CN115223105B - Big data based risk information monitoring and analyzing method and system - Google Patents
Big data based risk information monitoring and analyzing method and system Download PDFInfo
- Publication number
- CN115223105B CN115223105B CN202211140046.4A CN202211140046A CN115223105B CN 115223105 B CN115223105 B CN 115223105B CN 202211140046 A CN202211140046 A CN 202211140046A CN 115223105 B CN115223105 B CN 115223105B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- suspected smoke
- area
- dust
- obtaining
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 122
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000000779 smoke Substances 0.000 claims abstract description 142
- 239000000428 dust Substances 0.000 claims abstract description 105
- 238000010276 construction Methods 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 73
- 238000004590 computer program Methods 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000009792 diffusion process Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 description 8
- 238000013523 data management Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000010410 dusting Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect 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
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/269—Analysis of motion using gradient-based methods
-
- 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
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Emergency Management (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of data monitoring and management, in particular to a risk information monitoring and analyzing method and system based on big data. The method calls the monitoring video in the database, and a suspected smoke area, a suspected smoke area position and an operation equipment position of each frame of monitoring image in the monitoring video are identified. And obtaining a first dust raising possibility through the motion characteristics and the area diffusion characteristics of suspected smoke areas between the adjacent frame monitoring images. And obtaining a second dust raising possibility through the distribution relation of the positions between the suspected smoke area and the operation equipment. And judging whether the suspected smoke area is dust by combining the first dust raising possibility and the second dust raising possibility. The invention realizes the distinguishing of smoke and raised dust in the construction site, and can monitor and early-warning and manage the generated fire risk in time.
Description
Technical Field
The invention relates to the technical field of data monitoring and management, in particular to a risk information monitoring and analyzing method and system based on big data.
Background
For monitoring the risk information of the construction site, the fire risk is one of important monitoring targets. For the fire risk, the position of the fire risk is uncertain, and if the fire risk is sensed by using the sensor, a large number of sensors need to be deployed in a building site, so that a large amount of cost is generated, and therefore, the monitoring video is usually used for identifying the risk information in a monitoring management means of the fire risk information, and the acquisition cost of the risk data is reduced.
In the prior art, whether a fire disaster happens currently is judged through open fire identification, the condition that the open fire is shielded is not considered, and the fire risk monitoring is inaccurate. If whether a fire disaster happens is judged through smoke identification, the influence of dust emission on a construction site is not considered, the dust emission is mistakenly identified into smoke, and wrong risk information judgment is carried out.
Disclosure of Invention
In order to solve the above technical problems, the present invention aims to provide a risk information monitoring and analyzing method and system based on big data, and the adopted technical scheme is as follows:
the invention provides a risk information monitoring and analyzing method based on big data, which comprises the following steps:
extracting a monitoring video of a construction site in a database, and acquiring a suspected smoke area, a suspected smoke area position and an operating equipment position of each frame of monitoring image in the monitoring video;
obtaining a suspected smoke motion vector according to the difference of the suspected smoke area positions between the adjacent frame monitoring images; obtaining an image overall motion vector between adjacent frame monitoring images; obtaining the motion difference between the suspected smoke motion vector and the image overall motion vector, obtaining the area difference between the suspected smoke areas between adjacent frame monitoring images, and obtaining a first dust raising possibility according to the motion difference and the area difference;
acquiring a first distance between the suspected smoke area position and the operating equipment position; acquiring a second distance of the position of the operation equipment between adjacent frame monitoring images; obtaining a second dust raising possibility according to the first distance and the second distance;
weighting and summing the first raise dust possibility and the second raise dust possibility to obtain a raise dust possibility; and judging whether the suspected smoke area is dust according to the dust raising possibility, if not, judging the suspected smoke area as a smoke area, and feeding back an early warning signal.
Further, the method for acquiring the suspected smoke area comprises the following steps:
and processing the monitoring image by using a dark channel prior defogging algorithm, identifying the suspected smoke area, and obtaining the position of the suspected smoke area according to the position of the suspected smoke area in the monitoring image.
