CN114067534B - Geological disaster early warning method and system based on machine vision - Google Patents
Geological disaster early warning method and system based on machine vision Download PDFInfo
- Publication number
- CN114067534B CN114067534B CN202210023964.2A CN202210023964A CN114067534B CN 114067534 B CN114067534 B CN 114067534B CN 202210023964 A CN202210023964 A CN 202210023964A CN 114067534 B CN114067534 B CN 114067534B
- Authority
- CN
- China
- Prior art keywords
- target
- early warning
- climate
- value
- information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 241001464837 Viridiplantae Species 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 8
- 239000002689 soil Substances 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
-
- 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
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of disaster early warning, in particular to a geological disaster early warning method and system based on machine vision, which comprises the following steps: acquiring the received image sequence data at the target area; acquiring the received climate sequence data at the target area; generating a first target climate ratio based on the climate information of the preset time points, wherein the first target climate ratio is the ratio of the target climate quantity corresponding to the multiple preset time points in the preset time period to the total climate quantity; acquiring target images of a plurality of preset time points, extracting target object features in each target image based on machine vision, judging that the target object features meet a first requirement, and outputting first early warning information; and generating an early warning coefficient value based on the first target climate ratio, the target feature in each target image and the attribute information at the target area, pre-inputting the attribute information at the target area, obtaining an early warning grade based on the early warning coefficient value, and sending the first early warning information and the early warning grade to the target terminal.
Description
Technical Field
The invention relates to the technical field of disaster early warning, in particular to a geological disaster early warning method and system based on machine vision.
Background
Geological disasters refer to geological effects or phenomena formed under the action of natural or human factors, which cause losses to human life and property, and damage to the environment. The distribution change rule of geological disasters in time and space is not only limited by natural environment, but also related to human activities, and is often the result of interaction between human and the natural world.
Before geological disasters occur, pre-signs often appear, for example, before debris flow appears, the pre-signs often appear under the conditions of heavy rain and less vegetation; fire is probably caused by rain, withered yellow vegetation and dryness. Therefore, early warning can be effectively carried out on geological disasters by combining weather conditions and local vegetation conditions, and macroscopic regulation and control can be carried out according to early warning levels.
However, no suitable technical scheme is available at present, and disaster early warning can be carried out by combining weather and local vegetation conditions.
Disclosure of Invention
The embodiment of the invention provides a geological disaster early warning method and system based on machine vision, which can be used for carrying out disaster early warning by combining weather and local vegetation conditions, so that the early warning accuracy is improved, managers can effectively manage and regulate before disasters occur, and the disasters are avoided.
In a first aspect of the embodiments of the present invention, a geological disaster early warning method based on machine vision is provided, including:
acquiring received image sequence data at a target area, wherein the image sequence data comprises target images corresponding to each preset time point;
acquiring received climate sequence data at the target area, wherein the climate sequence data comprises climate information corresponding to each preset time point;
generating a first target climate ratio based on the climate information of the preset time points, wherein the first target climate ratio is the ratio of the target climate quantity and the total climate quantity corresponding to the multiple preset time points in a preset time period;
if the first target climate ratio is larger than the first preset climate numerical value, acquiring target images of the plurality of preset time points, extracting target object features in each target image based on machine vision, judging that the target object features meet a first requirement, and outputting first early warning information;
and generating an early warning coefficient value based on the first target climate ratio, the target feature in each target image and the attribute information at the target area, pre-inputting the attribute information at the target area, obtaining an early warning grade based on the early warning coefficient value, and sending the first early warning information and the early warning grade to a target terminal.
Optionally, in a possible implementation manner of the first aspect, generating a first target climate ratio based on the climate information at the preset time point, where the first target climate ratio is a ratio of a target climate quantity corresponding to multiple preset time points in a preset time period to a total climate quantity includes:
acquiring climate information corresponding to each preset time point in the climate sequence data, and determining the target climate quantity corresponding to a plurality of preset time points and the target climate information in the climate sequence data, wherein each preset time point corresponds to one climate information;
and acquiring the total amount of climate information in the climate sequence data to obtain a total climate number, and acquiring a ratio of the target climate number to the total climate number.
Optionally, in a possible implementation manner of the first aspect, if the target climate information is a rain climate, the target feature is a green plant feature, and the first warning information is landslide warning information;
and if the target climate information is non-rainwater climate, the target characteristic is a yellow plant characteristic, and the first early warning information is fire early warning information.
Optionally, in a possible implementation manner of the first aspect, the obtaining target images at the multiple preset time points, extracting a target feature in each target image based on machine vision, determining that the target feature meets a first requirement, and outputting first warning information includes:
presetting a target pixel threshold;
selecting target pixel points which are positioned in the target pixel threshold value in each target image based on machine vision, and extracting the quantity value of the target pixel points;
and acquiring the ratio of the number value of the target pixel points to the total pixel point number value to obtain a target pixel ratio value as a target object characteristic, wherein if the target pixel ratio value does not correspond to a preset ratio value, the target object characteristic does not meet a first requirement, and outputting first early warning information.
