CN117809441B - Mobile sentinel danger early warning system for forest fire prevention - Google Patents
Mobile sentinel danger early warning system for forest fire prevention Download PDFInfo
- Publication number
- CN117809441B CN117809441B CN202410233739.0A CN202410233739A CN117809441B CN 117809441 B CN117809441 B CN 117809441B CN 202410233739 A CN202410233739 A CN 202410233739A CN 117809441 B CN117809441 B CN 117809441B
- Authority
- CN
- China
- Prior art keywords
- early warning
- module
- patrol
- data
- image
- 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
- 230000002265 prevention Effects 0.000 title claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 54
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000011156 evaluation Methods 0.000 claims abstract description 23
- 238000005457 optimization Methods 0.000 claims abstract description 14
- 238000007689 inspection Methods 0.000 claims description 65
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 14
- 239000000779 smoke Substances 0.000 claims description 12
- 230000003993 interaction Effects 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 230000007613 environmental effect Effects 0.000 claims description 6
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 3
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 3
- 238000002485 combustion reaction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000007480 spreading Effects 0.000 abstract description 2
- 238000003892 spreading Methods 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- 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
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- 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
- G08B17/005—Fire alarms; Alarms responsive to explosion for forest fires, e.g. detecting fires spread over a large or outdoors area
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/06—Electric actuation of the alarm, e.g. using a thermally-operated switch
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
- Y02A40/28—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture specially adapted for farming
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Animal Husbandry (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Marine Sciences & Fisheries (AREA)
- Educational Administration (AREA)
- Mining & Mineral Resources (AREA)
- Agronomy & Crop Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Computing Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of forest fire prevention and discloses a mobile sentinel danger early warning system for forest fire prevention, which comprises a region dividing module, a patrol route planning module, a patrol data acquisition module, a patrol data processing module, a region safety index analysis module, a general safety evaluation module, a danger early warning module, a patrol route optimization module, a patrol early warning module and a control center, wherein the number of suspected fire areas exceeding a threshold range, a fire occurrence degree base, a smoldering generation degree index and an open flame occurrence degree index are provided with the patrol early warning module and the patrol route optimization module, so that early warning prompt is carried out, potential hazards are found in the first time, danger early warning is carried out in the first time, related measures are adopted, optimization of the patrol route is carried out according to early warning conditions, an optimal patrol route is formed by combining a dangerous early warning viewpoint and a spreading wind direction condition, potential fire risks are found timely, and the potential hazards are avoided timely, and the potential hazards are reduced.
Description
Technical Field
The invention relates to the technical field of forest fire prevention, in particular to a mobile sentinel danger early warning system for forest fire prevention.
Background
The mobile sentry is an integrated monitoring system, can be used as an independent monitoring system, is characterized by being 'mobile monitoring, is convenient to use and easy to deploy at any time and any place', integrates the flexibility of on-board law enforcement equipment on demand rapid deployment and the panoramic monitoring view angle of an unmanned aerial vehicle, creatively concentrates various power supply modes and wireless transmission modes on one mobile sentry mobile monitoring device, powerfully compensates the application pain point of the existing monitoring, greatly improves the applicability of the mobile monitoring, and is complex in application scene, so that the application scene of the mobile sentry needs to be improved specifically according to the actual application scene.
The forest fire hazard is large, the fire is difficult to put out, and therefore the forest fire is particularly important when the fire is still in a sprouting state, and the forest fire is not easy to find because the fire is often in a deep mountain old forest, so that the finding of the fire has important significance for putting out the fire early, the mobile sentry is applied to forest fire prevention, the probability of finding the fire can be improved, the danger early warning is the most critical and important function when the mobile sentry is applied to forest fire prevention, the potential fire risk of the forest can be found in time, the occurrence of the fire can be avoided in time, and the forest safety is protected.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a mobile sentinel danger early warning system for forest fire prevention, which is used for solving the problems in the background art.
