CN110705759B - Water level early warning monitoring method and device, storage medium and electronic equipment - Google Patents

Water level early warning monitoring method and device, storage medium and electronic equipment Download PDF

Info

Publication number
CN110705759B
CN110705759B CN201910879437.XA CN201910879437A CN110705759B CN 110705759 B CN110705759 B CN 110705759B CN 201910879437 A CN201910879437 A CN 201910879437A CN 110705759 B CN110705759 B CN 110705759B
Authority
CN
China
Prior art keywords
water level
early warning
level monitoring
preset
structural feature
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
Application number
CN201910879437.XA
Other languages
Chinese (zh)
Other versions
CN110705759A (en
Inventor
王红伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN201910879437.XA priority Critical patent/CN110705759B/en
Publication of CN110705759A publication Critical patent/CN110705759A/en
Priority to PCT/CN2020/092807 priority patent/WO2021051863A1/en
Application granted granted Critical
Publication of CN110705759B publication Critical patent/CN110705759B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Evolutionary Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Mathematical Physics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Medical Informatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Alarm Systems (AREA)

Abstract

The application relates to a water level early warning monitoring method, a water level early warning monitoring device, a storage medium and electronic equipment, belonging to the technical field of water level monitoring, wherein the method comprises the following steps: acquiring a first water level monitoring image of a preset water level monitoring place at a first time point, and segmenting to obtain a first building structure characteristic diagram; acquiring a second water level monitoring image of a second time point at fixed time, and segmenting to obtain a second building structure characteristic diagram; acquiring a structural feature change area relative to the first building structural feature map in the second building structural feature map, and acquiring a structural feature initial area corresponding to the structural feature change area in the first building structural feature map; extracting a plurality of characteristic change subdomain sequences of a preset water level monitoring place; and inputting the characteristic change subdomain sequence of the preset sequence into a machine learning model to obtain a regular early warning risk value of the preset water level monitoring place. According to the method and the device, the water level monitoring and early warning are efficiently and accurately realized through a machine learning model based on the extraction of the real-time characteristic change subdomain sequence.

