Three-dimensional object image generation
A volume of an object is extracted from a three-dimensional image to generate a three-dimensional object image, where the three-dimensional object image represents the object but little to no other aspects of the three-dimensional image. The three-dimensional image is yielded from an examination in which the object, such as a suitcase, is situated within a volume, such as a luggage bin, that may contain other aspects or objects that are not of interest, such as sidewalls of the luggage bin. The three-dimensional image is projected to generate a two-dimensional image, and a two-dimensional boundary of the object is defined, where the two-dimensional boundary excludes or cuts off at least some of the uninteresting aspects. In some embodiments, the two-dimensional boundary is reprojected over the three-dimensional image to generate a three-dimensional boundary, and voxels comprised within the three-dimensional boundary are extracted to generate the three-dimensional object image.
1. A method for generating a three-dimensional object image from a three-dimensional image depicting an object and a secondary object, comprising:
projecting the three-dimensional image along a first axis to generate a first two-dimensional projection image;
first adding a two-dimensional boundary encompassing the object responsive to the first two-dimensional projection image;
second adding a three-dimensional boundary encompassing the object within the three-dimensional image by projecting the two-dimensional boundary over at least a portion of the three-dimensional image; and
extracting voxels comprised within the three-dimensional boundary to generate the three-dimensional object image depicting the object but not depicting the secondary object.
2. The method of claim 1 , wherein the object is a suitcase.
3. The method of claim 2 , wherein the secondary object is a luggage bin.
4. The method of claim 1 , comprising:
projecting the two-dimensional boundary along a second axis, different than the first axis, to generate a first one-dimensional projection line; and
identifying a first set of one or more edges of the object responsive to the first one-dimensional projection line.
5. The method of claim 4 , comprising:
projecting the two-dimensional boundary along a third axis, different than the first axis and different than the second axis, to generate a second one-dimensional projection line; and
identifying a second set of one or more edges of the object responsive to the second one-dimensional projection line.
6. The method of claim 5 , comprising characterizing the two-dimensional boundary responsive to the first set of one or more edges and the second set of one or more edges.
7. The method of claim 1 , comprising:
reprojecting the two-dimensional boundary over at least a portion of the three-dimensional image to generate a three-dimensional sub-image.
8. The method of claim 7 , comprising:
projecting the three-dimensional sub-image along a second axis, different than the first axis, to generate a second two-dimensional projection image.
9. The method of claim 8 , comprising:
identifying a third set of one or more edges of the object responsive to the second two-dimensional projection image.
10. The method of claim 9 , the second adding the three-dimensional boundary comprising adding the three-dimensional boundary responsive to the third set of one or more edges.
11. The method of claim 8 , the comprising:
projecting the second two-dimensional projection image along a third axis, different than the second axis, to generate a third one-dimensional projection line; and
identifying a third set of one or more edges of the object responsive to the third one-dimensional projection line.
12. The method of claim 1 , comprising, prior to the projecting:
adding a search path relative to the three-dimensional image;
generating a set of planes angled at a predefined angle relative to the search path;
identifying a first boundary plane by sequentially examining the set of planes to identify a first edge of the object; and
trimming the three-dimensional image responsive to the first boundary plane.
13. The method of claim 1 , at least one of the first adding the two-dimensional boundary or second adding the three-dimensional boundary responsive to user input.
14. The method of claim 1 , wherein the three-dimensional image is yielded from a radiation examination of the object and the secondary object.
15. A system comprising:
a processing unit; and
memory configured to store instructions that when executed by the processing unit perform a method, comprising:
projecting a three-dimensional image of an object and a secondary object in which the object is situated during a radiation examination to generate a two-dimensional projection image;
adding a two-dimensional boundary encompassing the object responsive to the two-dimensional projection image;
projecting the two-dimensional boundary over a portion of the three-dimensional image to add a three-dimensional boundary encompassing the object; and
extracting voxels comprised within the three-dimensional boundary to generate a three-dimensional object image depicting the object but not depicting the secondary object.
16. The method of claim 15 , the method comprising presenting the two-dimensional projection image to a user.
17. The method of claim 16 , the adding comprising adding the two-dimensional boundary responsive to user input received responsive to the presenting.
18. The method of claim 15 , the projecting comprising projecting the three-dimensional image along a first axis and the method comprising:
projecting the two-dimensional projection image along a second axis, different than the first axis, to generate a one-dimensional projection line; and
identifying an edge of the object responsive to the one-dimensional projection line.
19. The method of claim 18 , the adding comprising adding the two-dimensional boundary responsive to the edge.
20. A computer-readable medium comprising computer executable instructions that when executed perform a method for generating a three-dimensional object image from a three-dimensional image depicting an object and a secondary object, the method comprising:
projecting a three-dimensional image along a first axis to generate a first two-dimensional projection image;
adding a two-dimensional boundary encompassing the object responsive to the first two-dimensional projection image;
adding a three-dimensional boundary encompassing the object within the three-dimensional image by projecting the two-dimensional boundary over at least a portion of the three-dimensional image; and
extracting voxels comprised within the three-dimensional boundary to generate the three-dimensional object image depicting the object but not depicting the secondary object.