Segmentation of 3d point clouds for dense 3d modeling
AssigneeQUALCOMM Incorporated
InventorsSundeep Vaddadi, Andrew Moore Ziegler, Onur C. Hamsici
Life of this patent
Estimating the term…
Abstract
Techniques for segmentation of three-dimensional (3D) point clouds are described herein. An example of a method for user-assisted segmentation of a 3D point cloud described herein includes obtaining a 3D point cloud of a scene containing a target object; receiving a seed input indicative of a location of the target object within the scene; and generating a segmented point cloud corresponding to the target object by pruning the 3D point cloud based on the seed input.
Claims43
A method for user-assisted segmentation of a three-dimensional (3D) point cloud, the method comprising:
- obtaining a 3D point cloud of a scene containing a target object;
- receiving a seed input indicative of a location of the target object within the scene;
- and
- generating a segmented point cloud corresponding to the target object by pruning the 3D point cloud based on the seed input.
An apparatus that facilitates user-assisted segmentation of a three-dimensional (3D) point cloud, the apparatus comprising:
- a point cloud segmenter configured to obtain a 3D point cloud of a scene containing a target object;
- and
- an input device coupled to the point cloud segmenter and configured to receive a seed input indicative of a location of the target object within the scene;
- wherein the point cloud segmenter is further configured to generate a segmented point cloud corresponding to the target object by pruning the 3D point cloud based on the seed input.
An apparatus that facilitates user-assisted segmentation of a three-dimensional (3D) point cloud, the apparatus comprising:
- means for obtaining a 3D point cloud of a scene containing a target object;
- means for receiving a seed input indicative of a location of the target object within the scene;
- and
- means for generating a segmented point cloud corresponding to the target object by pruning the 3D point cloud based on the seed input.
A computer program product residing on a processor-executable computer storage medium, the computer program product comprising processor-executable instructions configured to cause a processor to:
- obtain a three-dimensional (3D) point cloud of a scene containing a target object;
- receive a seed input indicative of a location of the target object within the scene;
- and
- generate a segmented point cloud corresponding to the target object by pruning the 3D point cloud based on the seed input.
Dependencies are inferred from the claim text.