# US 2022/0092868 A1 · Method and apparatus for detecting open flame, and storage medium

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

- Number: US 2022/0092868 A1
- Document ID: US20220092868A1
- Status: Published application
- Kind: A1
- Application number: 17/425,255
- Filed: 2019-12-26
- Published: 2022-03-24
- Earliest claimed: 2019-01-22
- Assignees: Hangzhou Hikmicro Sensing Technology Co., Ltd.
- Applicants: Hangzhou Hikmicro Sensing Technology Co., Ltd.
- Inventors: Feng LI; Wei YANG; Hengyu JIANG; Jiajie LI
- Web page: https://patentgrep.com/patent/US20220092868A1

## CPC

- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/255: {Detecting or recognising potential candidate objects based on visual cues, e.g. shapes}
- G06V 10/62: relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/768: {using context analysis, e.g. recognition aided by known co-occurring patterns}
- G06V 20/44: {Event detection}
- G06V 20/50: Context or environment of the image
- G08B 17/005: {for forest fires, e.g. detecting fires spread over a large or outdoors area (fire fighting forest fires A62C3/02)}
- G08B 17/125: {by using a video camera to detect fire or smoke}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS

## Abstract

A method for detecting an open flame includes: acquiring a plurality of frames of first images of a suspected target in a monitoring region; acquiring gray scale change features of the plurality of frames of first images and attribute features of the suspected target based on the plurality of frames of first images, the gray scale change features being configured to indicate temperature changes of the suspected target; and determining the suspected target in the monitoring region as an open flame, if the gray scale change features of the plurality of frames of first images and the attribute features of the suspected target both satisfy an open flame condition.

## Claims

### Claim 1

A method for detecting an open flame, which is applied to an electronic device and comprises:
acquiring a plurality of frames of first images of a suspected target in a monitoring region;
acquiring gray scale change features of the plurality of frames of first images and attribute features of the suspected target based on the plurality of frames of first images, the gray scale change features being configured to indicate temperature changes of the suspected target; and
determining the suspected target in the monitoring region as an open flame, in response to the gray scale change features of the plurality of frames of first images and the attribute features of the suspected target both satisfying an open flame condition.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the open flame condition comprises a gray scale change curve of an open flame image and a physical attribute range of the open flame; and
wherein said determining the suspected target in the monitoring region as the open flame, in response to the gray scale change features of the plurality of frames of first images and the attribute features of the suspected target both satisfying the open flame condition comprises:
determining the suspected target in the monitoring region as the open flame, in response to the gray scale change features of the plurality of frames of first images according with the gray scale change curve of the open flame image and the attribute features of the suspected target being within the physical attribute range.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the gray scale change curve of the open flame image comprises at least one of a time-domain change curve or a frequency-domain change curve;
wherein the gray scale change features of the plurality of frames of first images comprise at least one of change features of gray scales of the plurality of frames of first images in a time domain or change features of gray scales of the plurality of frames of first images in a frequency domain; and
wherein said determining the suspected target in the monitoring region as the open flame comprises:
determining the suspected target in the monitoring region as the open flame, in response to the change features of the gray scales of the plurality of frames of first images in the time domain satisfying the time-domain change curve and the attribute features of the suspected target being within the physical attribute range, in a case that the gray scale change features of the plurality of frames of first images comprise the change features of the gray scales of the plurality of frames of first images in the time domain;
determining the suspected target in the monitoring region as the open flame, in response to the change features of the gray scales of the plurality of frames of first images in the frequency domain satisfying the frequency-domain change curve and the attribute feature of the suspected target being within the physical attribute range, in a case that the gray scale change features of the plurality of frames of first images comprise the change features of the gray scales of the plurality of frames of first images in the frequency domain; or
determining the suspected target in the monitoring region as the open flame, in response to the change features of the gray scales of the plurality of frames of first images in the frequency domain satisfying the frequency-domain change curve and the change features of the gray scales of the plurality of frames of first images in the time domain satisfying the time-domain change curve, and the attribute features of the suspected target being within the physical attribute range, in a case that the gray scale change features of the plurality of frames of first images comprise the change features of the gray scales of the plurality of frames of first images in the frequency domain and the change features of the gray scales of the plurality of frames of first images in the time domain.

