CN112257523A - Smoke identification method and system of image type fire detector - Google Patents

Smoke identification method and system of image type fire detector Download PDF

Info

Publication number
CN112257523A
CN112257523A CN202011071209.9A CN202011071209A CN112257523A CN 112257523 A CN112257523 A CN 112257523A CN 202011071209 A CN202011071209 A CN 202011071209A CN 112257523 A CN112257523 A CN 112257523A
Authority
CN
China
Prior art keywords
image sequence
smoke
target area
image
suspected target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011071209.9A
Other languages
Chinese (zh)
Inventor
高淑娟
王海峰
闻泉源
于海生
袁驰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yingkou New Shanying Alarm Equipment Co ltd
Original Assignee
Yingkou New Shanying Alarm Equipment Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yingkou New Shanying Alarm Equipment Co ltd filed Critical Yingkou New Shanying Alarm Equipment Co ltd
Priority to CN202011071209.9A priority Critical patent/CN112257523A/en
Publication of CN112257523A publication Critical patent/CN112257523A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes

Abstract

The invention provides a smoke identification method and a smoke identification system of an image type fire detector, which solve the technical problems of higher algorithm complexity and lower positioning precision in the existing smoke identification method and comprise the following steps: acquiring a video image of a monitoring site, and converting the video image into an image sequence; setting a reference point of an RGB color space; carrying out motion foreground region segmentation on an image sequence in an RGB color space to obtain a suspected target region; judging the smoke motion rule of the image sequence in the suspected target area to determine a smoke target area; the method has the advantages of low algorithm complexity, high detection efficiency and high recognition effect, and can be widely applied to the technical field of flame detection.

