Laser mirror vision

• US 7,205,529 B2
• Filed: 02/01/2002
• Issued: 04/17/2007
• Est. Priority Date: 02/01/2001
• Status: Expired due to Fees

• Current Assignee: Marel Hf
• Original Assignee: Marel Hf
• Inventors: Andersen, Kristinn, Erlingsson, Vidar, Narfason, Sigurbjorn, Hallvardsson, Kristian
• Primary Examiner(s): Lauchman; Layla G.
• Assistant Examiner(s): VALENTIN, JUAN D
• Application Number:
  US10/470,775
• Publication Number:
  US 20040114153A1
• Time in Patent Office: 1,901 Days
• Field of Search: None
• US Class Current: 250/223.00R
• CPC Class Codes: G01B 11/00 Measuring arrangements characterised by the use of optical techniques
• CPC Class Codes: G01B 11/25 by projecting a pattern, e.g. one or more lines, moiré fringes on the object G01B11/255 takes precedence ; image analysis for depth or shape recovery G06T7/50
• CPC Class Codes: G01B 11/2545 with one projection direction and several detection directions, e.g. stereo
• CPC Class Codes: G01F 17/00 Methods or apparatus for determining the capacity of containers or cavities, or the volume of solid bodies measuring linear dimensions to determine volume G01B
• CPC Class Codes: G06T 7/55 from multiple images
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: H04N 13/218 using spatial multiplexing

Abstract

The present invention relates to a method and an apparatus for determining a three dimensional image of the a moving object by means of reflecting means such as mirrors and a planar beam of light such as a laser light. As the object enters the light a two dimensional image of the object is captured, wherein the image comprises both the reflection of the beam of light from the object and also the reflection from the reflecting means. By transformation procedure a two dimensional image is transformed to a two dimensional object image and based on plurality of such images a three dimensional image is defined from which the volume can be calculated. This can be used to determine the weight distribution of the object, which is important for portioning.

Claims

1. A method for determining a three dimensional image of a moving object, the method comprising the steps of, repetitively:

capturing a two dimensional image of the object with a capturing means, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from a plurality reflecting means,

dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the at least one reflecting means, and

transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure,

while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the objects domain, defining a three dimensional image, and

storing the images in a computer system,

wherein the reflecting means comprise at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein the mutual object domain gives the coordinates of the two dimensional cross sectional profile of the image.

2. The method according to claim 1, wherein the transformation of the image domains into a mutual object domain comprises transforming each scan element in the image domain with a transformation function adapted for transforming that specific image domain into the mutual object domain.

3. The method according to claim 1, wherein the transformation function comprises translational transformation.

4. The method according to claim 1 wherein the transformation function comprises rotational transformation.

5. The method according to claim 1 wherein the transformation function comprises scaling transformation.

6. The method according to claim 1, wherein the planar beam of light is situated above the moving object and wherein the plane of the beam light is perpendicular to the moving direction of the object.

7. The method according to claim 1, wherein the reflecting side of said at least one back mirror is positioned perpendicular to the moving direction of the object.

8. The method according to claim 1, wherein said at least one side mirror is positioned parallel to the moving direction of the object.

9. The method according to claim 1, wherein the light source, the capturing means, said least one side mirror and said least one back mirror are assembled and mounted as a one unit in a fixed position, wherein said at least one first side mirror is situated between the capturing means and said at least one back mirror.

10. The method according to claim 1 wherein the moving means is a conveyor belt.

11. A method for determining a three dimensional image of a moving object, the method comprising the steps of, repetitively:

capturing a two dimensional image of the object with a capturing means, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from a plurality reflecting means,

dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the at least one reflecting means, and

transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure, while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the objects domain, defining a three dimensional image, and

storing the images in a computer system,

wherein the reflecting means comprise at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein the transformation from the image domains to the mutual object domain, is based on database wherein the coordinates of the picture scan elements in the image domains are given new coordinates in accordance with said transformations to the mutual object domain.

12. A method for determining a three dimensional image of a moving object, the method comprising the steps of, repetitively:

capturing a two dimensional image of the object with a capturing means, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from a plurality reflecting means,

dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the at least one reflecting means, and

transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure,

while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the objects domain, defining a three dimensional image, and

storing the images in a computer system,

wherein the reflecting means comprise at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein the at least one back mirror is a single rear back mirror situated opposite the capturing means and above the moving object.

