CN115049955A - Fire detection analysis method and device based on video analysis technology - Google Patents
Fire detection analysis method and device based on video analysis technology Download PDFInfo
- Publication number
- CN115049955A CN115049955A CN202210546717.0A CN202210546717A CN115049955A CN 115049955 A CN115049955 A CN 115049955A CN 202210546717 A CN202210546717 A CN 202210546717A CN 115049955 A CN115049955 A CN 115049955A
- Authority
- CN
- China
- Prior art keywords
- image
- fire
- smoke
- video
- images
- 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
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 60
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 238000005516 engineering process Methods 0.000 title claims abstract description 25
- 239000000779 smoke Substances 0.000 claims abstract description 108
- 238000012544 monitoring process Methods 0.000 claims abstract description 71
- 238000000034 method Methods 0.000 claims abstract description 11
- 230000003068 static effect Effects 0.000 claims description 56
- 238000012806 monitoring device Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 12
- 238000009792 diffusion process Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 6
- 230000002093 peripheral effect Effects 0.000 claims description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 abstract description 2
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7847—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content
- G06F16/785—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content using colour or luminescence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7847—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content
- G06F16/786—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content using motion, e.g. object motion or camera motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
Abstract
The invention relates to the technical field of fire detection and analysis, and discloses a fire detection and analysis method and a fire detection and analysis device based on a video analysis technology, wherein the method comprises the steps of collecting a plurality of groups of smoke video images and fire light video images when a fire occurs; the method and the device for detecting and analyzing the fire disaster based on the video analysis technology can be used for detecting and judging the fire disaster in real time in a monitoring environment by acquiring and processing the image characteristics of smoke and fire light and the dynamic change characteristics of the smoke and the fire light as the comparison standards of food fire disaster detection identification and judgment when the fire disaster occurs, reducing the interference of similar objects in the environment on the fire disaster detection, effectively improving the accuracy of the fire disaster identification and judgment and being beneficial to improving the effect of video fire disaster detection.
Description
Technical Field
The invention relates to the technical field of fire detection and analysis, in particular to a fire detection and analysis method and device based on a video analysis technology.
Background
The image fire detection technology is to detect and analyze the flame and smoke in the monitoring image and the temperature in the monitoring environment through a detection picture in the monitoring equipment so as to realize the detection of the image fire.
The existing image fire detection method is used for carrying out static analysis on a flame image and a smoke image so as to identify and judge a fire phenomenon, but the identification accuracy of the image fire detection method is not high, and during detection, objects with similar characteristics in a monitoring environment can be identified by mistake so as to cause the phenomenon of fire detection false alarm, and the accuracy of the image fire detection result is greatly influenced by environmental characteristics.
Disclosure of Invention
In order to solve the problems that the identification accuracy of the image fire detection mode is not high, objects with similar characteristics in a monitoring environment can be identified by mistake during detection, and the accuracy of the image fire detection result is greatly influenced by the environmental characteristics, the image fire detection method is realized by the following technical scheme: a fire detection and analysis method based on a video analysis technology comprises the following specific steps:
s1, collecting a plurality of groups of smoke video images and fire video images when a fire disaster occurs;
s2, acquiring the minimum variation range (D1min, D2min) of the pixel gray values of continuous multi-frame images in the smoke video image, and acquiring the minimum gray value Dmin and the maximum gray value Dmax of the image in the smoke video image;
s3, acquiring the minimum variation range (F1min, F2min) of the pixel gray values of continuous multi-frame images in the fire video image, and acquiring the minimum gray value Fmin and the maximum gray value Fmax of the images in the fire video image;
s4, identifying the motion change parameters of the smoke features relative to the static environment features in the smoke video image, and acquiring the diffusion motion features of the smoke features relative to the static environment features;
s5, identifying motion change parameters of the fire light characteristics relative to the static environment characteristics in the fire light video images, and acquiring swing motion characteristics of the fire light characteristics relative to the static environment characteristics;
s6, detecting the environmental space by using the monitoring equipment, and analyzing and processing the monitoring picture of the monitoring equipment in real time by using a video analysis technology;
s7, judging whether the analyzed image pixel is in (D1min, D2min) or (F1min, F2min) according to the processed image pixel, judging that no fire hazard exists in a monitoring picture of the monitoring equipment when the image pixel does not fall into (D1min, D2min) or (F1min, F2min), and otherwise, executing S8;
and S8, judging whether the smoke features in the dynamic images accord with the diffusion motion features of the smoke features relative to the static environment features or not according to the processed dynamic images, or judging whether the fire light features in the dynamic images accord with the swing motion features of the fire light features relative to the static environment features or not, judging whether a fire disaster occurs in the monitoring pictures of the monitoring equipment or not if the fire light features in the dynamic images accord with the swing motion features of the fire light features relative to the static environment features, and otherwise, judging that no fire disaster exists in the monitoring pictures of the monitoring equipment.