Description

Water level early warning monitoring method and device, storage medium and electronic equipment
Technical Field
The application relates to the technical field of water level monitoring, in particular to a water level early warning monitoring method and device, a storage medium and electronic equipment.
Background
At places with lower terrain, such as overpasses, pedestrian overpasses and the like, the water level is easy to rise seriously in heavy rain, and vehicles and personnel are easy to be submerged. For example, overpasses in different places have different construction styles according to surrounding environments, risks caused by water levels are different due to the construction characteristics, and therefore, early warning and monitoring of the water levels in the places are difficult.
At present, the water level early warning monitoring in the places usually carries out early warning by setting a monitoring alarm containing various sensors, and the water level early warning monitoring is carried out by matching with workers to observe in real time according to a camera. In the prior art, the water level early warning monitoring cannot be carried out in time based on real-time environment change according to the characteristics of different monitoring places, and huge human resources are required to be consumed.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present application and therefore may include information that does not constitute prior art known to a person of ordinary skill in the art.
Disclosure of Invention
An object of this application is to provide a water level early warning monitoring scheme, and then at least to a certain extent through machine learning model, be real-time characteristic change subdomain sequence based on the water level control place of extracting, realize carrying out the water level control early warning high-efficiently, accurately.
According to one aspect of the application, a water level early warning monitoring method is provided, which comprises the following steps:
when a water level early warning monitoring signal is received, acquiring a first water level monitoring image of a preset water level monitoring place at a first time point when the water level early warning monitoring signal is received, and segmenting the first water level monitoring image to obtain a first building structure characteristic diagram;
acquiring a second water level monitoring image of the preset water level monitoring place of a second time point after the first time point in a timing mode, and dividing the second water level monitoring image to obtain a second building structure characteristic diagram;
acquiring a structural feature change area in the second building structural feature map relative to the first building structural feature map, and acquiring a structural feature initial area in the first building structural feature map corresponding to the structural feature change area;
extracting a plurality of characteristic change subdomain sequences of the preset water level monitoring place based on the structural characteristic change area, the structural characteristic initial area and a preset standard building structural characteristic diagram;
And inputting the characteristic change subdomain sequence of the preset sequence in the characteristic change subdomain sequences into a pre-trained machine learning model to obtain a regular early warning risk value of the preset water level monitoring place.
In an exemplary embodiment of the present application, the extracting a plurality of characteristic change sub-domain series of the predetermined water level monitoring place based on the structural characteristic change area, the structural characteristic initial area and the preset standard building structural characteristic map includes
A plurality of inner contours which are the same as the edge contours in shape are obtained based on the inward shrinkage of the edge contours of the structural feature change areas;
extracting an outer change subdomain between the edge profile and an outermost inner profile of the plurality of inner profiles, extracting an inner change subdomain surrounded by an innermost inner profile of the plurality of inner profiles, and extracting other change subdomains between two adjacent inner profiles of the plurality of inner profiles;
sequentially acquiring initial subdomains and standard subdomains of positions corresponding to the outer side variation subdomain, the inner side variation subdomain and the other variation subdomains in the structural feature initial region and the preset standard building structural feature graph;
And connecting each of the outer side change subdomain, the inner side change subdomain and the other change subdomains in series with the initial subdomain and the standard subdomain at corresponding positions to obtain a plurality of characteristic change subdomain sequences.
In an exemplary embodiment of the present application, the training method of the machine learning model is:
acquiring a characteristic change subdomain sequence sample set of a predetermined sequence, wherein each sample calibrates a corresponding regular early warning risk value in advance;
respectively inputting the data of each sample into a machine learning model to obtain a regular early warning risk value output by the machine learning model;
if the obtained regular early warning risk value is inconsistent with the regular early warning risk value calibrated in advance for the sample after the data of the sample is input into the machine learning model, adjusting the coefficient of the machine learning model until the obtained regular early warning risk value is consistent with the regular early warning risk value calibrated in advance for the sample;
and when the data of all the samples are input into the machine learning model, the obtained regular early warning risk value is consistent with the regular early warning risk value calibrated for the data sample in advance, and the training is finished.
In an exemplary embodiment of the present application, after the obtaining, when receiving the water level early warning monitoring signal, a first water level monitoring image of a predetermined water level monitoring place at a first time point when receiving the water level early warning monitoring signal, and segmenting the first water level monitoring image to obtain a first building structure characteristic map, the method further includes:
According to the first building structure characteristic diagram, calibrating a water level early warning category for the preset water level monitoring place;
acquiring the weight of a preset water level monitoring element according to the water level early warning category, wherein the preset water level monitoring element comprises a water level rising rate, the number of people and the moving frequency of people;
regularly collecting a plurality of second water level monitoring images after the first time point to form a second water level monitoring image sequence so as to obtain the water level rising rate, the number of people and the moving frequency of people based on the second water level monitoring image sequence;
