Automated vehicle occupancy detection
Described herein are systems and methods for detecting the number of occupants in a vehicle. The detecting may be performed using a camera and a processing device. The detecting may be anonymous and the image of the interior of the vehicle is not stored on the processing device.
1. A method comprising:
utilizing a camera to capture an image of an interior of a vehicle;
sending the image to a processor;
determining an estimate of the number of occupants in the interior of the vehicle;
storing the estimate of the number of occupants in the interior of the vehicle; and
altering a behavior of the vehicle based on the estimate of the number of occupants in the interior of the vehicle; wherein:
the vehicle follows a route having a destination,
the determining is performed by the processor using a convolutional neural network,
the convolutional neural network comprises:
a convolutional layer with a 3×3 filter,
a pooling layer with a 2×2 filter,
a feature map, and
two connected layers configured to transform the feature maps into the estimate of the number of occupants in the interior of the vehicle,
the camera is positioned within the interior of the vehicle, and
the altering comprises at least one of stopping the vehicle at the destination, repeating the route, or starting the route.
2. The method of claim 1 , wherein the camera is an infrared camera.
3. The method of claim 1 , wherein the camera is an optical camera.
4. The method of claim 1 , wherein the storing comprises:
saving the number of occupants in the interior of the vehicle in at least one of the processor, a mobile device, or a cloud-based storage system, and
deleting the image.
5. The method of claim 1 , wherein the determining is performed by the processor.
6. The method of claim 1 , wherein:
the altering comprises stopping at the destination when the estimate of the number of occupants in the interior of the vehicle is zero.
7. The method of claim 1 , wherein:
the altering comprises repeating the route when the estimate of the number of occupants in the interior of the vehicle is greater than one.
8. The method of claim 1 , wherein:
the altering comprises starting the route when the estimate of the number of occupants in the interior of the vehicle is greater than zero.
9. The method of claim 8 , wherein:
at least one of the two connected layers comprises 128 neurons.
10. The method of claim 8 , wherein:
at least one of the two connected layers comprises 5 neurons.