Further, the method for acquiring the position of the working equipment comprises the following steps:
and acquiring real position information of the operation equipment through a sensor arranged on the operation equipment, and calibrating the real position information into the monitoring image to acquire the position of the operation equipment.
Further, the obtaining a suspected smoke motion vector according to a difference between the positions of the suspected smoke areas between the adjacent frame monitoring images includes:
the method comprises the steps of obtaining a first suspected smoke area edge in a target frame monitoring image, and obtaining a second suspected smoke area edge in a previous frame monitoring image of the target frame monitoring image;
acquiring the minimum distance between each pixel point on the edge of the second suspected smoke area and the edge of the first suspected smoke area; taking each pixel point on the edge of the second suspected smoke area as a vector starting point; taking the pixel point of the vector starting point corresponding to the minimum distance in the first suspected smoke area as a vector terminal point; each group of corresponding vector starting point and vector end point form a motion vector; and selecting a preset number of motion vectors with the maximum mode length as reference motion vectors, and taking the average vector of the reference motion vectors as the suspected smoke motion vector.
Further, the obtaining of the image overall motion vector between the adjacent frame monitoring images includes:
and obtaining the image overall motion vector between the adjacent frame monitoring images through an optical flow method.
Further, the obtaining the motion difference between the suspected smoke motion vector and the image overall motion vector comprises:
and taking the included angle between the suspected smoke motion vector and the whole image motion vector as the motion difference.
Further, the obtaining a first dust raising probability according to the motion difference and the area difference comprises:
and acquiring the ratio of the area difference to the sampling frequency of the monitoring image, and taking the product of the ratio and the reciprocal of the motion difference as the first dust raising possibility.
Further, the obtaining a second dust raising possibility according to the first distance and the second distance comprises:
obtaining the second dust possibility according to a second dust possibility formula, the second dust possibility formula including:
wherein,
as the second dust raising possibility,
for the number of working devices in the monitoring image at time t,
for the time t, the first time in the monitoring image
The work device position of the individual work devices,
time of day in the monitoring image
The work apparatus position of the individual work apparatuses,
is composed of
And with
The distance between the two or more of the two or more,
for the suspected smoke region location in the monitored image at time t,
the position of the operation equipment which is closest to the position of the suspected smoke area in the monitoring image at the time t,
is composed of
And with
In between the distance between the first and second electrodes is less than the predetermined distance,
is the first fitting coefficient.
Further, the determining whether the suspected smoke area is dust according to the dust raising possibility includes:
and if the dust raising possibility is larger than a preset possibility threshold, the suspected smoke area in the monitoring image at the current moment is considered as the dust raising.
The invention also provides a risk information monitoring and analyzing system based on big data, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes any step of the risk information monitoring and analyzing method based on big data when executing the computer program.
The invention has the following beneficial effects:
according to the embodiment of the invention, the monitoring videos in the database are analyzed, so that the layout of data acquisition devices is reduced, and the monitoring cost is reduced. Through extracting and analyzing risk data for suspected smoke areas in the monitored images, the phenomenon of missed identification when open fire identification is used due to the influence of shelters is avoided. According to the embodiment of the invention, the difference of the motion characteristics of the raised dust and the smoke is considered, and the first raised dust possibility is obtained by analyzing the motion characteristics of the suspected smoke area. Further, in consideration of the fact that the generation of the flying dust has a direct correlation with the working equipment, the second flying dust probability is obtained by analyzing the distribution of the suspected smoke region position and the working equipment position. And judging whether the suspected smoke area in the monitoring image is raised dust or not by combining the first raised dust possibility and the second raised dust possibility, thereby realizing accurate fire risk monitoring and early warning.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a risk information monitoring and analyzing method based on big data according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given to a method and system for monitoring and analyzing risk information based on big data according to the present invention, with reference to the accompanying drawings and preferred embodiments, and the detailed description thereof will be given below. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of a risk information monitoring and analyzing method and system based on big data in detail with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a big data-based risk information monitoring and analyzing method according to an embodiment of the present invention is shown, where the method includes:
step S1: and extracting the monitoring video of the construction site in a database, and acquiring the suspected smoke area, the suspected smoke area position and the operating equipment position of each frame of monitoring image in the monitoring video.
