Method and apparatus for early warning of danger

Patent metadata

Field	Value
Publication number	US-10121075-B2
Application number	US-201515525218-A
Country	US
Kind code	B2
Filing date	Oct 20, 2015
Priority date	Nov 6, 2014
Publication date	Nov 6, 2018
Grant date	Nov 6, 2018

Abstract

Provided are a method and an apparatus for early warning of danger, the method including acquiring image information of a target object through a first wearable device worn by a user, detecting a physical characteristic of the target object based on the acquired image information, determining a degree of danger that is a degree to which safety of the user is endangered, by using the detected physical characteristic, and providing a warning to the user based on the determined degree of danger of an event.

First claim

The invention claimed is:

1. A method for early warning of danger, performed by a wearable device, the method comprising:
acquiring, by an image sensor of the wearable device, image information of a target object;
acquiring, by an audio sensor of the wearable device, audio information of a surrounding environment;
detecting a physical characteristic of the target object based on the acquired image information;
detecting an audio characteristic of the target object by separating the audio characteristic from a background sound based on the acquired audio information;
determining a degree of danger that is a degree to which safety of a user is endangered, by using the detected physical characteristic and the audio characteristic; and
providing a warning to the user based on the determined degree of danger.

2. The method of claim 1 , wherein the determining of the degree of danger comprises:
determining a time taken by the target object to reach the wearable device based on the image information; and
determining the degree of danger with respect to the target object according to at least one of the physical characteristic of the target object, the time taken by the target object to reach the wearable device, and the audio characteristic of the target object.

3. The method of claim 1 , wherein the physical characteristic of the target object comprises a face of a person, a trunk of the person, limbs of the person, teeth of an animal, a tail of the animal, or eyes of the animal.

4. The method of claim 1 , wherein the audio characteristic of the target object comprises at least one of a volume, a pitch, a Mel Frequency Cepstrum Coefficient (MFCC), a human speech, and a Power Normalized Cepstral Coefficient (PNCC).

5. The method of claim 1 ,
wherein the acquiring of the image information comprises: acquiring weather information or odor information, and
wherein the determining of the degree of danger comprises: determining the degree of danger based on the weather information or the odor information.

6. The method of claim 1 , wherein the providing of the warning comprises: providing the warning in different ways according to the degree of danger.

7. The method of claim 1 , further comprising: receiving the acquired image information or audio information through a second wearable device,
wherein the determining of the degree of danger comprises: determining the degree of danger based on information received from the second wearable device.

8. The method of claim 1 ,
wherein the detecting of the physical characteristic comprises:
detecting whether the target object is a person by using the image information; and
if the target object is the person, detecting a face of the person, and
wherein the determining of the degree of danger comprises: determining the degree of danger according to whether the detected face is included in a preset face database.

9. A computer-program product comprising a non-transitory computer-readable program including instructions, to be executed by one or more processors, for:
acquiring, by an image sensor, image information of a target object;
acquiring, by an audio sensor, audio information of a surrounding environment;
detecting a physical characteristic of the target object based on the acquired image information;
detecting an audio characteristic of the target object by separating the audio characteristic from a background sound based on the acquired audio information;
determining a degree of danger that is a degree to which safety of a user is endangered, by using the detected physical characteristic and the audio characteristic; and
providing a warning to the user based on the determined degree of danger.

10. A wearable device for early warning of danger, the wearable device comprising:
an image sensor configured to acquire image information of a target object;
an audio sensor configured to acquire audio information of a surrounding environment;
a processor configured to detect a physical characteristic of the target object based on the acquired image information, detect an audio characteristic of the target object by separating the audio characteristic from a background sound based on the acquired audio information, and determine a degree of danger that is a degree to which safety of a user is endangered, by using the detected physical characteristic and the audio characteristic; and
a warning unit configured to warn the user based on the determined degree of danger.

11. The wearable device of claim 10 , wherein the processor determines a time taken by the target object to reach the wearable device based on the image information and determines the degree of danger with respect to the target object according to at least one of the physical characteristic of the target object, the time taken by the target object to reach the wearable device, and the audio characteristic of the target object.

12. The wearable device of claim 10 , wherein the physical characteristic of the target object comprises a face of a person, a trunk of the person, limbs of the person, teeth of an animal, a tail of the animal, or eyes of the animal.

13. The wearable device of claim 10 , wherein the audio characteristic of the target object comprises at least one of a volume, a pitch, a Mel Frequency Cepstrum Coefficient (MFCC), human speech, and a Power Normalized Cepstral Coefficient (PNCC).

14. The wearable device of claim 10 , further comprising:
another sensor configured to acquire weather information or odor information, and
wherein the processor determines the degree of danger based on the weather information or the odor information.

15. The wearable device of claim 10 , wherein the warning unit provides the warning in different ways according to the degree of danger.

16. The wearable device of claim 10 , further comprising: a receiving unit configured to receive the acquired image information or audio information through a second wearable device,
wherein the processor determines the degree of danger based on information received from the second wearable device.

17. The wearable device of claim 10 ,
wherein the processor detects whether the target object is a person by using the image information and, if the target object is the person, detects a face of the person, and determines the degree of danger according to whether the detected face is included in a preset face database.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Du Xiaoyi
• Luo Hengliang
• Deng Haifeng
• Zhang Li

Classifications

• G06K9/00671 Primary

  Physics · mapped topic

• G06F3/012

  Head tracking input arrangements · CPC title

• G06K9/00302

  Physics · mapped topic

• G08B21/02 Primary

  Alarms for ensuring the safety of persons · CPC title

• G06V40/174

  Facial expression recognition · CPC title