Abstract: Example vehicle occupancy management systems and methods are described. In one implementation, a method receives a current vehicle image representing a current interior of a vehicle. An occupancy management system detects at least one passenger in the vehicle based on the current vehicle image and determines a seating location of the passenger. A seat map is generated that identifies the seating location of the passenger in the vehicle.

Abstract: In one implementation, a method activates an unmanned aircraft inside a vehicle to capture images of the vehicle interior. The method accesses a flight path for the unmanned aircraft and receives data associated with the vehicle's current movement. The method adjusts the flight path of the unmanned aircraft to compensate for the vehicle's current movement.

Abstract: Example vehicle inspection systems and methods are described. In one implementation, a method activates an unmanned aircraft inside a vehicle to capture images of the vehicle interior. The method accesses a flight path for the unmanned aircraft and receives data associated with the vehicle's current movement. The method adjusts the flight path of the unmanned aircraft to compensate for the vehicle's current movement.

Abstract: Example vehicle occupancy management systems and methods are described. In one implementation, a method receives a current vehicle image representing a current interior of a vehicle. An occupancy management system detects at least one passenger in the vehicle based on the current vehicle image and determines a seating location of the passenger. A seat map is generated that identifies the seating location of the passenger in the vehicle.

Abstract: A method is disclosed for detecting and classifying one or more traffic lights. The method may include converting an RGB frame to an HSV frame. The HSV frame may be filtered by at least one threshold value to obtain at least one saturation frame. At least one contour may be extracted from the at least one saturation frame. Accordingly, a first portion of the RGB may be cropped in order to encompass an area including the at least one contour. The first portion may then be classified by an artificial neural network to determined whether the first portion corresponds to a not-a-traffic-light class, a red-traffic-light class, a green-traffic-light class, a yellow-traffic-light class, or the like.

Abstract: A method is disclosed for detecting and classifying one or more traffic lights. The method may include converting an RGB frame to an HSV frame. The HSV frame may be filtered by at least one threshold value to obtain at least one saturation frame. At least one contour may be extracted from the at least one saturation frame. Accordingly, a first portion of the RGB may be cropped in order to encompass an area including the at least one contour. The first portion may then be classified by an artificial neural network to determined whether the first portion corresponds to a not-a-traffic-light class, a red-traffic-light class, a green-traffic-light class, a yellow-traffic-light class, or the like.

Abstract: A method is disclosed for detecting and classifying one or more traffic lights. The method may include converting an RGB frame to an HSV frame. The HSV frame may be filtered by at least one threshold value to obtain at least one saturation frame. At least one contour may be extracted from the at least one saturation frame. Accordingly, a first portion of the RGB may be cropped in order to encompass an area including the at least one contour. The first portion may then be classified by an artificial neural network to determined whether the first portion corresponds to a not-a-traffic-light class, a red-traffic-light class, a green-traffic-light class, a yellow-traffic-light class, or the like.

Abstract: A method and an apparatus for background subtraction highly applicable in autonomous driving scenarios are described. The method involves a reduction of illumination effects by constructing a normality background image from a normality model based on a plurality of baseline images taken under different illuminating conditions. A subtracted image is obtained by subtracting the normality background image from a scene image pixel-wise (i.e., pixel-by-pixel). The scene image may contain one or more foreground objects. The foreground objects are identified by highlighting the pixels in the subtracted image whose intensity is more than a predetermined standard deviation in the normality model. An illumination-invariant color space transformation algorithm may optionally be utilized to further reduce the variant illumination effects.

Abstract: The disclosure relates to systems and methods for estimating or determining the motion of a vehicle and/or the distance to objects within view of a rear camera. A method for rear obstacle detection using structure from motion includes identifying image features in a first frame corresponding to features in a second frame, wherein the first frame and the second frame comprise adjacent image frames captured by a rear-facing camera of a vehicle. The method includes determining parameters for a non-planar motion model based on the image features. The method includes determining camera motion based on the parameters for the non-planar motion model.

Abstract: An autonomous vehicle includes interior sensors including an IR camera and a visible light camera. Images of an interior of the vehicle are captured using the cameras both before and after a passenger rides in the vehicle. The IR images from before and after are subtracted to obtain a difference image. Pixels above a threshold intensity a clustered. Clusters having an above-threshold size are determined to be anomalies. Portions of images from the visible light camera corresponding to the anomalies are sent to a dispatcher, who may then clear the vehicle to pick up another passenger or proceed to a cleaning station. Anomalies may be identified based on a combination of the IR images and visible light images.

Abstract: A system for providing media content in a vehicle includes a content component, a noise component, and a closed captioning component. The content component is configured to receive content from a content provider, wherein the content is configured for rendering by the media system of a vehicle. The noise component is configured to determine a noise level within a cabin of the vehicle. The closed captioning component is configured to, in response to determining that the noise level exceeds a threshold, trigger display of closed captioning for the content.