The invention provides the following technical scheme: a mobile sentinel danger early warning system for forest fire prevention comprises a regional division module, a patrol route planning module, a patrol data acquisition module, a patrol data processing module, a regional safety index analysis module, a total safety evaluation module, a danger early warning module, a patrol route optimization module, a patrol early warning module and a control center;
the region dividing module is used for dividing the region of the target object into n sub-regions and numbering the sub-regions, wherein the n sub-regions are marked as 1, 2 and 3 … … i … … n;
The patrol route planning module carries out patrol route planning on the mobile sentry of each subarea, sets m patrol points and marks the m patrol points as follows 、/>、/>……/>……；
The patrol data acquisition module acquires smoke data, image data, temperature data, humidity data and wind power data, pre-processes the data and transmits the data to the patrol data processing module;
the inspection data processing module analyzes the image data based on an improved inter-frame difference method, calculates the number of suspected fire region points through an image extraction training model, acquires a fire occurrence degree base based on smoke data, humidity data and temperature data, and transmits the fire occurrence degree base to the inspection early warning module and the region safety index analysis module;
The regional safety index analysis module calculates a smoldering flame generation degree index and a bright flame generation degree index based on the suspected flame regional points and the fire occurrence degree base data, analyzes and calculates regional safety indexes of all the subregions, and transmits the regional safety indexes to the inspection early warning module and the overall safety evaluation module;
The overall safety evaluation module comprehensively calculates the safety indexes of all the subareas to obtain an overall safety index, carries out safety evaluation, transmits data to the control center for human-computer interaction if the evaluation result is safe, and transmits the data to the danger early warning module if the evaluation result is dangerous;
The inspection early-warning module performs primary early-warning analysis and advanced early-warning analysis, if the analysis result is in accordance with early warning, the inspection early-warning module transmits an early-warning instruction to the danger early-warning module, and simultaneously transmits a route resetting instruction to the inspection route optimization module, and the inspection early-warning module comprises a primary early-warning unit and an advanced early-warning unit;
After analyzing the data, the patrol route optimization module performs key patrol on all areas with high danger occurrence probability, generates an optimal patrol route and transmits the optimal patrol route to the patrol route planning module;
The danger early warning module carries out primary early warning notification and secondary early warning notification, and transmits data to the control center for man-machine interaction;
The control center is used for carrying out man-machine interaction on the data and sending a control instruction to the mobile sentry.
Preferably, the primary early warning unit performs early warning analysis on the data of the inspection data processing module, if the analysis result is primary early warning, a primary early warning instruction is sent to the dangerous early warning module, if the analysis result is secondary early warning, a secondary early warning instruction is sent to the dangerous early warning module, if the analysis result is unnecessary early warning, no instruction is sent, the advanced early warning unit performs early warning analysis on the data of the regional safety index analysis module, if the analysis result is primary early warning, a primary early warning instruction is sent to the dangerous early warning module, if the analysis result is secondary early warning, a secondary early warning instruction is sent to the dangerous early warning module, and if the analysis result is unnecessary early warning, no instruction is sent.
Preferably, the danger early warning module comprises a primary early warning notification unit and a secondary early warning notification unit, wherein the primary early warning notification unit is used for receiving a primary early warning instruction and carrying out primary early warning processing, and the secondary early warning notification unit is used for receiving a secondary early warning instruction and carrying out secondary early warning processing.
Preferably, the detailed mode of extracting the suspected flame region points by the patrol data processing module through the image extraction training model is as follows:
step S01: inputting model data: inputting image data of all patrol points of all subregions, preprocessing the image data of the jth patrol point of the ith subregion, dividing the image data into K frames of images, wherein the interval time of each frame of image is t;
step S02: performing pixel-by-pixel differential operation on the k frame and the k+1 frame images: ， and performing pixel-by-pixel addition operation on the k frame image and the k+1 frame image as a result of subtracting the k+1 frame image from the k frame image: /(I) Wherein/>F (K) is the gray value of the K frame image, f (k+1) is the gray value of the k+1 frame image, and k=1, 2, 3 … … K;
step S03: based on the traditional interframe difference method And/>Performing differential operation, and taking an absolute value: Wherein/> Binarizing the image after difference into a formula: wherein A is a binary image, and T is a binarization threshold;
Step S04: the suspected flame region identification is carried out on all binary images with A=1: the pixel coordinates of the image are marked as (X, Y) and substituted into the formula: Wherein/> (X, Y) is the edge of the moving object of the kth frame image,/>(X, Y) is the moving target edge of the (k+1) th frame image, sim (k, k+1) is the target edge similarity of the (k+1) th frame image and the (k+1) th frame image, and [ delta ] is the image area;
Calculating a target edge similarity mean value: Wherein/> For the average value of the similarity of the edges of the targets, if the result is found/>If the detection result is greater than the determination threshold YP, the ith region and the jth inspection point image are determined to be suspected flame regions, and if the detection result is required/>When the image is larger than the judging threshold YP, eliminating the jth patrol point image of the ith area;
Step S05: counting the judgment results of all the patrol point images of all the subareas, and marking the number of the patrol point images of the ith subarea judged to be the suspected flame area as The probability of the occurrence of a suspected flame region in the ith region is: Wherein/> Probability of occurrence of a suspected flame region image for the ith sub-region;
correcting the determination result based on the focus loss function: Wherein, the method comprises the steps of, wherein, As a focal point loss function, epsilon is a correction and adjustment parameter, the value is more than or equal to 0 and less than or equal to 5, and then step S02 is executed once;
step S06: outputting final data: outputting the number of the patrol point images of all the sub-areas suspected flame areas finally, and recording the number of the patrol point images of the i th sub-area finally judged as the suspected flame area as 。
Preferably, the calculation formula of the fire occurrence degree base is as follows: Wherein/> Base number of fire occurrence for jth patrol point area in ith sub-area,/>For the smoke density value of the jth inspection point area in the ith sub-area,/>For the ambient temperature value of the jth patrol point area in the ith sub-area,/>For the environmental humidity value of the jth patrol point area in the ith sub-area,/>Is the weather temperature value of the current day.
