Application US20190391587

DATA PIPELINE AND DEEP LEARNING SYSTEM FOR AUTONOMOUS DRIVING
[+] Show Details

US20190391587

1. A method, comprising: (11) (4)

receiving an image captured using a sensor on a vehicle;

decomposing the received image into a plurality of component images;

providing each component image of the plurality of component images as a different input to a different layer of a plurality of layers of an artificial neural network to determine a result; and

using the result of the artificial neural network to at least in part autonomously operate the vehicle.

2. The method of claim 1, wherein the sensor is a high dynamic range camera. (0)

3. The method of claim 1, wherein the sensor is a camera sensor, a radar sensor, an ultrasonic sensor, or a LiDAR sensor. (0)

4. The method of claim 1, wherein decomposing the received image into the plurality of component images includes using a high-pass filter or a low-pass filter. (0)

5. The method of claim 1, wherein decomposing the received image into the plurality of component images includes using a high-pass filter, a band-pass filter, or a low-pass filter. (0)

6. The method of claim 1, wherein a graphics processing unit is used to decompose the received image into at least one of the plurality of component images. (0)

7. The method of claim 1, wherein a tone-mapper processor is used to decompose the received image into at least one of the plurality of component images. (0)

8. The method of claim 1, wherein the plurality of component images includes a high-pass data component and a low-pass data component. (3) (0)

13. The method of claim 1, wherein each of the plurality of component images has a lower bit depth than the received image. (0)

14. The method of claim 1, wherein the received image is preprocessed prior to decomposing the received image into the plurality of component images. (0)

15. The method of claim 1, wherein at least one of the plurality of component images is pre-y) processed prior to providing each component image of the plurality of component images to the different layer of the plurality of layers of the artificial neural network. (1) (0)

17. The method of claim 1, wherein the plurality of component images includes a feature and edge data component and a global data component. (1) (0)

19. A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for: (0) (4)

receiving an image captured using a sensor on a vehicle;

decomposing the received image into a plurality of component images;

providing each component image of the plurality of component images as a different input to a different layer of a plurality of layers of an artificial neural network to determine a result; and

using the result of the artificial neural network to at least in part autonomously operate the vehicle.

20. A system, comprising: (0) (5)

a sensor on a vehicle;

a vehicle control module;

one or more image signal processors configured to: receive an image captured using the sensor; and

decompose the received image into a plurality of component images;

an artificial intelligence processor; and

a memory coupled with the artificial intelligence processor, wherein the memory is configured to provide the artificial intelligence processor with instructions which when executed cause the artificial intelligence processor to: receive each component image of the plurality of component images as a different to input to a different layer of a plurality of layers of an artificial neural network to determine a result; and

provide the result of the artificial neural network to the vehicle control module to at least in part autonomously operate the vehicle.

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Application US20190391587

DATA PIPELINE AND DEEP LEARNING SYSTEM FOR AUTONOMOUS DRIVING

Patent Matrix® Search