Further, in S2, the method for acquiring the gray scale value of the smoke video image includes:
s201, obtaining multiple groups of continuous multi-frame images of the smoke video images within a period of continuous time;
s202, processing the multi-frame images of each group of smoke video images to obtain the gray value D of each frame of image pixel;
s203, recording the change range of the pixel gray level value of continuous multi-frame images (D1, D2), and recording the change range of the pixel gray level value of the continuous multi-frame images in a plurality of groups of smoke video images;
s204, determining the minimum variation range (D1min, D2min) of the pixel gray value of the continuous multi-frame image, and determining the minimum gray value Dmin and the maximum gray value Dmax of the image in the smoke video image.
Further, in S3, the method for obtaining the gray scale value of the fire video image includes:
s301, acquiring multiple groups of continuous multi-frame images of the flare video images within a period of continuous time;
s302, processing the multi-frame images of each group of the flare video images to obtain a gray value F of each frame of image pixel;
s303, recording the change range of the pixel gray level values of continuous multi-frame images (F1, F2), and recording the change range of the pixel gray level values of the continuous multi-frame images in a plurality of groups of the flare video images;
s304, determining the minimum variation range (F1min, F2min) of the pixel gray values of the continuous multi-frame images, and determining the minimum gray value Fmin and the maximum gray value Fmax of the images in the flare video images.
Further, the specific step of acquiring the diffusion motion characteristic of the smoke characteristic relative to the static environment characteristic in S4 includes:
s401, extracting a dynamic smoke image containing peripheral static environment characteristics in the smoke video image, and acquiring continuous multi-frame images of the dynamic smoke image;
s402, marking static environment characteristics and smoke characteristics in continuous multi-frame images;
s403, processing continuous multi-frame images by image segmentation to obtain static environment characteristic images and smoke characteristic images;
s404, identifying the motion change parameters of the smoke features relative to the static environment features in the dynamic smoke image, and obtaining the diffusion motion features of the smoke features relative to the static environment features.
Further, the specific step of acquiring the swing motion characteristic of the flare characteristic relative to the static environment characteristic in S5 includes:
s501, extracting a dynamic flare image containing peripheral static environment characteristics in the flare video image, and acquiring continuous multi-frame images of the dynamic flare image;
s502, marking static environment characteristics and fire characteristics in continuous multi-frame images;
s503, processing continuous multi-frame images by image segmentation to obtain static environment characteristic images and flare characteristic images;
s504, identifying the motion change parameters of the fire light characteristics relative to the static environment characteristics in the dynamic fire light image, and obtaining the swing motion characteristics of the fire light characteristics relative to the static environment characteristics.
Further, the gray value D of the frame image in the smoke video image in S202 and the gray value F of the frame image in the flare video image in S302 are:
where R, G, B are color component values.
Further, the method for identifying the smoke characteristic motion change parameter in S404 and the flare characteristic motion change parameter in S504 includes:
dividing each frame of image in the dynamic image into blocks with the size of M multiplied by N pixels, in a matching window with the size of (N +2w ), w is a residual value of the matching window relative to the boundary of the image, comparing a current block with a corresponding block in a previous frame, finding out the best match based on a matching standard to obtain a substitute position of the current block, combining the position changes of the blocks with smoke characteristics or fire characteristics to obtain the operation change parameters of the smoke characteristics or the fire characteristics in continuous multi-frame images of the dynamic image, wherein the matching standard is minimum Mean Square Error (MSE) or Minimum Absolute Error (MAE):
where f (m, n) denotes that the current block is located in the current frame as (m, n), and f (m + i, n + j) denotes that the current block is located in the previous frame as (m + i, n + j).
