3-dimensional model creation methods and apparatuses

1. A method for creating a 3-Dimensional model for objects in an inspected luggage in a CT system, comprising:

acquiring slice data of the luggage with the CT system;

interpolating the slice data to generate 3D volume data of the luggage;

performing unsupervised segmentation on the 3D volume data of the luggage to obtain a plurality of segmental regions;

performing isosurface extraction on the plurality of segmental regions to obtain corresponding isosurfaces; and

performing 3D surface segmentation on the isosurfaces to form a 3D model for the objects in the luggage;

wherein the unsupervised segmentation is performed by using a Statistical Region Merging (SRM) algorithm which is extended into 3D processing by:

joining an atomic number and density of the 3D volume data into a vector so as to represent a 3D voxel as two vectors and replacing a grey difference in a conventional SRM with a module of a difference vector between the two vectors, replacing a 2D gradient in the conventional SRM with a 3D gradient, and replacing an area of a pixel in a 2D region in the conventional SRM with a volume of a voxel.

2. The method of claim 1 , further comprising, before performing unsupervised segmentation on the 3D volume data of the luggage:

thresholding the 3D volume data of the luggage to remove data of objects of no interest; and

filtering the 3D volume data of the luggage.

3. The method of claim 1 , wherein said performing 3D surface segmentation on the isosurfaces comprises:

segmenting the isosurfaces into a plurality of curved surfaces; and

joining two of the curved surfaces if a line connecting centers of the two curved surfaces is inside the isosurfaces.

4. The method of claim 1 , further comprising performing hole-filling, smoothing, and model limiting processes on the results of 3D surface segmentation.

5. The method of claim 1 , wherein the CT system comprises a dual-energy CT system, and the 3D volume data of the luggage comprises electron density volume data and atomic number volume data.

6. The method of claim 1 , wherein the CT system comprises a mono-energy CT system, and the 3D volume data of the luggage comprises linear attenuation coefficient volume data.

7. An apparatus for creating a 3-Dimensional model for objects in an inspected luggage in a CT system, comprising:

a storage device configured to store slice data of the luggage;

a central processing unit configured to:

interpolate the slice data to generate 3D volume data of the luggage;

perform unsupervised segmentation on the 3D volume data of the luggage to obtain a plurality of segmental regions;

perform isosurface extraction on the plurality of segmental regions to obtain corresponding isosurfaces; and

perform 3D surface segmentation on the isosurfaces to form a 3D model for the objects in the luggage;

wherein the central processing unit is further configured to perform the unsupervised segmentation by using a Statistical Region Merging (SRM) algorithm which is extended into 3D processing by:

joining an atomic number and density of the 3D volume data into a vector so as to represent a 3D voxel as two vectors and replacing a grey difference in a conventional SRM with a module of a difference vector between the two vectors, replacing a 2D gradient in the conventional SRM with a 3D gradient, and replacing an area of a pixel in a 2D region in the conventional SRM with a volume of a voxel.

8. The apparatus of claim 7 , wherein the central processing unit is further configured to:

threshold the 3D volume data of the luggage to remove data of objects of no interest; and

filter the 3D volume data of the luggage.

9. The apparatus of claim 7 , wherein the central processing unit is further configured to:

segment the isosurfaces into a plurality of curved surfaces; and

join two of the curved surfaces if a line connecting centers of the two curved surfaces is inside the isosurfaces.