Description

Smoke identification method and system of image type fire detector
Technical Field
The invention relates to the technical field of smoke detection, in particular to a smoke identification method and a smoke identification system of an image type fire detector.
Background
With the development of urban buildings towards high-rise and intensive directions, the occurrence of fire disasters is more and more frequent, the loss is more and more large, and the importance of preventing and treating the fire disasters is more and more obvious; in recent years, due to the rapid development of computer vision, the advantages of video detectors are gradually shown, and the application fields of the video detectors are more and more extensive. The video detector is a fire detector based on an image processing technology, and video devices such as a camera and the like are utilized to capture video information, and then an image recognition algorithm is called to judge whether a fire disaster occurs or not.
In the existing video detector, the smoke identification processing method is complex, the software operation amount is too large, the situation of misjudgment often occurs in the smoke detection identification process, and the flame positioning precision is low.
Disclosure of Invention
In view of this, the embodiment of the present application provides a smoke identification method and an identification system for an image-type fire detector, and aims to solve the technical problems of higher algorithm complexity and lower positioning accuracy in the existing smoke identification method.
A first aspect of the present application provides a smoke recognition method of an image type fire detector for recognizing a smoke signal in a visible light, comprising the steps of:
acquiring a video image of a monitoring site, and converting the video image into an image sequence;
setting a reference point of an RGB color space;
carrying out motion foreground region segmentation on the image sequence in the RGB color space to obtain a suspected target region;
and judging the smoke motion rule of the image sequence in the suspected target area to determine the smoke target area.
Preferably, the setting of the reference point of the color space range specifically includes:
selecting an RGB color space range of a reference target in an initial frame of the image sequence, wherein reference points of value ranges in an R channel, a G channel and a B channel in the RGB color space are respectively set as (Rstart, Rend), (Gstart, Gend) and (Bstart, Bend).
Preferably, before the image sequence in the RGB color space is subjected to motion foreground region segmentation, the method further includes preprocessing the image sequence, and outputting the processed image sequence; the preprocessing the image sequence specifically includes:
eliminating background noise of the image sequence by adopting a median filtering method, outputting the processed image sequence, and realizing by applying the following formula:
g(x，y)＝Med{f(x-k，y-l)，(k，l)∈W}
wherein f (x, y) is an image sequence, g (x, y) is a processed image sequence, W is a two-dimensional template, and k and l are respectively an abscissa and an ordinate of a center point of the two-dimensional template.
Preferably, the moving foreground region segmentation is performed on the image sequence in the RGB color space to obtain a suspected target region, and specifically includes:
calculating component values of an R channel, a G channel, and a B channel in an RGB color space of the processed image sequence G (x, y), defined as R, G and B, respectively, comparing R, G and a maximum value and a minimum value in B, and outputting a comparison result:
max＝max(R,G,B)
min＝min(R,G,B)
wherein max is the maximum of R, G and B, min is the minimum of R, G and B;
comparing R, G and B with the reference points to obtain the suspected target area, wherein the suspected target area is determined according to the following conditions:
condition a:
|max-min|<T1
condition B:
T2<max<T3
condition C:
Rstart<＝R&&R<＝Rend
Gstart<＝G&&G<＝Gend
Bstart<＝B&&B<＝Bend
in the formula, T1Is a first threshold value, T2Is a second threshold value, T3Is a third threshold;
and when the component values of the R channel, the G channel and the B channel meet the conditions C and A or the conditions C and B, judging that the image sequence belongs to the suspected object area.
Preferably, the method for determining the smoke target area by judging the smoke motion rule of the image sequence in the suspected target area specifically includes the following steps:
judging the motion area between the current frame and the previous frame of the image sequence in the suspected target area;
judging the upward movement displacement between the current frame and the previous frame of the image sequence in the suspected target area;
judging the left-right direction movement displacement between the current frame and the previous frame of the image sequence in the suspected target area;
and calculating the picture percentage occupied by the image sequence according to the motion area, the upward motion displacement and the left-right motion displacement so as to determine a smoke target area.
Preferably, the motion area between the current frame and the previous frame of the image sequence in the suspected target area is determined by using the following formula:
|Regiont-Regiont-1|<T4
in the formula, RegiontIs a smoke Region pixel value, Region, of a current frame of an image sequencet-1The value of a pixel, T, of a smoke region of a frame preceding the image sequence4Is the fourth threshold.
Preferably, the upward movement displacement between the current frame and the previous frame of the image sequence in the suspected target area is determined by using the following formula:
|Tt-Tt-1|<T5
in the formula, TtIs the pixel value, T, of the current frame of the image sequence from the top of the suspected target areat-1Is the pixel value, T, at the top of the suspected target area in the previous frame of the image sequence5Is the fifth threshold.
Preferably, the left-right direction movement displacement between the current frame and the previous frame of the image sequence in the suspected target area is determined, and the following formula is adopted to implement the following steps:
|Rt-Rt-1|＜T6‖|Lt-Lt-1|＜T7