A fire detection device based on a video analysis technology comprises a monitoring device and a computer processing device, wherein the monitoring device is connected with the computer device through a network, an image recognition module and a dynamic video extraction module are arranged in the computer device, the image recognition module is used for recognizing and acquiring a smoke characteristic image or a fire characteristic image appearing in a monitoring picture of the monitoring device, and the dynamic video extraction module is used for extracting a dynamic image of the smoke characteristic or the fire characteristic appearing in the monitoring picture of the monitoring device;
the computer equipment is provided with a gray value calculation module and a video image dynamic characteristic analysis module, wherein the gray value calculation module is used for calculating the gray value of the smoke characteristic image or the fire characteristic image acquired by the image recognition module, and the video image dynamic characteristic analysis module is used for processing and analyzing the motion characteristics of the smoke characteristic or the fire characteristic in the smoke characteristic or the fire characteristic dynamic image extracted by the dynamic video extraction module.
Furthermore, early warning devices are arranged in the monitoring equipment and the computer equipment, and the early warning devices are connected with the video image dynamic characteristic analysis module through electric signals.
Furthermore, a driving adjusting module is arranged inside the monitoring device and used for controlling the monitoring angle and the monitoring focal length of the monitoring device.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the fire detection and analysis method and device based on the video analysis technology, when a fire disaster occurs, the image characteristics of smoke and fire light and the dynamic change characteristics of the smoke and the fire light are used as the comparison standards for food fire detection identification and judgment, real-time fire detection can be performed on a monitored environment, the interference of similar objects in the environment on fire detection is reduced, the accuracy of fire identification and judgment can be effectively improved, and the video fire detection effect is favorably improved.
2. According to the fire detection and analysis method and device based on the video analysis technology, through the network connection between the monitoring equipment and the computer equipment, the matched use of the image recognition module and the gray value calculation module in the computer equipment and the matched use of the dynamic video extraction module and the video image dynamic feature analysis module, the real-time fire detection can be carried out on the monitoring area of the monitoring equipment, and the fire hazard can be found in time.
Drawings
FIG. 1 is a flow chart of a method of fire detection and analysis according to the present invention;
FIG. 2 is a schematic structural diagram of a fire detection and analysis device according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the fire detection and analysis method and the device based on the video analysis technology is as follows:
referring to fig. 1, a fire detection and analysis method based on video analysis technology includes the following steps:
s1, collecting a plurality of groups of smoke video images and fire video images when a fire disaster occurs;
s2, obtaining the minimum variation range (D1min, D2min) of the pixel gray value of continuous multi-frame images in the smoke video image, and obtaining the minimum gray value Dmin and the maximum gray value Dmax of the images in the smoke video image:
s201, obtaining continuous multi-frame images of a plurality of groups of smoke video images in a period of continuous time;
s202, processing the multi-frame images of each group of smoke video images, and acquiring the gray value D of each frame of image pixel:
where R, G, B are color component values.
S203, recording the change range of the pixel gray level value of the continuous multi-frame images (D1, D2), and recording the change range of the pixel gray level value of the continuous multi-frame images in the multiple groups of smoke video images;
s204, determining the minimum variation range (D1min, D2min) of the pixel gray value of the continuous multi-frame image, and determining the minimum gray value Dmin and the maximum gray value Dmax of the image in the smoke video image.
S3, acquiring the minimum variation range (F1min, F2min) of the pixel gray values of continuous multi-frame images in the fire video image, and acquiring the minimum gray value Fmin and the maximum gray value Fmax of the images in the fire video image:
s301, acquiring continuous multi-frame images of a plurality of groups of flare video images in a continuous time;
s302, processing the multi-frame images of each group of the flare video images, and acquiring the gray value F of each frame of image pixel:
where R, G, B are color component values.
S303, recording the change range of the pixel gray level value of continuous multi-frame images (F1, F2), and recording the change range of the pixel gray level value of the continuous multi-frame images in a plurality of groups of flare video images;
s304, determining the minimum variation range (F1min, F2min) of the pixel gray values of the continuous multi-frame images, and determining the minimum gray value Fmin and the maximum gray value Fmax of the images in the flare video images.
