and
wherein determining the shadow overlying the region of interest is based on the fused shadow.
18. The system of claim 16 , further comprising a light source configured to illuminate the occupant, and wherein determining the object shadow is also based on a location of the light source.
19. The system of claim 11 , wherein determining the shadow overlying the region of interest in the source image further comprises the controller detecting an external shadow due to an external illumination source outside of the vehicle.
20. The system of claim 11 , wherein the shadow overlying the region of interest includes a boundary of the shadow overlying the region of interest.