in the formula, RtFor the pixel value, R, of the image sequence for which the current frame has moved to the rightt-1For pixel values shifted to the right in the previous frame of the image sequence, T6Is a sixth threshold value, LtFor the pixel value, L, of the current frame of the image sequence shifted to the leftt-1For pixel values shifted to the left, T, of a preceding frame of the image sequence7Is the seventh threshold.
Preferably, the percentage of the picture occupied by the image sequence is calculated according to the motion area, the upward motion displacement and the left-right motion displacement to determine the smoke target area, and the following method is adopted:
if the image sequence simultaneously meets the following conditions, judging that the position of the image sequence is a smoke target area;
N>T8
R et-1g>Ti9
and (R)t-1-Lt-1)*(Bt-1-Tt-1)>T10
Rt-1-Lt-1>T11||Bt-1-Tt-1>T12
Determining a smoke target area as follows:
Smoket(Lt-1,Tt-1,Rt-1-Lt-1,Bt-1-Tt-1)
wherein N is the number of images determined as a suspected smoke region, and T8Is an eighth threshold value, Bt-1Is the pixel value T of the bottom end of the distance suspected target area of the previous frame of the image sequence9Is a ninth threshold value, T10Is a tenth threshold value, T11Is an eleventh threshold value, T12Is a twelfth threshold;
a second aspect of the present application provides a smoke recognition system of an image type fire detector, comprising:
the system comprises an image acquisition module, a video acquisition module and a video display module, wherein the image acquisition module is used for acquiring video images of a monitoring site and converting the video images into an image sequence;
the parameter setting module is used for setting a reference point of an RGB color space;
the foreground segmentation module is used for carrying out motion foreground region segmentation on the image sequence in the RGB color space so as to obtain a suspected target region;
and the target determining module is used for judging the smoke motion rule of the image sequence in the suspected target area so as to determine the smoke target area.
The method comprises the steps of acquiring a video image of a monitoring site by using a binocular camera, converting the video image into an image sequence, and performing motion foreground region segmentation on the image sequence in an RGB color space by setting a reference point of the RGB color space to acquire a suspected target region; and determining the smoke target area by judging the smoke motion rule of the image sequence in the suspected target area. The algorithm is low in complexity, and high in detection efficiency and recognition effect.
Drawings
FIG. 1 is a schematic flow chart of a flame identification method of an image-type fire detector according to the present invention;
fig. 2 is a schematic diagram illustrating a flow of determining a smoke target area in a smoke recognition method of an image-type fire detector according to an embodiment of the present application;
fig. 3 is a schematic block diagram of a smoke recognition system of an image-type fire detector according to an embodiment of the present disclosure.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, a schematic diagram of specific process steps of a smoke identification method for an image-type fire detector according to an embodiment of the present application is shown, and for convenience of description, only the parts related to the embodiment are shown, which are detailed as follows:
in one embodiment, the above-mentioned smoke recognition method for an image-type fire detector is used for recognizing a smoke signal in visible light, and includes the following steps:
s101, obtaining a video image of a monitoring site, and converting the video image into an image sequence.
Specifically, a binocular camera is adopted to obtain real-time video images of a monitoring site, and the video images are converted into an image sequence.
And S102, setting a reference point of the RGB color space.
Specifically, an RGB color space range of the reference target is selected in an initial frame of the image sequence, and reference points of value ranges in an R channel, a G channel, and a B channel in the RGB color space are respectively set to (Rstart, Rend), (Gstart, gent), (Bstart, Bend).
And S103, preprocessing the image sequence.
Specifically, in the process of acquiring a video image, the binocular camera is interfered by factors such as the binocular camera itself and the environment, so that the acquired video image is distorted or contains noise, the signal-to-noise ratio of the image is reduced, and a target is difficult to distinguish, so that the video image needs to be preprocessed before being subjected to algorithm processing.
In this embodiment, a median filtering method is used to pre-process a video image, and the median filtering method filters a high-frequency component in the video sequence by filtering an image sequence to remove background noise of the image sequence, so as to smooth the image, and outputs a processed image sequence, and is implemented by applying the following formula:
g(x，y)＝Med{f(x-k，y-l)，(k，l)∈W} (1)
wherein f (x, y) is an image sequence, g (x, y) is a processed image sequence, W is a two-dimensional template, and k and l are respectively an abscissa and an ordinate of a center point of the two-dimensional template.
And S104, carrying out motion foreground region segmentation on the image sequence in the RGB color space to obtain a suspected target region.
Specifically, the component value of the R channel, the component value of the G channel, and the component value of the B channel in the RGB color space put into each frame of the image sequence G (x, y) after the calculation processing are respectively defined as R, G and B, the maximum value and the minimum value in R, G and B are compared, and the comparison result is output:
max＝max(R,G,B) (2)
min＝min(R,G,B) (3)
wherein max is the maximum of R, G and B, min is the minimum of R, G and B;
comparing R, G and B with the reference points to obtain the suspected target area, wherein the suspected target area is determined according to the following conditions:
condition a:
|max-min|<T1 (4)
condition B:
T2<max<T3 (5)
condition C:
Rstart<＝R&&R<＝Rend
Gstart<＝G&&G<＝Gend
Bstart<＝B&&B<＝Bend (6)
in the formula, T1Is a first threshold value, T2Is a second threshold value, T3Is the third threshold.