S4, identifying the motion change parameters of the smoke features relative to the static environment features in the smoke video image, and acquiring the diffusion motion features of the smoke features relative to the static environment features:
s401, extracting a dynamic smoke image containing peripheral static environment characteristics in the smoke video image, and acquiring continuous multi-frame images of the dynamic smoke image;
s402, marking static environment characteristics and smoke characteristics in continuous multi-frame images;
s403, processing continuous multi-frame images by image segmentation to obtain static environment characteristic images and smoke characteristic images;
s404, identifying the motion change parameters of the smoke features relative to the static environment features in the dynamic smoke image, and acquiring the diffusion motion features of the smoke features relative to the static environment features:
dividing each frame of image in the dynamic smoke image into blocks with the size of M multiplied by N pixels, in a matching window with the size of (N +2w ), w is a residual value of the matching window relative to the boundary of the image, comparing a current block with a corresponding block in a previous frame, finding out the best match based on a matching standard to obtain a substitution position of the current block, combining the position changes of the blocks with smoke characteristics or fire light characteristics to obtain the operation change parameters of the smoke characteristics or the fire light characteristics in continuous multi-frame images of the dynamic image, wherein the matching standard is minimum Mean Square Error (MSE) or Minimum Absolute Error (MAE):
where f (m, n) denotes that the current block is located in the current frame as (m, n), and f (m + i, n + j) denotes that the current block is located in the previous frame as (m + i, n + j).
S5, identifying the motion change parameters of the fire light characteristics relative to the static environment characteristics in the fire light video images, and acquiring the swing motion characteristics of the fire light characteristics relative to the static environment characteristics:
s501, extracting dynamic flare images containing peripheral static environment characteristics in the flare video images, and acquiring continuous multi-frame images of the dynamic flare images;
s502, marking static environment characteristics and fire light characteristics in continuous multi-frame images;
s503, processing continuous multi-frame images by image segmentation to obtain static environment characteristic images and flare characteristic images;
s504, identifying the motion change parameters of the fire light characteristics relative to the static environment characteristics in the dynamic fire light image, and acquiring the swing motion characteristics of the fire light characteristics relative to the static environment characteristics:
dividing each frame of image in the dynamic flare image into blocks with the size of M multiplied by N pixels, in a matching window with the size of (N +2w ), w is a residual value of the matching window relative to the boundary of the image, comparing a current block with a corresponding block in a previous frame, finding out the best match based on a matching standard to obtain a substitution position of the current block, combining the position changes of the blocks with the smoke characteristics or the flare characteristics to obtain the operation change parameters of the smoke characteristics or the flare characteristics in continuous multi-frame images of the dynamic image, wherein the matching standard is minimum Mean Square Error (MSE) or Minimum Absolute Error (MAE):
where f (m, n) denotes that the current block is located in the current frame as (m, n), and f (m + i, n + j) denotes that the current block is located in the previous frame as (m + i, n + j).
S6, detecting the environmental space by using the monitoring equipment, and analyzing and processing the monitoring picture of the monitoring equipment in real time by using a video analysis technology;
s7, judging whether the analyzed image pixel is in (D1min, D2min) or (F1min, F2min) according to the processed image pixel, judging that no fire hazard exists in a monitoring picture of the monitoring equipment when the image pixel does not fall into (D1min, D2min) or (F1min, F2min), and otherwise, executing S8;
and S8, judging whether the smoke features in the analyzed dynamic images accord with the diffusion motion features of the smoke features relative to the static environment features or not according to the processed dynamic images, or judging whether the fire light features in the analyzed dynamic images accord with the swing motion features of the fire light features relative to the static environment features or not, judging that a fire disaster occurs in the monitoring picture of the monitoring equipment if the smoke features accord with the swing motion features of the fire light features relative to the static environment features, and otherwise, judging that no fire disaster exists in the monitoring picture of the monitoring equipment.
Referring to fig. 2, a fire detection apparatus based on a video analysis technology includes a monitoring device and a computer processing device, the monitoring device is connected to the computer device via a network, an image recognition module and a dynamic video extraction module are disposed in the computer device, the image recognition module is configured to recognize and obtain a smoke characteristic image or a fire characteristic image appearing in a monitoring picture of the monitoring device, and the dynamic video extraction module is configured to extract a dynamic image of the smoke characteristic or the fire characteristic appearing in the monitoring picture of the monitoring device;
the computer equipment is provided with a gray value calculation module and a video image dynamic characteristic analysis module, wherein the gray value calculation module is used for calculating the gray value of the smoke characteristic image or the fire characteristic image acquired by the image recognition module, and the video image dynamic characteristic analysis module is used for processing and analyzing the motion characteristics of the smoke characteristic or the fire characteristic in the smoke characteristic or the fire characteristic dynamic image extracted by the dynamic video extraction module.
The monitoring equipment and the computer equipment are both provided with early warning devices, the early warning devices are in electric signal connection with the video image dynamic characteristic analysis module, and the monitoring equipment is internally provided with a driving adjustment module which is used for controlling the monitoring angle and the monitoring focal length of the monitoring equipment.
The working principle is as follows:
the monitoring device is used for monitoring an environmental space needing to be monitored in real time, a picture monitored by the monitoring device can be transmitted to the computer device in real time through the network system, the image recognition module in the computer device can recognize and acquire a smoke characteristic image or a fire characteristic image appearing in the monitoring picture of the monitoring device, and the gray value calculation module can calculate the gray value of the smoke characteristic image or the fire characteristic image acquired by the image recognition module, so that whether the smoke characteristic image or the fire characteristic image exists in the monitoring picture or not is recognized.
When the smoke characteristic image or the fire characteristic image appears in the monitoring image, the dynamic video extraction module can extract the dynamic image of the smoke characteristic or the fire characteristic appearing in the monitoring picture of the monitoring equipment, the video image dynamic characteristic analysis module can process and analyze the motion characteristic of the smoke characteristic or the fire characteristic in the smoke characteristic or the fire characteristic dynamic image extracted by the dynamic video extraction module, and whether the smoke characteristic image or the fire characteristic image identified by the image identification module is real or not is judged, so that whether a fire disaster exists in the monitoring area of the monitoring equipment or not is judged.
When a fire disaster exists, the video image dynamic characteristic analysis module transmits information to the monitoring equipment and the early warning device in the computer equipment through the electric signal, the early warning device gives out an alarm, and meanwhile, the driving adjusting module in the monitoring equipment can control the monitoring angle of the monitoring equipment and adjust the monitoring focal length, so that the details of the fire disaster in the monitoring area of the monitoring equipment can be further mastered.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A fire detection and analysis method based on a video analysis technology is characterized in that: the method comprises the following specific steps:
s1, collecting a plurality of groups of smoke video images and fire video images when a fire disaster occurs;
s2, acquiring the minimum variation range (D1min, D2min) of the pixel gray values of continuous multi-frame images in the smoke video image, and acquiring the minimum gray value Dmin and the maximum gray value Dmax of the image in the smoke video image;
s3, acquiring the minimum variation range (F1min, F2min) of the pixel gray values of continuous multi-frame images in the fire video image, and acquiring the minimum gray value Fmin and the maximum gray value Fmax of the images in the fire video image;
s4, identifying the motion change parameters of the smoke features relative to the static environment features in the smoke video image, and acquiring the diffusion motion features of the smoke features relative to the static environment features;
s5, identifying motion change parameters of the fire light characteristics relative to the static environment characteristics in the fire light video images, and acquiring swing motion characteristics of the fire light characteristics relative to the static environment characteristics;
s6, detecting the environmental space by using the monitoring equipment, and analyzing and processing the monitoring picture of the monitoring equipment in real time by using a video analysis technology;
s7, judging whether the analyzed image pixel is in (D1min, D2min) or (F1min, F2min) according to the processed image pixel, judging that no fire hazard exists in a monitoring picture of the monitoring equipment when the image pixel does not fall into (D1min, D2min) or (F1min, F2min), and otherwise, executing S8;
and S8, judging whether the smoke features in the dynamic images accord with the diffusion motion features of the smoke features relative to the static environment features or not according to the processed dynamic images, or judging whether the fire light features in the dynamic images accord with the swing motion features of the fire light features relative to the static environment features or not, judging whether a fire disaster occurs in the monitoring pictures of the monitoring equipment or not if the fire light features in the dynamic images accord with the swing motion features of the fire light features relative to the static environment features, and otherwise, judging that no fire disaster exists in the monitoring pictures of the monitoring equipment.
2. A fire detection and analysis method based on video analysis technology as claimed in claim 1, characterized in that: the method for acquiring the gray value of the smoke video image in the S2 comprises the following steps:
s201, obtaining multiple groups of continuous multi-frame images of the smoke video images within a period of continuous time;
s202, processing the multi-frame images of each group of smoke video images to obtain the gray value D of each frame of image pixel;
s203, recording the change range of the pixel gray level value of continuous multi-frame images (D1, D2), and recording the change range of the pixel gray level value of the continuous multi-frame images in a plurality of groups of smoke video images;
s204, determining the minimum variation range (D1min, D2min) of the pixel gray value of the continuous multi-frame image, and determining the minimum gray value Dmin and the maximum gray value Dmax of the image in the smoke video image.
