IP Library › Granted Patent US 9,889,859
Granted Patent B2
US 9,889,859 · App. 14/976,665 · Granted Feb 13, 2018

Dynamic sensor range in advanced driver assistance systems

Inventors: Igor Tatourian (Santa Clara, CA); Rita H Wouhaybi (Portland, OR); Peter C. Brink (Tempe, AZ)
Assignee: Intel Corporation
B60W50/045B60R1/00B60W50/14G05D1/0088G06K9/00805G06K9/209G06K9/3241B60R2300/205B60W2050/046B60W2420/40B60W2420/42B60W2420/52B60W2420/54B60W2520/10B60W2600/00B60W2710/30
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,889,859
App. No.
14/976,665
Filed
Dec 21, 2015
Granted
Feb 13, 2018
Kind
B2
Art Unit
3663
USPC
701/28
Abstract

Various systems and methods for implementing dynamic sensor range in advanced driver assistance systems are described herein. A system for managing an autonomous vehicle comprises a vehicle control system in a vehicle to detect a speed of the vehicle and adjust a forward-facing camera array based on the speed of the vehicle.

Claims (81)

1. A system for managing an autonomous vehicle, the system comprising:

a vehicle control system in a vehicle to:

detect a speed of the vehicle; and

adjust a forward-facing camera array based on the speed of the vehicle, wherein to adjust the camera array, the vehicle control system is to:

determine whether the speed of the vehicle violates a threshold speed:

control a low-resolution camera in the camera array to capture a low-resolution image; and

control a high-resolution camera in the camera array to capture an object identified in the low-resolution image.

2. The system of claim 1 , wherein to control the high-resolution camera, the vehicle control system is to:

identify an object of interest in the low-resolution image using a simple object classifier,

determine a location of the object of interest in the low-resolution image;

determine a portion of a high-resolution image captured by the high-resolution camera that corresponds to the location of the object of interest in the low-resolution image; and

process the portion of the high-resolution image using a complex object classifier.

3. The system of claim 1 , wherein to control the high-resolution camera, the vehicle control system is to:

identify an object of interest in the low-resolution image using a simple object classifier,

determine a location of the object of interest in the low-resolution image;

control the high-resolution camera to frame the object of interest and capture a high-resolution image; and

process the high-resolution image using a complex object classifier.

4. The system of claim 3 , wherein to control the high-resolution camera to frame the object of interest, the vehicle control system is to:

control at least one of a zoom or a focus to frame the object of interest.

5. A system for managing an autonomous vehicle, the system comprising:

a vehicle control system in a vehicle to:

detect a speed of the vehicle; and

adjust a forward-facing camera array based on the speed of the vehicle; and

a sensor fusion module to:

access a model of a road in a route that the vehicle is travelling, the road having a feature indicating a dangerous portion of the road;

use the camera array to recognize the feature; and

adjust a sensor in the vehicle when the feature is recognized.

6. The system of claim 5 , wherein to adjust the sensor, the sensor fusion module is to:

increase a resolution of a camera in the camera array.

7. The system of claim 5 , wherein to adjust the sensor, the sensor fusion module is to:

increase a sampling rate of the sensor.

8. The system of claim 7 , wherein the sensor comprises one of: a camera, a radar sensor, a LIDAR sensor, an ultrasonic sensor, or an infrared sensor.

9. The system of claim 5 , wherein to access the model in the route, the sensor fusion module is to:

determine a location or a route of the vehicle;

transmit the location or the route of the vehicle to a cloud service; and

receive from the cloud service, the model of the road in the route.

10. The system of claim 5 , wherein the model is based on a plurality of traversals over the road made by previous vehicles.

11. The system of claim 5 , wherein the model is revised using a machine learning technique.

12. A system for managing an autonomous vehicle, the system comprising:

a vehicle control system in a vehicle to:

detect a speed of the vehicle; and

adjust a forward-facing camera array based on the speed of the vehicle; and

an image capture module to:

determine a gaze direction of a driver of the vehicle; and

process an image from a camera of the camera array based on the gaze direction, wherein to process the image from the camera of the camera array based on the gaze direction, the image capture module is to:

capture the image; and

transmit the image to a cloud service.

13. The system of claim 12 , wherein to process the image from the camera of the camera array based on the gaze direction, the image capture module is to:

adjust the camera array based on the image to identify an object of interest in the image; and

advise the driver based on the identification of the object of interest.

14. A method of augmenting vehicle sensors, the method comprising:

detecting at a vehicle control system in a vehicle, a speed of the vehicle; and

adjusting by the vehicle control system, a forward-facing camera array based on the speed of the vehicle, wherein adjusting the camera array comprises:

determining whether the speed of the vehicle violates a threshold speed;

controlling a low-resolution camera in the camera array to capture a low-resolution image; and

controlling a high-resolution camera in the camera array to capture an object identified in the low-resolution image.

15. The method of claim 14 , wherein controlling the high-resolution camera comprises:

identifying an object of interest in the low-resolution image using a simple object classifier,

determining a location of the object of interest in the low-resolution image;

determining a portion of a high-resolution image captured by the high-resolution camera that corresponds to the location of the object of interest in the low-resolution image; and

processing the portion of the high-resolution image using a complex object classifier.

16. The method of claim 14 , wherein controlling the high-resolution camera comprises:

identifying an object of interest in the low-resolution image using a simple object classifier,

determining a location of the object of interest in the low-resolution image;

controlling the high-resolution camera to frame the object of interest and capture a high-resolution image; and

processing the high-resolution image using a complex object classifier.

17. The method of claim 16 , wherein controlling the high-resolution camera to frame the object of interest comprises:

controlling at least one of a zoom or a focus to frame the object of interest.

18. The method of claim 14 , wherein adjusting the camera array comprises:

adjusting one of a focal length or a resolution to identify objects farther away from the vehicle when the speed of the vehicle increases.

19. At least one non-transitory machine-readable medium including instructions, which when executed by a machine, cause the machine to:

detect at a vehicle control system in a vehicle, a speed of the vehicle; and

adjust by the vehicle control system, a forward-facing camera array based on the speed of the vehicle, wherein the instructions to adjust the camera array comprise instructions to:

determine whether the speed of the vehicle violates a threshold speed;

control a low-resolution camera in the camera array to capture a low-resolution image; and

control a high-resolution camera in the camera array to capture an object identified in the low-resolution image.

20. The at least one machine-readable medium of claim 19 , wherein the instructions to control the high-resolution camera comprise instructions to:

identify an object of interest in the low-resolution image using a simple object classifier;

determine a location of the object of interest in the low-resolution image;

determine a portion of a high-resolution image captured by the high-resolution camera that corresponds to the location of the object of interest in the low-resolution image; and

process the portion of the high-resolution image using a complex object classifier.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 19, 2017
From: TATOURIAN, IGOR; WOUHAYBI, RITA H; BRINK, PETER C
To: INTEL CORPORATION
Reel/Frame 044432/0739 →
Continuity (1)
Related Publication 20170174227A1 · Jun 22, 2017