Vehicle cabin state recognizing device
The vehicle cabin state recognizing device of the present disclosure includes a plurality of cameras capable of capturing an image of a vehicle cabin provided on a steering wheel, and an image processing device connected to the plurality of cameras. The image processing device first acquires a captured image from each of the plurality of cameras. The image processing device then determines a shielding state of each of the plurality of cameras from a state of a captured image of each of the plurality of cameras. The image processing device further selects a captured image of the minimum shielding camera having the smallest shielding degree among the plurality of cameras. Then, the image processing device executes recognition processing for recognizing the state of the vehicle cabin with respect to the captured image of the minimum shielding camera.
1. A vehicle cabin state recognizing device comprising:
a plurality of cameras that is provided on a steering wheel of a vehicle and that is configured to capture an image of a vehicle cabin of the vehicle; and
an image processing device connected to each of the plurality of cameras, wherein the image processing device includes a processor, wherein the processor is configured to:
acquire the image captured by each of the plurality of cameras from each of the plurality of cameras;
calculate a brightness value of the image captured by each of the plurality of cameras;
select a camera from the plurality of cameras based on the brightness value, wherein the brightness value of the image captured by the selected camera is equal to or greater than a first predetermined value, wherein the selected camera is determined to be unshielded or partially shielded by a driver in the vehicle;
perform a recognition process recognizing a state of the vehicle cabin on the image captured by the selected camera; and
output a first recognition result of the recognition process recognizing the state of the vehicle cabin to a driving support system included in the vehicle.
2. The vehicle cabin state recognizing device according to claim 1 , wherein:
at least one of the plurality of cameras is provided at a left position relative to a center of the steering wheel when the steering wheel is in a neutral position; and
at least one of the plurality of cameras is provided at a right position relative to the center of the steering wheel when the steering wheel is in the neutral position.
3. The vehicle cabin state recognizing device according to claim 1 , wherein:
the plurality of cameras include at least three cameras;
at least one of the plurality of cameras is provided at a left position relative to a center of the steering wheel when the steering wheel is in a neutral position;
at least one of the plurality of cameras is provided at a right position relative to the center of the steering wheel when the steering wheel is in the neutral position; and
at least one of the plurality of cameras is provided at a position close to a center line of the steering wheel when the steering wheel is in the neutral position.
4. The vehicle cabin state recognizing device according to claim 1 , wherein the processor is further configured to:
select a plurality of the selected camera;
calculate a sharpness value of each of images captured by the plurality of selected cameras;
select an image from the images captured by the plurality of selected cameras based on the sharpness value, wherein the sharpness value of the selected image is equal to or greater than a second predetermined value; and
perform the recognition process on the selected image.
5. The vehicle cabin state recognizing device according to claim 1 , wherein
the recognition process further recognizes a state of the driver, and
the processor is further configured to:
select a plurality of the selected camera;
perform the recognition process on each of images captured by the plurality of selected cameras and obtain second recognition results;
calculate an eye size value of the driver in each of the second recognition results;
select a second recognition result from the second recognition results, wherein the eye size value in the selected second recognition result is the greatest in the calculated eye size value in the second recognition results; and
output the selected second recognition result to the driving support system included in the vehicle.
6. The vehicle cabin state recognizing device according to claim 1 , wherein the processor is further configured to
recalculate the brightness value of the image captured by each of the plurality of cameras after a predetermined period of time has elapsed, and
repeat the selection of the camera from the plurality of cameras based on the recalculated brightness value.