Optionally, in a possible implementation manner of the first aspect, obtaining a ratio of a number value of the target pixel to a total number value of the pixels to obtain a target pixel ratio value as the target object feature, and if the target pixel ratio value does not correspond to a preset ratio value, determining that the target object feature does not meet the first requirement includes:
the target pixel proportion value is calculated by the following formula,
wherein,
is the value of the target pixel scale and,
is as follows
The number value of the target pixel points of each target image,
is as follows
The total number of pixels of each target image is measured,
as to the total number of the target images,
is a weight value of the image,
the upper limit value of the target image is set;
presetting a preset proportion value
If, if
Is less than
Then the target feature does not meet the first requirement.
Optionally, in a possible implementation manner of the first aspect, generating an early warning coefficient value based on the first target climate ratio, the target feature in each target image, and the attribute information at the target area, where the attribute information at the target area is pre-recorded, obtaining an early warning level based on the early warning coefficient value, and sending the first early warning information and the early warning level to the target terminal includes:
extracting population density corresponding to the attribute information of the target area;
calculating and generating an early warning coefficient value based on the first target climate ratio value, the target feature in each target image and the population density through the following formula,
wherein,
for the value of the early warning coefficient,
the number of the target climates is,
as a function of the total number of climates,
in order to be the density of the population,
the weight of the population is the value of the population weight,
is an early warning weight value.
Optionally, in a possible implementation manner of the first aspect, generating an early warning coefficient value based on the first target climate ratio, the target feature in each target image, and the attribute information at the target area, where the attribute information at the target area is pre-recorded, obtaining an early warning level based on the early warning coefficient value, and sending the first early warning information and the early warning level to the target terminal includes:
presetting a plurality of early warning intervals, wherein each early warning interval has an early warning grade corresponding to the early warning interval;
and judging the early warning interval where the early warning coefficient value is located, and determining the early warning grade corresponding to the early warning coefficient value according to the early warning interval.
Optionally, in a possible implementation manner of the first aspect, the method further includes:
receiving early warning grade adjustment data sent by a target terminal, determining an early warning interval corresponding to the early warning grade adjustment data, and acquiring the highest numerical value and the lowest numerical value of the early warning interval;
and adjusting the early warning weight value based on the highest numerical value and the lowest numerical value of the early warning interval and the generated early warning coefficient value.
Optionally, in a possible implementation manner of the first aspect, adjusting the warning weight value based on the highest numerical value and the lowest numerical value of the warning interval and the generated warning coefficient value includes:
the early warning weight value is adjusted by the following formula,
wherein,
in order to adjust the early warning weight value,
is the highest numerical value of the early warning interval,
is the lowest numerical value of the early warning interval,
to adjust the weight values.
In a second aspect of the embodiments of the present invention, a geological disaster early warning system based on machine vision is provided, including:
the image acquisition module is used for acquiring received image sequence data at the target area, and the image sequence data comprises target images corresponding to each preset time point;
the climate acquisition module is used for acquiring received climate sequence data at the target area, and the climate sequence data comprises climate information corresponding to each preset time point;
the climate ratio determining module is used for generating a first target climate ratio based on the climate information of the preset time point, wherein the first target climate ratio is the ratio of the target climate quantity and the total climate quantity corresponding to the plurality of preset time points in a preset time period;
the image extraction module is used for acquiring the target images of the plurality of preset time points if the first target climate ratio is greater than the first preset climate numerical value, extracting target object features in each target image based on machine vision, judging that the target object features meet a first requirement, and outputting first early warning information;
and the early warning grade determining module is used for generating an early warning coefficient value based on the first target climate ratio, the target feature in each target image and the attribute information at the target area, pre-inputting the attribute information at the target area, obtaining an early warning grade based on the early warning coefficient value, and sending the first early warning information and the early warning grade to a target terminal.
In a third aspect of the embodiments of the present invention, a readable storage medium is provided, in which a computer program is stored, which, when being executed by a processor, is adapted to carry out the method according to the first aspect of the present invention and various possible designs of the first aspect of the present invention.
The invention provides a geological disaster early warning method and system based on machine vision, which can acquire and obtain images and data of a target area in a preset time period to obtain corresponding image sequence data and climate sequence data, process the image sequence data and the climate sequence data to obtain the ratio of the number of target climates to the total number of climates and the characteristics of a target object, obtain corresponding first early warning information if the ratio of the number of target climates to the total number of climates is larger than a first preset climatic value and the characteristics of the target object meet a first requirement, obtain early warning grades according to the first target climatic ratio, the characteristics of the target object and attribute information at the target area, effectively monitor and early warn the target area, determine the corresponding early warning grades according to different conditions and different attributes of different target areas, therefore, managers can conduct macroscopic regulation and control on the target area according to the early warning information and the early warning grade, and take corresponding disaster avoidance measures.
