Detection, counting and identification of occupants in vehicles

A system for detecting occupants in a vehicle using a plurality of images, comprising:

• a controller;
• a first camera positioned on a driver's side of the vehicle and a second camera positioned on a passenger's side of the vehicle, wherein the first camera and the second camera are operatively coupled to the controller, and wherein each of the first camera and the second camera comprises an imaging sensor, a pulsed illumination device, and a processor operatively coupling the imaging sensor to the pulsed illumination source for synchronizing pulses of illumination with exposure of the imaging sensor;
• and
• a trigger operatively connected to the controller to detect the vehicle and control the first camera and the second camera to acquire images of the vehicle, wherein the first camera acquires a first portion of the plurality of images from a first angle, wherein the second camera acquires a second portion of the plurality of images from a second angle, and wherein the first angle is different from the second angle;
• and
• machine readable instructions stored in a non-transient storage medium and configured to be executed by the controller, wherein executing the machine readable instructions causes the controller to:
• detect an oncoming vehicle based upon the trigger;
• acquire the first portion of the plurality of images and the second portion of the plurality of images;
• perform automated facial detection on the plurality of images;
• based on the automated facial detection, generate a gallery of facial images from the plurality images, wherein the gallery of facial images comprises a first facial image of at least one of the occupants taken from the first angle and a second facial image of said at least one of the occupants taken from the second angle, thereby resulting in said gallery of facial images comprising multiple images of said at least one of the occupants;
• perform, after formation of the gallery of facial images, automated facial recognition on the gallery of facial images to form facial groupings, wherein each of the facial groupings comprise facial images of only one of the occupants and wherein at least one of said facial groupings comprises said multiple images of the at least one of the occupants and no facial images of other ones of said occupants;
• generate a confidence score for each of the images in the facial groupings based on the automated facial detection performed on each of the facial groupings;
• select a representative image from each of the facial groupings based on the corresponding confidence scores;
• output the representative image from each of the facial groupings to create a set of unique images, each of which is representative of only one of the occupants;
• and
• count the groups to determine how many occupants are in the vehicle.

A method of detecting occupants in a vehicle using a system comprising a first camera positioned on a driver's side of the vehicle and a second camera positioned on a passenger's side of the vehicle, The method comprising:

• detecting an oncoming vehicle;
• using the first camera and the second camera, acquiring a plurality of images of occupants in the vehicle in response to detection of the vehicle, wherein the first camera acquires a first portion of the plurality of images from a first angle, wherein the second camera acquires a second portion of the plurality of images from a second angle, and wherein the first angle is different from the second angle;
• performing automated facial detection on the plurality of images;
• based on the automated facial detection, generating a gallery of facial images from the plurality of images, wherein the gallery of facial images comprises a first facial image of at least one of the occupants taken from the first angle and a second facial image of said at least one of the occupants taken from the second angle, thereby resulting in said gallery of facial images comprising multiple images of said at least one of the occupants;
• performing, after forming the gallery of facial images, automated facial recognition on the gallery of facial images to form facial groupings, wherein each of the facial groupings comprise facial images of only one of the occupants and wherein at least one of said facial groupings comprises said multiple images of the at least one of the occupants and no facial images of other ones of said occupants;
• determining a facial offset angle from a line of sight of an imaging sensor that acquired the image for each image in each of the facial groupings;
• selecting a representative image from each of the facial groupings based on which image in the facial grouping has a smallest offset angle;
• outputting the representative image from each of the facial groupings to create a set of unique images, each of which is representative of only one of the occupants;
• and
• counting the groupings to determine how many occupants are in the vehicle.

A system for detecting occupants in a vehicle using a plurality of images, comprising:

• a controller;
• a first camera positioned on a driver's side of the vehicle and a second camera positioned on a passenger's side of the vehicle, wherein the first camera and second camera are operatively coupled to the controller and wherein each of the first camera and the second camera comprises an imaging sensor, a pulsed illumination device, and a processor operatively coupling the imaging sensor to the pulsed illumination source for synchronizing pulses of illumination with exposure of the imaging sensor;
• and
• a trigger operatively connected to the controller to detect the vehicle and control the first camera and the second camera to acquire images of the vehicle, wherein the first camera acquires a first portion of the plurality of images from a first angle, wherein the second camera acquires a second portion of the plurality of images from a second angle, and wherein the first angle is different from the second angle;
• and
• machine readable instructions stored in a non-transient storage medium and configured to be executed by the controller, wherein executing the machine readable instructions causes the controller to:
• detect an oncoming vehicle based upon the trigger;
• acquire the first portion of the plurality of images and the second portion of the plurality of images;
• perform automated facial detection on the plurality of images;
• based on the automated facial detection, generate a gallery of facial images from the plurality images, wherein the gallery of facial images comprises a first facial image of at least one of the occupants taken from the first angle and a second facial image of said at least one of the occupants taken from the second angle, thereby resulting in said gallery of facial images comprising multiple images of said at least one of the occupants;
• perform, after formation of the gallery of facial images, automated facial recognition on the gallery of facial images to form facial groupings, wherein each of the facial groupings comprise facial images of only one of the occupants and wherein at least one of said facial groupings comprises said multiple images of the at least one of the occupants and no facial images of other ones of said occupants;
• determine a facial offset angle from a line of sight of an imaging sensor that acquired the image for each image in each of the facial groupings;
• select a representative image from each of the facial groupings based on which image in the facial grouping has a smallest facial offset angle;
• output the representative image from each of the facial groupings to create a set of unique images, each of which is representative of only one of the occupants;
• and
• count the groupings to determine how many occupants are in the vehicle.