8. Preferably, the calculation formula of the smoldering generating degree index is as follows: Wherein/> Generating a degree index for smoldering combustion of the ith sub-region,/>For the total concentration of carbon monoxide in the ith sub-zone,/>，/>For/>J=1, 2, 3 … … m;
the calculation formula of the open flame occurrence index is as follows: Wherein/> For the bright flame occurrence index of the ith sub-region,/>Wherein/>The occurrence probability parameter of the ith sub-area;
The calculation formula of the area safety index is as follows: Wherein/> For the region safety index of the ith sub-region,/>Is a first proportional constant,/>For the second proportionality constant, γ is the other influencing factor.
A remove sentry danger early warning system for forest fire prevention, the computational formula of total security index is: wherein ZT is the overall security index, Wherein/>For/>Is a weight factor of (a).
The invention has the technical effects and advantages that:
The invention is beneficial to early warning and prompting the number of suspected fire areas exceeding a threshold range, the base number of fire occurrence degrees, the smoldering occurrence degree index and the open flame occurrence degree index, discovering potential safety hazards at first time, early warning danger at first time, taking relevant measures, optimizing the patrol route according to early warning conditions, combining the patrol viewpoint of the early warning danger and the wind direction spreading condition to form an optimal patrol route, discovering potential fire risks timely, avoiding fire occurrence timely and reducing the potential safety hazards.
Drawings
Fig. 1 is a flow chart of the mobile sentinel hazard early warning system for forest fire prevention of the invention.
Fig. 2 is a diagram of a patrol early-warning module according to the present invention.
FIG. 3 is a block diagram of a hazard warning module according to the present invention.
Detailed Description
The following will be described in detail and with reference to the drawings, wherein the embodiments of the present invention are described by way of illustration only, and the embodiments of the present invention are not limited to the embodiments described below, and all other embodiments of the present invention are within the scope of the present invention.
The invention provides a mobile sentry hazard early warning system for forest fire prevention, which comprises a regional division module, a patrol route planning module, a patrol data acquisition module, a patrol data processing module, a regional safety index analysis module, a total safety evaluation module, a hazard early warning module, a patrol route optimization module, a patrol early warning module and a control center, wherein the regional division module is used for dividing the regional security index;
The regional division module divides the region into n sub-regions and sets up the mobile guard for patrol, the patrol route planning module plans the patrol route of each sub-region and transmits the patrol route to the patrol data acquisition module and the control center, the patrol data acquisition module acquires the patrol point data on the patrol route of each sub-region and transmits the patrol point data to the patrol data processing module, the patrol data processing module processes and analyzes the acquired data and transmits the processed data to the regional security index analysis module and the patrol early warning module, the regional security index analysis module analyzes and calculates the security index of each sub-region and transmits the processed data to the overall security assessment module and the patrol early warning module, the overall security assessment module carries out overall security assessment on the region, if the evaluation result is safe, transmitting the data to a control center, if the evaluation result is dangerous, transmitting the data to a dangerous early warning module, wherein the dangerous early warning module carries out the inspection early warning analysis on the data, if the analysis result is dangerous, transmitting the data to the dangerous early warning module and an inspection route optimizing module, and after the analysis on the data, generating an optimal inspection route, covering all inspection points with dangerous inspection points and inspection route planning modules with high dangerous probability, and transmitting the inspection points to the control center, wherein the dangerous early warning module carries out early warning on dangerous conditions and transmits the dangerous situations to the control center, and the control center carries out man-machine interaction after receiving the data and simultaneously controls a mobile whistle.