and acquiring a regular early warning risk value of the preset water level monitoring place based on the water level rising rate, the number of people, the moving frequency of people and the weight of the preset water level monitoring element.
In an exemplary embodiment of the present application, the calibrating the water level early warning category for the predetermined water level monitoring place according to the first building structure characteristic diagram includes:
acquiring the areas of all buildings on the first building structure characteristic diagram according to the first building structure characteristic diagram;
acquiring water level rise contribution factors of all buildings from a preset water level monitoring building information table;
Acquiring the water level rise rate of the preset water level monitoring place according to the areas of all the buildings and the water level rise contribution factors;
and according to the water level rising rate, calibrating the water level early warning category for the preset water level monitoring place.
In an exemplary embodiment of the present application, the obtaining, according to the water level early warning category, a weight of a predetermined water level monitoring element, where the predetermined water level monitoring element includes a water level rising rate, a number of people, and a moving frequency of people, includes:
according to the water level early warning type, searching a target early warning type corresponding to the water level early warning type from a preset water level early warning information table;
and acquiring the weight of a preset water level monitoring element associated with the target early warning category, wherein the preset water level monitoring element comprises a water level rising rate, the number of people and the moving frequency of people.
In an exemplary embodiment of the present application, the obtaining a periodic early warning risk value of the predetermined water level monitoring location based on the water level rising rate, the number of people, the moving frequency of people, and the weight of the predetermined water level monitoring element includes:
and obtaining the regular early warning risk value according to a formula U ═ mX nY)/wV, wherein U is the regular early warning risk value, X is the water level rising rate, Y is the number of people, V is the moving frequency of people, and m, n and w are the weights of the preset water level monitoring elements associated with the target early warning category respectively.
According to an aspect of the present application, there is provided a water level early warning monitoring apparatus, comprising:
the system comprises a first acquisition module, a first display module and a second acquisition module, wherein the first acquisition module is used for acquiring a first water level monitoring image of a preset water level monitoring place at a first time point when a water level early warning monitoring signal is received, and segmenting the first water level monitoring image to obtain a first building structure characteristic diagram;
the second acquisition module is used for acquiring a second water level monitoring image of the preset water level monitoring place at a second time point after the first time point in a timing manner, and segmenting the second water level monitoring image to obtain a second building structure characteristic diagram;
a third obtaining module, configured to obtain a structural feature change area in the second architectural structural feature map relative to the first architectural structural feature map, and obtain a structural feature initial area in the first architectural structural feature map that corresponds to the structural feature change area;
the extraction module is used for extracting a plurality of characteristic change subdomain sequences of the preset water level monitoring place based on the structural characteristic change area, the structural characteristic initial area and a preset standard building structural characteristic diagram;
And the prediction module is used for inputting the characteristic change subdomain sequences of the preset sequences in the plurality of characteristic change subdomain sequences into a machine learning model trained in advance to obtain the regular early warning risk value of the preset water level monitoring place.
According to an aspect of the present application, there is provided a computer readable storage medium having a water level pre-warning monitoring program stored thereon, wherein the water level pre-warning monitoring program is executed by a processor to implement the method of any one of the above.
According to an aspect of the present application, there is provided an electronic device, comprising:
a processor; and
the memory is used for storing a water level early warning monitoring program of the processor; wherein the processor is configured to perform any of the methods described above via execution of the water level warning monitoring program.
The method comprises the steps of firstly, when a water level early warning monitoring signal is received, obtaining a first water level monitoring image of a preset water level monitoring place at a first time point when the water level early warning monitoring signal is received, and dividing the first water level monitoring image to obtain a first building structure characteristic diagram; therefore, the first building structure characteristic diagram which can clearly and concisely represent the condition of the building structure when the water level early warning monitoring signal is received by the preset water level monitoring place can be obtained. Then, a second water level monitoring image of the preset water level monitoring place at a second time point after the first time point is obtained in a timing mode, and the second water level monitoring image is divided to obtain a second building structure characteristic diagram; in this way, a second building structure characteristic diagram which can clearly and simply represent the real-time building structure condition of the preset water level monitoring place can be obtained. Further, acquiring a structural feature change area relative to the first building structural feature map in the second building structural feature map, and acquiring a structural feature initial area corresponding to the structural feature change area in the first building structural feature map; the structural characteristics of the change of the outline structure of the water level monitoring place in real time can be clearly obtained. Then, extracting a plurality of characteristic change subdomain sequences of the preset water level monitoring place based on the structural characteristic change area, the structural characteristic initial area and a preset standard building structural characteristic diagram; a plurality of characteristic change subdomain sequences which can simply reflect the dynamic change condition of the building structure of the preset water level monitoring place can be obtained, and then the risk of the monitoring place can be accurately and efficiently analyzed. And finally, inputting the characteristic change subdomain sequences of the preset sequences in the plurality of characteristic change subdomain sequences into a pre-trained machine learning model to obtain the regular early warning risk value of the preset water level monitoring place. Therefore, the water level monitoring and early warning is efficiently and accurately carried out through the machine learning model based on the fact that the extracted water level monitoring place is a real-time characteristic change sub-domain sequence.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
