IMAGE RECOGNITION APPARATUS

• US 20120099763A1
• Filed: 09/08/2011
• Published: 04/26/2012
• Est. Priority Date: 10/26/2010
• Status: Active Grant

• Current Assignee: Fujitsu Ten Limited (DENSO Corporation)
• Original Assignee: Fujitsu Ten Limited (DENSO Corporation)
• Inventors: KATOH, Tetsuhiro, MURASHITA, Kimitaka
• Granted Patent: US 8,594,377 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 10/22 by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Abstract

An image recognition part of an image recognition apparatus recognizes an object based on a target area in an outside-vehicle image obtained by a camera installed in a vehicle. A position identifying part identifies an optical axis position of the camera relative to the vehicle based on the outside-vehicle image, and an area changing part changes a position of the target area in the outside-vehicle image according to the optical axis position of the camera. Therefore, it is possible to recognize an object properly based on the target area in the outside-vehicle image even though the optical axis position of the camera is displaced.

Claims

1. An image recognition apparatus that recognizes an object based on an image, the image recognition apparatus comprising:

a recognition unit that recognizes the object based on a target area in an image obtained by a camera installed in a vehicle;

an identifying unit that identifies an optical axis position of the camera relative to the vehicle based on the image; and

a changing unit that changes a position of the target area in the image according to the optical axis position identified by the identifying unit.

2. The image recognition apparatus according to claim 1, further comprising:

a derivation unit that derives an amount of displacement of the optical axis position from an initial position based on the image; and

an informing unit that informs a user that the amount of displacement is more than a threshold value in a case where the amount of displacement is more than the threshold value.

3. The image recognition apparatus according to claim 1, further comprising:

a derivation unit that derives an amount of displacement of the optical axis position from an initial position based on the image; and

an adjustment unit that adjusts the optical axis position in a case where the amount of displacement is more than a threshold value.

4. The image recognition apparatus according to claim 1, wherein

the changing unit changes the position of the target area in the image in a first direction opposite to a second direction, in a case where the optical axis position has changed in the second direction relative to a previous optical axis position.

5. The image recognition apparatus according to claim 1, wherein

the identifying unit identifies the optical axis position by deriving a vanishing point position in the image.

6. The image recognition apparatus according to claim 1, wherein

the object recognized by the recognition unit is another vehicle that is running in front of the vehicle in which the camera is installed.

7. The image recognition apparatus according to claim 6, wherein

the target area includes a vanishing point in the image.

8. The image recognition apparatus according to claim 1, wherein

the object recognized by the recognition unit is lane marks that define a traffic lane in which the vehicle runs.

9. An image recognition method for recognizing an object based on an image, the method comprising the steps of:

(a) recognizing the object based on a target area in an image obtained by a camera installed in a vehicle;

(b) identifying an optical axis position of the camera relative to the vehicle based on the image; and

(c) changing a position of the target area in the image according to the optical axis position identified in step (b).

10. The image recognition method according to claim 9, further comprising the steps of:

(d) deriving an amount of displacement of the optical axis position from an initial position based on the image; and

(e) informing a user that the amount of displacement is more than a threshold value in a case where the amount of displacement is more than the threshold value.

11. The image recognition method according to claim 9, further comprising the steps of:

(d) deriving an amount of displacement of the optical axis position from an initial position based on the image; and

(e) adjusting the optical axis position in a case where the amount of displacement is more than a threshold value.

12. The image recognition method according to claim 9, wherein

in the step (c), the position of the target area in the image is changed in a first direction opposite to a second direction, in a case where the optical axis position has changed in the second direction relative to a previous optical axis position.

13. The image recognition method according to claim 9, wherein

in the step (b), the optical axis position is identified by deriving a vanishing point position in the image.

14. The image recognition method according to claim 9, wherein

in the step (a), the object that is recognized is another vehicle that is running in front of the vehicle in which the camera is installed.

15. The image recognition method according to claim 14, wherein

the target area includes a vanishing point in the image.

16. The image recognition method according to claim 9, wherein

in the step (a), the object that is recognized is lane marks that define a traffic lane in which the vehicle runs.