Abstract: A method is disclosed for detecting and classifying one or more traffic lights. The method may include converting an RGB frame to an HSV frame. The HSV frame may be filtered by at least one threshold value to obtain at least one saturation frame. At least one contour may be extracted from the at least one saturation frame. Accordingly, a first portion of the RGB may be cropped in order to encompass an area including the at least one contour. The first portion may then be classified by an artificial neural network to determined whether the first portion corresponds to a not-a-traffic-light class, a red-traffic-light class, a green-traffic-light class, a yellow-traffic-light class, or the like.

Abstract: A vehicle includes a pair of cameras disposed on the vehicle and oriented to view an entrance to the vehicle. The vehicle also includes a processor configured to compare a profile image of a passenger's facial feature from one of the pair with a frontal image of the passenger's facial feature from the other of the pair. The processor is configured to lock the entrance to the vehicle in response to the facial features being different.

Abstract: A method is disclosed for detecting and classifying one or more traffic lights. The method may include converting an RGB frame to an HSV frame. The HSV frame may be filtered by at least one threshold value to obtain at least one saturation frame. At least one contour may be extracted from the at least one saturation frame. Accordingly, a first portion of the RGB may be cropped in order to encompass an area including the at least one contour. The first portion may then be classified by an artificial neural network to determined whether the first portion corresponds to a not-a-traffic-light class, a red-traffic-light class, a green-traffic-light class, a yellow-traffic-light class, or the like.

Abstract: A method and an apparatus for background subtraction highly applicable in autonomous driving scenarios are described. The method involves a reduction of illumination effects by constructing a normality background image from a normality model based on a plurality of baseline images taken under different illuminating conditions. A subtracted image is obtained by subtracting the normality background image from a scene image pixel-wise (i.e., pixel-by-pixel). The scene image may contain one or more foreground objects. The foreground objects are identified by highlighting the pixels in the subtracted image whose intensity is more than a predetermined standard deviation in the normality model. An illumination-invariant color space transformation algorithm may optionally be utilized to further reduce the variant illumination effects.

Abstract: A vehicle includes a pair of cameras disposed on the vehicle and oriented to view an entrance to the vehicle. The vehicle also includes a processor configured to compare a profile image of a passenger's facial feature from one of the pair with a frontal image of the passenger's facial feature from the other of the pair. The processor is configured to lock the entrance to the vehicle in response to the facial features being different.

Abstract: An autonomous vehicle includes interior sensors including an IR camera and a visible light camera. Images of an interior of the vehicle are captured using the cameras both before and after a passenger rides in the vehicle. The IR images from before and after are subtracted to obtain a difference image. Pixels above a threshold intensity a clustered. Clusters having an above-threshold size are determined to be anomalies. Portions of images from the visible light camera corresponding to the anomalies are sent to a dispatcher, who may then clear the vehicle to pick up another passenger or proceed to a cleaning station. Anomalies may be identified based on a combination of the IR images and visible light images.

Abstract: The present invention extends to methods, systems, and computer program products for detecting vehicles in low light conditions. Cameras are used to obtain RGB images of the environment around a vehicle. RGB images are converted to LAB images. The “A” channel is filtered to extract contours from LAB images. The contours are filtered based on their shapes/sizes to reduce false positives from contours unlikely to correspond to vehicles. A neural network classifies an object as a vehicle or non-vehicle based the contours. Accordingly, aspects provide reliable autonomous driving with lower cost sensors and improved aesthetics. Vehicles can be detected at night as well as in other low light conditions using their head lights and tail lights, enabling autonomous vehicles to better detect other vehicles in their environment. Vehicle detections can be facilitated using a combination of virtual data, deep learning, and computer vision.

Abstract: A scenario is defined that including models of vehicles and a typical driving environment as well as a traffic light having a state (red, green, amber). A model of a subject vehicle is added to the scenario and camera location is defined on the subject vehicle. Perception of the scenario by a camera is simulated to obtain an image. The image is annotated with a location and state of the traffic light. Various annotated images may be generated for difference scenarios, including scenarios lacking a traffic light or having traffic lights that do not govern the subject vehicle. A machine learning model is then trained using the annotated images to identify the location and state of traffic lights that govern the subject vehicle.

Abstract: An autonomous bus includes sensors and actuators sufficient to perform autonomous navigation. The controller of the bus receives a route and proceeds to pick-up locations along the route. A camera having an external region around a door in its field of view evaluates whether an individual matching recognition information of an intended passenger is present. If so, a door actuator permits entry of the individual and entry of the individual is verified. If the individual does not enter or another individual enters, an alert may be generated and the controller may refrain from moving. During transit noise levels and levels of stress chemicals may be monitored. Where noise or stress chemicals indicate a problem, an alert may be generated.