In the embodiment of the invention, in order to realize the analysis and management of risk information monitoring, a big data management and analysis platform needs to be established, the monitoring video fed back by each monitoring camera in a construction site is uploaded to the big data management and analysis platform to form a database, when the risk information monitoring and analysis is executed, the real-time monitoring video is called from the database, the monitoring video is analyzed and managed, if the fire risk is identified, an early warning signal is fed back, and the early warning signal is fed back to a worker through the big data management and analysis platform. It should be noted that, in the embodiment of the present invention, the big data management analysis platform may further identify the violation of the operator through a target identification algorithm of the neural network, and also feed back an early warning signal for the generated violation.
When risk information analysis is performed on a monitoring video, a suspected smoke area position and an operation equipment position in each monitoring image need to be identified.
The specific identification method of the suspected smoke area comprises the following steps: and processing the monitoring image by using a dark channel prior defogging algorithm, identifying a suspected smoke area, and obtaining the position of the suspected smoke area according to the position of the suspected smoke area in the monitoring image. In the embodiment of the present invention, the suspected smoke area is a center point of the suspected smoke area.
It should be noted that the dark channel prior defogging algorithm is a well-known technical means for those skilled in the art, and is not described herein. Because the characteristics of the flying dust in the image still can cause the dark channel prior defogging algorithm to identify the flying dust, the identified fog area is a suspected smog area, and whether the fog area is the smog generated by fire risks or the flying dust generated by the movement of operating equipment needs to be judged after analysis.
The method for acquiring the position of the operating equipment comprises the following steps:
and acquiring the real position information of the operation equipment through a sensor arranged on the operation equipment, and calibrating the real position information into the monitoring image to acquire the position of the operation equipment. It should be noted that the calibration of the real position information in the image is a technical means well known to those skilled in the art, and is not described herein in detail.
Step S2: obtaining a suspected smoke motion vector according to the difference of the suspected smoke area positions between the adjacent frame monitoring images; obtaining an image overall motion vector between adjacent frame monitoring images; and obtaining the motion difference between the suspected smoke motion vector and the image overall motion vector, obtaining the area difference between the suspected smoke areas between the adjacent frame monitoring images, and obtaining a first dust raising possibility according to the motion difference and the area difference.
The dust generated in the construction site is generally generated by operation equipment, such as dust generated by the running of some trucks, and the like, so the dust has the characteristics of quick forming, quick diffusion, certain motion characteristics and the like. In the case of smoke, which is generated by the risk of fire, the shape of the smoke region is changed with the fire, the smoke is formed and diffused slowly with respect to the dust, and since the fire source moves more slowly with respect to the working equipment, the fire source can be considered to be fixed for a short time, and thus the moving characteristics of smoke are not obvious with respect to the dust. Therefore, by combining the diffusion characteristics and the motion characteristics of the raised dust and the smoke, the suspected smoke motion vector is obtained according to the position difference of the suspected smoke area between the adjacent frame monitoring images, and the suspected smoke motion vector is used for representing the motion characteristics of the suspected smoke area in the continuous monitoring images. And further obtaining an image overall motion vector between adjacent frame monitoring images, and obtaining a motion difference between the suspected smoke motion vector and the image overall motion vector, wherein the smaller the motion difference is, the more the motion of the suspected smoke region conforms to the overall motion trend of an object in the image, namely the more the suspected smoke region is likely to be generated by a moving object in the image. And further acquiring the area difference between the suspected smoke areas between the adjacent frame monitoring images, and expressing the diffusion characteristic of the suspected smoke areas by using the area difference, namely, the larger the area difference is, the stronger the diffusivity of the suspected smoke areas is, and the more possible the suspected smoke areas are dust raising areas. And obtaining the first dust raising possibility of the suspected smoke area according to the motion difference and the area difference.
