Automatic beam-shaping using an on-car camera system

• US 9,896,022 B1
• Filed: 04/20/2015
• Issued: 02/20/2018
• Est. Priority Date: 04/20/2015
• Status: Active Grant

• Current Assignee: Ambarella International LP (Ambarella Incorporated)
• Original Assignee: Ambarella Incorporated
• Inventors: Pertsel, Shimon, Fink, Alexander
• Primary Examiner(s): Harvey, David
• Application Number:
  US14/690,945
• Time in Patent Office: 1,037 Days
• Field of Search: 348148
• CPC Class Codes: B60Q 1/085 due to special conditions, e.g. adverse weather, type of road, badly illuminated road signs or potential dangers B60Q1/10, B60Q1/12, B60Q1/1423 take precedence
• CPC Class Codes: B60Q 1/115 by electric means details of the electric drive components, e.g. motors, shafts, ball joints B60Q1/076
• CPC Class Codes: B60Q 1/122 with electrical actuating means details of the electric drive components, e.g. motors, shafts, ball joints B60Q1/076
• CPC Class Codes: B60Q 1/143 combined with another condition, e.g. using vehicle recognition from camera images or activation of wipers
• CPC Class Codes: B60Q 2300/112 Vehicle speed
• CPC Class Codes: B60Q 2300/122 Steering angle
• CPC Class Codes: B60Q 2300/142 Turn signal actuation
• CPC Class Codes: B60Q 2300/32 Road surface or travel path
• CPC Class Codes: B60Q 2300/322 Road curvature
• CPC Class Codes: B60Q 2300/335 Number or size of road lanes
• CPC Class Codes: B60Q 2300/336 Crossings
• CPC Class Codes: B60Q 2300/42 oncoming vehicle
• CPC Class Codes: B60Q 2300/45 Special conditions, e.g. pedestrians, road signs or potential dangers
• CPC Class Codes: B60Q 2300/47 Direct command from other road users, i.e. the command for switching or changing the beam is sent by other vehicles or road devices
• CPC Class Codes: G06V 20/582 of traffic signs
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

An apparatus comprising a sensor, an interface and a processor. The sensor may be configured to generate a video signal based on a targeted view from a vehicle of a perspective of a driver. The interface may be configured to receive status information about one or more components of the vehicle. The processor may be configured to generate a control signal in response to (i) a classification of objects in the video signal and (ii) the status information. The control signal may be used to adjust one or more headlights of the vehicle. The adjustment of the headlights may be based on a location of the objects in the video signal.

Claims

1. An apparatus comprising:

a sensor configured to generate a video signal based on a targeted view from a vehicle from a perspective of a driver;

an interface configured to receive status information from one or more components of said vehicle; and

a processor configured to (i) perform video analysis on video frames of said video signal to detect objects, (ii) perform a classification of said objects, (iii) provide a confidence level of said classification and (iv) generate a control signal in response to (a) said classification of said objects and (b) said status information, wherein (A) said control signal is used to reshape a beam of one or more headlights of said vehicle, (B) said reshaping of said beams of said headlights is determined by aggregating information based on (i) a location of said objects in said video signal, (ii) said confidence level of said classification and (iii) said status information and (C) said status information is used to adjust said confidence level of said classification of said objects.

2. The apparatus according to claim 1, wherein (i) said status information comprises a turn signal, (ii) said turn signal is used to predict a future lane of travel of said vehicle and (iii) said reshaping of said beams of said headlights responds to said prediction of said future lane.

3. The apparatus according to claim 1, wherein said objects comprise at least one of road markings, traffic, road signs, other vehicles, pedestrians, animals and a path of upcoming roadways.

4. The apparatus according to claim 1, wherein (i) said sensor is a front facing camera attached to said vehicle and (ii) said sensor is implemented as one of (a) a component of a camera and (b) a video capturing device.

5. The apparatus according to claim 1, wherein said processor is further configured to receive a plurality of said video signals from a plurality of said sensors.

6. The apparatus according to claim 1, wherein (i) said status information comprises at least one of (a) a current orientation of said headlights, (b) a turn signal, (c) a speed of said vehicle, (d) a position of a steering wheel, (e) location information received from a GPS satellite and (f) location information received from another vehicle and (ii) said status information is received through an on-board diagnostics port.

7. The apparatus according to claim 1, wherein said confidence level is adjusted in response to a second classification of a second object detected in said video frame.

8. The apparatus according to claim 1, wherein (i) one of said objects detected by said video analysis is a curve in a roadway and (ii) said beams of said headlights of said vehicle are reshaped to illuminate said curve in said roadway.

9. The apparatus according to claim claim 8, wherein said confidence level of said classification of said curve is increased in response to reading a road sign using said video analysis.

10. The apparatus according to claim 8, wherein said confidence level of said classification of said curve in said roadway is detected adjusted based on at least one of (i) lane markers, (ii) a shape of said roadway, (iii) road signs detected in said video signal and (iv) position information of an approaching vehicle received through a vehicle to vehicle identification system.

11. The apparatus according to claim 8, wherein said beams of said headlights of said vehicle are reshaped based on at least one of a range of said headlights and a shape of said curve in said roadway.

12. The apparatus according to claim 1, wherein (i) one of said objects detected is a second vehicle and (ii) said beams of said headlights of said vehicle are adjusted to illuminate said second vehicle.

13. The apparatus according to claim 12, wherein (i) said second vehicle is an oncoming vehicle, (ii) said apparatus is configured to detect a windshield of said oncoming vehicle and (iii) said beams of said headlights of said vehicle are reshaped to direct light away from said windshield of said oncoming vehicle.

14. The apparatus according to claim 12, wherein said second vehicle is at least one of a vehicle on a side of a road and an emergency vehicle.

15. The apparatus according to claim 1, wherein (i) one of said objects detected is a lane boundary, (ii) said beams of said headlights of said vehicle are adjusted to illuminate a lane based on said lane boundary and (iii) said lane is detected based on at least one of said lane boundary and said status information.

16. The apparatus according to claim 1, wherein (i) one of said objects detected is an intersecting roadway and (ii) said headlights of said vehicle are adjusted to create a wider beam when approaching said intersecting roadway.

17. The apparatus according to claim 1, wherein (i) said status information comprises GPS may data, (ii) said object comprises a shape of a road and (iii) said GPS map data confirms said classification of said shape of said road.

18. The apparatus according to claim 1, wherein (i) said location is calculated based on a comparison of a current size of said objects detected in a current video frame to a reference size of a reference object and (ii) said reference object is retrieved from a look up table based on said classification of said objects.

19. The apparatus according to claim 18, wherein said look up table is updateable.

20. The apparatus according to claim 1, wherein said classification of said objects is based on recognizing said objects in a said video frame of said video signal.