×

Method For Displaying Recognition Result Obtained By Three-Dimensional Visual Sensor And Three-Dimensional Visual Sensor

  • US 20100232683A1
  • Filed: 02/23/2010
  • Published: 09/16/2010
  • Est. Priority Date: 03/11/2009
  • Status: Active Grant
First Claim
Patent Images

1. A method for displaying recognition result of a three-dimensional visual sensor, the three-dimensional visual sensor including:

  • an imaging unit that includes at least one camera;

    a registration unit in which three-dimensional information expressing a full-scale recognition-target object is registered as a three-dimensional model; and

    a recognition unit that performs three-dimensional measurement to a recognition-target object whose three-dimensional model is registered in the registration unit using an image produced by imaging of the imaging unit and checks three-dimensional information restored by the measurement with the registered three-dimensional model to recognize a position and an attitude of the recognition-target object, on condition that a world coordinate system is defined such that a distance from a reference plane traversing a direction of an optical axis of the camera in the imaging unit becomes a Z-coordinate indicating a height,wherein at least one of the cameras is set to a processing object,a first step, a second step, a third step, and a fourth step are performed every camera of the processing object,in the first step, a manipulation of specification of a direction of a line of sight with respect to an imaging surface of the camera being received,in the second step, a plurality of Z-coordinates included in a three-dimensional model being corrected to perform perspective transformation of a post-correction three-dimensional model into a coordinate system of the imaging surface of the camera of the processing object for the three-dimensional model to which coordinate transformation is performed in a world coordinate system such that the position and attitude of the three-dimensional model become identical to those of the recognition-target object recognized by the recognition unit,in the third step, perspective transformation of a point having a three-dimensional coordinate value obtained by setting a height according to a corresponding pre-correction Z-coordinate into a point having a three-dimensional coordinate value obtained by setting a point included in an projection image of the three-dimensional model produced in the coordinate system of the imaging surface of the camera of the processing object by the perspective transformation processing being performed from the direction of the line of sight received in the first step,in the fourth step, the projection image produced by the perspective transformation in the third step being displayed on a monitor device, anda rule of correction operation is applied to the Z-coordinate correction in the second step,in the rule of correction operation, a correction amount to each Z-coordinate being set to zero when an orthogonal relationship is established between the direction of the line of sight received in the first step and the imaging surface of the camera of the processing object, each Z-coordinate being corrected to a constant value Z0 when the direction of the line of sight becomes parallel to the imaging surface, each post-correction Z-coordinate being brought close to the constant value Z0 as the relationship between the direction of the line of sight and the imaging surface becomes close to a parallel state from the orthogonal state, a difference between post-correction Z-coordinates Z1′ and

    Z2′

    of any two of Z-coordinates Z1 and Z2 (Z1>

    Z2) being gradually decreased while a relationship of Z1′

    >

    Z2′

    is maintained.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×