In this embodiment, it needs to be specifically described that the area dividing module is configured to divide an area of a target object into n sub-areas, and number the n sub-areas, where the n sub-areas are marked as 1,2, and 3 … … i … … n, and each sub-area is provided with a mobile whistle for inspection, and information sharing can be performed between the mobile whistles in each sub-area;
the patrol route planning module carries out patrol route planning on the mobile sentry of each subarea, sets m patrol points, wherein the patrol range of all patrol points of the patrol route can cover the whole subarea, numbers the m patrol points and marks the m patrol points as follows 、/>、/>……/>……/>Transmitting the planned route to a control center, and controlling the mobile sentry to patrol according to the planned route;
The inspection data acquisition module acquires smoke data, image data, temperature data, humidity data and wind power data, the mobile sentry performs data acquisition at each inspection point of the subareas, the data are preprocessed and then transmitted to the inspection data processing module, the smoke data, the humidity data, the temperature data and the wind power data can be directly acquired through the sensor, the image data is acquired through the image acquisition equipment, for example, a high-definition camera equipped with the mobile sentry is acquired, the image data is shot video data, the smoke data is a smoke density value, the humidity data is an environmental humidity value, the temperature data is an environmental temperature value, and the wind power data is a wind speed value and a wind direction;
The inspection data processing module analyzes the image data based on an improved inter-frame difference method, calculates the number of suspected fire areas through an image extraction training model, acquires the fire occurrence degree base number based on smoke data, humidity data and temperature data, transmits the fire occurrence degree base number to the inspection early warning module and the area safety index analysis module, analyzes the image data by using the improved inter-frame difference method, can avoid the defect that a complete target area cannot be extracted by using the traditional frame difference method, can effectively remove a high-brightness area which moves rapidly in an original image, effectively extracts suspected flame areas, and lays a foundation for the subsequent calculation of the number of the suspected flame areas;
The regional safety index analysis module calculates a smoldering flame generation degree index and a bright flame generation degree index based on the suspected flame regional points and the fire occurrence degree base data, analyzes and calculates regional safety indexes of all the subregions, and transmits the regional safety indexes to the inspection early warning module and the overall safety evaluation module;
The overall safety evaluation module comprehensively calculates the safety indexes of all the subareas to obtain an overall safety index, carries out safety evaluation, transmits data to the control center for human-computer interaction if the evaluation result is safe, and transmits the data to the danger early warning module if the evaluation result is dangerous;
The inspection early-warning module carries out primary early-warning analysis and advanced early-warning analysis, if the analysis result is in accordance with early warning, the inspection early-warning module transmits an early-warning instruction to the dangerous early-warning module, meanwhile, the inspection early-warning module sends a route resetting instruction to the inspection route optimizing module, the inspection early-warning module comprises a primary early-warning unit and an advanced early-warning unit, the primary early-warning unit carries out early-warning analysis on data of the inspection data processing module, if the analysis result is primary early-warning, the primary early-warning instruction is sent to the dangerous early-warning module, if the analysis result is secondary early-warning, the secondary early-warning instruction is sent to the dangerous early-warning module, if the analysis result is no early-warning, the instruction is not sent to the dangerous early-warning module, if the analysis result is no early-warning, the advanced early-warning unit carries out early-warning analysis on data of the regional safety index analysis module, if the analysis result is primary early-warning instruction is sent to the dangerous early-warning module, and if the analysis result is secondary early-warning, the instruction is not sent;
After analyzing the data, the patrol route optimization module performs key patrol on all areas with high danger occurrence probability, generates an optimal patrol route and transmits the optimal patrol route to the patrol route planning module;
The dangerous early warning module carries out primary early warning notification and secondary early warning notification and transmits data to the control center for human-computer interaction, the dangerous early warning module comprises a primary early warning notification unit and a secondary early warning notification unit, the primary early warning notification unit is used for receiving primary early warning instructions and carrying out primary early warning processing, the secondary early warning notification unit is used for receiving secondary early warning instructions and carrying out secondary early warning processing, and the specific mode of the primary early warning processing is as follows: sending an emergency early warning notice to a control center, wherein a manager needs to be dispatched to survey a patrol point or a subarea on site to check whether dangerous hidden danger exists, and the specific mode of the secondary early warning processing is as follows: sending a patrol early warning notice to a control center, and sending a patrol instruction to a mobile guard, wherein the mobile guard moves to an early warning patrol point, and a manager performs remote investigation, and the content of the early warning notice comprises an early warning grade, an early warning subarea position and an early warning patrol point coordinate;
The control center is used for carrying out man-machine interaction on the data and sending a control instruction to the mobile sentry.
