METHOD FOR DISLAYING MEASUREMENT EFFECTIVE AREA IN THREE-DIMENSIONAL VISUAL SENSOR AND THREE-DIMENSIONAL VISUAL SENSOR

• US 20110122231A1
• Filed: 10/29/2010
• Published: 05/26/2011
• Est. Priority Date: 11/24/2009
• Status: Active Grant

• Current Assignee: Omron Corporation
• Original Assignee: Omron Corporation
• Inventors: Takahashi, Reiji, Taneno, Atsushi, FUJIEDA, SHIRO, Yoshino, Masanao, Ukai, Kenichi
• Granted Patent: US 8,964,001 B2
• Time in Patent Office: Days
• US Class Current: 348/47
• CPC Class Codes: G05B 2219/37017 Calibration of vision system, set correct attidude of sensor to workpiece
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/10012 Stereo images
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/593 from stereo images
• CPC Class Codes: G06T 7/75 involving models
• CPC Class Codes: H04N 13/239 using two 2D image sensors having a relative position equal to or related to the interocular distance H04N13/243 takes precedence
• CPC Class Codes: H04N 13/243 using three or more 2D image sensors
• CPC Class Codes: H04N 2013/0081 Depth or disparity estimation from stereoscopic image signals

Abstract

One of stereo cameras is set such that a front view of a support surface of a workpiece is imaged, an image produced by the camera is displayed, and a range of an area where measurement processing is enabled is assigned by a rectangular frame. A manipulation assigning an upper limit and a lower limit of a height measurement range is accepted. When each assignment is fixed, zero is set as a z-coordinate to each constituent pixel of an image to which the rectangular frame is set, and a z-coordinate based on the upper limit of the height measurement range and a z-coordinate based on the lower limit are set to coordinates corresponding to the rectangular frame. Perspective transformation of three-dimensional information produced by the setting is performed from a direction of a line of sight set by a user, a produced projection image is displayed on a monitor.

Claims

1. A method for displaying an area where measurement processing is enabled in a three-dimensional visual sensor in which a space including a measurement target and a support surface of the measurement target is imaged with a plurality of stereo cameras to perform three-dimensional measurement of the measurement target using a produced stereo image, the method comprising:

a first step of setting a position and an attitude of one of the plurality of stereo cameras such that a front view of the support surface of the measurement target is imaged, displaying a two-dimensional image produced by the one of the plurality of stereo camera on a monitor, accepting a manipulation assigning a range in the support surface of an effective area of the measurement processing on the displayed image, and accepting an input of a numerical value indicating a height range of the measurement target;

a second step of setting a specific coordinate corresponding to one numerical value in the height range accepted in the first step to each pixel constituting the two-dimensional image produced by the one of the plurality of stereo camera as a z-coordinate and producing three-dimensional information by setting a z-coordinate based on an upper limit of the height range and a z-coordinate based on a lower limit to each of a plurality of coordinates indicating the effective area assigned by the range assigning manipulation;

a third step of accepting a manipulation assigning a direction of a line of sight with respect to the three-dimensional information and producing a projection image by performing perspective transformation of the three-dimensional information from the direction assigned by the manipulation; and

a fourth step of displaying the projection image on the monitor.

2. The method according to claim 1, wherein the projection image is edited into an image in which a projection range of the effective area is identified and a post-editing image is displayed on the monitor in the fourth step.

3. A three-dimensional visual sensor in which a space including a measurement target and a support surface of the measurement target is imaged with a plurality of stereo cameras to perform three-dimensional measurement of the measurement target using a produced stereo image, the three-dimensional visual sensor comprising:

a range assignment accepting unit that sets one of the stereo cameras as a reference camera, displays a two-dimensional image produced by the reference camera on a monitor, accepts a manipulation assigning a range in the support surface of an effective area of the measurement processing on the displayed image, and accepts an input of a numerical value indicating a height range of the measurement target;

a three-dimensional information producing unit that sets a specific coordinate corresponding to one numerical value in the height range accepted by the range assignment accepting unit to each pixel constituting the two-dimensional image produced by the reference camera as a z-coordinate and produces three-dimensional information by setting a z-coordinate based on an upper limit of the height range and a z-coordinate based on a lower limit to each of a plurality of coordinates indicating the effective area assigned by the range assigning manipulation;

a perspective transformation unit that accepts a manipulation assigning a direction of a line of sight with respect to the three-dimensional information and produces a projection image by performing perspective transformation of the three-dimensional information from the direction assigned by the manipulation; and

a projection image display unit that displays the projection image on the monitor.

4. The three-dimensional visual sensor according to claim 3, further comprising:

a registration unit in which a three-dimensional model of the measurement target is registered;

a recognition unit that recognizes a position and an attitude of the measurement target by matching three-dimensional information restored from the stereo image with the three-dimensional model; and

a model projection unit that performs perspective transformation of the three-dimensional model, set to the position and attitude recognized by the recognition unit, into a coordinate system of the reference camera,

wherein the three-dimensional information producing unit sets a z-coordinate based on a height set to corresponding point in the three-dimensional model to each point of a projection image of the three-dimensional model produced by the model projection unit, and the three-dimensional information producing unit includes each post-setting point in three-dimensional information as a target of the perspective transformation processing, and

wherein the projection image display unit edits the projection image produced by the perspective transformation unit into a state where the three-dimensional model in the image and the effective area are identified, and the projection image display unit displays a post-editing image on the monitor.