According to the technical scheme provided by the invention, when the early warning coefficient value is generated, the climate, the target object characteristics and the attribute information of the target area at a plurality of time points are comprehensively considered, so that the early warning coefficient value calculated by the method has more considered dimensions and is more accurate. The early warning weight value is adjusted according to the early warning level adjustment data input by the user, so that the adjusted early warning weight value is more suitable for the current applicable scene, and the subsequent generation of the early warning coefficient value is more accurate. Through the mode, the technical scheme of the invention can carry out deep learning, and continuously adjust the early warning weight value according to the early warning grade adjustment data, so that the accuracy of the early warning coefficient value is continuously improved.
Drawings
FIG. 1 is a flow chart of a first embodiment of a geological disaster warning method based on machine vision;
FIG. 2 is a flow chart of a second embodiment of a geological disaster warning method based on machine vision;
fig. 3 is a structural diagram of a first embodiment of a geological disaster warning system based on machine vision.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the processes do not mean the execution sequence, and the execution sequence of the processes should be determined by the functions and the internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
It should be understood that in the present application, "comprising" and "having" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that, in the present invention, "a plurality" means two or more. "and/or" is merely an association describing an associated object, meaning that three relationships may exist, for example, and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "comprises A, B and C" and "comprises A, B, C" means that all three of A, B, C comprise, "comprises A, B or C" means that one of A, B, C comprises, "comprises A, B and/or C" means that any 1 or any 2 or 3 of A, B, C comprises.
It should be understood that in the present invention, "B corresponding to a", "a corresponds to B", or "B corresponds to a" means that B is associated with a, and B can be determined from a. Determining B from a does not mean determining B from a alone, but may be determined from a and/or other information. And the matching of A and B means that the similarity of A and B is greater than or equal to a preset threshold value.
As used herein, "if" may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
The invention provides a geological disaster early warning method based on machine vision, as shown in figure 1, comprising the following steps:
step S110, collecting received image sequence data at the target area, where the image sequence data includes target images corresponding to each preset time point. The image sequence data can be regarded as a set of all image data in a preset time period, the preset time period can be from 5/1/2021 to 5/31/2021, and each preset time point can be regarded as a day, at this time, 31 preset time points can be regarded as existing, and each preset time point corresponds to a target image. The target area may be a pre-divided area, such as a mountain, hill, or the like. The target image is an aerial image of a mountain or a hill, a remote sensing image and the like.
Step S120, obtaining received climate sequence data at the target area, wherein the climate sequence data comprises climate information corresponding to each preset time point. The climate sequence data can be regarded as a set of all climate data in a preset time period, the preset time period can be from 5/1/2021 to 5/31/2021, each preset time point can be regarded as a day, at this time, 31 preset time points can be regarded as existing, and each preset time point corresponds to one climate information. The target area may be a pre-divided area, such as a mountain, hill, or the like. The climate information may include temperature, humidity, presence of rain and snow, etc., and the climate information in the present invention mainly considers the dimension of rain and snow at the target area.
Step S130, generating a first target climate ratio based on the climate information of the preset time points, wherein the first target climate ratio is the ratio of the target climate quantity and the total climate quantity corresponding to the multiple preset time points in the preset time period.
Step S140, if the first target climate ratio is larger than the first preset climate value, acquiring the target images of the plurality of preset time points, extracting the target feature in each target image based on machine vision, judging that the target feature meets a first requirement, and outputting first early warning information.
Taking the first warning information as the landslide warning information as an example, the first target climate ratio at this time is the number of rainy and snowy days accounting for the total weather in the preset time period, for example, the rainy and snowy days are 20 days, the preset time period is from 5/1/2021 to 5/31/2021, and the number of non-rainy and snowy days accounting for the total weather in the preset time period is 20/31. The first preset climate value is 0.5, and at this time 20/31 is already greater than 0.5, it is considered that a landslide is likely to occur in the climate dimension at this time, the present invention acquires target images at a plurality of preset time points, acquires a target feature in the target image at the target area, and the first requirement may be preset, and may output the first warning information according to the target feature.
Step S150, generating an early warning coefficient value based on the first target climate ratio, the target feature in each target image and the attribute information at the target area, inputting the attribute information at the target area in advance, obtaining an early warning grade based on the early warning coefficient value, and sending the first early warning information and the early warning grade to a target terminal.
After the first early warning information is obtained, the early warning coefficient value can be obtained according to the first target climate ratio, the target object characteristics in each target image and the attribute information of the target area, the early warning coefficient value can reflect the possibility of geological disasters of the area, and when the early warning coefficient value is larger, the possibility of geological disasters is proved to be higher.
