# US 11,298,049 B2 · Method and device for detecting dangerous situation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,298,049 B2
- Document ID: US11298049B2
- Status: Granted
- Kind: B2
- Application number: 16/139,807
- Filed: 2018-09-24
- Published: 2019-03-28
- Granted: 2022-04-12
- Earliest claimed: 2017-09-27
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Joon-Ho Kim; Joo-Young Kim; Hyun-Jae Baek; Do-Jun Yang
- Web page: https://patentgrep.com/patent/US11298049B2

## CPC

- A61B 5/1117: {Fall detection}
- A61B 5/0022: {Monitoring a patient using a global network, e.g. telephone networks, internet}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method includes obtaining, by a device and from a dynamic vision sensor (DVS), a set of images of an object that identifies that the object has moved. The method includes determining, by the device, that the object is associated with a predetermined posture based on the set of images. The method includes determining, by the device, a group to which the object belongs based on an attribute of the object and an attribute of the group. The method includes determining, by the device, whether the object is associated with the dangerous situation based on identifying that the object is associated with the predetermined posture and based on setting information associated with the group to which the object belongs.

## Claims

### Claim 1

A method of detecting a dangerous situation, the method comprising:
obtaining, by a device and from a dynamic vision sensor (DVS), a set of images of an object;
determining, by the device, a group to which the object belongs based on an attribute of the object and an attribute of the group;
analyzing, by the device, the set of images of the object to obtain information associated with a change in motion of the object for a time frame;
determining, by the device, that the object has fallen based on the information associated with the change in motion of the object for the time frame;
determining, by the device, that the object is associated with the dangerous situation based on determining that the object has fallen; and
determining, by the device, a danger level associated with the dangerous situation based on the change in motion of the object being less than a threshold value for the time frame, and based on setting information associated with the group to which the object belongs,
wherein the setting information is determined based on profile information associated with users of the group.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
generating information associated with the group based on the profile information for the users having similar attributes to the object; and
determining the setting information associated with the group based on the generating the information associated with the group.

### Claim 3 (depends on 2)

The method of claim 2, wherein the profile information indicates a gender, an age, a lesion, a normal activity, a walking speed, an activity pattern, a stride, and whether an auxiliary device is installed.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
determining the group to which the object belongs using a learning network model driven by an artificial intelligence (AI) engine.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
updating the setting information associated with the group to which the object belongs by analyzing at least one image, from among the set of images, of the object obtained from the DVS.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
obtaining user profile information comprising the attribute of the object from an external device;
determining that a similarity between the attribute of the object and the attribute of the group satisfies a threshold; and
determining the group to which the object belongs based on the similarity between the attribute of the object and the attribute of the group satisfying the threshold.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
obtaining an image comprising the information associated with a surrounding environment of the DVS; and
determining the danger level associated with the dangerous situation based on the image comprising the information associated with the surrounding environment of the DVS.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
comparing a posture of the object and a predetermined posture,
wherein the determining that the object has fallen comprises determining that the object has fallen based on comparing the posture of the object and the predetermined posture.

### Claim 9 (depends on 1)

The method of claim 1, wherein the obtaining the set of images comprises:
adjusting a resolution of the set of images based on a privacy level of a space where the DVS is installed.

### Claim 10

A dangerous situation detection device comprising:
a dynamic vision sensor (DVS) configured to obtain a set of images of an object;
a memory configured to store one or more instructions; and
a processor configured to execute the one or more instructions to:
determine a group to which the object belongs based on an attribute of the group and an attribute of the object;
analyze the set of images of the object to obtain information associated with a change in motion of the object for a time frame;
determine, based on the set of images, that the object has fallen based on the information associated with the change in motion of the object for the time frame;
determine that the object is associated with a dangerous situation based on determining that the object has fallen; and
determine a danger level associated with the dangerous situation based on the change in motion of the object being less than a threshold value for the time frame, and based on setting information associated with the group to which the object belongs,
wherein the setting information is determined based on profile information associated with users of the group.

### Claim 11 (depends on 10)

The dangerous situation detection device of claim 10, wherein the processor is further configured to:
identify the profile information associated with the users of the group; and
determine the setting information based on the profile information.

### Claim 12 (depends on 11)

The dangerous situation detection device of claim 11, wherein the profile information indicates a gender, an age, a lesion, a normal activity, a walking speed, an activity pattern, a stride, and whether an auxiliary device is installed.

### Claim 13 (depends on 10)

The dangerous situation detection device of claim 10, wherein the processor is further configured to determine the group to which the object belongs by using a learning network model driven by an artificial intelligence (AI) engine.

### Claim 14 (depends on 10)

The dangerous situation detection device of claim 10, wherein the processor is further configured to:
update the setting information associated with the group to which the object belongs based on the set of images obtained from the DVS.

### Claim 15 (depends on 10)

The dangerous situation detection device of claim 10, wherein the processor is further configured to:
determine that a similarity between the attribute of the group and the attribute of the object satisfies a threshold; and
determine the group to which the object belongs based on the similarity between the attribute of the object and the attribute of the group satisfying the threshold.

### Claim 16

A computer program product comprising a computer readable storage medium comprising instructions that, when executed by one or more processors, cause the one or more processors to:
obtain, from a dynamic vision sensor (DVS), a set of images of an object;
determine a group to which the object belongs based on an attribute of the object and an attribute of the group;
analyze the set of images of the object to obtain information associated with a change in motion of the object for a time frame;
determine that the object has fallen based on the information associated with the change in motion of the object for the time frame;
determine that the object is in a dangerous situation based on determining that the object has fallen; and
determine a danger level associated with the dangerous situation based on the change in motion of the object being less than a threshold value for the time frame, and based on setting information associated with the group to which the object belongs,
wherein the setting information is determined based on profile information associated with users of the group.