3. A fire detection and analysis method based on video analysis technology as claimed in claim 2, characterized in that: the method for acquiring the gray value of the fire video image in S3 comprises the following steps:
s301, acquiring continuous multi-frame images of a plurality of groups of flare video images in a period of continuous time;
s302, processing the multi-frame images of each group of the flare video images to obtain a gray value F of each frame of image pixel;
s303, recording the change range of the pixel gray level values of continuous multi-frame images (F1, F2), and recording the change range of the pixel gray level values of the continuous multi-frame images in a plurality of groups of the flare video images;
s304, determining the minimum variation range (F1min, F2min) of the pixel gray values of the continuous multi-frame images, and determining the minimum gray value Fmin and the maximum gray value Fmax of the images in the flare video images.
4. A fire detection and analysis method based on video analysis technology as claimed in claim 1, characterized in that: the specific step of acquiring the diffusion motion characteristic of the smoke characteristic relative to the static environment characteristic in the S4 includes:
s401, extracting a dynamic smoke image containing peripheral static environment characteristics in the smoke video image, and acquiring continuous multi-frame images of the dynamic smoke image;
s402, marking static environment characteristics and smoke characteristics in continuous multi-frame images;
s403, processing continuous multi-frame images by image segmentation to obtain static environment characteristic images and smoke characteristic images;
s404, identifying the motion change parameters of the smoke features relative to the static environment features in the dynamic smoke image, and obtaining the diffusion motion features of the smoke features relative to the static environment features.
5. A fire detection and analysis method based on video analysis technology as claimed in claim 4, characterized in that: the specific step of acquiring the swinging motion characteristic of the flare characteristic relative to the static environment characteristic in the S5 includes:
s501, extracting a dynamic flare image containing peripheral static environment characteristics in the flare video image, and acquiring continuous multi-frame images of the dynamic flare image;
s502, marking static environment characteristics and fire light characteristics in continuous multi-frame images;
s503, processing continuous multi-frame images by image segmentation to obtain static environment characteristic images and flare characteristic images;
s504, identifying the motion change parameters of the fire light characteristics relative to the static environment characteristics in the dynamic fire light image, and obtaining the swing motion characteristics of the fire light characteristics relative to the static environment characteristics.
6. A fire detection and analysis method based on video analysis technology as claimed in claim 3, characterized in that: the gray value D of the frame image in the smoke video image in S202 and the gray value F of the frame image in the flare video image in S302 are:
where R, G, B are color component values.
7. A fire detection and analysis method based on video analysis technology as claimed in claim 5, characterized in that: the identification method of the smoke characteristic motion change parameter in S404 and the flare characteristic motion change parameter in S504 is as follows:
dividing each frame of image in the dynamic image into blocks with the size of M multiplied by N pixels, in a matching window with the size of (N +2w ), w is a residual value of the matching window relative to the boundary of the image, comparing a current block with a corresponding block in a previous frame, finding out the best match based on a matching standard to obtain a substitute position of the current block, combining the position changes of the blocks with smoke characteristics or fire characteristics to obtain the operation change parameters of the smoke characteristics or the fire characteristics in continuous multi-frame images of the dynamic image, wherein the matching standard is minimum Mean Square Error (MSE) or Minimum Absolute Error (MAE):
where f (m, n) denotes that the current block is located in the current frame as (m, n), and f (m + i, n + j) denotes that the current block is located in the previous frame as (m + i, n + j).
8. A fire detection device based on video analysis technology, which is applied to the fire detection and analysis method based on video analysis technology as claimed in any one of claims 1-7, and comprises a monitoring device and a computer processing device, and is characterized in that: the monitoring equipment is connected with the computer equipment through a network, an image recognition module and a dynamic video extraction module are arranged in the computer equipment, the image recognition module is used for recognizing and acquiring a smoke characteristic image or a fire characteristic image appearing in a monitoring picture of the monitoring equipment, and the dynamic video extraction module is used for extracting a dynamic image of the smoke characteristic or the fire characteristic appearing in the monitoring picture of the monitoring equipment;
the computer equipment is provided with a gray value calculation module and a video image dynamic characteristic analysis module, wherein the gray value calculation module is used for calculating the gray value of the smoke characteristic image or the fire characteristic image acquired by the image recognition module, and the video image dynamic characteristic analysis module is used for processing and analyzing the motion characteristics of the smoke characteristic or the fire characteristic in the smoke characteristic or the fire characteristic dynamic image extracted by the dynamic video extraction module.