And when the component values of the R channel, the G channel and the B channel meet the conditions C and A or the conditions C and B, judging that the image sequence belongs to the suspected object area.
And S105, judging the smoke motion rule of the image sequence in the suspected target area to determine the smoke target area.
Referring to fig. 2, a schematic diagram of the flow steps for determining the smoke target area in the smoke identification method of the image-type fire detector according to an embodiment of the present application is shown, and for convenience of description, only the relevant portions of the embodiment are shown, and the following details are described below:
specifically, in the initial stage of a fire, particles generated by combustion move upwards under the influence of heat in the smoke generating process of combustible materials, the smoke moves at a high speed, and after the smoke rises to a certain degree, the smoke is diffused to occupy a large amount of space of a video picture in a short time; influenced by air current in the air, the form of smog is comparatively complicated, and the smog region presents certain motion law, and the smog motion law of image sequence includes the motion area of image sequence, upward movement displacement, left and right direction motion displacement, specifically includes following step:
s1051, judging the motion area between the current frame and the previous frame of the image sequence in the suspected target area, and realizing by adopting the following formula:
|Regiont-Regiont-1|<T4 (7)
in the formula, RegiontIs a smoke Region pixel value, Region, of a current frame of an image sequencet-1The value of a pixel, T, of a smoke region of a frame preceding the image sequence4Is the fourth threshold.
S1052, judging the upward movement displacement between the current frame and the previous frame of the image sequence in the suspected target area, and realizing the displacement by adopting the following formula:
|Tt-Tt-1|<T5 (8)
in the formula, TtIs the pixel value, T, of the current frame of the image sequence from the top of the suspected target areat-1Is the pixel value, T, at the top of the suspected target area in the previous frame of the image sequence5Is the fifth threshold.
S1053, judging the left-right direction movement displacement between the current frame and the previous frame of the image sequence in the suspected target area, and realizing by adopting the following formula:
|Rt-Rt-1|＜T6‖|Lt-Lt-1|＜T7 (9)
in the formula, RtIs the pixel value of the right shift of the current frame of the image sequence, namely the suspected smoke area of the current frameOf the rightmost pixel value, Rt-1Is the pixel value shifted to the right in the previous frame of the image sequence, i.e. the rightmost pixel value of the suspected smoke region in the previous frame, T6Is a sixth threshold value, LtIs the pixel value of the left-shifted current frame of the image sequence, i.e. the leftmost pixel value of the suspected smoke region of the current frame, Lt-1Is the pixel value of the previous frame of the image sequence shifted to the left, i.e. the leftmost pixel value of the suspected smoke area of the previous frame, T7Is the seventh threshold.
S1054, calculating the percentage of the picture occupied by the image sequence according to the motion area, the upward motion displacement and the left-right motion displacement to determine the smoke target area, and realizing the following steps:
if the image sequence simultaneously meets the following conditions, judging that the position of the image sequence is a smoke target area:
N>T8 (10)
R et-1g>Ti9 (11)
and (R)t-1-Lt-1)*(Bt-1-Tt-1)>T10 (12)
Rt-1-Lt-1>T11||Bt-1-Tt-1>T12 (13)
Wherein N is the number of images determined as a suspected smoke region, and T8Is an eighth threshold value, Bt-1Is the pixel value T of the bottom end of the distance suspected target area of the previous frame of the image sequence9Is a ninth threshold value, T10Is a tenth threshold value, T11Is an eleventh threshold value, T12Is the twelfth threshold.
Determining a smoke target area as follows:
Smoket(Lt-1,Tt-1,Rt-1-Lt-1,Bt-1-Tt-1) (14)
and after the smoke target area is determined, outputting a smoke profile and giving out acousto-optic alarm.
Referring to fig. 3, a schematic block diagram of a smoke recognition system of an image-type fire detector according to an embodiment of the present application shows only parts related to the embodiment for convenience of description, and the details are as follows:
in one embodiment, a smoke recognition system for an image-based fire detector includes:
the image acquisition module 100 is configured to acquire a video image of a monitoring site and convert the video image into an image sequence.
The parameter setting module 200 is configured to set a reference point of the RGB color space.
A pre-processing module 300 for pre-processing the image sequence.
A foreground segmentation module 400, configured to perform motion foreground region segmentation on the image sequence in the RGB color space to obtain a suspected target region.
And the target determining module 500 is configured to determine a smoke motion rule of the image sequence in the suspected target area to determine the smoke target area.
It should be noted that, in this embodiment, a smoke identification system of an image type fire detector is an embodiment of an identification system corresponding to the smoke identification method of the image type fire detector, and therefore, regarding specific implementation of software methods in each module of an evaluation system, reference may be made to the embodiments of fig. 1 to 2, and details are not repeated here.
In summary, the method includes the steps that a binocular camera is used for obtaining video images of a monitoring site, the video images are converted into image sequences, and a suspected target area is obtained by setting reference points of an RGB color space and carrying out motion foreground area segmentation on the image sequences in the RGB color space; and determining the smoke target area by judging the smoke motion rule of the image sequence in the suspected target area. The algorithm is low in complexity, and high in detection efficiency and recognition effect.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims (10)

