Vehicular system for testing performance of headlamp detection systems
AssigneeMagna Electronics Inc.
InventorAnuj S. Potnis
Life of this patent
Estimating the term…
Abstract
A method for testing a vehicular driving assist system includes providing a neural network and training the neural network using a database of images, with each image of the database of images including an image of a headlight or a taillight of a vehicle. The trained neural network is provided with an input image that does not include a headlight or a taillight. The neural network, using the input image, generates an output image, with the output image including an image of a headlight or taillight generated by the neural network. The output image is provided as an input to the driving assist system to test the driving assist system.
Claims20
A method for testing a vehicular driving assist system, the method comprising:
- providing a neural network;
- training the neural network using a database of images, wherein each image of the database comprises an image of a headlight of a vehicle or an image of a taillight of a vehicle;
- providing to the trained neural network an input image that does not include a headlight or a taillight;
- generating, by the neural network using the input image, an output image, wherein the output image comprises an image of a headlight generated by the neural network or an image of a taillight generated by the neural network;
- and
- testing the vehicular driving assist system using the generated output image as an input to the vehicular driving assist system.
A method for testing a vehicular driving assist system, the method comprising:
- providing a generative adversarial network (GAN);
- training the GAN using a database of video recordings, wherein each video recording of the database comprises a plurality of images that include a headlight of a vehicle or a taillight of a vehicle;
- providing to the trained GAN an input image that does not include a headlight or a taillight;
- generating, by the GAN using the input image, an output image, wherein the output image comprises an image of a headlight generated by the GAN or an image of a taillight generated by the GAN;
- and
- testing the vehicular driving assist system using the generated output image as an input to the vehicular driving assist system.
A method for testing an automatic headlight control system, the method comprising:
- providing a neural network;
- training the neural network using a database of images, wherein each image of the database comprises an image of a headlight of a vehicle or an image of a taillight of a vehicle;
- providing to the trained neural network an input image that does not include a headlight or a taillight;
- generating, by the neural network using the input image, an output image, wherein the output image comprises an image of a headlight generated by the neural network or an image of a taillight generated by the neural network;
- testing the vehicular driving assist system using the generated output image as an input to the automatic headlight control system;
- and
- wherein the automatic headlight control system classifies the generated output image as including a headlight or a taillight and determines a position of the headlight or the taillight within the generated output image.
Dependencies are inferred from the claim text.