9. A fire detection system based on video analytics as claimed in claim 8, wherein: and the monitoring equipment and the computer equipment are both provided with early warning devices, and the early warning devices are connected with the video image dynamic characteristic analysis module through electric signals.
10. A fire detection system based on video analysis as claimed in claim 9, wherein: the monitoring device is internally provided with a driving adjusting module, and the driving adjusting module is used for controlling the monitoring angle and the monitoring focal length of the monitoring device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210546717.0A CN115049955A (en) | 2022-05-19 | 2022-05-19 | Fire detection analysis method and device based on video analysis technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210546717.0A CN115049955A (en) | 2022-05-19 | 2022-05-19 | Fire detection analysis method and device based on video analysis technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115049955A true CN115049955A (en) | 2022-09-13 |
Family
ID=83158601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210546717.0A Pending CN115049955A (en) | 2022-05-19 | 2022-05-19 | Fire detection analysis method and device based on video analysis technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115049955A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115376268A (en) * | 2022-10-21 | 2022-11-22 | 山东太平天下智慧科技有限公司 | Monitoring alarm fire-fighting linkage system based on image recognition |
| CN116824166A (en) * | 2023-08-29 | 2023-09-29 | 南方电网数字电网研究院有限公司 | Transmission line smoke identification method, device, computer equipment and storage medium |
-
2022
- 2022-05-19 CN CN202210546717.0A patent/CN115049955A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115376268A (en) * | 2022-10-21 | 2022-11-22 | 山东太平天下智慧科技有限公司 | Monitoring alarm fire-fighting linkage system based on image recognition |
| CN115376268B (en) * | 2022-10-21 | 2023-02-28 | 山东太平天下智慧科技有限公司 | Monitoring alarm fire-fighting linkage system based on image recognition |
| CN116824166A (en) * | 2023-08-29 | 2023-09-29 | 南方电网数字电网研究院有限公司 | Transmission line smoke identification method, device, computer equipment and storage medium |
| CN116824166B (en) * | 2023-08-29 | 2024-03-08 | 南方电网数字电网研究院股份有限公司 | Transmission line smoke identification method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111739250B (en) | Fire detection method and system combining image processing technology and infrared sensor | |
| CN115049955A (en) | Fire detection analysis method and device based on video analysis technology | |
| CN107085714B (en) | Forest fire detection method based on video | |
| CN110059635B (en) | Skin defect detection method and device | |
| CN110096945B (en) | Indoor monitoring video key frame real-time extraction method based on machine learning | |
| KR102391853B1 (en) | System and Method for Processing Image Informaion | |
| KR20210014988A (en) | Image analysis system and method for remote monitoring | |
| CN112183219A (en) | Public safety video monitoring method and system based on face recognition | |
| CN116229668A (en) | Fire disaster positioning system based on infrared video monitoring | |
| CN115272917A (en) | Wire galloping early warning method, device, equipment and medium based on power transmission line | |
| CN113343779A (en) | Environment anomaly detection method and device, computer equipment and storage medium | |
| 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 | |
| CN111899210A (en) | Arc detection method based on image recognition | |
| US20210225146A1 (en) | Image-based disaster detection method and apparatus | |
| KR101806503B1 (en) | Realtime fire sensing method | |
| CN116797977A (en) | Method and device for identifying dynamic target of inspection robot and measuring temperature and storage medium | |
| CN111325073B (en) | Monitoring video abnormal behavior detection method based on motion information clustering | |
| CN111145234A (en) | Fire smoke detection method based on binocular vision | |
| JPH06308256A (en) | Cloudy fog detecting method | |
| CN111935480B (en) | Detection method for image acquisition device and related device | |
| CN111191575B (en) | Naked flame detection method and system based on flame jumping modeling | |
| JP6664078B2 (en) | Three-dimensional intrusion detection system and three-dimensional intrusion detection method | |
| CN113239894A (en) | Crowd sensing system based on crowd behavior analysis assistance | |
| CN112396024A (en) | Forest fire alarm method based on convolutional neural network |
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 |