System and method for detecting obstacle

• US 7,349,582 B2
• Filed: 05/24/2007
• Issued: 03/25/2008
• Est. Priority Date: 05/23/2001
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Hattori, Hiroshi, Onoguchi, Kazunori, Takeda, Nobuyuki
• Primary Examiner(s): Kassa; Yosef
• Application Number:
  US11/752,950
• Publication Number:
  US 20070223840A1
• Time in Patent Office: 306 Days
• Field of Search: 382/219, 382/274, 382/275, 382/284, 382/291, 348/139, 348/143
• US Class Current: 382/276
• CPC Class Codes: G01C 11/06 by comparison of two or more pictures of the same area
• CPC Class Codes: G01S 11/12 using electromagnetic waves other than radio waves
• CPC Class Codes: G06T 7/30 Determination of transform parameters for the alignment of images, i.e. image registration
• 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
• 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: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

A method for detecting an obstacle by using two cameras, the obstacle being on a reference plane in a field of view common to the two cameras, the method inputting a first image and a second image from the two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating a similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on the degree of similarity D and the degree of similarity P on a reference plane region, obtaining a difference K between the degree of similarity D and the degree of similarity P both obtained as being on the reference plane region, judging that the obstacle is at a position where the difference K is large, judging that there is no obstacle when there is no difference K of degree of similarity equal to or greater than a threshold value set beforehand about the vertical directions of all of the images, and detecting that there is the obstacle when there is the difference K of degree of similarity equal to or more than the threshold value in the vertical direction of the image.

Claims

1. A method for detecting an obstacle by using two cameras, the obstacle being on a reference plane in a field of view common to the two cameras, the method comprising:

inputting a first image and a second image from the two cameras, respectively;

transforming the first image to a transformed image on a basis of image transform which is introduced from a geometrical relationship between a reference plane and the two cameras for transforming any given pixel in a reference plane region in the first image to a corresponding pixel in the second image;

obtaining a degree of similarity D indicating a similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image and being a function of position in the vertical direction of the image;

establishing, when any given image line in a specified region in the second image is a contact line of the obstacle with the reference plane, the processing region for an inter-image arithmetic operation between the first image and the second image, and a plurality of the processing regions being established with the image line being shifted in the vertical direction;

obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image and being a function of position in the vertical direction of the image;

establishing the processing region for an inter-image arithmetic operation between the second image and the transformed image, and a plurality of the processing regions being established with the image line being shifted in the vertical direction;

detecting the obstacle on a basis of the degree of similarity D and the degree of similarity P on a reference plane region;

obtaining a difference K between the degree of similarity D and the degree of similarity P both obtained as being on the reference plane region;

judging that the obstacle is at a position where the difference K is large;

judging that there is no obstacle when there is no difference K of degree of similarity equal to or greater than a threshold value set beforehand about the vertical directions of all of the images; and

detecting that there is the obstacle when there is the difference K of degree of similarity equal to or more than the threshold value in the vertical direction of the image.

2. The method as claimed in claim 1, further comprising:

carrying out threshold value processing of the difference K with a threshold value equal to or greater than zero, in which the difference K is given as K(y) as function of y the direction of which is taken as the vertical direction of the image and a result of the threshold value processing of K(y) is taken as K_th(y);

judging that there is none of the obstacle in a case when K_th(y) satisfies

$\underset{y}{\sum <br><br>}<br><br>K_{\mathrm{th}}<br><br>\left(Y\right)=0;<br><br>$

and

judging that a y₀ that minimizes

$<br><br>\mathrm{\alpha <br><br>}<br><br>\underset{y}{\sum <br><br>}<br><br>K_{\mathrm{th}}<br><br>\left(y\right)-\underset{y}{\overset{y_0}{\sum <br><br>}}<br><br>K_{\mathrm{th}}<br><br>\left(y\right)<br><br>$

is the position of the obstacle in the cases other than the above, where α

is any one of constants from 0 to 1.

3. The method as claimed in claim 1, further comprising:

selecting and outputting either a result of detection of a plurality of the obstacles or a position of an obstacle detected as being the closest to three or more cameras, wherein the two cameras are part of the three or more cameras.