1. A smoke recognition method of an image type fire detector is used for recognizing smoke signals in visible light, and is characterized by comprising the following steps:
acquiring a video image of a monitoring site, and converting the video image into an image sequence;
setting a reference point of an RGB color space;
carrying out motion foreground region segmentation on the image sequence in the RGB color space to obtain a suspected target region;
and judging the smoke motion rule of the image sequence in the suspected target area to determine the smoke target area.
2. The smoke recognition method of an image-type fire detector according to claim 1, wherein the setting of the reference point of the color space range specifically includes:
selecting an RGB color space range of a reference target in an initial frame of the image sequence, wherein reference points of value ranges in an R channel, a G channel and a B channel in the RGB color space are respectively set as (Rstart, Rend), (Gstart, Gend) and (Bstart, Bend).
3. The smoke recognition method of an image-type fire detector according to claim 2, wherein before the segmentation of the moving foreground region of the image sequence in the RGB color space, the method further comprises preprocessing the image sequence and outputting the processed image sequence; the preprocessing the image sequence specifically includes:
eliminating background noise of the image sequence by adopting a median filtering method, outputting the processed image sequence, and realizing by applying the following formula:
g(x，y)＝Med{f(x-k，y-l)，(k，l)∈W}
wherein f (x, y) is an image sequence, g (x, y) is a processed image sequence, W is a two-dimensional template, and k and l are respectively an abscissa and an ordinate of a center point of the two-dimensional template.
4. The smoke identification method of an image-based fire detector according to claim 3, wherein the moving foreground region segmentation is performed on the image sequence in the RGB color space to obtain the suspected target region, and specifically comprises:
calculating component values of an R channel, a G channel, and a B channel in an RGB color space of the processed image sequence G (x, y), defined as R, G and B, respectively, comparing R, G and a maximum value and a minimum value in B, and outputting a comparison result:
max＝max(R,G,B)
min＝min(R,G,B)
wherein max is the maximum of R, G and B, min is the minimum of R, G and B;
comparing R, G and B with the reference points to obtain the suspected target area, wherein the suspected target area is determined according to the following conditions:
condition a:
|max-min|<T1
condition B:
T2<max<T3
condition C:
Rstart<＝R&&R<＝Rend
Gstart<＝G&&G<＝Gend
Bstart<＝B&&B<＝Bend
in the formula, T1Is a first threshold value, T2Is a second threshold value, T3Is a third threshold;
and when the component values of the R channel, the G channel and the B channel meet the conditions C and A or the conditions C and B, judging that the image sequence belongs to the suspected object area.
5. The smoke identification method of the image-type fire detector according to claim 4, wherein the method for determining the smoke motion law of the image sequence in the suspected target area to determine the smoke target area comprises the following steps:
judging the motion area between the current frame and the previous frame of the image sequence in the suspected target area;
judging the upward movement displacement between the current frame and the previous frame of the image sequence in the suspected target area;
judging the left-right direction movement displacement between the current frame and the previous frame of the image sequence in the suspected target area;
and calculating the picture percentage occupied by the image sequence according to the motion area, the upward motion displacement and the left-right motion displacement so as to determine a smoke target area.
6. The method as claimed in claim 5, wherein the determining the moving area between the current frame and the previous frame of the image sequence in the suspected target area is implemented by using the following formula:
|Regiont-Regiont-1|<T4
in the formula, RegiontIs a smoke Region pixel value, Region, of a current frame of an image sequencet-1The value of a pixel, T, of a smoke region of a frame preceding the image sequence4Is the fourth threshold.
7. The method as claimed in claim 6, wherein the determining the upward movement displacement between the current frame and the previous frame of the image sequence in the suspected target area is implemented by using the following formula:
|Tt-Tt-1|<T5
in the formula, TtIs the pixel value, T, of the current frame of the image sequence from the top of the suspected target areat-1Is the pixel value, T, at the top of the suspected target area in the previous frame of the image sequence5Is the fifth threshold.
8. The method as claimed in claim 7, wherein the determining the left-right movement displacement between the current frame and the previous frame of the image sequence in the suspected target area is implemented by using the following formula:
|Rt-Rt-1|＜T6‖|Lt-Lt-1|＜T7
in the formula, RtFor the pixel value, R, of the image sequence for which the current frame has moved to the rightt-1For pixel values shifted to the right in the previous frame of the image sequence, T6Is a sixth threshold value, LtFor the pixel value, L, of the current frame of the image sequence shifted to the leftt-1For pixel values shifted to the left, T, of a preceding frame of the image sequence7Is the seventh threshold.
9. The method for identifying smoke of an image-type fire detector according to claim 8, wherein the percentage of the picture occupied by the image sequence is calculated according to the moving area, the upward moving displacement and the left-right moving displacement to determine the smoke target area, and the method is implemented by the following steps:
if the image sequence simultaneously meets the following conditions, judging that the position of the image sequence is a smoke target area;
N>T8
Ret-1g>Ti9
(Rt-1-Lt-1)*(Bt-1-Tt-1)>T10
Rt-1-Lt-1>T11||Bt-1-Tt-1>T12
determining a smoke target area as follows:
Smoket(Lt-1,Tt-1,Rt-1-Lt-1,Bt-1-Tt-1)
wherein N is the number of images determined as a suspected smoke region, and T8Is an eighth threshold value, Bt-1Is the pixel value T of the bottom end of the distance suspected target area of the previous frame of the image sequence9Is a ninth threshold value, T10Is a tenth threshold value, T11Is an eleventh threshold value, T12Is the twelfth threshold.
10. A smoke recognition system for an image-based fire detector, comprising:
the system comprises an image acquisition module, a video acquisition module and a video display module, wherein the image acquisition module is used for acquiring video images of a monitoring site and converting the video images into an image sequence;
the parameter setting module is used for setting a reference point of an RGB color space;
the foreground segmentation module is used for carrying out motion foreground region segmentation on the image sequence in the RGB color space so as to obtain a suspected target region;
and the target determining module is used for judging the smoke motion rule of the image sequence in the suspected target area so as to determine the smoke target area.
CN202011071209.9A 2020-10-09 2020-10-09 Smoke identification method and system of image type fire detector Pending CN112257523A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011071209.9A CN112257523A (en) 2020-10-09 2020-10-09 Smoke identification method and system of image type fire detector