13. A method for determining a three dimensional image of a moving object, the method comprising the steps of, repetitively:

capturing a two dimensional image of the object with a capturing means, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from a plurality reflecting means,

dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the at least one reflecting means, and

transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure,

while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the objects domain, defining a three dimensional image, and

storing the images in a computer system,

wherein the reflecting means comprise at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein the at least one side mirror is positioned along to the moving direction of the object and in the plane of the planar beam of light so that light is reflected from the mirror to the object and back to the mirror thereby allowing the side view image of the object which are otherwise not detectable by the capturing means to be detectable.

14. A method for determining a three dimensional image of a moving object, the method comprising the steps of, repetitively:

capturing a two dimensional image of the object with a capturing means, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from a plurality reflecting means,

dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the at least one reflecting means, and

transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure,

while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the objects domain, defining a three dimensional image, and

storing the images in a computer system,

wherein the reflecting means comprise at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein the frequency of capturing a two dimensional image is controlled by the capturing means in a way that when no profile image is detected the image processing is minimal and the scan frequency is maximal.

15. A method for determining a three dimensional image of a moving object, the method comprising the steps of, repetitively:

capturing a two dimensional image of the object with a capturing means, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from a plurality reflecting means,

dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the at least one reflecting means, and

transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure,

while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the objects domain, defining a three dimensional image, and

storing the images in a computer system,

wherein the reflecting means comprise at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein from the three dimensional image the total volume of the object is calculated.

16. A method for determining a three dimensional image of a moving object, the method comprising the steps of, repetitively:

capturing a two dimensional image of the object with a capturing means, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from a plurality reflecting means,

dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the at least one reflecting means, and

transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure,

while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the objects domain, defining a three dimensional image, and

storing the images in a computer system,

wherein the reflecting means comprise at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein, by weighing the object and by using information relating to a total volume of the object, a mass distribution is determined.

17. A method for determining a three dimensional image of a moving object, the method comprising the steps of, repetitively:

capturing a two dimensional image of the object with a capturing means, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from a plurality reflecting means,

dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the at least one reflecting means, and

transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure,

while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the objects domain, defining a three dimensional image, and

storing the images in a computer system,

wherein the reflecting means comprise at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein a mass distribution is used for cutting the object.

18. A method for determining a three dimensional image of a moving object, the method comprising the steps of, repetitively:

capturing a two dimensional image of the object with a capturing means, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from a plurality reflecting means,

dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the at least one reflecting means, and

transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure,

while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the objects domain, defining a three dimensional image, and

storing the images in a computer system,

wherein the reflecting means comprise at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein the purity of contour line obtained from the two-dimensional profile image of the object is used as an indicator for the surface roughness of the object.

19. A method for determining a three dimensional image of a moving object, the method comprising the steps of, repetitively:

capturing a two dimensional image of the object with a capturing means, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from a plurality reflecting means,

dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the at least one reflecting means, and

transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure,

while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the objects domain, defining a three dimensional image, and

storing the images in a computer system,

wherein the reflecting means comprise at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein the capturing means comprises means for capturing colour and wherein the colour is used as an indicator for fat content and/or muscle content and/or water content and/or chemical composition.

20. An apparatus for determining a three dimensional image of an moving object, the apparatus comprising:

a conveyor for conveying the object

a plurality of reflecting means,

capturing means for capturing a two dimensional image of the object while the object is being conveyed, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from the reflecting means,

a computer system for storing the captured images and for dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the least one reflecting means and for transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the object domain generating a three dimensional image of the object,

wherein the reflecting means comprises at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein the mutual object domain gives the coordinates of the two dimensional cross sectional profile of the image.

21. A method for determining a three dimensional image of a moving object, the method comprising the steps of, repetitively:

capturing a two dimensional image of the object with a capturing means, the captured image comprising a scan element based on a reflection of a planar beam of light from the object and a scan element based on a reflection of the planar beam of light from the object, further reflected from a plurality reflecting means,

dividing the two dimensional image into at least two image domains, wherein one image domain comprises a reflection of the planar beam of light from the object and at least one image domain comprises a reflection of the planar beam of light from the at least one reflecting means, and

transforming the image domains into a two dimensional mutual object domain by means of a transformation procedure,

while the object is being subjected to the planar beam of light and based on the plurality of the two dimensional images in the objects domain, defining a three dimensional image, and

storing the images in a computer system,

wherein the reflecting means comprise at least one side and at least one back mirror adapted to view side and top image parts of the object, and

wherein the mass distribution is used for cutting the object in accordance to predefined criteria, and wherein said criteria is based on the speed on the moving means and the mass distribution.