IP Library Granted Patent US 10,565,721
Granted Patent B2
US 10,565,721 · App. 15/442,896 · Granted Feb 18, 2020

Information processing device and information processing method for specifying target point of an object

Inventor: Takayuki Sugiura (Yokohama, JP)
Assignee: Kabushiki Kaisha Toshiba
G06T7/70G01S7/4808G06K9/6218G06T7/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,565,721
App. No.
15/442,896
Granted
Feb 18, 2020
Kind
B2
Abstract

According to an embodiment, an information processing device includes an acquirer, a categorizer, a shape fitter, and a specifier. The acquirer is configured to acquire position information of each of a plurality of detection points. The categorizer is configured to cluster the detection points into one or more detection point groups each representing an object. The shape fitter is configured to apply a predetermined shape model to each detection point group on the basis of the position information of each of the clustered detection points included in the each detection point group. The specifier is configured to specify a target point of the object on the basis of the shape model.

Claims (36)

1. An information processing device comprising:

a memory; and

processing circuitry configured to operate as:

an acquirer configured to acquire position information of detection points;

a categorizer configured to cluster the detection points into one or more detection point groups each representing an object;

a shape fitter configured to fit a predetermined shape model into each detection point group on the basis of the position information of the clustered detection points belonging to the each detection point group; and

a specifier configured to specify a target point that is a single point representing the object on the basis of the shape model, wherein

the processing circuitry is further configured to operate as a searcher configured to search for detection point groups clustered on the basis of the position information at different timings of at least a first timing and a second timing, a detection point group at the first timing and a detection point group at the second timing representing an identical object, and

the specifier specifies, as the target point of the object at the first timing, a position in the shape model fitted into the detection point group at the first timing, the position corresponding to the target point set on the basis of the shape model fitted into the detection point group at the second timing.

2. The device according to claim 1 , wherein the acquirer acquires the position information of the detection points from observation information on surrounding of a sensor.

3. The device according to claim 1 , wherein the specifier specifies, as the target point, one of candidate points set to the shape model in advance.

4. The device according to claim 2 , wherein the specifier specifies, as the target point, a candidate point closest to the sensor among the candidate points set to the shape model in advance.

5. The device according to claim 1 , wherein the specifier specifies, as the target point, a candidate point having a highest distribution rate of the detection points among candidate points set to the shape model in advance.

6. The device according to claim 1 , wherein the specifier specifies, as the target point, a candidate point closest to any one of the detection points among candidate points set to the shape model in advance.

7. The device according to claim 1 , wherein

the shape fitter fits, into the detection point group, shape models that are different from each other in at least one of a shape and a position, and

the specifier specifies the target point of the object on the basis of the shape models.

8. The device according to claim 2 , wherein the sensor includes at least one of a distance sensor and an image capturing device.

9. The device according to claim 1 mounted on a moving object or a stationary object.

10. The device according to claim 1 , wherein the processing circuitry is further configured to operate as an output unit configured to output output information including information indicating the specified target point.

11. An information processing method comprising:

acquiring position information of detection points;

clustering the detection points into one or more detection point groups each representing an object;

fitting a predetermined shape model into each detection point group on the basis of the position information of the clustered detection points belonging to the each detection point group; and

specifying a target point that is a single point representing the object on the basis of the shape model, wherein

detection point groups clustered on the basis of the position information at different timings of at least a first timing and a second timing are searched, and a detection point group at the first timing and a detection point group at the second timing represent an identical object, and

as the target point of the object at the first timing, a position in the shape model fitted into the detection point group at the first timing is specified, the position corresponding to the target point set on the basis of the shape model fitted into the detection point group at the second timing.

12. The method according to claim 11 , wherein the position information of the detection points is acquired from observation information on surrounding of a sensor.

13. The method according to claim 11 , wherein one of candidate points set to the shape model in advance is specified as the target point.

14. The method according to claim 12 , wherein a candidate point closest to the sensor is specified as the target point among candidate points set to the shape model in advance.

15. The method according to claim 11 , wherein a candidate point having a highest distribution rate of the detection points is specified as the target point among candidate points set to the shape model in advance.

16. The method according to claim 11 , wherein a candidate point closest to any one of the detection points is specified as the target point among candidate points set to the shape model in advance.

17. The method according to claim 11 , wherein

shape models that are different from each other in at least one of a shape and a position are fit into the detection point group, and

the target point of the object is specified on the basis of the shape models.

18. The method according to claim 12 , wherein the sensor includes at least one of a distance sensor and an image capturing device.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 14, 2017
From: SUGIURA, TAKAYUKI
To: KABUSHIKI KAISHA TOSHIBA
Reel/Frame 042010/0091 →
Priority Claims (1)
JP 2016-107455 · May 30, 2016 · national
Continuity (1)
Related Publication 20170345180A1 · Nov 30, 2017