### Claim 4 (depends on 2)

The method according to claim 2, wherein the attribute features of the suspected target comprise at least one of: an area of the suspected target of the suspected target, a shape of the suspected target, a time that the suspected target stays at a same position, or whether the suspected target is dynamic; and
wherein the physical property range comprises an area range of the open flame, a shape of the open flame, a duration that the open flame stays at a same position, and the open flame is dynamic.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the attribute features of the suspected target comprise a time that the suspected target stays at a same position, and said acquiring the attribute features of the suspected target based on the plurality of frames of first images comprises:
determining a position of the suspected target in each frame of first image;
acquiring at least two frames of first images in which the suspected target has a same position, and an interval time between two adjacent frames of first images among the at least two frames of first images; and
acquiring a time that the suspected target stays at the same position by accumulating the interval time.

### Claim 6 (depends on 1)

The method according to claim 1, wherein said acquiring the plurality of frames of first images of the suspected target in the monitoring region comprises:
acquiring a plurality of frames of second images in the monitoring region, wherein a region displayed by the second images comprises a region displayed by the first images;
acquiring images of a suspected region by extracting a region having a gray scale value greater than a gray scale threshold from the second images, wherein the suspected target is located in the suspected region; and
acquiring the plurality of frames of first images by extracting the images of the suspected target from a plurality of frames of images of the suspected region.

### Claim 7 (depends on 6)

The method according to claim 6, wherein, based on a plurality of suspected targets being located in the images of the suspected region, said acquiring the plurality of frames of first images by extracting the images of the suspected target from the plurality of frames of images of the suspected region comprises:
acquiring distances between each suspected target and other suspected targets in each image of the suspected region;
acquiring distance ranges between each open flame and other open flames in the open flame image; and
acquiring the plurality of frames of first images by segmenting a region of the suspected target from each frame of image of the suspected region, in response to the distances between each suspected target and other suspected targets in the image of the suspected region being within the distance ranges.

### Claim 8

An apparatus for detecting an open flame, comprising:
a first acquiring module, configured to acquire a plurality of frames of first images of a suspected target in a monitoring region;
a second acquiring module, configured to acquire gray scale change features of the plurality of frames of first images and attribute features of the suspected target based on the plurality of frames of first images, the gray scale change features being configured to indicate temperature changes of the suspected target; and
a first determining module, configured to determine the suspected target in the monitoring region as an open flame, if the gray scale change features of the plurality of frames of first images and the attribute features of the suspected target both satisfy an open flame condition.

### Claim 9 (depends on 8)

The apparatus according to claim 8, wherein the open flame condition comprises a gray scale change curve of an open flame image and a physical attribute range of the open flame; and
wherein the first determining module is configured to determine the suspected target in the monitoring region as the open flame, if the gray scale change features of the plurality of frames of first images accord with the gray scale change curve of the open flame image and the attribute features of the suspected target are within the physical attribute range.

### Claim 10 (depends on 9)

The apparatus according to claim 9, wherein the gray scale change curve of the open flame image comprises at least one of a time-domain change curve or a frequency-domain change curve;
wherein the gray scale change features of the plurality of frames of first image comprise at least one of change features of gray scales of the plurality of frames of first images in a time domain or change features of gray scales of the plurality of frames of first images in a frequency domain; and
wherein the first determining module is configured to:
determine the suspected target in the monitoring region as the open flame, in response to determining that the change features of the gray scales of the plurality of frames of first images in the time domain satisfy the time-domain change curve and the attribute features of the suspected target are within the physical attribute range, in a case that the gray scale change features of the plurality of frames of first images comprise the change features of the gray scales of the plurality of frames of first images in the time domain;
determine the suspected target in the monitoring region as the open flame, in response to determining that the change features of the gray scales of the plurality of frames of first images in the frequency domain satisfy the frequency-domain change curve and the attribute feature of the suspected target are within the physical attribute range, in a case that the gray scale change features of the plurality of frames of first images comprise the change features of the gray scales of the plurality of frames of first images in the frequency domain; or
determine the suspected target in the monitoring region as the open flame, in response to determining that the change features of the gray scales of the plurality of frames of first images in the frequency domain satisfy the frequency-domain change curve and the change features of the gray scales of the plurality of frames of first images in the time domain satisfy the time-domain change curve, and the attribute features of the suspected target are within the physical attribute range, in a case that the gray scale change features of the plurality of frames of first images comprise the change features of the gray scales of the plurality of frames of first images in the frequency domain and the change features of the gray scales of the plurality of frames of first images in the time domain.