In the technical solution provided by the present invention, as shown in fig. 2, step S130 specifically includes:
step S1301, acquiring climate information corresponding to each preset time point in the climate sequence data, and determining the target climate number corresponding to the target climate information and a plurality of preset time points in the climate sequence data, wherein each preset time point corresponds to one climate information. The climate information of each preset time point in the climate sequence data is acquired, and the climate information of each preset time point is compared with the target climate information. The target climate information may be rainy or snowy weather, or may be non-rainy or non-snowy weather.
For example, whether rain and snow weather occurs in each preset time point within a preset time period is judged, if a certain preset time point rains and snows, the weather information corresponding to the preset time point is the rain and snow weather, and if the certain preset time point does not rains and snows, the weather information corresponding to the preset time point is the non-rain and snow weather.
Step S1302, obtaining the total amount of the climate information in the climate sequence data to obtain a total climate number, and obtaining a ratio of the target climate number to the total climate number. The ratio of the target climate quantity to the total climate quantity can be obtained, for example, if the total number of the preset time points in the climate sequence data is 31 and the number of the target climate is 3, the ratio of the target climate quantity to the total climate quantity is 3/31, the number of rainy and snowy days in the preset time period to the total weather can be obtained through the above method, and the number of non-rainy and snowy days in the preset time period to the total weather is 28/31.
According to the technical scheme provided by the invention, if the target climate information is the rainwater climate, the target characteristic is the green plant characteristic, and the first early warning information is landslide early warning information. According to the technical scheme, landslide early warning can be carried out, when target climate information is rain climate, the probability of landslide is higher when the rain quantity in a preset time period is larger, the probability of landslide is higher when fewer green plants are used for proving that the fixity of the soil in the target area is smaller, the probability of landslide is higher, and the probability of landslide is higher when more green plants are used for proving that the fixity of the soil in the target area is higher, and the probability of landslide is lower. When landslide early warning is carried out, two dimensions of climate and vegetation are comprehensively considered, and therefore more accurate geological disaster early warning is carried out.
And if the target climate information is non-rainwater climate, the target characteristic is a yellow plant characteristic, and the first early warning information is fire early warning information. According to the technical scheme provided by the invention, fire early warning can be carried out, when the target climate information is a non-rainy and snowy climate, the probability of fire is higher when the rainfall is smaller in the preset time period, and more yellow plants prove that more plants which are easy to catch fire are more, so that the probability of fire is increased at the moment. When fire disaster early warning is carried out, two dimensions of climate and vegetation are comprehensively considered, and therefore more accurate geological disaster early warning is carried out.
In the technical solution provided by the present invention, step S140 specifically includes:
a target pixel threshold is set in advance. According to the present invention, different target pixel thresholds are set according to different target object characteristics, for example, the target object characteristics are green plant characteristics, and at this time, the target pixel threshold is a pixel interval corresponding to green, and the pixel interval may be a set, and RGB values in the set are, for example, (0, 255, 0), (127, 255, 0), (64, 224, 205), and … …).
And selecting target pixel points which are positioned in the target pixel threshold value in each target image based on machine vision, and extracting the quantity value of the target pixel points. The method determines target pixel points which are positioned in the target pixel threshold value in each target image in a machine vision mode, and extracts the number value of the target pixel points, for example, the number of the target pixel points in the target image is totally 100, at the moment, the number of the target pixel points positioned in the target pixel threshold value is 10, and at the moment, the number value of the target pixel points is 10.
And acquiring the ratio of the number value of the target pixel points to the total pixel point number value to obtain a target pixel ratio value as a target object characteristic, wherein if the target pixel ratio value does not correspond to a preset ratio value, the target object characteristic does not meet a first requirement, and outputting first early warning information. According to the technical scheme provided by the invention, the ratio of the number value of the target pixel point to the total pixel point number value is used as the target feature, when the number of the target pixel points in the target pixel threshold is 10 and the total pixel point number value is 100, the ratio of the number value of the target pixel point to the total pixel point number value is 10/100, and 10/100 can be the target feature.
In the invention, whether the target pixel proportion value corresponds to the preset proportion value or not is judged, taking geological disasters as landslide disasters as an example, when the target pixel proportion value is larger than the preset proportion value, the target pixel proportion value is considered to be corresponding to the preset proportion value, and when the target pixel proportion value is smaller than the preset proportion value, the target pixel proportion value is considered to be not corresponding to the preset proportion value.
If the target pixel proportion value is smaller than the preset proportion value, it is considered that green vegetation in the target area is less at the moment, the fixing capacity of soil in the target area is poor, and geological disasters such as landslide and the like easily occur, the target pixel proportion value is not corresponding to the preset proportion value at the moment, the target feature does not meet the first requirement, and first early warning information is output.
Different target object characteristics may correspond to different first requirements, when the geological disaster is a fire disaster, the target object characteristic yellow plant characteristics corresponding to the fire disaster are regarded as non-corresponding to the preset ratio value when the target pixel ratio value is larger than the preset ratio value, because the yellow plant characteristics are more, the fire disaster is easy to happen at the moment, and at the moment, first early warning information is output.
The invention can set different first requirements according to different actual conditions and actual scenes.
According to the technical scheme provided by the invention, the step of obtaining the proportion of the number value of the target pixel point to the total number value of the pixel points to obtain the target pixel proportion value as the target object characteristic, wherein if the target pixel proportion value does not correspond to the preset proportion value, the step that the target object characteristic does not meet the first requirement comprises the following steps:
the target pixel proportion value is calculated by the following formula,
wherein,
is the value of the target pixel scale and,
is as follows
The number value of the target pixel points of each target image,
is as follows
The total number of pixels of each target image is measured,
as to the total number of the target images,
is a weight value of the image,
can be regarded as the second
The number value of the target pixel points of each target image,
is as follows
The total number of pixels of each target image is measured,
can be regarded as the second
An object image, and
is the upper limit value of the target image.
Presetting a preset proportion value
If, if
Is less than
Then the target feature does not meet the first requirement. Taking the feature of the target as the feature of the green plant as an example, by
The average value of the target pixel point values in all the target images in the preset time period in the total pixel point number value can be obtained. The image weight value may be prePreviously set, for example, the number of vegetation under a unit pixel, and the like.
The number of pixel points of the green plants of the target image in the preset time period can be reflected,
the larger the vegetation is, the more green vegetation is in the target area, the larger the fixing force of the vegetation to the soil is, and the more difficult the landslide is.
The smaller the vegetation is, the less green vegetation is in the target area, the smaller the fixing force of the vegetation to the soil is, and the more landslide is likely to occur.
The invention can preset the preset proportion value
Presetting a proportional value
Can be determined according to actual scenes and preset proportional values of different regions
May be different.
The technical scheme provided by the invention further comprises the following steps:
and extracting the population density corresponding to the attribute information at the target area. The population density of each target area can be preset, and the greater the population density, the higher the risk of geological disaster, so the invention introduces the dimension of population density to generate the early warning coefficient value.
Calculating and generating an early warning coefficient value based on the first target climate ratio value, the target feature in each target image and the population density through the following formula,
wherein,
for the value of the early warning coefficient,
the number of the target climates is,
as a function of the total number of climates,
in order to be the density of the population,
the weight of the population is the value of the population weight,
is an early warning weight value. By passing
And obtaining a ratio value of the target climate quantity to the total climate quantity.
Taking the predicted geological disasters as landslides and debris flows as examples,
the larger the weather, the more rainy and snowy weather, the more possibility of landslide and debris flow at the time,
the larger the vegetation, the more green vegetation proves, and the possibility of landslide and debris flow is reduced. The greater the population density, the higher the risk of geological disasters, and the invention can synthesize the three dimensions to obtain the early warning coefficient value, so that managers can comprehensively consider the possibility and the hazard of the geological disasters to carry out priority treatment and thorough treatment on the corresponding areas, thereby reducing the possibility of address disastersCan reduce the loss caused by geological disasters.
When geological disasters such as landslide and debris flow are predicted, the higher the early warning coefficient value is, the higher the possibility and danger of geological disasters are. The administrator needs to perform priority and emphasis processing at this time.
According to the technical scheme provided by the invention, an early warning coefficient value is generated based on the first target climate ratio, the target feature in each target image and the attribute information at the target area, the attribute information at the target area is pre-recorded, an early warning grade is obtained based on the early warning coefficient value, and the first early warning information and the early warning grade are sent to a target terminal, wherein the early warning coefficient value comprises the following steps:
a plurality of early warning intervals are preset, and each early warning interval has an early warning grade corresponding to the early warning interval. In order to enable an administrator to know the early warning condition of a target area more intuitively, the method and the system can preset a plurality of early warning intervals, and each early warning interval has an early warning grade corresponding to the early warning interval. For example, the value corresponding to the early warning interval 1 is greater than or equal to 10 and less than 20; the numerical value corresponding to the early warning interval 2 is greater than or equal to 20 and less than 30. The early warning interval 1 may correspond to a first early warning level, and the early warning interval 1 may correspond to a second early warning level. The invention does not limit the number of the early warning grades and the early warning intervals.
And judging the early warning interval where the early warning coefficient value is located, and determining the early warning grade corresponding to the early warning coefficient value according to the early warning interval. For example, the early warning coefficient value is 25, and at this time, the early warning coefficient value is within the early warning interval 2 greater than or equal to 20 and less than 30, the early warning interval corresponding to the early warning coefficient value is the early warning interval 2.
The technical scheme provided by the invention further comprises the following steps:
the method comprises the steps of receiving early warning grade adjustment data sent by a target terminal, determining an early warning interval corresponding to the early warning grade adjustment data, and obtaining the highest numerical value and the lowest numerical value of the early warning interval. After the early warning interval is obtained and sent to the administrator, the administrator possibly adjusts the early warning interval to be low or high according to the actual situation.
When the administrator turns down and turns up the early warning interval according to the actual situation, the administrator of the early warning coefficient value obtained by the technical scheme provided by the invention is proved to be inaccurate, so that the administrator can actively adjust the early warning coefficient value. At the moment, the invention can determine the early warning interval adjusted by the administrator and acquire the highest numerical value and the lowest numerical value corresponding to the early warning interval. For example, the early warning interval displayed by the administrator is the early warning interval 2, and the administrator inputs early warning level adjustment data to adjust the early warning interval 2 to be the early warning interval 3. The numerical value corresponding to the warning interval 3 may be greater than or equal to 30 and less than 40. The highest value 40 and the lowest value 30 of the warning interval 3 are obtained at this time. The highest value 40 at this time may be considered as a quasi-value, that is, the warning interval 3 does not actually include 40, but for the subsequent calculation, 40 is quasi-to be the highest value in the warning interval 3.
And adjusting the early warning weight value based on the highest numerical value and the lowest numerical value of the early warning interval and the generated early warning coefficient value. The invention can update and adjust according to the highest numerical value and the lowest numerical value of the early warning interval and the generated early warning coefficient value, so that the adjusted early warning weight value is more accurate and is suitable for calculating geological disasters in a local target area.
According to the technical scheme provided by the invention, the adjustment of the early warning weight value based on the highest numerical value and the lowest numerical value of the early warning interval and the generated early warning coefficient value comprises the following steps:
the early warning weight value is adjusted by the following formula,
wherein,
in order to adjust the early warning weight value,
is the highest numerical value of the early warning interval,
is the lowest numerical value of the early warning interval,
to adjust the weight values. When the early warning weight value is adjusted, the early warning weight value is adjusted to be higher or lower according to the behavior of an administrator.
When the administrator heightens the early warning interval, the invention can adjust the early warning interval according to the formula
Obtaining the adjusted early warning weight value
Can use the early warning weighted value
And (5) adjusting the height. By passing
Can reflect the distance relationship between the adjusted early warning interval and the output early warning coefficient value, if
The larger the value is, the more the numerical value difference between the early warning coefficient value and the adjusted early warning interval is proved to be, and the early warning weight value needs to be increased greatly at the moment. If it is not
The smaller the value is, the smaller the difference between the early warning coefficient value and the adjusted early warning interval is, and the higher the early warning weight value needs to be.
When the administrator lowers the early warning interval, the invention can set the early warning interval according to the formula
Obtaining the adjusted early warning weight value
Can use the early warning weighted value
And (5) turning down. By passing
Can reflect the distance relationship between the adjusted early warning interval and the output early warning coefficient value, if
The larger the value is, the more the numerical value difference between the early warning coefficient value and the adjusted early warning interval is proved to be, and the early warning weight value needs to be greatly reduced at the moment. If it is not
The smaller the value is, the smaller the difference between the early warning coefficient value and the adjusted early warning interval is, and the lower the early warning weight value needs to be adjusted at the moment.
Through the mode, the early warning weight value can be dynamically and intelligently changed according to the early warning grade adjusting data input by the user, and the accuracy of the early warning system during disaster early warning is improved.
The technology provided by the invention is a geological disaster early warning system based on machine vision, as shown in figure 3, comprising:
the image acquisition module is used for acquiring received image sequence data at the target area, and the image sequence data comprises target images corresponding to each preset time point;
the climate acquisition module is used for acquiring received climate sequence data at the target area, and the climate sequence data comprises climate information corresponding to each preset time point;
the climate ratio determining module is used for generating a first target climate ratio based on the climate information of the preset time point, wherein the first target climate ratio is the ratio of the target climate quantity and the total climate quantity corresponding to the plurality of preset time points in a preset time period;
the image extraction module is used for acquiring the target images of the plurality of preset time points if the first target climate ratio is greater than the first preset climate numerical value, extracting target object features in each target image based on machine vision, judging that the target object features meet a first requirement, and outputting first early warning information;
and the early warning grade determining module is used for generating an early warning coefficient value based on the first target climate ratio, the target feature in each target image and the attribute information at the target area, pre-inputting the attribute information at the target area, obtaining an early warning grade based on the early warning coefficient value, and sending the first early warning information and the early warning grade to a target terminal.
The readable storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media may be any available media that can be accessed by a general purpose or special purpose computer. For example, a readable storage medium is coupled to the processor such that the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Additionally, the ASIC may reside in user equipment. Of course, the processor and the readable storage medium may also reside as discrete components in a communication device. The readable storage medium may be a read-only memory (ROM), a random-access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
The present invention also provides a program product comprising execution instructions stored in a readable storage medium. The at least one processor of the device may read the execution instructions from the readable storage medium, and the execution of the execution instructions by the at least one processor causes the device to implement the methods provided by the various embodiments described above.
In the above embodiments of the terminal or the server, it should be understood that the Processor may be a Central Processing Unit (CPU), other general-purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (3)
1. A geological disaster early warning method based on machine vision is characterized by comprising the following steps:
step S110, collecting received image sequence data at a target area, wherein the image sequence data comprises target images corresponding to each preset time point;
step S120, obtaining received climate sequence data at the target area, wherein the climate sequence data comprises climate information corresponding to each preset time point;
step S130, generating a first target climate ratio based on the climate information of the preset time points, wherein the first target climate ratio is the ratio of the target climate quantity and the total climate quantity corresponding to the multiple preset time points in a preset time period;
step S130 specifically includes:
acquiring climate information corresponding to each preset time point in the climate sequence data, and determining the target climate quantity corresponding to a plurality of preset time points and the target climate information in the climate sequence data, wherein each preset time point corresponds to one climate information;
obtaining the total amount of climate information in the climate sequence data to obtain a total climate number, and obtaining the ratio of the target climate number to the total climate number
Step S140, if the first target climate ratio is larger than the first preset climate value, acquiring target images of the plurality of preset time points, extracting target object features in each target image based on machine vision, judging that the target object features meet a first requirement, and outputting first early warning information;
step S140 specifically includes:
presetting a target pixel threshold;
selecting target pixel points which are positioned in the target pixel threshold value in each target image based on machine vision, and extracting the quantity value of the target pixel points;
acquiring the ratio of the number value of the target pixel points to the total pixel point number value to obtain a target pixel ratio value as a target object characteristic, and if the target pixel ratio value does not correspond to a preset ratio value, outputting first early warning information if the target pixel ratio value does not meet a first requirement;
the target pixel proportion value is calculated by the following formula,
wherein,
is the value of the target pixel scale and,
is as follows
The number value of the target pixel points of each target image,
is as follows
The total number of pixels of each target image is measured,
as to the total number of the target images,
is a weight value of the image,
the upper limit value of the target image is set;
presetting a preset proportion value
If, if
Is less than
If the target object characteristic does not meet the first requirement;
s150, generating an early warning coefficient value based on the first target climate ratio, the target feature in each target image and the attribute information at the target area, pre-inputting the attribute information at the target area, obtaining an early warning grade based on the early warning coefficient value, and sending the first early warning information and the early warning grade to a target terminal;
step S150 specifically includes:
extracting population density corresponding to the attribute information of the target area;
calculating and generating an early warning coefficient value based on the first target climate ratio value, the target feature in each target image and the population density through the following formula,
wherein,
for the value of the early warning coefficient,
the number of the target climates is,
as a function of the total number of climates,
in order to be the density of the population,
the weight of the population is the value of the population weight,
is an early warning weight value;
presetting a plurality of early warning intervals, wherein each early warning interval has an early warning grade corresponding to the early warning interval;
judging an early warning interval where the early warning coefficient value is located, and determining an early warning grade corresponding to the early warning coefficient value according to the early warning interval;
receiving early warning grade adjustment data sent by a target terminal, determining an early warning interval corresponding to the early warning grade adjustment data, and acquiring the highest numerical value and the lowest numerical value of the early warning interval;
adjusting an early warning weight value based on the highest numerical value and the lowest numerical value of the early warning interval and the generated early warning coefficient value;
the early warning weight value is adjusted by the following formula,
wherein,
in order to adjust the early warning weight value,
is the highest numerical value of the early warning interval,
is the lowest numerical value of the early warning interval,
to adjust the weight values.
2. The machine-vision-based geological disaster warning method as claimed in claim 1,
if the target climate information is rain climate, the target characteristic is green plant characteristic, and the first early warning information is landslide early warning information;
and if the target climate information is non-rainwater climate, the target characteristic is a yellow plant characteristic, and the first early warning information is fire early warning information.
3. A geological disaster early warning system based on machine vision, which is used for realizing the geological disaster early warning method based on machine vision as claimed in any one of claims 1 to 2, and is characterized by comprising:
the image acquisition module is used for acquiring received image sequence data at the target area, and the image sequence data comprises target images corresponding to each preset time point;
the climate acquisition module is used for acquiring received climate sequence data at the target area, and the climate sequence data comprises climate information corresponding to each preset time point;
the climate ratio determining module is used for generating a first target climate ratio based on the climate information of the preset time point, wherein the first target climate ratio is the ratio of the target climate quantity and the total climate quantity corresponding to the plurality of preset time points in a preset time period;
the image extraction module is used for acquiring the target images of the plurality of preset time points if the first target climate ratio is greater than the first preset climate numerical value, extracting target object features in each target image based on machine vision, judging that the target object features meet a first requirement, and outputting first early warning information;
and the early warning grade determining module is used for generating an early warning coefficient value based on the first target climate ratio, the target feature in each target image and the attribute information at the target area, pre-inputting the attribute information at the target area, obtaining an early warning grade based on the early warning coefficient value, and sending the first early warning information and the early warning grade to a target terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210023964.2A CN114067534B (en) | 2022-01-11 | 2022-01-11 | Geological disaster early warning method and system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210023964.2A CN114067534B (en) | 2022-01-11 | 2022-01-11 | Geological disaster early warning method and system based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114067534A CN114067534A (en) | 2022-02-18 |
| CN114067534B true CN114067534B (en) | 2022-03-29 |
Family
ID=80230743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210023964.2A Active CN114067534B (en) | 2022-01-11 | 2022-01-11 | Geological disaster early warning method and system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114067534B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114998752B (en) * | 2022-08-04 | 2023-01-06 | 深圳市海清视讯科技有限公司 | Geological disaster identification method, device, equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8620841B1 (en) * | 2012-08-31 | 2013-12-31 | Nest Labs, Inc. | Dynamic distributed-sensor thermostat network for forecasting external events |
| CN113139020A (en) * | 2021-04-22 | 2021-07-20 | 成都智汇数援科技有限公司 | Self-adaptive migration method of landslide monitoring and early warning model |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4601684B2 (en) * | 2008-04-25 | 2010-12-22 | シャープ株式会社 | Evacuation route acquisition system, portable terminal device, evacuation route acquisition method, evacuation route acquisition program, computer-readable recording medium |
| WO2018119880A1 (en) * | 2016-12-29 | 2018-07-05 | 柳成荫 | Early warning method and device for rainfall induced landslides based on rainfall and soil moisture |
| CN107657329B (en) * | 2017-07-04 | 2021-07-06 | 江苏鸿利智能科技股份有限公司 | Intelligent scheduling decision method for flood and drought prevention based on extreme weather condition |
| CN108320461A (en) * | 2018-02-08 | 2018-07-24 | 中国地质大学（武汉） | A kind of landslide disaster monitoring device and its monitoring method |
| CN110634258A (en) * | 2019-08-19 | 2019-12-31 | 广西电网有限责任公司电力科学研究院 | Mountain fire identification method aiming at satellite monitoring mountain fire data of power transmission line |
| US10964201B1 (en) * | 2019-09-27 | 2021-03-30 | The Travelers Indemnity Company | Wildfire defender |
| CN111799886A (en) * | 2020-06-04 | 2020-10-20 | 庄宿龙 | Lightning protection field state monitoring system and method |
| CN113283276A (en) * | 2020-12-30 | 2021-08-20 | 四川弘和通讯有限公司 | Linkage thermal imaging self-learning fire point detection method and system |
-
2022
- 2022-01-11 CN CN202210023964.2A patent/CN114067534B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8620841B1 (en) * | 2012-08-31 | 2013-12-31 | Nest Labs, Inc. | Dynamic distributed-sensor thermostat network for forecasting external events |
| CN113139020A (en) * | 2021-04-22 | 2021-07-20 | 成都智汇数援科技有限公司 | Self-adaptive migration method of landslide monitoring and early warning model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114067534A (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110119728B (en) | Remote sensing image cloud detection method based on multi-scale fusion semantic segmentation network | |
| CN111079663A (en) | High-altitude parabolic monitoring method and device, electronic equipment and storage medium | |
| JP5388829B2 (en) | Intruder detection device | |
| Giuliani et al. | Using crowdsourced web content for informing water systems operations in snow-dominated catchments | |
| WO2007000999A1 (en) | Image analysis device and image analysis method | |
| CN111275040B (en) | Positioning method and device, electronic equipment and computer readable storage medium | |
| CN113469278B (en) | Strong weather target identification method based on deep convolutional neural network | |
| CN110488391B (en) | Weather prediction system, method and storage medium for small area | |
| Li et al. | A filtering method for ICESat-2 photon point cloud data based on relative neighboring relationship and local weighted distance statistics | |
| CN114067534B (en) | Geological disaster early warning method and system based on machine vision | |
| CN111680259A (en) | Cloud particle phase recognition method and system | |
| CN114926466B (en) | Land integrated monitoring and decision-making method and platform based on big data | |
| CN116612609B (en) | Disaster early warning method and system based on landslide hazard prediction | |
| JP2001143054A (en) | Satellite image-processing method | |
| KR20200071042A (en) | Method for predicting of tropical thunderstorms | |
| KR101874968B1 (en) | Visibility measuring system base on image information and method for using the same | |
| CN110969642B (en) | Video filtering method and device, electronic equipment and storage medium | |
| CN113269175B (en) | Fire monitoring method and device | |
| Zhao et al. | Image dehazing based on haze degree classification | |
| Sardar et al. | Ensemble learning with CNN and BMO for drought prediction | |
| KR102457470B1 (en) | Apparatus and Method for Artificial Intelligence Based Precipitation Determination Using Image Analysis | |
| KR101877173B1 (en) | Coastline Detection System using Satellite Image and method thereof | |
| CN116243273A (en) | Photon counting laser radar data filtering method and device | |
| JP2021009457A (en) | Agriculture support device | |
| KR20230143499A (en) | Raindrop Size Distribution and Rainrate Estimation Method Using CCTV |
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 |