Transporter segmentation for data capture system

1. A server, comprising:

a memory storing calibration data; and

a processor connected with the memory, the processor configured to:

obtain a point cloud depicting a capture volume containing a transporter having a body and a holder carrying an object to be dimensioned;

obtain a set of positions associated with the transporter, the set of positions being further associated with markers positioned on the transporter;

based on the set of positions and the calibration data, select a first portion of the point cloud excluding the body of the transporter and a mast of the holder;

based on the calibration data, select a second portion of the point cloud from the first portion, excluding a base of the holder; and

dimension the object based on the second portion of the point cloud,

wherein the calibration data includes positions of structural features of the transporter relative to the markers positioned on the transporter.

2. The server of claim 1 , further comprising:

a communications interface;

wherein the processor is further configured, in order to obtain the point cloud, to receive initial point clouds from a plurality of capture nodes via the communications interface, and combine the initial point clouds to generate the point cloud.

3. The server of claim 1 , wherein the processor is configured, in order to select the first portion, to:

generate a cutting plane corresponding to a forward surface of the mast; and

discard points on a predetermined side of the cutting plane.

4. The server of claim 3 , wherein the processor is configured, in order to select the second portion, to:

detect a lower surface of the base;

generate an upper surface of the base according to the calibration data; and

discard points between the lower surface and the upper surface.

5. The server of claim 4 , wherein the processor is configured, in order to detect the lower surface, to generate a bounding box containing the object and the base, based on the first portion.

6. The server of claim 5 , wherein the processor is further configured to:

identify a center of the bounding box;

generate side surfaces corresponding to sides of the base according to the center and the calibration data; and

discard points between the lower surface, the upper surface, and the side surfaces.

7. The server of claim 5 , wherein the processor is configured to generate the lower surface with a predefined angle relative to the cutting plane.

8. The server of claim 1 , wherein the processor is further configured, in order to dimension the object, to:

generate a bounding box corresponding to the object from the second portion of the point cloud;

determine point densities for each of a plurality of slices adjacent to a surface of the bounding box; and

select an updated bounding box surface corresponding to the one of the slices with the greatest point density.

9. The server of claim 8 , wherein the processor is further configured to repeat the determination of point densities and selection of an updated bounding box surface for each remaining surface of the bounding box.

10. The server of claim 1 , wherein the processor is further configured to:

detect a reference surface of the transporter based on the set of positions and the calibration data; and

estimate a level of noise in the point cloud from the reference surface.

11. A method, comprising:

storing calibration data;

obtaining a point cloud depicting a capture volume containing a transporter having a body and a holder carrying an object to be dimensioned;

obtaining a set of positions associated with the transporter, the set of positions being further associated with markers positioned on the transporter;

based on the set of positions and the calibration data, selecting a first portion of the point cloud excluding the body of the transporter and a mast of the holder;

based on the calibration data, selecting a second portion of the point cloud from the first portion, excluding a base of the holder; and

dimensioning the object based on the second portion of the point cloud,

wherein the calibration data includes positions of structural features of the transporter relative to the markers positioned on the transporter.

12. The method of claim 11 , wherein obtaining the point cloud includes receiving initial point clouds from a plurality of capture nodes via a communications interface, and combining the initial point clouds to generate the point cloud.

13. The method of claim 11 , wherein selecting the first portion includes:

generating a cutting plane corresponding to a forward surface of the mast; and

discarding points on a predetermined side of the cutting plane.

14. The method of claim 13 , wherein selecting the second portion includes:

detecting a lower surface of the base;

generating an upper surface of the base according to the calibration data; and

discarding points between the lower surface and the upper surface.

15. The method of claim 14 , wherein detecting the lower surface includes generating a bounding box containing the object and the base, based on the first portion.

16. The method of claim 15 , further comprising:

identifying a center of the bounding box;

generating side surfaces corresponding to sides of the base according to the center and the calibration data; and

discarding points between the lower surface, the upper surface, and the side surfaces.

17. The method of claim 15 , further comprising generating the lower surface with a predefined angle relative to the cutting plane.

18. The method of claim 11 , wherein dimensioning the object includes:

generating a bounding box corresponding to the object from the second portion of the point cloud;

determining point densities for each of a plurality of slices adjacent to a surface of the bounding box; and

selecting an updated bounding box surface corresponding to the one of the slices with the greatest point density.

19. The method of claim 18 , further comprising: repeating the determination of point densities and selection of an updated bounding box surface for each remaining surface of the bounding box.

20. The method of claim 11 , further comprising:

detecting a reference surface of the transporter based on the set of positions and the calibration data; and

estimating a level of noise in the point cloud from the reference surface.