### Claim 11 (depends on 9)

The apparatus according to claim 9, wherein the attribute features of the suspected target comprise at least one of: an area of the suspected target, a shape of the suspected target, a time that the suspected target stays at a same position, or whether the suspected target is dynamic; and
wherein the physical property range comprises an area range of the open flame, a shape of the open flame, a duration that the open flame stays at a same position, and the open flame is dynamic.

### Claim 12 (depends on 8)

The apparatus according to claim 8, wherein the attribute features of the suspected target comprise a time that the suspected target stays at a same position; and
wherein the second acquiring module comprises:
a first determining unit, configured to determine a position of the suspected target in each frame of first image;
a first acquiring unit, configured to acquire at least two frames of first images in which the suspected target has a same position, and an interval time between two adjacent frames of first images among the at least two frames of first images; and
a second acquiring unit, configured to acquire a time that the suspected target stays at the same position by accumulating the interval time.

### Claim 13 (depends on 8)

The apparatus according to claim 8, wherein the first acquiring module comprises:
a third acquiring unit, configured to acquire a plurality of frames of second images in the monitoring region, wherein a region displayed by the second images includes a region displayed by the first images;
a first extracting unit, configured to acquire images of a suspected region by extracting a region having a gray scale value greater than a gray scale threshold from the second images, wherein the suspected target is located in the suspected region; and
a fourth acquiring unit, configured to acquire the plurality of frames of first images by extracting the images of the suspected target from a plurality of frames of images of the suspected region.

### Claim 14 (depends on 13)

The apparatus according to claim 13, wherein the plurality of suspected targets are located in the images of the suspected region; and
wherein the fourth acquiring unit comprises:
a first acquiring sub-unit, configured to acquire distances between each suspected target and other suspected targets in each image of the suspected region;
a second acquiring sub-unit, configured to acquire distance ranges between each open flame and other open flames in the open flame image; and
a first segmenting sub-unit, configured to acquire the plurality of frames of first images by segmenting a region of the suspected target from each frame of image of the suspected region, if the distances between each suspected target and other suspected targets in the image of the suspected region are within the distance ranges.

### Claim 15 (depends on 1)

An apparatus for detecting an open flame, comprising a processor and a memory, wherein the memory stores at least one instruction therein, the instruction being loaded and performed by the processor to implement the method for detecting the open flame according to claim 1.

### Claim 16 (depends on 1)

A non-transitory computer-readable storage medium storing at least one instruction therein, wherein the instruction is loaded and performed by a processor to implement the method for detecting the open flame according to claim 1.

### Claim 17 (depends on 3)

The method according to claim 3, wherein the attribute features of the suspected target comprise at least one of: an area of the suspected target of the suspected target, a shape of the suspected target, a time that the suspected target stays at a same position, or whether the suspected target is dynamic; and
wherein the physical property range comprises an area range of the open flame, a shape of the open flame, a duration that the open flame stays at a same position and the open flame is dynamic.

### Claim 18 (depends on 10)

The apparatus according to claim 10, wherein the attribute features of the suspected target comprise at least one of: an area of the suspected target, a shape of the suspected target, a time that the suspected target stays at a same position, or whether the suspected target is dynamic; and
wherein the physical property range comprises an area range of the open flame, a shape of the open flame, a duration that the open flame stays at a same position, and the open flame is dynamic.