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011071209.9A CN112257523A (en) 2020-10-09 2020-10-09 Smoke identification method and system of image type fire detector

Publications (1)

Publication Number Publication Date
CN112257523A true CN112257523A (en) 2021-01-22

Family

ID=74233519

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011071209.9A Pending CN112257523A (en) 2020-10-09 2020-10-09 Smoke identification method and system of image type fire detector

Country Status (1)

Country Link
CN (1) CN112257523A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115223105A (en) * 2022-09-20 2022-10-21 万链指数(青岛)信息科技有限公司 Big data based risk information monitoring and analyzing method and system
CN116091959A (en) * 2022-11-21 2023-05-09 武汉坤达安信息安全技术有限公司 Double-light linkage identification method and device based on all-weather smoke and fire
CN116311000A (en) * 2023-05-16 2023-06-23 合肥中科类脑智能技术有限公司 Firework detection method, device, equipment and storage medium

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115223105A (en) * 2022-09-20 2022-10-21 万链指数(青岛)信息科技有限公司 Big data based risk information monitoring and analyzing method and system
CN115223105B (en) * 2022-09-20 2022-12-09 万链指数(青岛)信息科技有限公司 Big data based risk information monitoring and analyzing method and system
CN116091959A (en) * 2022-11-21 2023-05-09 武汉坤达安信息安全技术有限公司 Double-light linkage identification method and device based on all-weather smoke and fire
CN116091959B (en) * 2022-11-21 2024-03-22 武汉坤达安信息安全技术有限公司 Double-light linkage identification method and device based on all-weather smoke and fire
CN116311000A (en) * 2023-05-16 2023-06-23 合肥中科类脑智能技术有限公司 Firework detection method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN112257523A (en) Smoke identification method and system of image type fire detector
KR100835380B1 (en) Method for detecting edge of an image and apparatus thereof and computer readable medium processing the method
JP3951984B2 (en) Image projection method and image projection apparatus
JP4429298B2 (en) Object number detection device and object number detection method
CN111047568B (en) Method and system for detecting and identifying steam leakage defect
US20210281748A1 (en) Information processing apparatus
CN111368771A (en) Tunnel fire early warning method and device based on image processing, computer equipment and computer readable storage medium
JP4533836B2 (en) Fluctuating region detection apparatus and method
CN109447011B (en) Real-time monitoring method for infrared leakage of steam pipeline
TWI394097B (en) Detecting method and system for moving object
CN115639248A (en) System and method for detecting quality of building outer wall
KR101044903B1 (en) Fire detecting method using hidden markov models in video surveillance and monitoring system
CN116402852A (en) Dynamic high-speed target tracking method and device based on event camera
JP5173549B2 (en) Image processing apparatus and imaging apparatus
TWI381735B (en) Image processing system and method for automatic adjustment of image resolution for image surveillance apparatus
KR101829386B1 (en) Apparatus and method for detecting target
JP2011090708A (en) Apparatus and method for detecting the number of objects
JP2009076094A (en) Moving object monitoring device
CN111062887B (en) Image definition judging method based on improved Retinex algorithm
US20220114736A1 (en) Method and system for motion segmentation
JP4674920B2 (en) Object number detection device and object number detection method
JP2004295416A (en) Image processing apparatus
JP2003240622A (en) Liquid level recognition processing device and liquid level monitoring system
JP6618438B2 (en) Foreground region extraction apparatus, method, and program
JP4998955B2 (en) Collapse detection system and method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination