Automatic beam-shaping using an on-car camera system
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
B60Q-001/08
B60Q-001/12
B60Q-001/115
H04N-007/18
G06K-009/00
출원번호
US-0690945
(2015-04-20)
등록번호
US-9896022
(2018-02-20)
발명자
/ 주소
Pertsel, Shimon
Fink, Alexander
출원인 / 주소
Ambarella, Inc.
대리인 / 주소
Christopher P. Maiorana, PC
인용정보
피인용 횟수 :
0인용 특허 :
18
초록▼
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
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.
대표청구항▼
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; anda processor configured to (i) perform video analysis
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; anda 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.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (18)
Holt Arthur W. (100 Caroline St. Oxford MD 21654), Character and pattern recognition machine and method.
Robert Anthony Laumeyer ; James Eugene Retterath, System for automatically generating database of objects of interest by analysis of images recorded by moving vehicle.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.