Distinguishing, in a point cloud data set represented by an image, a first object from a second object
AssigneeToyota Research Institute, Inc.
InventorJacopo Serafin
Life of this patent
Estimating the term…
Abstract
In a point cloud data set represented by an image, a first object can be caused to be distinguished from a second object. Current positions of points in the point cloud data set can be arguments for functions of a set of functions. The set of functions can include attraction functions for the points and repulsion functions for the points. Results of the set of functions can be calculated. Based on the results, at least some of the points can be caused to move from the current positions to new positions. In the point cloud data set represented by the image with the at least some of the points being at the new positions, the first object can be distinguished from the second object.
Claims20
A system for distinguishing, in a point cloud data set represented by an image, a first object from a second object, the system comprising:
- one or more processors;
- a data store communicably coupled to the one or more processors and storing the point cloud data set;
- and
- a memory communicably coupled to the one or more processors and storing:
- a functions module including instructions that when executed by the one or more processors cause the one or more processors to calculate results of a set of functions, wherein current positions of points in the point cloud data set are arguments for the functions and the set of functions includes attraction functions for the points and repulsion functions for the points;
- a reposition module including instructions that when executed by the one or more processors cause the one or more processors to cause, based on the results, at least some of the points to move from the current positions to new positions;
- an assessment module including instructions that when executed by the one or more processors cause the one or more processors to determine, based on the at least some of the points being at the new positions, an existence of a condition;
- a continuation module including instructions that when executed by the one or more processors cause the one or more processors to repeat, in response to a lack of the existence of the condition and with the current positions for the at least some of the points being replaced by the new positions, the instructions of the functions module, the instructions of the reposition module, and the instructions of the assessment module;
- and
- a distinguisher module including instructions that when executed by the one or more processors cause the one or more processors to distinguish, in response to the existence of the condition and in the point cloud data set represented by the image with the at least some of the points being at the new positions, the first object from the second object.
A method for distinguishing, in a point cloud data set represented by an image, a first object from a second object, the method comprising:
- calculating, by a processor, results of a set of functions, wherein current positions of points in the point cloud data set are arguments for the functions and the set of functions includes attraction functions for the points and repulsion functions for the points;
- causing, by the processor and based on the results, at least some of the points to move from the current positions to new positions;
- determining, by the processor and based on the at least some of the points being at the new positions, an existence of a condition;
- repeating, by the processor, in response to a lack of the existence of the condition, and with the current positions for the at least some of the points being replaced by the new positions, the calculating, the causing, and the determining;
- and
- distinguishing, by the processor, in response to the existence of the condition, and in the point cloud data set represented by the image with the at least some of the points being at the new positions, the first object from the second object.
A non-transitory computer-readable medium for distinguishing, in a point cloud data set represented by an image, a first object from a second object, the non-transitory computer-readable medium including instructions that when executed by one or more processors cause the one or more processors to:
- calculate results of a set of functions, wherein current positions of points in the point cloud data set are arguments for the functions and the set of functions includes attraction functions for the points and repulsion functions for the points;
- cause, based on the results, at least some of the points to move from the current positions to new positions;
- determine, based on the at least some of the points being at the new positions, an existence of a condition;
- repeat, in response to a lack of the existence of the condition and with the current positions for the at least some of the points being replaced by the new positions, the instructions that cause the one or more processors to calculate the results, the instructions that cause the one or more processors to cause the at least some of the points to move, and the instructions that cause the one or more processors to determine the existence of the condition;
- and
- distinguish, in response to the existence of the condition and in the point cloud data set represented by the image with the at least some of the points being at the new positions, the first object from the second object.
Dependencies are inferred from the claim text.