Back to results
US 12,579,822 B2Granted
Vehicle display system for nighttime driving
AssigneeGM Global Technology Operations LLC
InventorsManoj Sharma, Joseph F. Szczerba, Akilesh Rajavenkatanarayanan
Life of this patent
Estimating the term…
Abstract
A method for providing information to an occupant of a vehicle includes training a machine learning algorithm to receive a nighttime image as an input and produce an enhanced image as an output. The method also includes capturing the nighttime image of an environment surrounding the vehicle using a camera of the vehicle. The method also includes enhancing the nighttime image using the machine learning algorithm to produce the enhanced image. The method also includes identifying an object of interest in the enhanced image using a computer vision algorithm. The method also includes notifying the occupant of the vehicle about the object of interest.
Claims15
A method for providing information to an occupant of a vehicle, the method comprising:
- generating a training dataset, wherein the training dataset includes a plurality of image pairs, wherein each of the plurality of image pairs includes a sample input image and a sample output image, and wherein generating the training dataset further comprises:
- capturing the plurality of image pairs using a camera of the vehicle, wherein, for each of the plurality of image pairs, the sample input image is a normal exposure image of a nighttime environment surrounding the vehicle and the sample output image is a computer restored image of the nighttime environment surrounding the vehicle, wherein capturing one of the plurality of image pairs further comprises:
- capturing the sample input image using the camera;
- and
- generating the sample output image by restoring the sample input image using at least one of:
- a computer vision denoising algorithm and a computer vision dehazing algorithm;
- training a machine learning algorithm to receive a nighttime image as an input and produce an enhanced image as an output using supervised learning with the training dataset;
- capturing the nighttime image of an environment surrounding the vehicle using the camera of the vehicle;
- enhancing the nighttime image using the machine learning algorithm to produce the enhanced image;
- identifying an object of interest in the enhanced image using a computer vision algorithm;
- and
- notifying the occupant of the vehicle about the object of interest.
9 more elements
A system for providing information to an occupant of a vehicle, the system comprising:
- a notification system including:
- a camera;
- a display;
- a vehicle controller in electrical communication with the camera and the display, wherein the vehicle controller includes a non-volatile memory storing instructions which cause the vehicle controller to:
- capture a nighttime image of an environment surrounding the vehicle using the camera;
- enhance the nighttime image using a machine learning algorithm to produce an enhanced image;
- identify an object of interest in the enhanced image using a computer vision algorithm;
- and
- notify the occupant of the vehicle about the object of interest using the display;
- and
- a training system including:
- a training camera system including:
- a beam splitter having a first port, a second port, and a third port;
- a first training camera in optical communication with the first port of the beam splitter;
- a second training camera;
- a reverse apodizing neutral density filter in optical communication with the second training camera and the second port of the beam splitter;
- a relay lens in optical communication with the third port of the beam splitter;
- and
- a training controller in electrical communication with the first training camera and the second training camera, wherein the training controller includes a non-volatile memory storing instructions which program the training controller to:
- generate a training dataset using the training camera system, wherein the training dataset includes a plurality of image pairs, and wherein each of the plurality of image pairs includes a sample input image and a sample output image;
- and
- train the machine learning algorithm using supervised learning with the training dataset.
19 more elements
A system for providing information to an occupant of a vehicle, the system comprising:
- a notification system including:
- a camera;
- an augmented reality head-up display (AR-HUD) system including an occupant position tracking device and an AR-HUD projector;
- a vehicle controller in electrical communication with the camera and the AR-HUD system, wherein the vehicle controller includes a non-volatile memory storing instructions which cause the vehicle controller to:
- capture a nighttime image of an environment surrounding the vehicle using the camera;
- enhance the nighttime image using a machine learning algorithm to produce an enhanced image;
- identify an object of interest in the enhanced image using a computer vision algorithm;
- determine a location of the object of interest relative to the vehicle;
- determine a position of the occupant of the vehicle using the occupant position tracking device;
- calculate a size, shape, and location of a graphic based on the position of the occupant and the location of the object of interest relative to the vehicle;
- and
- notify the occupant of the vehicle about the object of interest by displaying the graphic on a windscreen of the vehicle using the AR-HUD system based on the size, shape, and location.
9 more elements
Dependencies are inferred from the claim text.