In this embodiment, it should be specifically described that the detailed manner in which the inspection data processing module extracts the suspected flame region points through the image extraction training model is as follows:
step S01: inputting model data: inputting image data of all patrol points of all subregions, preprocessing the image data of the jth patrol point of the ith subregion, dividing the image data into K frames of images, wherein the interval time of each frame of image is t, and the value of t can be set by oneself, and t=0.2 s is selected in the embodiment;
step S02: performing pixel-by-pixel differential operation on the k frame and the k+1 frame images: ， and performing pixel-by-pixel addition operation on the k frame image and the k+1 frame image as a result of subtracting the k+1 frame image from the k frame image: /(I) Wherein/>F (K) is the gray value of the K frame image, f (k+1) is the gray value of the k+1 frame image, and k=1, 2, 3 … … K;
step S03: based on the traditional interframe difference method And/>Performing differential operation, and taking an absolute value: Wherein/> Binarizing the image after difference into a formula: Wherein a is a binary image, T is a binary threshold, the threshold is selected and can be set by itself, the implementation is not limited in particular, all binary images with a=1 are considered as moving images, and all binary images with a=0 are considered as still images;
Step S04: the suspected flame region identification is carried out on all binary images with A=1: the pixel coordinates of the image are marked as (X, Y) and substituted into the formula: Wherein/> (X, Y) is the edge of the moving object of the kth frame image,/>(X, Y) is the moving target edge of the (k+1) th frame image, sim (k, k+1) is the target edge similarity of the (k+1) th frame image and the (k+1) th frame image, and [ delta ] is the image area;
Calculating a target edge similarity mean value: Wherein/> For the average value of the similarity of the edges of the targets, if the result is found/>If the detection result is greater than the determination threshold YP, the ith region and the jth inspection point image are determined to be suspected flame regions, and if the detection result is required/>If the value of the judgment threshold value YP is larger than the judgment threshold value YP, eliminating the jth patrol point image of the ith area, wherein the value of the judgment threshold value YP needs to be specifically set according to the specific situation of the forest protection level;
Step S05: counting the judgment results of all the patrol point images of all the subareas, and marking the number of the patrol point images of the ith subarea judged to be the suspected flame area as The probability of the occurrence of a suspected flame region in the ith region is: Wherein/> Probability of occurrence of a suspected flame region image for the ith sub-region;
correcting the determination result based on the focus loss function: Wherein, the method comprises the steps of, wherein, As a focal point loss function, epsilon is a correction and adjustment parameter, the value is more than or equal to 0 and less than or equal to 5, and then step S02 is executed once;
the focus loss function is used for correcting the image extraction training model, so that the accuracy of the model is improved, the false alarm rate is reduced, and the detection capability of the model to the small target flame in the early stage of forest fire is improved;
step S06: outputting final data: outputting the number of the patrol point images of all the sub-areas suspected flame areas finally, and recording the number of the patrol point images of the i th sub-area finally judged as the suspected flame area as I.e. the number of suspected flame region points.
In this embodiment, it should be specifically described that the calculation formula of the fire occurrence degree base is: Wherein/> Base number of fire occurrence for jth patrol point area in ith sub-area,/>For the smoke density value of the jth inspection point area in the ith sub-area,/>The environmental temperature value of the jth inspection point area in the ith sub-area/>For the environmental humidity value of the jth patrol point area in the ith sub-area,/>As the weather temperature value of the same day, when/>The greater the value of (c) is, the greater the likelihood of fire in the current area, and the need to enhance the inspection or dispatch of the inspection point in the field by the manager.
9. In this embodiment, it should be specifically described that the calculation formula of the smoldering generating degree index is: Wherein/> Generating a degree index for smoldering combustion of the ith sub-region,/>For the total concentration of carbon monoxide in the ith sub-zone,/>，/>For/>J=1, 2, 3 … … m;
the calculation formula of the open flame occurrence index is as follows: Wherein/> For the bright flame occurrence index of the ith sub-region,/>Wherein/>The greater the bright flame occurrence index, the greater the risk is for the occurrence probability parameter of the ith sub-region.
In this embodiment, it should be specifically described that the calculation formula of the area security index is: Wherein/> For the region safety index of the ith sub-region,/>Is a first proportional constant,/>For the second proportionality constant, γ is the other influencing factor.
A remove sentry danger early warning system for forest fire prevention, the computational formula of total security index is: wherein ZT is the overall security index, Wherein/>For/>Is a weight factor of (a).
In this embodiment, it needs to be specifically described that the specific manner of the primary early warning unit performing early warning analysis on the data of the patrol data processing module is:
step S11: judging the number of suspected fire areas: if the number of the suspected fire areas is satisfied Outputting the judgment result as U1, otherwise outputting the judgment result as N1, wherein/>For a first threshold constant, satisfy/>The specific numerical value can be specifically set according to the value of m, which is not specifically limited in this embodiment;
Step S12: determining the flame occurrence degree base: if the base number of fire occurrence degree is satisfied Outputting the judgment result as U2, or outputting the judgment result as N2, wherein/>For a second threshold constant, satisfy/>The specific numerical values can be specifically set according to actual conditions, and the specific numerical values are not specifically limited in this embodiment;
Step S13: judging the early warning level: if the judgment result is U1, the first-stage early warning instruction is judged, if the judgment result is U2 only, the second-stage early warning instruction is judged, and if the judgment result is N1 and N2, the judgment result is that early warning is not needed.
In this embodiment, it needs to be specifically described that the specific manner of performing early warning analysis on the data of the regional security index analysis module by the advanced early warning unit is:
step S21: judging smoldering generation index: if the smoldering generation index satisfies Outputting a judgment result as U3, otherwise outputting a judgment result as N3;
step S22: judging the bright flame occurrence index: if the open flame occurrence index satisfies Outputting a judging result as U4, otherwise outputting a judging result as N4;
Step S23: judging the early warning level: if the judging result is U3 and U4, judging the first-stage early warning instruction, if the judging result is one of U3 and U4, judging the second-stage early warning instruction, and if the judging result is N3 and N4, judging the judging result to be unnecessary to early warning.
In this embodiment, it needs to be specifically described that the inspection route optimization module screens out inspection points with determination results of U1 and U2, performs key marking on coordinates of the inspection points, and calculates a route offset angle of the marked inspection points: Wherein/> Route deviation angle of jth tour point in ith area,/>Patrol angle for the jth patrol point of the ith area,/>Taking a j-th inspection point as an example of an included wind speed angle, taking the j-th inspection point as an inspection point of a key mark, taking the j-th inspection point as a coordinate origin, wherein the inspection angle is an included angle between a path of the j+1-th inspection point and the j-th inspection point and a positive axis of the coordinate origin, the included wind speed angle is an included angle between a wind direction tested at the j-th inspection point and the positive axis of the coordinate origin, the positive axis of the coordinate origin is an x-axis positive axis, correcting the inspection path based on the path offset angle, generating an optimal inspection path, and preferentially inspecting an area where fire is likely to happen, thereby reducing the fire occurrence probability.
In this embodiment, it should be specifically described that the standard for performing the security evaluation by the overall security evaluation module is: if the overall safety index is satisfiedAnd if the safety is judged, otherwise, judging that the safety is dangerous, and sending a secondary early warning instruction to a dangerous early warning module.
In this embodiment, it needs to be specifically explained that, the difference between this implementation and the prior art mainly lies in that this embodiment possesses the inspection early warning module and the inspection route optimization module, be favorable to carrying out the early warning suggestion through suspected fire region point quantity, the degree base of fire occurrence, smoldering production degree index and the degree index of bright flame occurrence that surpass threshold value scope, the potential safety hazard is found in the first time, dangerous early warning is carried out in the first time, and take relevant measures, carry out the optimization of inspection route according to the early warning condition simultaneously, combine dangerous early warning inspection point and spread wind direction condition, form the best inspection route, in time discover potential fire risk, in time avoid the conflagration to take place, reduce the potential safety hazard.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (4)
1. A remove sentry danger early warning system for forest fire prevention, its characterized in that: the system comprises a regional division module, a patrol route planning module, a patrol data acquisition module, a patrol data processing module, a regional safety index analysis module, a total safety evaluation module, a danger early warning module, a patrol route optimization module, a patrol early warning module and a control center;
the region dividing module is used for dividing the region of the target object into n sub-regions and numbering the sub-regions, wherein the n sub-regions are marked as 1, 2 and 3 … … i … … n;
The patrol route planning module carries out patrol route planning on the mobile sentry of each subarea, sets m patrol points and marks the m patrol points as follows 、/>、/>……/>……；
The patrol data acquisition module acquires smoke data, image data, temperature data, humidity data and wind power data, pre-processes the data and transmits the data to the patrol data processing module;
the inspection data processing module analyzes the image data based on an improved inter-frame difference method, calculates the number of suspected fire region points through an image extraction training model, acquires a fire occurrence degree base based on smoke data, humidity data and temperature data, and transmits the fire occurrence degree base to the inspection early warning module and the region safety index analysis module;
The calculation formula of the fire occurrence degree base number is as follows: Wherein/> Base number of fire occurrence for jth patrol point area in ith sub-area,/>For the smoke density value of the jth inspection point area in the ith sub-area,/>For the ambient temperature value of the jth patrol point area in the ith sub-area,/>For the environmental humidity value of the jth patrol point area in the ith sub-area,/>The weather temperature value of the current day;
The regional safety index analysis module calculates a smoldering flame generation degree index and a bright flame generation degree index based on the suspected flame regional points and the fire occurrence degree base data, analyzes and calculates regional safety indexes of all the subregions, and transmits the regional safety indexes to the inspection early warning module and the overall safety evaluation module;
the calculation formula of the smoldering generation index is as follows: Wherein/> Generating a degree index for smoldering combustion of the ith sub-region,/>For the total concentration of carbon monoxide in the ith sub-zone,/>，/>For/>J=1, 2, 3 … … m;
the calculation formula of the open flame occurrence index is as follows: Wherein/> For the bright flame occurrence index of the ith sub-region,/>Wherein/>For the probability parameter of occurrence of the ith sub-region,/>The number of the patrol point images of the suspected flame area is finally judged as the ith sub-area;
The calculation formula of the area safety index is as follows: Wherein/> For the region safety index of the ith sub-region,/>Is a first proportional constant,/>Being a second proportionality constant, gamma being other influencing factors;
The overall safety evaluation module comprehensively calculates the safety indexes of all the subareas to obtain an overall safety index, carries out safety evaluation, transmits data to the control center for human-computer interaction if the evaluation result is safe, and transmits the data to the danger early warning module if the evaluation result is dangerous;
The calculation formula of the overall safety index is as follows: wherein ZT is the overall security index, Wherein/>For/>Weight factors of (2);
The inspection early-warning module performs primary early-warning analysis and advanced early-warning analysis, if the analysis result is in accordance with early warning, the inspection early-warning module transmits an early-warning instruction to the danger early-warning module, and simultaneously transmits a route resetting instruction to the inspection route optimization module, and the inspection early-warning module comprises a primary early-warning unit and an advanced early-warning unit;
After analyzing the data, the patrol route optimization module performs key patrol on all areas with high danger occurrence probability, generates an optimal patrol route and transmits the optimal patrol route to the patrol route planning module;
The danger early warning module carries out primary early warning notification and secondary early warning notification, and transmits data to the control center for man-machine interaction;
The control center is used for carrying out man-machine interaction on the data and sending a control instruction to the mobile sentry.
2. A mobile sentinel hazard early warning system for forest fires as defined in claim 1 wherein: the primary early warning unit performs early warning analysis on the data of the inspection data processing module, if the analysis result is primary early warning, a primary early warning instruction is sent to the dangerous early warning module, if the analysis result is secondary early warning, a secondary early warning instruction is sent to the dangerous early warning module, if the analysis result is unnecessary early warning, no instruction is sent, the advanced early warning unit performs early warning analysis on the data of the regional safety index analysis module, if the analysis result is primary early warning, a primary early warning instruction is sent to the dangerous early warning module, if the analysis result is secondary early warning, a secondary early warning instruction is sent to the dangerous early warning module, and if the analysis result is unnecessary early warning, no instruction is sent.
3. A mobile sentinel hazard early warning system for forest fires as defined in claim 1 wherein: the dangerous early warning module comprises a primary early warning notification unit and a secondary early warning notification unit, wherein the primary early warning notification unit is used for receiving a primary early warning instruction and carrying out primary early warning processing, and the secondary early warning notification unit is used for receiving a secondary early warning instruction and carrying out secondary early warning processing.
4. A mobile sentinel hazard early warning system for forest fires as defined in claim 1 wherein: the specific mode of extracting suspected flame area points by the patrol data processing module through the image extraction training model is as follows:
step S01: inputting model data: inputting image data of all patrol points of all subregions, preprocessing the image data of the jth patrol point of the ith subregion, dividing the image data into K frames of images, wherein the interval time of each frame of image is t;
step S02: performing pixel-by-pixel differential operation on the k frame and the k+1 frame images: ， and performing pixel-by-pixel addition operation on the k frame image and the k+1 frame image as a result of subtracting the k+1 frame image from the k frame image: /(I) Wherein/>F (K) is the gray value of the K frame image, f (k+1) is the gray value of the k+1 frame image, and k=1, 2, 3 … … K;
step S03: based on the traditional interframe difference method And/>Performing differential operation, and taking an absolute value: Wherein/> Binarizing the image after difference into a formula: wherein A is a binary image, and T is a binarization threshold;
Step S04: the suspected flame region identification is carried out on all binary images with A=1: the pixel coordinates of the image are marked as (X, Y) and substituted into the formula: Wherein/> (X, Y) is the edge of the moving object of the kth frame image,/>(X, Y) is the moving target edge of the (k+1) th frame image, sim (k, k+1) is the target edge similarity of the (k+1) th frame image and the (k+1) th frame image, and [ delta ] is the image area;
Calculating a target edge similarity mean value: Wherein/> For the average value of the similarity of the edges of the targets, if the result is found/>If the detection result is greater than the determination threshold YP, the ith region and the jth inspection point image are determined to be suspected flame regions, and if the detection result is required/>When the image is larger than the judging threshold YP, eliminating the jth patrol point image of the ith area;
Step S05: counting the judgment results of all the patrol point images of all the subareas, and marking the number of the patrol point images of the ith subarea judged to be the suspected flame area as The probability of the occurrence of a suspected flame region in the ith region is: Wherein/> Probability of occurrence of a suspected flame region image for the ith sub-region;
correcting the determination result based on the focus loss function: Wherein, the method comprises the steps of, wherein, As a focal point loss function, epsilon is a correction and adjustment parameter, the value is more than or equal to 0 and less than or equal to 5, and then step S02 is executed once;
step S06: outputting final data: outputting the number of the patrol point images of all the sub-areas suspected flame areas finally, and recording the number of the patrol point images of the i th sub-area finally judged as the suspected flame area as 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410233739.0A CN117809441B (en) | 2024-03-01 | 2024-03-01 | Mobile sentinel danger early warning system for forest fire prevention |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410233739.0A CN117809441B (en) | 2024-03-01 | 2024-03-01 | Mobile sentinel danger early warning system for forest fire prevention |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117809441A CN117809441A (en) | 2024-04-02 |
| CN117809441B true CN117809441B (en) | 2024-06-07 |
Family
ID=90426005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410233739.0A Active CN117809441B (en) | 2024-03-01 | 2024-03-01 | Mobile sentinel danger early warning system for forest fire prevention |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117809441B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001067566A (en) * | 1999-08-30 | 2001-03-16 | Fujitsu Ltd | Fire detecting device |
| CN105719421A (en) * | 2016-04-27 | 2016-06-29 | 丛静华 | Big data mining based integrated forest fire prevention informatization system |
| CN110929923A (en) * | 2019-11-08 | 2020-03-27 | 温州设计集团有限公司 | Urban safety risk management and control system based on digital twin technology |
| CN111476964A (en) * | 2020-03-04 | 2020-07-31 | 宁波财经学院 | Remote forest fire prevention monitoring system and method |
| CN112687070A (en) * | 2020-12-14 | 2021-04-20 | 浙江弄潮儿智慧科技有限公司 | Forest fire prevention early warning information emergency command system based on 5G communication |
-
2024
- 2024-03-01 CN CN202410233739.0A patent/CN117809441B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001067566A (en) * | 1999-08-30 | 2001-03-16 | Fujitsu Ltd | Fire detecting device |
| CN105719421A (en) * | 2016-04-27 | 2016-06-29 | 丛静华 | Big data mining based integrated forest fire prevention informatization system |
| CN110929923A (en) * | 2019-11-08 | 2020-03-27 | 温州设计集团有限公司 | Urban safety risk management and control system based on digital twin technology |
| CN111476964A (en) * | 2020-03-04 | 2020-07-31 | 宁波财经学院 | Remote forest fire prevention monitoring system and method |
| CN112687070A (en) * | 2020-12-14 | 2021-04-20 | 浙江弄潮儿智慧科技有限公司 | Forest fire prevention early warning information emergency command system based on 5G communication |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117809441A (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103106766B (en) | Forest fire identification method and forest fire identification system | |
| CN107437318B (en) | Visible light intelligent recognition algorithm | |
| KR102531272B1 (en) | Control device using artificial intelligence learning images and vibrations and intrusion alert systme including the same | |
| KR102398841B1 (en) | Method and system for determining danger in constuction sites based on image analysis | |
| CN101625789A (en) | Method for monitoring forest fire in real time based on intelligent identification of smoke and fire | |
| CN117037406B (en) | Intelligent monitoring and early warning system for forest fire | |
| KR102407327B1 (en) | Apparatus for Monitoring Fire And System having the same | |
| CN113011833A (en) | Safety management method and device for construction site, computer equipment and storage medium | |
| CN111257507A (en) | Gas concentration detection and accident early warning system based on unmanned aerial vehicle | |
| JP2014194686A (en) | Crime prevention system | |
| CN103152558A (en) | Intrusion detection method based on scene recognition | |
| CN110390790A (en) | A kind of gridding forest fire protection monitoring and pre-alarming method and system | |
| CN116704411A (en) | Security control method, system and storage medium based on Internet of things | |
| US20220366687A1 (en) | System and method for drone land condition surveillance | |
| CN114998846A (en) | Method and system for realizing intelligent system of offshore drilling platform and related components | |
| CN116778192A (en) | Fire safety early warning system based on air-ground equipment cooperation | |
| KR101903615B1 (en) | Visual observation system and visual observation method using the same | |
| CN114462882A (en) | Safety protection system for water conservancy construction based on internet of things | |
| CN115169777A (en) | Intelligent supervision system for safety operation | |
| CN117809441B (en) | Mobile sentinel danger early warning system for forest fire prevention | |
| US20150362370A1 (en) | Sensor-free image-based and computationally effective approach to vehicular, industrial and domestic air pollution estimation and control | |
| CN117671576A (en) | Imaging processing method for identifying dangerous target | |
| CN116778660A (en) | Fire disaster early warning system based on fire engineering | |
| CN116206253A (en) | Method and system for detecting and judging site fire behavior based on deep learning | |
| CN114582085A (en) | Early warning device |
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 |