System and method for object detection and dimensioning

1. A method comprising:

obtaining, from a depth sensor, depth data representing a target object;

defining a mask having a structure which decreases in density away from a central point of the mask;

overlaying the mask on the depth data and selecting a subset of the depth data comprising data points having coordinates which match coordinates of a point of the mask;

detecting a cluster of data points from the subset;

detecting, based on the cluster, the target object; and

determining an object dimension of the target object based on the cluster.

2. The method of claim 1 , wherein the mask comprises an arrangement of lines which decrease in density away from the central point.

3. The method of claim 2 , wherein the lines extend radially from the central point of the mask.

4. The method of claim 1 , wherein overlaying the mask on the depth data comprises aligning the central point with a center of a frame of the depth data.

5. The method of claim 1 , wherein detecting the cluster of data points from the subset comprises:

selecting a starting point from the subset of the depth data, the starting point comprising a closest data point of the subset to the central point of the mask; and

selecting the cluster of data points about the starting point.

6. The method of claim 1 , wherein detecting the target object comprises applying plane and object detection to the detected cluster of data points.

7. The method of claim 1 , wherein detecting the target object comprises:

generating a bounding region for the cluster of data points;

selecting a second subset of the depth data comprising data points contained in the bounding region; and

applying plane and object detection to the second subset of depth data to identify the target object.

8. A device comprising:

a depth sensor configured to obtain depth data representing a target object;

a memory;

a processor interconnected with the depth sensor and the memory, the processor configured to:

obtain, from the depth sensor, depth data representing the target object;

define a mask having a structure which decreases in density away from a central point of the mask;

overlay the mask on the depth data and select a subset of the depth data comprising data points having coordinates which match coordinates of a point of the mask;

detect a cluster of data points from the subset;

detect, based on the cluster, the target object; and

determine an object dimension of the target object based on the cluster.

9. The device of claim 8 , wherein the mask comprises an arrangement of lines which decrease in density away from the central point.

10. The device of claim 9 , wherein the lines extend radially from the central point of the mask.

11. The device of claim 8 , wherein, to overlay the mask on the depth data, the processor is configured to align the central point of the mask with a center of a frame of the depth data.

12. The device of claim 8 , wherein, to detect the cluster of data points from the subset, processor is configured to:

select a starting point from the subset of the depth data, the starting point comprising a closest data point of the subset to the central point of the mask; and

select the cluster of data points about the starting point.

13. The device of claim 8 , wherein to detect the target object, the processor is configured to: apply plane and object detection to the detected cluster of data points.

14. The device of claim 8 , wherein to detect the target object, the processor is configured to:

generate a bounding region for the cluster of data points;

select a second subset of the depth data comprising data points contained in the bounding region; and

apply plane and object detection to the second subset of depth data to identify the target object.

15. A non-transitory computer-readable medium storing a plurality of computer-readable instructions executable by a processor, wherein execution of the instructions configures the processor to:

obtain, from a depth sensor, depth data representing a target object;

define a mask having a structure which decreases in density away from a central point of the mask;

overlay the mask on the depth data and select a subset of the depth data comprising data points having coordinates which match coordinates of a point of the mask;

detect a cluster of data points from the subset;

detect, based on the cluster, the target object; and

determine an object dimension of the target object based on the cluster.

16. The non-transitory computer-readable medium of claim 15 , wherein the mask comprises an arrangement of lines which decrease in density away from the central point.

17. The non-transitory computer-readable medium of claim 16 , wherein the lines extend radially from the central point of the mask.

18. The non-transitory computer-readable medium of claim 15 , wherein, to overlay the mask on the depth data, the instructions configure the processor to: align the central point of the mask with a center of a frame of the depth data.

19. The non-transitory computer-readable medium of claim 15 , wherein, to detect the cluster of data points from the subset, instructions configure the processor to:

select a starting point from the subset of the depth data, the starting point comprising a closest data point of the subset to the central point of the mask; and

select the cluster of data points about the starting point.

20. The non-transitory computer-readable medium of claim 15 , wherein to detect the target object, the instructions configure the processor to: apply plane and object detection to the detected cluster of data points.

21. The non-transitory computer-readable medium of claim 15 , wherein to detect the target object, the instructions configure the processor to:

generate a bounding region for the cluster of data points;

select a second subset of the depth data comprising data points contained in the bounding region; and

apply plane and object detection to the second subset of depth data to identify the target object.

22. The non-transitory computer-readable medium of claim 15 , wherein the instructions further configure the processor to: dimension the target object and output dimensions of the target object.