Preferably, obtaining the suspected smoke motion vector according to the difference of the suspected smoke area positions between the adjacent frame monitoring images includes:
acquiring a first suspected smoke area edge in a target frame monitoring image, and acquiring a second suspected smoke area edge in a previous frame monitoring image of the target frame monitoring image;
acquiring the minimum distance between each pixel point on the edge of the second suspected smoke area and the edge of the first suspected smoke area; taking each pixel point on the edge of the second suspected smoke area as a vector starting point; taking the pixel point with the minimum distance corresponding to the vector starting point in the first suspected smoke area as a vector terminal point; each group of corresponding vector starting points and vector end points form a motion vector; and selecting a preset number of motion vectors with the maximum modular length as reference motion vectors, and taking the average vector of the reference motion vectors as a suspected smoke motion vector. It should be noted that, when calculating the distance between each pixel point on the edge of the second suspected smoke area and the edge of the first suspected smoke area, the two suspected smoke area edges need to be placed under the same coordinate system.
In the embodiment of the present invention, the preset number is set to 8, that is, 8 motion vectors with the largest modulo length are selected as the reference motion vectors.
It should be noted that, the edge obtaining method of the suspected smoke area may adopt the existing edge detection technology, and the distance from the edge pixel point to another edge is also the existing technical means, which is not described herein again.
Preferably, obtaining the image overall motion vector between the monitoring images of the adjacent frames comprises: and obtaining the image overall motion vector between the monitoring images of the adjacent frames by an optical flow method. It should be noted that the optical flow method is a well-known technical means for those skilled in the art, and is not described herein.
Preferably, the obtaining the motion difference between the suspected smoke motion vector and the image overall motion vector comprises: and taking the included angle between the suspected smoke motion vector and the whole image motion vector as the motion difference, wherein the motion difference is larger when the included angle is larger.
The method for specifically obtaining the first dust raising possibility comprises the following steps: and acquiring the ratio of the area difference to the sampling frequency of the monitoring image, wherein the ratio represents the area change rate in unit time, namely, the higher the area change rate is, the stronger the diffusivity of the suspected smoke area is. The product of the ratio and the inverse of the motion difference is taken as the first dust raising probability. In the embodiment of the present invention, the expression of the first dust raising possibility is:
wherein,
as a first possibility of dust raising,
in order to monitor the sampling frequency of the camera,
the area of the suspected smoke region in the monitored image at time t,
the area of the suspected smoke region in the monitored image at time t-1,
in order to be able to make the difference in movement,
is the second fitting coefficient. In this expression, the higher the area change rate is, the smaller the motion difference is, which indicates that the more diffusible the suspected fog region is, the more the motion characteristic matches the motion characteristic of the moving object in the image, the more likely the suspected fog region is a raised dust, and the greater the possibility of the first raised dust is. The purpose of the second fitting coefficient is to prevent the denominator from being 0, in the embodiment of the present invention
Is set to 1.
And step S3: acquiring a first distance between the position of the suspected smoke area and the position of the operating equipment; acquiring a second distance of the position of the operation equipment between the adjacent frame monitoring images; a second dusting probability is obtained based on the first distance and the second distance.
According to the analysis and the prior knowledge in the step S2, there is a correlation between the generation of the flying dust and the movement of the operation equipment, so that the distribution of the suspected smoke area and the position of the operation equipment in the monitoring image needs to be further analyzed, that is, the closer the suspected smoke area is to the position of the operation equipment, the more likely the suspected smoke area is the flying dust generated by the moving operation equipment. A first distance between the suspected smoke area location and the work equipment location is thus obtained.
Further analysis is performed to take into account that the more drastic the movement of the working equipment, the more likely it is that the dust is generated in the construction site, and thus the second distance of the working equipment position between the adjacent frame monitor images is acquired. Obtaining a second dust raising possibility according to the first distance and the second distance, specifically comprising:
obtaining the second dust raising possibility according to a second dust raising possibility formula, wherein the second dust raising possibility formula comprises:
wherein,
in order for the second possibility of raising dust,
for the number of operating devices in the monitoring image at time t,
for the time t, the first time in the monitoring image
The work device position of the individual work devices,
the first time in the monitoring image is the t-1 time
The work apparatus position of the individual work apparatuses,
is composed of
And with
In between the distance between the first and second electrodes is less than the predetermined distance,
for the suspected smoke region location in the monitored image at time t,
the position of the operation equipment which is closest to the position of the suspected smoke area in the monitoring image at the time t,
is composed of
And
the distance between the two or more of the two or more,
is the first fitting coefficient.
In the second dust emission probability formula, more than one job device in the image is considered, and therefore, a second distance of each job device between adjacent frames needs to be counted, the second distance represents a moving distance of each job device, that is, the larger the moving distance is, the more the moving job devices are, the more dust emission is easily generated, and the second dust emission probability is higher. In the second dust emission possibility formula, the first distance is used as a denominator, that is, the smaller the first distance, the closer the suspected smoke region is to the nearest working equipment, the more likely the suspected smoke region is to be the generated dust emission, and the larger the second possibility. The purpose of the first fitting coefficient is to prevent the denominator from being 0, which, in the present embodiment,
is set to 1.
And step S4: weighting and summing the first dust raising possibility and the second dust raising possibility to obtain the dust raising possibility; and judging whether the current suspected smoke area is dust according to the dust raising possibility, if not, judging the suspected smoke area as a smoke area, and feeding back an early warning signal.
Combining the first dust raising possibility and the second dust raising possibility, and obtaining the dust raising possibility in a weighted summation mode, wherein the expression is as follows:
wherein,
in order to make the dust raising possible,
as a first possibility of dust raising,
the weight corresponding to the first raise dust probability,
as a second possibility of the dust being blown out,
a weight corresponding to the second dusting probability. In the embodiment of the invention, the
The setting is made to be 0.4,
set to 0.6. It should be noted that, before the weighted summation, the first raise dust probability and the second raise dust probability need to be normalized respectively, and the normalized result is weighted summation, and the normalization method is a technical means well known to those skilled in the art and will not be described herein.
Whether the suspected smoke area in the current monitoring image is the dust raising can be judged according to the dust raising possibility, namely if the dust raising possibility is larger than a preset possibility threshold value, the suspected smoke area in the current monitoring image is considered as the dust raising. The likelihood threshold is set to 0.7 in an embodiment of the present invention.
If the suspected smoke area is not the flying dust, the suspected smoke area is judged to be the smoke area, namely, the fire risk is considered to appear in the current monitoring image, the early warning signal needs to be fed back in time, the monitoring analysis of risk information is realized, the personal safety of workers and the financial loss of a building site can be guaranteed through the feedback of the workers to the early warning signal, and the safety and the stability of construction buildings are guaranteed.
In summary, the embodiment of the present invention calls the monitoring video in the database, and identifies the suspected smoke area, the suspected smoke area position, and the operation device position of each frame of monitoring image in the monitoring video. And obtaining a first dust raising possibility through the motion characteristics and the area diffusion characteristics of suspected smoke areas between the adjacent frame monitoring images. And obtaining a second dust raising possibility through the distribution relation of the positions between the suspected smoke area and the working equipment. And judging whether the suspected smoke area is dust by combining the first dust raising possibility and the second dust raising possibility. The invention realizes the distinguishing of smoke and raised dust in the construction site, and can monitor and early-warn and manage the generated fire risk in time.
The invention also provides a risk information monitoring and analyzing system based on big data, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein when the processor executes the computer program, any step of the risk information monitoring and analyzing method based on big data is realized.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. The processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A risk information monitoring and analyzing method based on big data is characterized by comprising the following steps:
extracting a monitoring video of a construction site in a database, and acquiring a suspected smoke area, a suspected smoke area position and an operation equipment position of each frame of monitoring image in the monitoring video;
obtaining a suspected smoke motion vector according to the difference of the suspected smoke area positions between the adjacent frame monitoring images; obtaining an image overall motion vector between adjacent frame monitoring images; obtaining a motion difference between the suspected smoke motion vector and the image overall motion vector, obtaining an area difference between the suspected smoke areas between adjacent frame monitoring images, and obtaining a first dust raising possibility according to the motion difference and the area difference, specifically comprising: acquiring a ratio of the area difference to the sampling frequency of the monitoring image, and taking the product of the ratio and the reciprocal of the motion difference as the first dust raising possibility;
acquiring a first distance between the suspected smoke area position and the operating equipment position; acquiring a second distance of the position of the operation equipment between adjacent frame monitoring images; obtaining a second dust raising possibility according to the first distance and the second distance, specifically comprising: obtaining the second dust raising possibility according to a second dust raising possibility formula, wherein the second dust raising possibility formula comprises:
wherein,
in order for the second possibility of raising dust,
is composed of
The number of operating devices in the monitored image at the time,
is composed of
Time of day in the monitoring image
The work device position of the individual work devices,
is composed of
Time of day in the monitoring image
The work apparatus position of the individual work apparatuses,
is composed of
And
in between the distance between the first and second electrodes is less than the predetermined distance,
is composed of
The suspected smoke region location in the monitored image at the time,
is composed of
The position of the working equipment which is closest to the position of the suspected smoke area in the monitoring image at the moment,
is composed of
And
the distance between the two or more of the two or more,
is a first fitting coefficient;
weighting and summing the first raise dust possibility and the second raise dust possibility to obtain a raise dust possibility; and judging whether the suspected smoke area is dust according to the dust raising possibility, if not, judging the suspected smoke area as a smoke area, and feeding back an early warning signal.
2. The big data-based risk information monitoring and analyzing method according to claim 1, wherein the suspected smoke area obtaining method comprises:
processing the monitoring image by using a dark channel prior defogging algorithm, identifying the suspected smoke area, and obtaining the position of the suspected smoke area according to the position of the suspected smoke area in the monitoring image.
3. The big data-based risk information monitoring and analyzing method according to claim 1, wherein the method for acquiring the position of the operating equipment comprises the following steps:
and acquiring real position information of the operation equipment through a sensor arranged on the operation equipment, and calibrating the real position information into the monitoring image to acquire the position of the operation equipment.
4. The big-data-based risk information monitoring and analyzing method according to claim 1, wherein the obtaining the suspected smoke motion vector according to the difference of the suspected smoke area positions between the adjacent frame monitoring images comprises:
the method comprises the steps of obtaining a first suspected smoke area edge in a target frame monitoring image, and obtaining a second suspected smoke area edge in a previous frame monitoring image of the target frame monitoring image;
acquiring the minimum distance between each pixel point on the edge of the second suspected smoke area and the edge of the first suspected smoke area; taking each pixel point on the edge of the second suspected smoke area as a vector starting point; taking the pixel point of the vector starting point corresponding to the minimum distance in the first suspected smoke area as a vector terminal point; each group of corresponding vector starting point and vector end point form a motion vector; and selecting a preset number of motion vectors with the maximum mode length as reference motion vectors, and taking the average vector of the reference motion vectors as the suspected smoke motion vector.
5. The big-data-based risk information monitoring and analyzing method according to claim 1, wherein the obtaining of the image global motion vector between the monitoring images of the adjacent frames comprises:
and obtaining the image overall motion vector between the adjacent frame monitoring images through an optical flow method.
6. The big-data-based risk information monitoring and analyzing method according to claim 1, wherein the obtaining the motion difference between the suspected smoke motion vector and the image global motion vector comprises:
and taking the included angle between the suspected smoke motion vector and the whole image motion vector as the motion difference.
7. The big-data-based risk information monitoring and analyzing method according to claim 1, wherein the determining whether the suspected smoke area is dust according to the dust emission possibility includes:
and if the dust raising possibility is larger than a preset possibility threshold, the suspected smoke area in the monitoring image at the current moment is considered as the dust raising.
8. A big data-based risk information monitoring and analyzing system, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211140046.4A CN115223105B (en) | 2022-09-20 | 2022-09-20 | Big data based risk information monitoring and analyzing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211140046.4A CN115223105B (en) | 2022-09-20 | 2022-09-20 | Big data based risk information monitoring and analyzing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115223105A CN115223105A (en) | 2022-10-21 |
| CN115223105B true CN115223105B (en) | 2022-12-09 |
Family
ID=83617497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211140046.4A Active CN115223105B (en) | 2022-09-20 | 2022-09-20 | Big data based risk information monitoring and analyzing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115223105B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116259005B (en) * | 2023-02-04 | 2024-05-28 | 国网浙江省电力有限公司嘉兴供电公司 | Intelligent monitoring system based on roof photovoltaic fire control |
| CN116453064B (en) * | 2023-06-16 | 2023-08-18 | 烟台黄金职业学院 | Method for identifying abnormal road conditions of tunnel road section based on monitoring data |
| CN118038627B (en) * | 2024-04-15 | 2024-06-18 | 大连乾曜科技有限公司 | Tunnel road section safety monitoring method based on vehicle big data |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982313A (en) * | 2012-10-31 | 2013-03-20 | 深圳辉锐天眼科技有限公司 | Smog detecting method |
| CN106897720A (en) * | 2017-01-11 | 2017-06-27 | 济南中维世纪科技有限公司 | A kind of firework detecting method and device based on video analysis |
| CN106997461A (en) * | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| JP2019179573A (en) * | 2019-06-21 | 2019-10-17 | ホーチキ株式会社 | Fire detection system and fire detection method |
| JP2020021300A (en) * | 2018-08-01 | 2020-02-06 | 株式会社シー・イー・デー・システム | Fire monitoring device, fire monitoring system, and program for fire monitoring device |
| CN110874592A (en) * | 2019-10-21 | 2020-03-10 | 南京信息职业技术学院 | Forest fire smoke image detection method based on total bounded variation |
| CN112257523A (en) * | 2020-10-09 | 2021-01-22 | 营口新山鹰报警设备有限公司 | Smoke identification method and system of image type fire detector |
| CN112634577A (en) * | 2019-09-24 | 2021-04-09 | 中科智云科技有限公司 | Method and apparatus for smoke alarm |
| CN113553985A (en) * | 2021-08-02 | 2021-10-26 | 中再云图技术有限公司 | High-altitude smoke detection and identification method based on artificial intelligence, storage device and server |
| WO2022121129A1 (en) * | 2020-12-12 | 2022-06-16 | 南方电网调峰调频发电有限公司 | Fire recognition method and apparatus, and computer device and storage medium |
| CN114998737A (en) * | 2022-06-08 | 2022-09-02 | 徐州才聚智能科技有限公司 | Remote smoke detection method, system, electronic equipment and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516609B (en) * | 2019-08-28 | 2022-04-22 | 南京邮电大学 | Fire disaster video detection and early warning method based on image multi-feature fusion |
-
2022
- 2022-09-20 CN CN202211140046.4A patent/CN115223105B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982313A (en) * | 2012-10-31 | 2013-03-20 | 深圳辉锐天眼科技有限公司 | Smog detecting method |
| CN106897720A (en) * | 2017-01-11 | 2017-06-27 | 济南中维世纪科技有限公司 | A kind of firework detecting method and device based on video analysis |
