USER TERMINAL DEVICE AND METHOD OF RECOGNIZING OBJECT THEREOF

• US 20160171339A1
• Filed: 11/27/2015
• Published: 06/16/2016
• Est. Priority Date: 12/15/2014
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: CHOI, Hyung-tak, LEE, Ho-jung
• Granted Patent: US 10,204,292 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06V 2201/10 Recognition assisted with metadata

Abstract

A user terminal device is provided. The user terminal device includes a plurality of different types of sensors, a storage unit configured to store object information, and a controller configured to acquire sensing results of the plurality of sensors, determine a plurality of object categories respectively corresponding to the sensing results, and compare objects belonging to the plurality of object categories to estimate an object commonly belonging to the object categories as a recognition result.

Claims

1. An object recognizing method of a user terminal device, the object recognizing method comprising:

activating a plurality of different types of sensors;

acquiring sensing results of the plurality of sensors;

determining a plurality of object categories respectively corresponding to the sensing results; and

estimating an object commonly belonging to the plurality of object categories as a recognition result.

2. The object recognizing method of claim 1, further comprising:

giving the plurality of object categories probabilistic numbers to which an object to be recognized belongs,

wherein an object, which has a high probability as the object to be recognized among a plurality of objects commonly belonging to the plurality of object categories, is estimated as the recognition result based on the probabilistic numbers given to the plurality of object categories.

3. The object recognizing method of claim 1, wherein the determining of the plurality of object categories comprises:

in response to position information of the user terminal device being sensed by a position sensor as one of the plurality of sensors, determining an object category comprising objects existing in a location corresponding to the position information.

4. The object recognizing method of claim 3, wherein the determining of the plurality of object categories comprises:

in response to a smell being sensed by a smell sensor as one of the plurality of sensors, determining an object category comprising objects associated with the smell.

5. The object recognizing method of claim 4, wherein the determining of the plurality of object categories comprises:

in response to a sound being sensed by a sound sensor as one of the plurality of sensors, determining an object category comprising objects associated with the sound.

6. The object recognizing method of claim 1, wherein the determining of the plurality of object categories further comprises:

in response to a user image being captured by a camera as one of the plurality of sensors, parsing a user expression in the user image; and

determining one selected from a positive category comprising objects having positive attributes and a negative category comprising objects having negative attributes according to the user expression.

7. The object recognizing method of claim 1, wherein the determining of the plurality of object categories further comprises:

in response to a user voice being sensed by a sound sensor as one of the plurality of sensors, parsing a tone of the user voice; and

determining one selected from a positive category comprising objects having positive attributes and a negative category comprising objects having negative attributes according to a characteristic of the tone.

8. The object recognizing method of claim 1, wherein the determining of the plurality of object categories further comprises:

in response to a bio-signal being sensed by a bio-signal sensor as one of the plurality of sensors, determining one selected from a positive category comprising objects having positive attributes and a negative category comprising objects having negative attributes according to a characteristic of the bio-signal.

9. The object recognizing method of claim 1 wherein the plurality of sensors comprise at least one selected from a sound sensor, a smell sensor, a camera, a position sensor, a motion sensor, a pressure sensor, a fingerprint sensor, a hall sensor, an inertia sensor, an acceleration sensor, a heart rate sensor, an illumination sensor, a Wi-Fi sensor, and a compass sensor.

10. A user terminal device comprising:

a plurality of different types of sensors;

a storage unit configured to store object information; and

a controller configured to;

acquire sensing results of the plurality of sensors,

determine a plurality of object categories respectively corresponding to the sensing results, and

compare objects belonging to the plurality of object categories to estimate an object commonly belonging to the object categories as a recognition result.

11. The user terminal device of claim 10, wherein the controller is further configured to give the plurality of object categories probabilistic numbers to which an object to be recognized belongs and estimates an object, which has a high probability as the object to be recognized among a plurality of objects commonly belonging to the plurality of object categories, as the recognition result based on the probabilistic numbers given to the plurality of object categories.

12. The user terminal device of claim 10,

wherein the plurality of sensors comprise a position sensor,

wherein in response to position information of the user terminal device being sensed by the position sensor, the controller is further configured to determine an object category comprising objects existing in a location corresponding to the position information.

13. The user terminal device of claim 12,

wherein the plurality of sensors further comprise a smell sensor,

wherein in response to a smell being sensed by the smell sensor, the controller is further configured to determine an object category comprising objects associated with the smell.

14. The user terminal device of claim 13,

wherein the plurality of sensors further comprise a sound sensor,

wherein in response to a sound being sensed by the sound sensor, the controller is further configured to determine an object category comprising objects associated with the sound.

15. The user terminal device of claim 10,

wherein the plurality of sensors comprise a camera,

wherein in response to a user image being captured by the camera, the controller is further configured to parse a user expression in the user image and determines one selected from a positive category comprising objects having positive attributes and a negative category comprising objects having negative attributes according to the user expression.

16. The user terminal device of claim 10,

wherein the plurality of sensors further comprise a sound sensor,

wherein in response to a user voice being sensed by the sound sensor, the controller is further configured to parse a tone of the user voice and determines one selected from a positive category comprising objects having positive attributes and a negative category comprising objects having negative attributes according to a characteristic of the tone.

17. The user terminal device of claim 10,

wherein the plurality of sensors further comprise a bio-signal sensor,

wherein in response to a bio-signal of a user being sensed by the bio-signal sensor, the controller is further configured to determine one selected from a positive category comprising objects having positive attributes and a negative category comprising objects having negative attributes according to a characteristic of the bio-signal.

18. The user terminal device of claim 10, wherein the plurality of sensors comprise at least one selected from a sound sensor, a smell sensor, a camera, a position sensor, a motion sensor, a pressure sensor, a fingerprint sensor, a hall sensor, an inertia sensor, an acceleration sensor, a heart rate sensor, an illumination sensor, a Wi-Fi sensor, and a compass sensor.