Image processing apparatus

• US 20060291719A1
• Filed: 06/16/2006
• Published: 12/28/2006
• Est. Priority Date: 06/17/2005
• Status: Active Grant

• Current Assignee: Omron Corporation
• Original Assignee: Omron Corporation
• Inventors: Ikeda, Yasuyuki, Fujieda, Shiro
• Granted Patent: US 7,630,539 B2
• Time in Patent Office: Days
• US Class Current: 382/154
• CPC Class Codes: G01B 11/0608 Height gauges
• CPC Class Codes: G01B 11/24 for measuring contours or curvatures
• CPC Class Codes: G06T 2207/30148 Semiconductor; IC; Wafer
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/593 from stereo images

Abstract

Plural items of two-dimensional image processing and at least one item of a three-dimensional measurement process are registered in a processing item table. The items of two-dimensional image processing include at least one item of an on-first-image position specification process of specifying a position on a physical object in a first image. A sequence building unit combines the item of the on-first-image position specification process and the item of the three-dimensional measurement process to set the sequence for three-dimensional measurement by selection of a user.

Claims

1. An image processing apparatus which performs a process with a first image and a second image taken by a first camera and a second camera respectively, the first camera and the second camera being arranged so as to take a physical object from different directions,

the image processing apparatus comprising:

sequence setting means for setting a sequence of a processing item; and

sequence executing means for executing the set sequence,

wherein the sequence setting means provides plural items of two-dimensional image processing and at least one item of a three-dimensional measurement process as the processing item which can be set at a sequence element by selection of a user,

the provided items of the two-dimensional image processing include at least one item of an on-first-image position specification process of specifying a position on a physical object in the first image, and

the three-dimensional measurement process includes an on-second-image position specification process of specifying a position on a physical object in the second image, the position on the physical object in the second image corresponding to the position on the physical object in the first image which is specified in the on-first-image position specification process belonging to the same sequence as the sequence to which the on-second-image position specification process belongs to.

2. An image processing apparatus according to claim 1, wherein the three-dimensional measurement process further includes a process of computing a three-dimensional coordinate using the position specified in the on-first-image position specification process and the position specified in the on-second-image position specification process.

3. An image processing apparatus according to claim 1, wherein a plurality of kinds of items of the on-first-image position specification process and a plurality of kinds of items of the three-dimensional measurement process are provided so as to be able to be set at the sequence element by the selection of a user.

4. An image processing apparatus according to claim 1, wherein a three-dimensional measurement basic sequence is provided so as to be able to be utilized by the selection of a user, the three-dimensional measurement basic sequence including at least one item of the on-first-image position specification process and at least one item of the three-dimensional measurement process.

5. An image processing apparatus according to claim 1, wherein a first detection area is set to the first image to detect an edge position in an edge detection direction, the edge position being determined for the first detection area, in at least one on-first-image position specification process to which the processing item is provided, and

a second detection area is set to the second image, a particularly direction being set at the edge detection direction in the second detection area, the particular direction being determined based on a positional relationship between the first camera and the second camera and the edge position specified in the on-first-image position specification process, in the on-second-image position specification process in at least one three-dimensional measurement process to which the processing item is provided.

6. An image processing apparatus according to claim 5, wherein, in the second detection area, a range along the edge detection direction is set based on a range along an optical axis of the first camera which is specified by a user as a three-dimensional measurement target range.

7. An image processing apparatus according to claim 5, wherein the first camera has a rectangular visual field range while arranged so as to take the physical object from a front side,

the second camera is located at a position which is separated from the visual field of the first camera in a longitudinal direction or in a crosswise direction, the second camera is arranged so as to take the physical object from an oblique direction with respect to the direction in which the physical object is seen from the front side,

the first detection area is set in the first image at a position based on a user command in on-first-image position specification process, and

the edge detection direction of the first detection area is located in a row of the first camera and the second camera.

8. An image processing apparatus according to claim 1, wherein a representative position of an area on the first image having a high degree of correspondence to a model image is specified in at least one on-first-image position specification process to which the processing item is provided, the model image being previously registered before the measurement is performed, and

a representative position of an area on the second image having a high degree of correspondence to the model image is specified in the on-second-image position specification process in at least one three-dimensional measurement process to which the processing item is provided.

9. An image processing apparatus according to claim 8, wherein, in the on-second-image position specification process, a search area is set on the second image based on the positional relationship between the first camera and the second camera and the representative positions specified in the on-first-image position specification process, and the representative position of the area having the high degree of correspondence to the model image is specified in the search area.

10. An image processing apparatus according to claim 9, wherein the search area is set based on the range along the optical axis of the first camera specified by a user as the three-dimensional measurement target range.

11. An image processing apparatus according to claim 1, wherein a representative position of a measurement target area set on the first image based on the user command is specified to obtain the image in the measurement target area as the model image in at least one on-first-image position specification process to which the processing item is provided, and

a representative position of an area on the second image having a high degree of correspondence to the model image is specified in the on-second-image position specification process in at least one three-dimensional measurement process to which the processing item is provided.

12. An image processing apparatus according to claim 11, wherein, in the on-second-image position specification process, a search area is set on the second image based on the positional relationship between the first camera and the second camera and the representative positions specified in the on-first-image position specification process, and the representative position of the area having the high degree of correspondence to the model image is specified in the search area.

13. An image processing apparatus according to claim 11, wherein the search area is set based on the range along the optical axis of the first camera specified by a user as the three-dimensional measurement target range.

14. An image processing method in which a first image and a second image respectively taken by a first camera and a second camera are used, the first camera and the second camera being arranged so as to take a physical object from different directions,

the image processing method comprising:

a sequence setting step of setting a sequence of a processing item; and

a sequence executing step of executing the set sequence,

wherein the sequence setting step provides plural items of two-dimensional image processing and at least one item of a three-dimensional measurement process as the processing item which can be set at a sequence element by selection of a user,

the provided items of the two-dimensional image processing include at least one item of an on-first-image position specification process of specifying a position on a physical object in the first image, and

the three-dimensional measurement process includes an on-second-image position specification process of specifying a position on a physical object in the second image, the position on the physical object in the second image corresponding to the position on the physical object in the first image which is specified in the on-first-image position specification process belonging to the same sequence as the sequence to which the on-second-image position specification process belongs to.

15. An image processing method according to claim 14, wherein the three-dimensional measurement process further includes a process of computing a three-dimensional coordinate using the position specified in the on-first-image position specification process and the position specified in the second on-image position specification process.

16. An image processing apparatus which performs a process with a first image and a second image taken by a first camera and a second camera respectively, the first camera having a rectangular visual field range while arranged so as to take a physical object from a front side, the second camera being located at a position which is separated from the visual field of the first camera in a longitudinal direction or in a crosswise direction, the second camera being arranged so as to take the physical object from an oblique direction with respect to the direction in which the physical object is seen from the front side,

the image processing apparatus comprising:

on-first-image position specification means for specifying a position on the physical object in the first image;

on-second-image position specification means for specifying a position on the physical object in the second image, the position on the physical object in the second image corresponding to the position on the physical object in the first image specified by the on-first-image position specification means; and

three-dimensional coordinate computation means for computing a three-dimensional coordinate using the position specified by the on-first-image position specification means and the position specified by the on-second-image position specification means,

wherein the on-first-image position specification means sets a first detection area at a position in the first image based on a user command, the on-first-image position specification means specifies an edge position in an edge detection direction determined for the first detection area, and the edge detection direction of the first detection area is located in a row of the first camera and the second camera, and

the on-second-image position specification means sets a second detection area to the second image, a particular direction is set at the edge detection direction in the second detection area, the particular direction being determined based on a positional relationship between the first camera and the second camera and the edge position specified in the on-first-image position specification means, and the on-second-image position specification means specifies the edge position in the edge detection direction in the second detection area.

17. An image processing method in which a process is performed with a first image and a second image taken by a first camera and a second camera respectively, the first camera having a rectangular visual field range while arranged so as to take a physical object from a front side, the second camera being located at a position which is separated from the visual field of the first camera in a longitudinal direction or in a crosswise direction, the second camera being arranged so as to take the physical object from an oblique direction with respect to the direction in which the physical object is seen from the front side,

the image processing method comprising:

an on-first-image position specification step of specifying a position on the physical object in the first image;

an on-second-image position specification step of specifying a position on the physical object in the second image, the position on the physical object in the second image corresponding to the position on the physical object in the first image specified by the on-first-image position specification step; and

a three-dimensional coordinate computation step of computing a three-dimensional coordinate using the position specified by the on-first-image position specification step and the position specified by the on-second-image position specification step,

wherein the on-first-image position specification step sets a first detection area at a position in the first image based on a user command, the on-first-image position specification step specifies an edge position in an edge detection direction determined for the first detection area, and the edge detection direction of the first detection area is located in a row of the first camera and the second camera, and

the on-second-image position specification step sets a second detection area to the second image, a particular direction is set at the edge detection direction in the second detection area, the particular direction being determined based on a positional relationship between the first camera and the second camera and the edge position specified in the on-first-image position specification step, and the on-second-image position specification step specifies the edge position in the edge detection direction in the second detection area.