| CN106997461A (en) * | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| JP2020021300A (en) * | 2018-08-01 | 2020-02-06 | 株式会社シー・イー・デー・システム | Fire monitoring device, fire monitoring system, and program for fire monitoring device |
| JP2019179573A (en) * | 2019-06-21 | 2019-10-17 | ホーチキ株式会社 | Fire detection system and fire detection method |
| CN112634577A (en) * | 2019-09-24 | 2021-04-09 | 中科智云科技有限公司 | Method and apparatus for smoke alarm |
| CN110874592A (en) * | 2019-10-21 | 2020-03-10 | 南京信息职业技术学院 | Forest fire smoke image detection method based on total bounded variation |
| CN112257523A (en) * | 2020-10-09 | 2021-01-22 | 营口新山鹰报警设备有限公司 | Smoke identification method and system of image type fire detector |
| WO2022121129A1 (en) * | 2020-12-12 | 2022-06-16 | 南方电网调峰调频发电有限公司 | Fire recognition method and apparatus, and computer device and storage medium |
| CN113553985A (en) * | 2021-08-02 | 2021-10-26 | 中再云图技术有限公司 | High-altitude smoke detection and identification method based on artificial intelligence, storage device and server |
| CN114998737A (en) * | 2022-06-08 | 2022-09-02 | 徐州才聚智能科技有限公司 | Remote smoke detection method, system, electronic equipment and medium |
Non-Patent Citations (3)
| Title |
|---|
| Smoke vehicle detection based on robust codebook model and robust volume local binary count patterns;Huanjie Tao 等，;《Image and Vision Computing》;20190630;第86卷;全文 * |
| 基于视频的实时烟雾检测算法;张建明 等，;《计算机应用与软件》;20161231;第33卷(第12期);全文 * |
| 基于连续帧图像面积变化的火灾探测方法;刘伯运 等，;《消防科学与技术》;20161231;第35卷(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115223105A (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115223105B (en) | Big data based risk information monitoring and analyzing method and system | |
| JP6949988B2 (en) | Domain identification method, device, storage medium and processor | |
| US10417503B2 (en) | Image processing apparatus and image processing method | |
| US9615064B2 (en) | Tracking moving objects using a camera network | |
| US20180342067A1 (en) | Moving object tracking system and moving object tracking method | |
| JP2021514548A (en) | Target object monitoring methods, devices and systems | |
| US8170277B2 (en) | Automatic tracking apparatus and automatic tracking method | |
| US20090220123A1 (en) | Apparatus and method for counting number of objects | |
| CN116092018B (en) | Fire-fighting hidden danger monitoring method and system based on intelligent building | |
| CN111191507A (en) | Safety early warning analysis method and system for smart community | |
| CN117237879B (en) | Track tracking method and system | |
| CN109255360A (en) | A kind of objective classification method, apparatus and system | |
| CN111476160A (en) | Loss function optimization method, model training method, target detection method, and medium | |
| JPH0844874A (en) | Image change detector | |
| KR20220146225A (en) | Pig population counting and sicked pig detection system based on deep learning video analysis technology | |
| KR101525915B1 (en) | object information provision system and object information provision apparatus and object information providing method | |
| CN115762043B (en) | Intelligent building fire-fighting guidance system | |
| KR102081577B1 (en) | Intelligence Fire Detecting System Using CCTV | |
| WO2022012573A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
| CN115035543A (en) | Big data-based movement track prediction system | |
| CN113392713A (en) | Work clothes wearing identification method | |
| CN112578909B (en) | Method and device for equipment interaction | |
| KR102630545B1 (en) | Robot and robot control method carrying out management information according to the condition of the grass | |
| CN114937303B (en) | Scenic spot registration monitoring method based on face recognition | |
| US12020505B1 (en) | System and method for facial recognition accuracy |
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 |