CN114648852A - Tunnel fire monitoring method and system - Google Patents

Tunnel fire monitoring method and system Download PDF

Info

Publication number
CN114648852A
CN114648852A CN202210567872.0A CN202210567872A CN114648852A CN 114648852 A CN114648852 A CN 114648852A CN 202210567872 A CN202210567872 A CN 202210567872A CN 114648852 A CN114648852 A CN 114648852A
Authority
CN
China
Prior art keywords
tunnel contour
image
contour position
tunnel
smoothness
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.)
Granted
Application number
CN202210567872.0A
Other languages
Chinese (zh)
Other versions
CN114648852B (en
Inventor
杨钞
兰北章
李向阳
高继涛
赵快
陈亮
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.)
Sichuan Jiutong Zhilu Technology Co ltd
Original Assignee
Sichuan Jiutong Zhilu Technology 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 Sichuan Jiutong Zhilu Technology Co ltd filed Critical Sichuan Jiutong Zhilu Technology Co ltd
Priority to CN202210567872.0A priority Critical patent/CN114648852B/en
Publication of CN114648852A publication Critical patent/CN114648852A/en
Application granted granted Critical
Publication of CN114648852B publication Critical patent/CN114648852B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00—Fire alarms; Alarms responsive to explosion
    • G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00—Fire alarms; Alarms responsive to explosion
    • G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
    • G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke

Landscapes

  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a tunnel fire monitoring method and system, and belongs to the field of tunnel fire protection. The method comprises the step of collecting monitoring images in monitoring equipment in a tunnel, wherein the monitoring images comprise background images and current monitoring images. Obtaining a tunnel contour position based on the background image; and obtaining a tunnel contour position uniform smoothness set based on the tunnel contour position and the background image. And obtaining a stability set of the current monitoring tunnel contour position based on the current monitoring image and the tunnel contour position. And obtaining coverage similarity based on the tunnel contour position uniform smoothness set and the current monitoring tunnel contour position smoothness set. If the coverage similarity is larger than a coverage threshold value and the overall fuzziness of the monitoring image is smaller than a fuzziness threshold value, determining that the detection result is smoke; and generating alarm information.

Description

Tunnel fire monitoring method and system
Technical Field
The invention relates to the technical field of tunnel fire protection, in particular to a tunnel fire monitoring method and system.
Background
In order to monitor the fire in the tunnel in real time and ensure the fire safety; the fire inside the tunnel is typically monitored by smoke particle sensing or infrared, laser techniques. Traditional smog granule induction system needs smog granule to get into the sensor and can arouse the warning, and infrared and laser technology also need smog to shelter from and can arouse the warning. These prerequisites require that the situation is a relatively closed space. In the tunnel, the traditional pyrotechnic device has small effect because the air flow is large and the smoke is rapidly diffused.
Disclosure of Invention
The invention aims to provide a tunnel fire monitoring method and a tunnel fire monitoring system, which are used for solving the problems in the prior art.
In a first aspect, an embodiment of the present invention provides a tunnel fire monitoring method, including:
collecting a monitoring image in monitoring equipment in a tunnel; the monitoring image comprises a background image and a current monitoring image; the background image represents a background image when no smoke exists in the tunnel;
obtaining a tunnel contour position based on the background image;
obtaining a background image tunnel contour position smoothness set based on the background image and the tunnel contour position; the background image tunnel contour position smoothness set comprises a plurality of background image tunnel contour position stabilities, and the background image tunnel contour position stabilities represent different degrees of colors at tunnel contour positions in a background image and 8 surrounding positions;
obtaining a monitored image tunnel contour position smoothness set based on the current monitored image and the tunnel contour position; the monitoring image tunnel contour position stability set comprises a plurality of monitoring image tunnel contour position stabilities; the tunnel contour position smoothness of the multiple monitoring images represents different degrees of colors at the tunnel contour position in the current monitoring image and colors at the surrounding positions;
obtaining coverage similarity based on the background image tunnel contour position smoothness set and the monitoring image tunnel contour position smoothness set; the coverage similarity represents the degree of coverage of the current monitoring image by smoke at the tunnel contour position;
obtaining the overall fuzziness of the monitored image based on the current monitored image;
if the coverage similarity is larger than a coverage threshold value and the overall fuzziness of the monitoring image is smaller than a fuzziness threshold value, determining that the detection result is smoke; and generating alarm information.
Optionally, the obtaining a tunnel contour position based on the background image includes:
graying the background image to obtain a background grayscale image;
obtaining a first background gray difference value; the first background gray difference value is the difference of the first background gray value minus one of eight gray values around the first background gray value; the first background gray value represents a first gray value from the upper left corner in the background gray image;
if the first background gray level difference value is larger than the difference threshold value, taking the position of the first background gray level value as a contour point;
and obtaining all contour points in the background image by comparing the difference of the gray value in the background image minus one of the plurality of surrounding gray values with the difference threshold value for multiple times.
Optionally, the obtaining a background image tunnel contour position smoothness set based on the background image and the tunnel contour position includes:
obtaining the tunnel contour position smoothness of a first peripheral background image, wherein the tunnel contour position smoothness of the first peripheral background image represents the difference value of the RGB value of one position of the tunnel contour positions in the background image and one position of 8 positions around the tunnel contour positions;
the tunnel contour position smoothness of the first surrounding background image is obtained by the following formula calculation method:
Figure DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 952840DEST_PATH_IMAGE002
the tunnel contour position smoothness of the first surrounding background image,
Figure 939251DEST_PATH_IMAGE003
for the pixel value of the R channel in the contour position of the background image,
Figure 370232DEST_PATH_IMAGE004
pixel values of an R channel in a position around the outline of the background image;
Figure 218234DEST_PATH_IMAGE005
for the pixel value of the G channel in the contour position of the background image,
Figure 988743DEST_PATH_IMAGE006
pixel values of a G channel in a position around the outline of the background image;
Figure 146055DEST_PATH_IMAGE007
for the pixel value of the B channel in the contour position of the background image,
Figure 64333DEST_PATH_IMAGE008
pixel values of a B channel in a position around the outline of the background image;
obtaining the stability of the tunnel contour position of the background image; the background image tunnel contour position smoothness comprises a first surrounding background image tunnel contour position smoothness, a second surrounding background image tunnel contour position smoothness, a third surrounding background image tunnel contour position smoothness, a fourth surrounding background image tunnel contour position smoothness, a fifth surrounding background image tunnel contour position smoothness, a sixth surrounding background image tunnel contour position smoothness, a seventh surrounding background image tunnel contour position smoothness and an eighth surrounding background image tunnel contour position smoothness;
obtaining a background image tunnel contour position stability set of a plurality of tunnel contour positions through a plurality of times of calculation; the background image tunnel contour position smoothness set comprises a plurality of tunnel contour positions and corresponding background image tunnel contour position smoothness.
Optionally, obtaining a monitored image tunnel contour position smoothness set based on the current monitored image and the tunnel contour position includes:
acquiring the tunnel contour position smoothness of a first peripheral monitoring image, wherein the tunnel contour position smoothness of the first peripheral monitoring image represents the difference value of the RGB value of one position of the tunnel contour positions in the monitoring image and one position of 8 positions around the tunnel contour positions;
obtaining the stability of the tunnel contour position of the monitoring image; the monitoring image tunnel contour position smoothness comprises a first surrounding monitoring image tunnel contour position smoothness, a second surrounding monitoring image tunnel contour position smoothness, a third surrounding monitoring image tunnel contour position smoothness, a fourth surrounding monitoring image tunnel contour position smoothness, a fifth surrounding monitoring image tunnel contour position smoothness, a sixth surrounding monitoring image tunnel contour position smoothness, a seventh surrounding monitoring image tunnel contour position smoothness and an eighth surrounding monitoring image tunnel contour position smoothness; the flatness of the tunnel contour position of the monitoring image represents different degrees of colors of the contour position and a plurality of positions around the contour position in the monitoring image;
obtaining a monitoring image tunnel contour position stability set of a plurality of tunnel contour positions through multiple calculations; the monitoring image tunnel contour position smoothness set comprises a plurality of tunnel contour positions and corresponding monitoring image tunnel contour position smoothness.
Optionally, the obtaining of the coverage similarity based on the background image tunnel contour position smoothness set and the monitoring image tunnel contour position smoothness set includes:
obtaining a smoothness difference set; the stability difference value set is an absolute value of a difference of the stability of the tunnel contour position of the background image in the background image tunnel contour position stability set which subtracts the position corresponding to the stability of the tunnel contour position of the monitoring image in the monitoring image tunnel contour position stability set;
obtaining a number of stationarities, wherein the number of stationarities is the number smaller than a stationarities threshold in the stationarities difference set; the stationary number represents the number of ambiguous locations from the surrounding locations in all tunnel contour locations;
and obtaining the coverage similarity, wherein the coverage similarity is the product of the stable number divided by the number of the tunnel contour positions.
Optionally, obtaining the overall ambiguity of the monitored image based on the current monitored image includes:
acquiring a turnover monitoring image; the overturning monitoring image is an image obtained by overturning the current monitoring image by taking the center as an axis;
obtaining the fuzzy degree; the ambiguity represents a color difference between two positions corresponding to the axis of the center in the monitored image;
the fuzzy degree is obtained by the following formula calculation mode:
Figure 965293DEST_PATH_IMAGE009
wherein the content of the first and second substances,
Figure 400429DEST_PATH_IMAGE010
in order to be said degree of blurring,
Figure 728642DEST_PATH_IMAGE011
for the pixel values of the R channel in the contour position of the monitoring image,
Figure 71899DEST_PATH_IMAGE012
pixel values of an R channel in the contour surrounding position of the turnover monitoring image are obtained;
Figure 776549DEST_PATH_IMAGE013
for the pixel value of G channel in the contour position of the monitoring image，
Figure 318389DEST_PATH_IMAGE014
Pixel values of a G channel in the contour surrounding position of the turnover monitoring image are obtained;
Figure 833815DEST_PATH_IMAGE015
for the pixel values of the B channel in the contour position of the monitoring image,
Figure 461106DEST_PATH_IMAGE016
pixel values of a channel B in the contour surrounding position of the turnover monitoring image are obtained;
and normalizing the fuzzy degree to obtain the overall fuzzy degree of the monitoring image.
In a second aspect, an embodiment of the present invention provides a tunnel fire fighting system detection system, including:
an acquisition module: collecting a monitoring image in monitoring equipment in a tunnel; the monitoring image comprises a background image and a current monitoring image; the background image represents a background image when no smoke exists in the tunnel;
a tunnel contour acquisition module: obtaining a tunnel contour position based on the background image;
the scene image tunnel contour position smoothness set acquisition module comprises: obtaining a background image tunnel contour position smoothness set based on the background image and the tunnel contour position; the background image tunnel contour position smoothness set comprises a plurality of background image tunnel contour position stabilities, and the background image tunnel contour position stabilities represent different degrees of colors at tunnel contour positions in a background image and 8 surrounding positions;
the monitoring image tunnel contour position smoothness set acquisition module comprises: obtaining a monitored image tunnel contour position smoothness set based on the current monitored image and the tunnel contour position; the monitoring image tunnel contour position stability set comprises a plurality of monitoring image tunnel contour position stabilities; the tunnel contour position smoothness of the multiple monitoring images represents different degrees of colors at the tunnel contour position in the current monitoring image and colors at the surrounding positions;
a smoke judgment module: obtaining coverage similarity based on the background image tunnel contour position smoothness set and the monitoring image tunnel contour position smoothness set; the coverage similarity represents the degree of coverage of the current monitoring image by smoke at the tunnel contour position; obtaining the overall fuzziness of the monitored image based on the current monitored image; if the coverage similarity is larger than a coverage threshold value and the overall fuzziness of the monitoring image is smaller than a fuzziness threshold value, determining that the detection result is smoke;
an alarm module: and generating alarm information.
Optionally, the obtaining a tunnel contour position based on the background image includes:
graying the background image to obtain a background grayscale image;
obtaining a first background gray difference value; the first background gray difference value is the difference of the first background gray value minus one of eight gray values around the first background gray value; the first background gray value represents a first gray value from the upper left corner in the background gray image;
if the first background gray level difference value is larger than the difference threshold value, taking the position of the first background gray level value as a contour point;
and obtaining all contour points in the background image by comparing the difference of the gray value in the background image minus one of the plurality of surrounding gray values with the difference threshold value for multiple times.
Optionally, the obtaining a background image tunnel contour position smoothness set based on the background image and the tunnel contour position includes:
obtaining the tunnel contour position smoothness of a first peripheral background image, wherein the tunnel contour position smoothness of the first peripheral background image represents the difference value of the RGB value of one position of the tunnel contour positions in the background image and one position of 8 positions around the tunnel contour positions;
the tunnel contour position smoothness of the first surrounding background image is obtained by the following formula calculation method:
Figure 641551DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 303477DEST_PATH_IMAGE002
the tunnel contour position smoothness of the first surrounding background image,
Figure 239072DEST_PATH_IMAGE003
for the pixel value of the R channel in the contour position of the background image,
Figure 104391DEST_PATH_IMAGE004
pixel values of an R channel in a position around the outline of the background image;
Figure 885265DEST_PATH_IMAGE005
for the pixel value of the G channel in the contour position of the background image,
Figure 604959DEST_PATH_IMAGE006
pixel values of a G channel in a position around the outline of the background image;
Figure 445876DEST_PATH_IMAGE007
for the pixel value of the B channel in the contour position of the background image,
Figure 313338DEST_PATH_IMAGE008
pixel values of a B channel in a position around the outline of the background image;
obtaining the stability of the tunnel contour position of the background image; the background image tunnel contour position smoothness comprises a first surrounding background image tunnel contour position smoothness, a second surrounding background image tunnel contour position smoothness, a third surrounding background image tunnel contour position smoothness, a fourth surrounding background image tunnel contour position smoothness, a fifth surrounding background image tunnel contour position smoothness, a sixth surrounding background image tunnel contour position smoothness, a seventh surrounding background image tunnel contour position smoothness and an eighth surrounding background image tunnel contour position smoothness;
obtaining a background image tunnel contour position stability set of a plurality of tunnel contour positions through a plurality of times of calculation; the background image tunnel contour position smoothness set comprises a plurality of tunnel contour positions and corresponding background image tunnel contour position smoothness.
Optionally, the obtaining a monitored image tunnel contour position smoothness set based on the current monitored image and the tunnel contour position includes:
acquiring the tunnel contour position smoothness of a first peripheral monitoring image, wherein the tunnel contour position smoothness of the first peripheral monitoring image represents the difference value of the RGB values of one position of the tunnel contour positions in the monitoring image and one position of 8 peripheral positions;
obtaining the stability of the tunnel contour position of the monitoring image; the monitoring image tunnel contour position smoothness comprises a first surrounding monitoring image tunnel contour position smoothness, a second surrounding monitoring image tunnel contour position smoothness, a third surrounding monitoring image tunnel contour position smoothness, a fourth surrounding monitoring image tunnel contour position smoothness, a fifth surrounding monitoring image tunnel contour position smoothness, a sixth surrounding monitoring image tunnel contour position smoothness, a seventh surrounding monitoring image tunnel contour position smoothness and an eighth surrounding monitoring image tunnel contour position smoothness; the tunnel contour position smoothness of the monitoring image represents different degrees of colors of a contour position and a plurality of positions around the contour position in the monitoring image;
obtaining a monitoring image tunnel contour position stability set of a plurality of tunnel contour positions through multiple calculations; the monitoring image tunnel contour position smoothness set comprises a plurality of tunnel contour positions and corresponding monitoring image tunnel contour position smoothness.
Compared with the prior art, the embodiment of the invention achieves the following beneficial effects:
the smoke in the tunnel diffuses quickly, and particularly the smoke concentration near the tunnel mouths at two ends cannot reach the concentration of the sensor, so that detection leakage is generated; therefore, the application uses video to detect smoke. In addition, smoke is not fixed in shape and has multiple colors, so that the smoke is not convenient to detect through feature extraction. The image detection technology is adopted, so that a tunnel can be covered when smoke is diffused, and the effect of fuzzy images is caused; therefore, the aim of detecting the smoke is fulfilled by detecting the fuzzy degree of the picture, namely the covered degree; and then can effectively provide tunnel fire early warning information.
Drawings
Fig. 1 is a flowchart of a tunnel fire monitoring method according to an embodiment of the present invention.
Fig. 2 shows the case of the first background gray-scale value and the gray-scale values of the eight surrounding positions according to the embodiment of the present invention.
Fig. 3 is a schematic block structure diagram of an electronic device according to an embodiment of the present invention.
The labels in the figure are: a bus 500; a receiver 501; a processor 502; a transmitter 503; a memory 504; a bus interface 505.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present invention provides a tunnel fire monitoring method, including:
s101: collecting a monitoring image in monitoring equipment in a tunnel; the monitoring image comprises a background image and a current monitoring image; the background image represents a background image when no smoke is present in the tunnel.
S102: and obtaining the tunnel contour position based on the background image.
S103: based on the background image and the tunnel contour position, obtaining a background image tunnel contour position uniform smoothness set; the background image tunnel contour position smoothness set comprises a plurality of background image tunnel contour position uniform smoothness, and the background image tunnel contour position uniform smoothness represents the average value of different degrees of colors at the tunnel contour position in the background image and the colors at the 8 surrounding positions.
S104: obtaining a monitored image tunnel contour position smoothness set based on the current monitored image and the tunnel contour position; the monitoring image tunnel contour position smoothness set comprises a plurality of monitoring image tunnel contour position stabilities; the tunnel contour position smoothness of the multiple monitoring images represents different degrees of colors at the tunnel contour position in the current monitoring image from the colors of the surrounding positions.
S105: obtaining coverage similarity based on the background image tunnel contour position smoothness set and the monitoring image tunnel contour position smoothness set; the coverage similarity represents the degree to which the current monitoring image is covered by smoke at the tunnel contour position.
S106: and obtaining the overall fuzzy degree of the monitored image based on the current monitored image.
S107: if the coverage similarity is larger than a coverage threshold value and the overall fuzzy degree of the monitoring image is smaller than a fuzzy threshold value, determining that the detection result is smoke; and generating alarm information.
The background image represents a background image when no smoke is present in the tunnel, and the background image also has only a static background and has no running vehicle. The monitoring image is monitoring equipment in the tunnel.
With the above method, since the speed of diffusion of smoke in the tunnel is high, and the smoke is usually filled in the entire monitoring image when the smoke is diffused, the shape of the smoke cannot be recognized, so that it is difficult to recognize the smoke by a normal method. However, because the background in the tunnel is simple and the outline is clear, the smoke is identified by performing smoke covering identification on the outline of the tunnel.
Optionally, the obtaining a tunnel contour position based on the background image includes:
and graying the background image to obtain a background grayscale image.
Obtaining a first background gray difference value; the first background gray difference value is the difference of the first background gray value minus one of eight gray values around the first background gray value; the first background grayscale value represents a first grayscale value beginning at an upper left corner in the background grayscale image.
If the first background gray level difference value is larger than the difference threshold value, taking the position of the first background gray level value as a contour point;
and obtaining all contour points in the background image by comparing the difference of the gray value in the background image minus one of the plurality of surrounding gray values with the difference threshold value for multiple times.
Wherein, the eight gray values around the first background gray value are shown in fig. 2.
And graying the background image to obtain a background grayscale image. Obtaining a gray value in the background gray image corresponding to each pixel value of the background image; and replacing the pixel value of the corresponding position with the gray value to obtain a background gray image.
The gray value in the background gray image is obtained by the following formula calculation method:
Figure 648636DEST_PATH_IMAGE017
wherein the content of the first and second substances,
Figure 222836DEST_PATH_IMAGE018
is the gray value in the background gray image,
Figure DEST_PATH_IMAGE019
for the pixel values of the R channel in the background image,
Figure 765813DEST_PATH_IMAGE020
for the pixel values of the G channel in the background image,
Figure 665112DEST_PATH_IMAGE021
is the pixel value of the B channel in the background image.
By the method, if the whole judgment change is not obvious and the detection is not easy to be carried out based on the tunnel contour position, whether smoke exists in the contour part with obvious color change or not is judged. At the same time, since the position is only obtained, it is better to change the picture into the gray-scale map.
Optionally, the obtaining a background image tunnel contour position smoothness set based on the background image and the tunnel contour position includes:
obtaining the tunnel contour position smoothness of a first peripheral background image, wherein the tunnel contour position smoothness of the first peripheral background image represents the difference value of the RGB value of one position of the tunnel contour positions in the background image and one position of 8 positions around the tunnel contour positions;
the tunnel contour position smoothness of the first surrounding background image is obtained by the following formula calculation method:
Figure 804100DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 45857DEST_PATH_IMAGE002
the tunnel contour position smoothness of the first surrounding background image,
Figure 632171DEST_PATH_IMAGE003
for the pixel value of the R channel in the contour position of the background image,
Figure 490537DEST_PATH_IMAGE004
is the pixel value of the R channel in the position around the contour of the background image.
Figure 948063DEST_PATH_IMAGE005
Is the pixel value of the G channel in the contour position of the background image,
Figure 513168DEST_PATH_IMAGE006
is the pixel value of the G channel in the position around the outline of the background image.
Figure 349012DEST_PATH_IMAGE007
For the pixel value of the B channel in the contour position of the background image,
Figure 163516DEST_PATH_IMAGE008
pixel values of a B channel in a position around the outline of the background image;
obtaining the stability of the tunnel contour position of the background image; the background image tunnel contour position smoothness comprises a first surrounding background image tunnel contour position smoothness, a second surrounding background image tunnel contour position smoothness, a third surrounding background image tunnel contour position smoothness, a fourth surrounding background image tunnel contour position smoothness, a fifth surrounding background image tunnel contour position smoothness, a sixth surrounding background image tunnel contour position smoothness, a seventh surrounding background image tunnel contour position smoothness and an eighth surrounding background image tunnel contour position smoothness;
and obtaining a background image tunnel contour position smoothness set of a plurality of tunnel contour positions through a plurality of times of calculation. The background image tunnel contour position smoothness set comprises a plurality of tunnel contour positions and corresponding background image tunnel contour position smoothness.
Wherein, the smoothness between each tunnel contour position and 8 surrounding positions is obtained. The background image tunnel contour position uniform smoothness set comprises a plurality of tunnel contour positions and corresponding background image tunnel contour positions uniform smoothness. In this embodiment, the portion of the current monitored tunnel contour position smoothness set is [ (12,12,18,42,189,90,18,42,189,76), (13,12,90, 18,42,189) ]. [(12,12,18,42,189,90,18,42,189,76),(13,12,90, 18,42,189,90,18,42,189)]. The meaning of the element in (13,12,90, 18,42,189) is: line 13, column 12, line 90, monitor image tunnel contour position flatness at the first periphery of (13,12), 18, monitor image tunnel contour position flatness at the second periphery of (13,12), 42, monitor image tunnel contour position flatness at the third periphery of (13,12), 189, monitor image tunnel contour position flatness at the fourth periphery of (13,12), 90, monitor image tunnel contour position flatness at the fifth periphery of (13,12), 18, monitor image tunnel contour position flatness at the sixth periphery of (13,12), 42, monitor image tunnel contour position flatness at the seventh periphery of (13,12), 189, monitor image tunnel contour position flatness at the eighth periphery of (13, 12).
By the method, the tunnel contour position uniformity and smoothness of the background image at each tunnel contour position are obtained, the uniformity and smoothness of the tunnel contour position of the background image are used for judging the fuzzy degree of the monitoring image, the difference degree between the monitoring image and the background image can be accurately compared, and the degree of the smoke fuzzy picture can be judged.
Optionally, obtaining a monitored image tunnel contour position smoothness set based on the current monitored image and the tunnel contour position includes:
acquiring the tunnel contour position smoothness of a first peripheral monitoring image, wherein the tunnel contour position smoothness of the first peripheral monitoring image represents the difference value of the RGB value of one position of the tunnel contour positions in the monitoring image and one position of 8 positions around the tunnel contour positions;
obtaining the stability of the tunnel contour position of the monitoring image; the monitoring image tunnel contour position smoothness comprises a first surrounding monitoring image tunnel contour position smoothness, a second surrounding monitoring image tunnel contour position smoothness, a third surrounding monitoring image tunnel contour position smoothness, a fourth surrounding monitoring image tunnel contour position smoothness, a fifth surrounding monitoring image tunnel contour position smoothness, a sixth surrounding monitoring image tunnel contour position smoothness, a seventh surrounding monitoring image tunnel contour position smoothness and an eighth surrounding monitoring image tunnel contour position smoothness; the flatness of the tunnel contour position of the monitoring image represents different degrees of colors of the contour position and a plurality of positions around the contour position in the monitoring image;
and obtaining a tunnel contour position stability set of the monitoring images of a plurality of tunnel contour positions through a plurality of times of calculation. The monitoring image tunnel contour position smoothness set comprises a plurality of tunnel contour positions and corresponding monitoring image tunnel contour position smoothness.
The method for calculating the stability of the tunnel contour position of the monitoring image is the same as the method for calculating the stability of the tunnel contour position of the background image. The monitoring image tunnel contour position smoothness set includes a plurality of tunnel contour positions and corresponding monitoring image tunnel contour position smoothness, and as in this embodiment, the portion of the current monitoring tunnel contour position smoothness set is [ (12,12,18,42,189,90,18,42,189,76), (13,12,90, 18,42,189) ]. The meaning of the element in (13,12,90, 18,42,189) is: line 13, column 12, line 90, monitor image tunnel contour position flatness at the first periphery of (13,12), 18, monitor image tunnel contour position flatness at the second periphery of (13,12), 42, monitor image tunnel contour position flatness at the third periphery of (13,12), 189, monitor image tunnel contour position flatness at the fourth periphery of (13,12), 90, monitor image tunnel contour position flatness at the fifth periphery of (13,12), 18, monitor image tunnel contour position flatness at the sixth periphery of (13,12), 42, monitor image tunnel contour position flatness at the seventh periphery of (13,12), 189, monitor image tunnel contour position flatness at the eighth periphery of (13, 12).
By the method, the tunnel contour position in the background image is obtained, because the tunnel contour is difficult to detect after the monitoring image is covered by smoke. However, the tunnel contour position is a position with large change in the background image, the change degree of the current monitoring image after being covered by smoke and the surrounding position is greatly reduced, and the change is easier to identify.
Optionally, the obtaining of the coverage similarity based on the background image tunnel contour position smoothness set and the monitoring image tunnel contour position smoothness set includes:
obtaining a smoothness difference set; the stability difference value set is an absolute value of a difference of the stability of the tunnel contour position of the background image in the background image tunnel contour position stability set which subtracts the position corresponding to the stability of the tunnel contour position of the monitoring image in the monitoring image tunnel contour position stability set;
obtaining a number of stationarities, wherein the number of stationarities is the number smaller than a stationarities threshold in the stationarities difference set; the stationary number represents the number of ambiguous locations from the surrounding locations in all tunnel contour locations;
and obtaining the coverage similarity, wherein the coverage similarity is the product of the stable number divided by the number of the tunnel contour positions.
The threshold value of the plateau of the present embodiment is 20.
By the method, some contour positions are obtained, and whether the contour parts are covered or not is judged better because the color jump degree of the contour parts is large. The accuracy is greatly increased. By obtaining a change in color around the contour, the color jump becomes progressively smaller when masked. And obtaining the phase difference value of the color jump degree of the current image and the background image. The concentration of the smoke can be expressed, and the coverage of the smoke is obtained at the same time.
Optionally, obtaining the overall blur degree of the monitored image based on the current monitored image includes:
acquiring a turnover monitoring image; the overturning monitoring image is an image obtained by overturning the current monitoring image by taking the center as an axis;
obtaining the ambiguity; the ambiguity represents a color difference between two positions in the monitored image corresponding to the center as an axis.
The fuzzy degree is obtained by the following formula calculation mode:
Figure 690312DEST_PATH_IMAGE009
wherein the content of the first and second substances,
Figure 755980DEST_PATH_IMAGE010
in order to be said degree of ambiguity, the degree of ambiguity is,
Figure 624710DEST_PATH_IMAGE011
for the pixel values of the R channel in the contour position of the monitoring image,
Figure 175777DEST_PATH_IMAGE012
pixel values of an R channel in a position around the contour of the reversed monitoring image.
Figure 443948DEST_PATH_IMAGE013
For the pixel values of the G channel in the contour position of the monitoring image,
Figure 249224DEST_PATH_IMAGE014
pixel values of a G channel in a position around the contour of the reversed monitoring image.
Figure 944647DEST_PATH_IMAGE015
For the pixel values of the B channel in the contour position of the monitoring image,
Figure 717431DEST_PATH_IMAGE016
pixel values of a B channel in a position around the contour of the reversed monitoring image.
And normalizing the fuzzy degree to obtain the overall fuzzy degree of the monitoring image.
Wherein the degree of blurring is normalized by a softmax function.
By the method, the difference between the current monitoring image and the background image at the tunnel contour is calculated, the fuzzy degree between the tunnels is also calculated, and the two images are judged together, so that the judgment of smoke is greatly enhanced.
Example 2
Based on the tunnel fire monitoring method, the embodiment of the invention also provides a tunnel fire fighting system detection system, which comprises an acquisition module, a tunnel contour acquisition module, a background image tunnel contour position smoothness set acquisition module, a monitoring image tunnel contour position smoothness set acquisition module, a smoke judgment module and an alarm module.
The acquisition module is used for acquiring monitoring images in the monitoring equipment in the tunnel. The monitoring image comprises a background image and a current monitoring image. The background image represents a background image when no smoke is present in the tunnel.
And after the monitoring image is collected, inputting the monitoring image into a tunnel contour acquisition module.
The tunnel contour acquisition module is used for obtaining the position of the tunnel contour. And obtaining the tunnel contour position based on the background image.
And inputting the tunnel contour position into a background image tunnel contour position smoothness set acquisition module.
The background image tunnel contour position stability set acquisition module is used for acquiring a background image tunnel contour position stability set. And obtaining a background image tunnel contour position smoothness set based on the background image and the tunnel contour position. The background image tunnel contour position smoothness set comprises a plurality of background image tunnel contour position smoothness, and the background image tunnel contour position smoothness represents different degrees of colors at tunnel contour positions in a background image and 8 surrounding positions.
And inputting the tunnel contour position into a monitoring image tunnel contour position smoothness set acquisition module.
The monitoring image tunnel contour position stability set acquisition module is used for acquiring a monitoring image tunnel contour position stability set. And obtaining a monitored image tunnel contour position smoothness set based on the current monitored image and the tunnel contour position. The monitoring image tunnel contour position smoothness set comprises a plurality of monitoring image tunnel contour position stabilities. The tunnel contour position smoothness of the multiple monitoring images represents different degrees of colors at the tunnel contour position in the current monitoring image from the colors of the surrounding positions.
And inputting the monitoring image tunnel contour position smoothness set and the background image tunnel contour position smoothness set into a smoke judgment module.
The smoke judging module is used for judging whether smoke exists in the monitoring image. And obtaining coverage similarity based on the background image tunnel contour position smoothness set and the monitoring image tunnel contour position smoothness set. The coverage similarity represents the degree of the coverage of the current monitoring image by smoke at the contour position of the tunnel; and obtaining the overall fuzziness of the monitored image based on the current monitored image. And if the coverage similarity is larger than a coverage threshold value and the overall fuzziness of the monitoring image is smaller than a fuzziness threshold value, determining that the detection result is smoke.
The alarm module is used for generating alarm information.
The specific manner in which the respective modules perform operations has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
The method can also be used for detecting the water drop based on the current monitoring image and a water drop detection algorithm. The characteristics of the water drop: shape, texture, transparent color. And detecting the water drop by using a lens, extracting the water drop (convolving by using the water drop) in the whole image, and adopting a Yolov3 algorithm trained by using a plurality of water drop images. And if the current monitoring image has water drops, judging the current monitoring image to be fog. And if the current monitoring image has water drops, judging the current monitoring image to be smoke. In order to prevent the tunnel contour from being covered by the vehicle passing through the monitoring image, the vehicle can be detected firstly, the position of the vehicle can be excluded, and the condition of other positions can be detected. And detecting the vehicle based on the monitoring image to obtain a vehicle covering position. And acquiring the contour position of the partial tunnel and carrying out smoothness detection on the partial position. The partial tunnel profile positions are positions of the tunnel profile positions other than the vehicle covering position.
Averaging the stability of the tunnel contour position of the background image to obtain the uniform stability of the tunnel contour position of the background image;
the uniform smoothness of the tunnel contour position of the background image is obtained by the following formula calculation method:
Figure 789292DEST_PATH_IMAGE022
wherein, the first and the second end of the pipe are connected with each other,
Figure 774041DEST_PATH_IMAGE023
the tunnel contour position of the background image is uniform and stable;
Figure 109208DEST_PATH_IMAGE024
the tunnel contour position smoothness is a first surrounding background image;
Figure DEST_PATH_IMAGE025
the tunnel contour position smoothness of the second surrounding background image is obtained;
Figure 385599DEST_PATH_IMAGE026
the smoothness of the tunnel contour position of the third surrounding background image is obtained;
Figure 261152DEST_PATH_IMAGE027
the tunnel contour position smoothness of a fourth surrounding background image is obtained;
Figure 290287DEST_PATH_IMAGE028
the tunnel contour position smoothness of a fifth surrounding background image is obtained;
Figure 593093DEST_PATH_IMAGE029
setting the tunnel contour position smoothness of a sixth surrounding background image;
Figure 91201DEST_PATH_IMAGE030
the smoothness of the tunnel contour position of the seventh surrounding background image is obtained;
Figure 504865DEST_PATH_IMAGE031
and setting the tunnel contour position smoothness as the eighth surrounding background image.
An embodiment of the present invention further provides an electronic device, as shown in fig. 3, including a memory 504, a processor 502 and a computer program stored in the memory 504 and running on the processor 502, where the processor 502 executes the program to implement the steps of any one of the foregoing tunnel fire monitoring methods.
Where in fig. 3 a bus architecture (represented by bus 500) is shown, bus 500 may include any number of interconnected buses and bridges, and bus 500 links together various circuits including one or more processors, represented by processor 502, and memory, represented by memory 504. The bus 500 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 505 provides an interface between the bus 500 and the receiver 501 and transmitter 503. The receiver 501 and the transmitter 503 may be the same element, i.e. a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 502 is responsible for managing the bus 500 and general processing, and the memory 504 may be used for storing data used by the processor 502 in performing operations.
Embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of any one of the above-mentioned tunnel fire monitoring methods and the above-mentioned related data.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system is apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in an apparatus according to an embodiment of the invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

Claims (10)

1. A method for monitoring fire in a tunnel is characterized by comprising the following steps:
collecting a monitoring image in monitoring equipment in a tunnel; the monitoring image comprises a background image and a current monitoring image; the background image is the background image when no smoke exists in the tunnel;
obtaining a tunnel contour position based on the background image;
obtaining a background image tunnel contour position smoothness set based on the background image and the tunnel contour position; the background image tunnel contour position smoothness set comprises a plurality of background image tunnel contour position stabilities, and the background image tunnel contour position stabilities represent different degrees of colors at tunnel contour positions in a background image and 8 surrounding positions;
obtaining a monitored image tunnel contour position smoothness set based on the current monitored image and the tunnel contour position; the monitoring image tunnel contour position smoothness set comprises a plurality of monitoring image tunnel contour position stabilities; the tunnel contour position smoothness of the multiple monitoring images represents different degrees of colors at the tunnel contour position in the current monitoring image and colors at the surrounding positions;
obtaining coverage similarity based on the background image tunnel contour position smoothness set and the monitoring image tunnel contour position smoothness set; the coverage similarity represents the degree of coverage of the current monitoring image by smoke at the tunnel contour position;
obtaining the overall fuzziness of the monitored image based on the current monitored image;
if the coverage similarity is larger than a coverage threshold value and the overall fuzziness of the monitoring image is smaller than a fuzziness threshold value, determining that the detection result is smoke; and generating alarm information.
2. The method for monitoring tunnel fire according to claim 1, wherein the obtaining of the tunnel contour position based on the background image comprises:
graying the background image to obtain a background grayscale image;
obtaining a first background gray difference value; the first background gray difference value is the difference of the first background gray value minus one of eight gray values around the first background gray value; the first background gray value represents a first gray value from the top left corner in the background gray image;
if the first background gray level difference value is larger than the difference threshold value, taking the position of the first background gray level value as a contour point; and obtaining all contour points in the background image by comparing the difference of the gray value in the background image minus one of the plurality of surrounding gray values with the difference threshold value for multiple times.
3. The method according to claim 1, wherein the obtaining a background image tunnel contour position smoothness set based on the background image and the tunnel contour position comprises:
obtaining the tunnel contour position smoothness of a first peripheral background image, wherein the tunnel contour position smoothness of the first peripheral background image represents the difference value of the RGB value of one position of the tunnel contour positions in the background image and one position of 8 positions around the tunnel contour positions;
the tunnel contour position smoothness of the first surrounding background image is obtained by the following formula:
Figure 384121DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE002
for the tunnel contour position smoothness of the first surrounding background image,
Figure DEST_PATH_IMAGE003
for the pixel value of the R channel in the contour position of the background image,
Figure DEST_PATH_IMAGE004
pixel values of an R channel in a position around the outline of the background image;
Figure DEST_PATH_IMAGE005
for the pixel value of the G channel in the contour position of the background image,
Figure DEST_PATH_IMAGE006
is a stand forPixel values of a G channel in a position around the contour of the background image;
Figure DEST_PATH_IMAGE007
for the pixel value of the B channel in the contour position of the background image,
Figure DEST_PATH_IMAGE008
pixel values of a B channel in a position around the outline of the background image;
obtaining the stability of the tunnel contour position of the background image; the background image tunnel contour position smoothness comprises a first surrounding background image tunnel contour position smoothness, a second surrounding background image tunnel contour position smoothness, a third surrounding background image tunnel contour position smoothness, a fourth surrounding background image tunnel contour position smoothness, a fifth surrounding background image tunnel contour position smoothness, a sixth surrounding background image tunnel contour position smoothness, a seventh surrounding background image tunnel contour position smoothness and an eighth surrounding background image tunnel contour position smoothness;
obtaining a background image tunnel contour position stability set of a plurality of tunnel contour positions through a plurality of times of calculation; the background image tunnel contour position smoothness set comprises a plurality of tunnel contour positions and corresponding background image tunnel contour position smoothness.
4. The method for monitoring tunnel fire according to claim 1, wherein the obtaining a set of smoothness of tunnel contour positions of the monitored images based on the current monitored images and the tunnel contour positions comprises:
acquiring the tunnel contour position smoothness of a first peripheral monitoring image, wherein the tunnel contour position smoothness of the first peripheral monitoring image represents the difference value of the RGB value of one position of the tunnel contour positions in the monitoring image and one position of 8 positions around the tunnel contour positions;
obtaining the position stability of the tunnel contour of the monitoring image; the monitoring image tunnel contour position smoothness comprises a first surrounding monitoring image tunnel contour position smoothness, a second surrounding monitoring image tunnel contour position smoothness, a third surrounding monitoring image tunnel contour position smoothness, a fourth surrounding monitoring image tunnel contour position smoothness, a fifth surrounding monitoring image tunnel contour position smoothness, a sixth surrounding monitoring image tunnel contour position smoothness, a seventh surrounding monitoring image tunnel contour position smoothness and an eighth surrounding monitoring image tunnel contour position smoothness; the flatness of the tunnel contour position of the monitoring image represents different degrees of colors of the contour position and a plurality of positions around the contour position in the monitoring image;
obtaining a monitoring image tunnel contour position stability set of a plurality of tunnel contour positions through multiple calculations; the monitoring image tunnel contour position smoothness set comprises a plurality of tunnel contour positions and corresponding monitoring image tunnel contour position smoothness.
5. The method for monitoring tunnel fire according to claim 1, wherein the obtaining coverage similarity based on the background image tunnel contour position smoothness set and the monitoring image tunnel contour position smoothness set comprises:
obtaining a smoothness difference set; the stability difference value set is an absolute value of a difference of the stability of the tunnel contour position of the background image in the background image tunnel contour position stability set which subtracts the position corresponding to the stability of the tunnel contour position of the monitoring image in the monitoring image tunnel contour position stability set;
obtaining a number of stationarities, wherein the number of stationarities is the number smaller than a stationarities threshold in the stationarities difference set; the stationary number represents the number of ambiguous locations from the surrounding locations in all tunnel contour locations;
and obtaining the coverage similarity, wherein the coverage similarity is the product of the stable number divided by the number of the tunnel contour positions.
6. The method for monitoring tunnel fire according to claim 1, wherein the obtaining of the overall ambiguity of the monitored image based on the current monitored image comprises:
acquiring a turnover monitoring image; the overturning monitoring image is an image obtained by overturning the current monitoring image by taking the center as an axis;
obtaining the fuzzy degree; the ambiguity represents a color difference between two positions corresponding to the axis of the center in the monitored image;
the fuzzy degree is obtained by the following formula calculation mode:
Figure DEST_PATH_IMAGE009
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE010
in order to be said degree of blurring,
Figure DEST_PATH_IMAGE011
for the pixel values of the R channel in the contour position of the monitoring image,
Figure DEST_PATH_IMAGE012
pixel values of an R channel in the contour surrounding position of the turnover monitoring image are obtained;
Figure DEST_PATH_IMAGE013
for the pixel values of the G channel in the contour position of the monitoring image,
Figure DEST_PATH_IMAGE014
pixel values of G channels in the peripheral position of the outline of the turnover monitoring image are obtained;
Figure DEST_PATH_IMAGE015
for the pixel values of the B channel in the contour position of the monitoring image,
Figure DEST_PATH_IMAGE016
for the pixel value of B channel in the contour surrounding position of the reversed monitoring image(ii) a And normalizing the fuzzy degree to obtain the overall fuzzy degree of the monitoring image.
7. A tunnel fire extinguishing system detecting system, characterized by, includes:
an acquisition module: collecting a monitoring image in monitoring equipment in a tunnel; the monitoring image comprises a background image and a current monitoring image; the background image represents a background image when no smoke exists in the tunnel;
a tunnel contour acquisition module: obtaining a tunnel contour position based on the background image;
the scene image tunnel contour position smoothness set acquisition module comprises: obtaining a background image tunnel contour position smoothness set based on the background image and the tunnel contour position; the background image tunnel contour position smoothness set comprises a plurality of background image tunnel contour position stabilities, and the background image tunnel contour position stabilities represent different degrees of colors at tunnel contour positions in a background image and 8 surrounding positions;
the monitoring image tunnel contour position smoothness set acquisition module comprises: obtaining a monitored image tunnel contour position smoothness set based on the current monitored image and the tunnel contour position; the monitoring image tunnel contour position smoothness set comprises a plurality of monitoring image tunnel contour position stabilities; the tunnel contour position smoothness of the multiple monitoring images represents different degrees of colors at the tunnel contour position in the current monitoring image and colors at the surrounding positions;
a smoke judgment module: obtaining coverage similarity based on the background image tunnel contour position smoothness set and the monitoring image tunnel contour position smoothness set; the coverage similarity represents the degree of coverage of the current monitoring image by smoke at the tunnel contour position; obtaining the overall fuzziness of the monitored image based on the current monitored image; if the coverage similarity is larger than a coverage threshold value and the overall fuzziness of the monitoring image is smaller than a fuzziness threshold value, determining that the detection result is smoke;
an alarm module: and generating alarm information.
8. The system of claim 7, wherein the obtaining of the tunnel contour position based on the background image comprises:
graying the background image to obtain a background grayscale image;
obtaining a first background gray difference value; the first background gray difference value is the difference of the first background gray value minus one of eight gray values around the first background gray value; the first background gray value represents a first gray value from the upper left corner in the background gray image;
if the first background gray scale difference value is larger than the difference threshold value, taking the position of the first background gray scale value as a contour point; and obtaining all contour points in the background image by comparing the difference of the gray value in the background image minus one of the plurality of surrounding gray values with the difference threshold value for multiple times.
9. The system of claim 7, wherein the obtaining a background image tunnel contour position smoothness set based on the background image and the tunnel contour position comprises:
obtaining tunnel contour position smoothness of a first peripheral background image, wherein the tunnel contour position smoothness of the first peripheral background image represents a difference value of RGB values of one position of tunnel contour positions in a background image and one position of 8 positions around the tunnel contour positions;
the tunnel contour position smoothness of the first surrounding background image is obtained by the following formula calculation method:
Figure 878425DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 923742DEST_PATH_IMAGE002
the tunnel contour position smoothness of the first surrounding background image,
Figure 37060DEST_PATH_IMAGE003
for the pixel value of the R channel in the contour position of the background image,
Figure 54695DEST_PATH_IMAGE004
pixel values of an R channel in a position around the outline of the background image;
Figure 345999DEST_PATH_IMAGE005
for the pixel value of the G channel in the contour position of the background image,
Figure 878611DEST_PATH_IMAGE006
pixel values of a G channel in a position around the outline of the background image;
Figure 546353DEST_PATH_IMAGE007
for the pixel value of the B channel in the contour position of the background image,
Figure 667762DEST_PATH_IMAGE008
pixel values of a B channel in a position around the outline of the background image;
obtaining the stability of the tunnel contour position of the background image; the background image tunnel contour position smoothness comprises a first surrounding background image tunnel contour position smoothness, a second surrounding background image tunnel contour position smoothness, a third surrounding background image tunnel contour position smoothness, a fourth surrounding background image tunnel contour position smoothness, a fifth surrounding background image tunnel contour position smoothness, a sixth surrounding background image tunnel contour position smoothness, a seventh surrounding background image tunnel contour position smoothness and an eighth surrounding background image tunnel contour position smoothness;
obtaining a background image tunnel contour position stability set of a plurality of tunnel contour positions through a plurality of times of calculation; the background image tunnel contour position smoothness set comprises a plurality of tunnel contour positions and corresponding background image tunnel contour position smoothness.
10. The system of claim 7, wherein the obtaining of the monitored image tunnel contour position smoothness set based on the current monitored image and the tunnel contour position comprises:
acquiring the tunnel contour position smoothness of a first peripheral monitoring image, wherein the tunnel contour position smoothness of the first peripheral monitoring image represents the difference value of the RGB value of one position of the tunnel contour positions in the monitoring image and one position of 8 positions around the tunnel contour positions;
obtaining the stability of the tunnel contour position of the monitoring image; the monitoring image tunnel contour position smoothness comprises a first surrounding monitoring image tunnel contour position smoothness, a second surrounding monitoring image tunnel contour position smoothness, a third surrounding monitoring image tunnel contour position smoothness, a fourth surrounding monitoring image tunnel contour position smoothness, a fifth surrounding monitoring image tunnel contour position smoothness, a sixth surrounding monitoring image tunnel contour position smoothness, a seventh surrounding monitoring image tunnel contour position smoothness and an eighth surrounding monitoring image tunnel contour position smoothness; the flatness of the tunnel contour position of the monitoring image represents different degrees of colors of the contour position and a plurality of positions around the contour position in the monitoring image;
obtaining a monitoring image tunnel contour position stability set of a plurality of tunnel contour positions through multiple calculations; the monitoring image tunnel contour position smoothness set comprises a plurality of tunnel contour positions and corresponding monitoring image tunnel contour position smoothness.
CN202210567872.0A 2022-05-24 2022-05-24 Tunnel fire monitoring method and system Active CN114648852B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210567872.0A CN114648852B (en) 2022-05-24 2022-05-24 Tunnel fire monitoring method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210567872.0A CN114648852B (en) 2022-05-24 2022-05-24 Tunnel fire monitoring method and system

Publications (2)

Publication Number Publication Date
CN114648852A true CN114648852A (en) 2022-06-21
CN114648852B CN114648852B (en) 2022-08-12

Family

ID=81996962

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210567872.0A Active CN114648852B (en) 2022-05-24 2022-05-24 Tunnel fire monitoring method and system

Country Status (1)

Country Link
CN (1) CN114648852B (en)

Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1406366A (en) * 2000-12-28 2003-03-26 西门子建筑技术公司 Video smoke detection system
WO2006091328A2 (en) * 2005-02-18 2006-08-31 Honeywell International, Inc. Camera vision fire detector and system
US20080137906A1 (en) * 2006-12-12 2008-06-12 Industrial Technology Research Institute Smoke Detecting Method And Device
US20080186191A1 (en) * 2006-12-12 2008-08-07 Industrial Technology Research Institute Smoke detecting method and device
CN101339602A (en) * 2008-07-15 2009-01-07 中国科学技术大学 Video frequency fire hazard aerosol fog image recognition method based on light stream method
KR20100010712A (en) * 2008-07-23 2010-02-02 (주)에이치엠씨 Fire detecting system using smoke sensing
CN101751558A (en) * 2009-12-16 2010-06-23 北京智安邦科技有限公司 Tunnel smog detection method based on video and device thereof
CN101908141A (en) * 2010-08-04 2010-12-08 丁天 Video smoke detection method based on mixed Gaussian model and morphological characteristics
CN102136059A (en) * 2011-03-03 2011-07-27 苏州市慧视通讯科技有限公司 Video- analysis-base smoke detecting method
CN102163360A (en) * 2011-03-24 2011-08-24 杭州海康威视系统技术有限公司 Tunnel smoke video detecting method and device
CN103150549A (en) * 2013-02-05 2013-06-12 长安大学 Highway tunnel fire detecting method based on smog early-stage motion features
CN103886598A (en) * 2014-03-25 2014-06-25 北京邮电大学 Tunnel smoke detecting device and method based on video image processing
CN104050478A (en) * 2014-07-09 2014-09-17 湖南大学 Smog detection method and system
CN104794486A (en) * 2015-04-10 2015-07-22 电子科技大学 Video smoke detecting method based on multi-feature fusion
CN110070007A (en) * 2019-04-03 2019-07-30 北京环境特性研究所 Video smoke recognition methods, device, computer equipment and storage medium
CN112132870A (en) * 2020-09-27 2020-12-25 上海应用技术大学 Early smoke detection method for forest fire
CN112291536A (en) * 2020-12-26 2021-01-29 深圳应急者安全技术有限公司 Fire fighting identification method and fire fighting system

Patent Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1406366A (en) * 2000-12-28 2003-03-26 西门子建筑技术公司 Video smoke detection system
WO2006091328A2 (en) * 2005-02-18 2006-08-31 Honeywell International, Inc. Camera vision fire detector and system
CN101248465A (en) * 2005-02-18 2008-08-20 霍尼韦尔国际公司 Camera vision fire detector and system
US20080137906A1 (en) * 2006-12-12 2008-06-12 Industrial Technology Research Institute Smoke Detecting Method And Device
US20080186191A1 (en) * 2006-12-12 2008-08-07 Industrial Technology Research Institute Smoke detecting method and device
CN101339602A (en) * 2008-07-15 2009-01-07 中国科学技术大学 Video frequency fire hazard aerosol fog image recognition method based on light stream method
KR20100010712A (en) * 2008-07-23 2010-02-02 (주)에이치엠씨 Fire detecting system using smoke sensing
CN101751558A (en) * 2009-12-16 2010-06-23 北京智安邦科技有限公司 Tunnel smog detection method based on video and device thereof
CN101908141A (en) * 2010-08-04 2010-12-08 丁天 Video smoke detection method based on mixed Gaussian model and morphological characteristics
CN102136059A (en) * 2011-03-03 2011-07-27 苏州市慧视通讯科技有限公司 Video- analysis-base smoke detecting method
CN102163360A (en) * 2011-03-24 2011-08-24 杭州海康威视系统技术有限公司 Tunnel smoke video detecting method and device
CN103150549A (en) * 2013-02-05 2013-06-12 长安大学 Highway tunnel fire detecting method based on smog early-stage motion features
CN103886598A (en) * 2014-03-25 2014-06-25 北京邮电大学 Tunnel smoke detecting device and method based on video image processing
CN104050478A (en) * 2014-07-09 2014-09-17 湖南大学 Smog detection method and system
CN104794486A (en) * 2015-04-10 2015-07-22 电子科技大学 Video smoke detecting method based on multi-feature fusion
CN110070007A (en) * 2019-04-03 2019-07-30 北京环境特性研究所 Video smoke recognition methods, device, computer equipment and storage medium
CN112132870A (en) * 2020-09-27 2020-12-25 上海应用技术大学 Early smoke detection method for forest fire
CN112291536A (en) * 2020-12-26 2021-01-29 深圳应急者安全技术有限公司 Fire fighting identification method and fire fighting system

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
S. NODA等: "Fire detection in tunnels using an image processing method", 《PROCEEDINGS OF VNIS"94 - 1994 VEHICLE NAVIGATION AND INFORMATION SYSTEMS CONFERENCE》 *
XUEPENG JIANG等: "Experimental study of smoke character in long-sized railway tunnel", 《2010 INTERNATIONAL CONFERENCE ON MECHANIC AUTOMATION AND CONTROL ENGINEERING》 *
朱学慧: "基于图像处理的公路隧道火灾检测技术研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 *
杨伟松: "基于视频的高速公路隧道火灾检测技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
杨孟拓: "基于视频的隧道火灾早期预报技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
雷丹: "公路隧道视频火灾烟雾检测方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Also Published As

Publication number Publication date
CN114648852B (en) 2022-08-12

Similar Documents

Publication Publication Date Title
US6690011B2 (en) Infrared image-processing apparatus
CN109886210B (en) Traffic image recognition method and device, computer equipment and medium
US7936903B2 (en) Method and a system for detecting a road at night
US8810653B2 (en) Vehicle surroundings monitoring apparatus
US9047515B2 (en) Method and system for wildfire detection using a visible range camera
CN112102409B (en) Target detection method, device, equipment and storage medium
US20150086077A1 (en) System and method of alerting a driver that visual perception of pedestrian may be difficult
CN111178245A (en) Lane line detection method, lane line detection device, computer device, and storage medium
CN112036210B (en) Method and device for detecting obstacle, storage medium and mobile robot
CN111932596B (en) Method, device and equipment for detecting camera occlusion area and storage medium
US20220198801A1 (en) Method and system for detecting fire and smoke
Amato et al. Moving cast shadows detection methods for video surveillance applications
CN112562406B (en) Method and device for identifying off-line driving
CN110610137A (en) Method and device for detecting vehicle running state, electronic equipment and storage medium
CN111967396A (en) Processing method, device and equipment for obstacle detection and storage medium
CN111507126B (en) Alarm method and device of driving assistance system and electronic equipment
CN114648852B (en) Tunnel fire monitoring method and system
CN113569812A (en) Unknown obstacle identification method and device and electronic equipment
CN107767366A (en) A kind of transmission line of electricity approximating method and device
CN116863124A (en) Vehicle attitude determination method, controller and storage medium
CN115330657B (en) Ocean exploration image processing method and device and server
JP4176558B2 (en) Vehicle periphery display device
CN111626078A (en) Method and device for identifying lane line
CN112784817B (en) Method, device and equipment for detecting lane where vehicle is located and storage medium
CN113920089A (en) Target detection method and device and electronic controller

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
GR01 Patent grant
GR01 Patent grant