Measuring surface distances on human bodies
Automatic anthropometric measurements may be utilised for various applications, such as online shopping and virtual tailoring. It is an objective to provide an apparatus for measuring surface distances of a human body. An apparatus is configured to receive a point cloud representing a surface shape of a scanned human body. The apparatus can be configured to generate a registered mesh of the surface shape of the scanned human body by registering a template mesh onto the point cloud. The template mesh can include predefined measurement paths, and the registered mesh can also include the predefined measurement paths after the registration. The apparatus can generate raw measurement results using the predefined measurement paths. The apparatus can be configured to calculate, using regression optimisation, at least one measurement result corresponding to a surface distance on the scanned human body using the raw measurement results.
1. An apparatus for measuring surface distances on human bodies, the apparatus comprising at least one processor and at least one memory comprising computer program code, wherein the at least one memory and the computer program code being configured to, with the at least one processor, cause the apparatus to at least:
receive a point cloud representing a surface shape of a scanned human body;
generate a registered mesh of the surface shape of the scanned human body by registering a template mesh, representing a reference shape of a human body, onto the point cloud, wherein the template mesh comprises predefined measurement paths, and wherein the registered mesh also comprises the predefined measurement paths;
generate raw measurement results using the predefined measurement paths, wherein each raw measurement result in the raw measurement results corresponds to a measurement path in the predefined measurement paths;
calculate, using non-linear support vector regression, at least one measurement result corresponding to a surface distance on the scanned human body using the raw measurement results; and
register the template mesh onto the point cloud by determining a mapping that maps the template mesh onto the point cloud, wherein the mapping minimises a cost function, wherein the cost function comprises a stiffness term, and wherein the stiffness term indicates a similarity of transformations applied to neighbouring vertices of the template mesh in the mapping.
2. The apparatus according to claim 1 , further comprising at least one scanning device for scanning shapes of human bodies; wherein the at least one memory and the computer program code is further configured to, with the at least one processor, cause the apparatus to:
use the scanning device for obtaining the point cloud.
3. The apparatus according to claim 2 , wherein each measurement path in the predefined measurement paths comprises edges between vertices of the registered mesh.
4. The apparatus according to claim 2 , wherein the at least one memory and the computer program code is further configured to, with the at least one processor, cause the apparatus to, before generating the registered mesh:
pre-align the point cloud and the template mesh.
5. The apparatus according to claim 2 , wherein the at least one memory and the computer program code is further configured to, with the at least one processor, cause the apparatus to:
pre-align a z-coordinate of a lowest point of the point cloud and a z-coordinate of a lowest point of the template mesh, wherein a z-axis is substantially parallel with a height direction of the scanned human body.
6. The apparatus according to claim 1 , wherein each measurement path in the predefined measurement paths comprises edges between vertices of the registered mesh.
7. The apparatus according to claim 6 , wherein the at least one memory and the computer program code is further configured to, with the at least one processor, cause the apparatus to, before generating the registered mesh:
pre-align the point cloud and the template mesh.
8. The apparatus according to claim 6 , wherein the at least one memory and the computer program code is further configured to, with the at least one processor, cause the apparatus to:
pre-align a z-coordinate of a lowest point of the point cloud and a z-coordinate of a lowest point of the template mesh, wherein a z-axis is substantially parallel with a height direction of the scanned human body.
9. The apparatus according to claim 1 , wherein the at least one memory and the computer program code is further configured to, with the at least one processor, cause the apparatus to, before generating the registered mesh:
pre-align the point cloud and the template mesh.
10. The apparatus according to claim 1 , wherein the at least one memory and the computer program code is further configured to, with the at least one processor, cause the apparatus to:
pre-align a z-coordinate of a lowest point of the point cloud and a z-coordinate of a lowest point of the template mesh, wherein a z-axis is substantially parallel with a height direction of the scanned human body.
11. The apparatus according to claim 1 , wherein each measurement path in the predefined measurement paths is indicated by a vertex identification, ID.
12. The apparatus according to claim 1 , wherein the at least one memory and the computer program code is further configured to, with the at least one processor, cause the apparatus to:
register the template mesh onto the point cloud using a non-rigid iterative closest point, ICP, procedure.
13. The apparatus according to claim 1 , wherein the cost function comprises a distance term, wherein the distance term comprises distances, and wherein each distance in the distances corresponds to a distance between a point in the point cloud and a corresponding point in the template mesh.
14. The apparatus according to claim 1 , further configured to use the at least one measurement result in finding a fitting garment for the scanned human body.
15. The apparatus according to claim 1 , further configured to use the at least one measurement result in producing a garment for the scanned human body.
16. A method comprising:
receiving a point cloud representing a surface shape of a scanned human body;
generating a registered mesh of the surface shape of the scanned human body by registering a template mesh, representing a reference shape of a human body, onto the point cloud, wherein the template mesh comprises predefined measurement paths, and wherein the registered mesh also comprises the predefined measurement paths;
generating raw measurement results using the predefined measurement paths, wherein each raw measurement result in the raw measurement results corresponds to a measurement path in the predefined measurement paths;
calculating, using non-linear support vector regression, at least one measurement result corresponding to a surface distance on the scanned human body using the raw measurement results; and
registering the template mesh onto the point cloud by determining a mapping that maps the template mesh onto the point cloud, wherein the mapping minimises a cost function, wherein the cost function comprises a stiffness term, and wherein the stiffness term indicates a similarity of transformations applied to neighbouring vertices of the template mesh in the mapping.
17. A computer program product comprising at least one computer- readable medium bearing computer program code which, when executed by a computer, executes the method according to claim 16 .