Depth-based data capture system configuration

1. A data capture system for object dimensioning, comprising:

a projector to project a structured light pattern onto a capture volume to illuminate an object in the capture volume;

a depth sensor;

a set of image sensors; and

a computing device configured to:

responsive to detection of the object, control the depth sensor to obtain a depth scan of the object;

based on the depth scan, determine an attribute of the object;

select projection parameters based on the attribute by selecting one of a predefined set of classes according to the attribute, and selecting the projection parameters corresponding to the selected class;

control the projector to illuminate the object according to the projection parameters; and

control the set of image sensors to capture respective images of the object.

2. The data capture system of claim 1 , wherein the computing device is further configured to: generate a point cloud representing the object based on the images, for transmission to a dimensioning server.

3. The data capture system of claim 1 , wherein the depth sensor includes at least one of a lidar device and a time-of-flight camera.

4. The data capture system of claim 1 , wherein the depth scan includes depth measurements and color data.

5. The data capture system of claim 1 , wherein the attribute of the object includes at least one of a dimension, a shape, a color and a position.

6. The data capture system of claim 1 , wherein the predefined set of classes include dimension ranges.

7. The data capture system of claim 1 , wherein the projection parameters include at least one of illumination intensity, focal length, orientation, and structured light pattern type.

8. The data capture system of claim 1 , wherein the computing device is further configured to: select image capture parameters for the set of image sensors, according to the attribute of the object.

9. The data capture system of claim 8 , wherein the image capture parameters include at least one of focal length, shutter speed, and aperture size.

10. A method of data capture for object dimensioning, the method comprising:

responsive to detection of an object in a capture volume, controlling a depth sensor to obtain a depth scan of the object;

based on the depth scan, determining an attribute of the object;

selecting projection parameters based on the attribute by selecting one of a predefined set of classes according to the attribute, and selecting the projection parameters corresponding to the selected class;

controlling a projector to illuminate the object according to the projection parameters; and

controlling a set of image sensors to capture respective images of the object.

11. The method of claim 10 , further comprising: generating a point cloud representing the object based on the images, for transmission to a dimensioning server.

12. The method of claim 10 , wherein the depth sensor includes at least one of a lidar device and a time-of-flight camera.

13. The method of claim 10 , wherein the depth scan includes depth measurements and color data.

14. The method of claim 10 , wherein the attribute of the object includes at least one of a dimension, a shape, a color and a position.

15. The method of claim 10 , wherein the predefined set of classes include dimension ranges.

16. The method of claim 10 , wherein the projection parameters include at least one of illumination intensity, focal length, orientation, and structured light pattern type.

17. The method of claim 10 , further comprising: selecting image capture parameters for the set of image sensors, according to the attribute of the object.

18. The method of claim 17 , wherein the image capture parameters include at least one of focal length, shutter speed, and aperture size.