Fig. 1 schematically shows a flow chart of a water level early warning monitoring method.
Fig. 2 schematically illustrates an application scenario example of a water level early warning monitoring method.
FIG. 3 schematically illustrates a flow chart of a method of acquiring a plurality of signature change subdomain series.
Fig. 4 schematically shows a block diagram of a water level early warning monitoring apparatus.
Fig. 5 schematically shows an example block diagram of an electronic device for implementing the water level early warning monitoring method.
Fig. 6 schematically illustrates a computer-readable storage medium for implementing the above-described water level early warning monitoring method.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present application.
Furthermore, the drawings are merely schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
In the present exemplary embodiment, a water level early warning monitoring method is first provided, and the water level early warning monitoring method may be executed on a server, or may be executed on a server cluster or a cloud server, and the like. Referring to fig. 1, the water level early warning monitoring method may include the following steps:
step S110, when a water level early warning monitoring signal is received, acquiring a first water level monitoring image of a preset water level monitoring place at a first time point when the water level early warning monitoring signal is received, and segmenting the first water level monitoring image to obtain a first building structure characteristic diagram;
step S120, a second water level monitoring image of the preset water level monitoring place of a second time point after the first time point is obtained in a timing mode, and the second water level monitoring image is divided to obtain a second building structure characteristic diagram;
step S130, acquiring a structural feature change area relative to the first building structural feature map in the second building structural feature map, and acquiring a structural feature initial area corresponding to the structural feature change area in the first building structural feature map;
Step S140, extracting a plurality of characteristic change subdomain sequences of the preset water level monitoring place based on the structural characteristic change area, the structural characteristic initial area and a preset standard building structural characteristic diagram;
and S150, inputting the characteristic change subdomain sequence of the preset sequence in the characteristic change subdomain sequences into a pre-trained machine learning model to obtain a regular early warning risk value of the preset water level monitoring place.
In the water level early warning monitoring method, firstly, when a water level early warning monitoring signal is received, a first water level monitoring image of a preset water level monitoring place at a first time point when the water level early warning monitoring signal is received is obtained, and the first water level monitoring image is divided to obtain a first building structure characteristic diagram; therefore, the first building structure characteristic diagram which can clearly and concisely represent the condition of the building structure when the water level early warning monitoring signal is received by the preset water level monitoring place can be obtained. Then, a second water level monitoring image of the preset water level monitoring place at a second time point after the first time point is obtained in a timing mode, and the second water level monitoring image is divided to obtain a second building structure characteristic diagram; in this way, a second building structure characteristic diagram which can clearly and simply represent the real-time building structure condition of the preset water level monitoring place can be obtained. Further, acquiring a structural feature change area relative to the first building structural feature map in the second building structural feature map, and acquiring a structural feature initial area corresponding to the structural feature change area in the first building structural feature map; the structural characteristics of the change of the outline structure of the water level monitoring place in real time can be clearly obtained. Then, extracting a plurality of characteristic change subdomain sequences of the preset water level monitoring place based on the structural characteristic change area, the structural characteristic initial area and a preset standard building structural characteristic diagram; a plurality of characteristic change subdomain sequences which can simply reflect the dynamic change condition of the building structure of the preset water level monitoring place can be obtained, and then the risk of the monitoring place can be accurately and efficiently analyzed. And finally, inputting the characteristic change subdomain sequences of the preset sequences in the plurality of characteristic change subdomain sequences into a pre-trained machine learning model to obtain the regular early warning risk value of the preset water level monitoring place. Therefore, the water level monitoring and early warning is efficiently and accurately carried out through the machine learning model based on the fact that the extracted water level monitoring place is a real-time characteristic change sub-domain sequence.
Hereinafter, each step in the above-mentioned water level early warning monitoring method in the present exemplary embodiment will be explained and explained in detail with reference to the accompanying drawings.
In step S110, when a water level early warning monitoring signal is received, a first water level monitoring image of a predetermined water level monitoring place at a first time point when the water level early warning monitoring signal is received is obtained, and the first water level monitoring image is segmented to obtain a first building structure characteristic diagram.
In the embodiment of the present example, referring to fig. 2, when receiving a water level early warning monitoring signal sent by a water level monitoring location terminal 202, a server 201 obtains a first water level monitoring image of a predetermined water level monitoring location at a first time point when receiving the water level early warning monitoring signal, and segments the first water level monitoring image to obtain a first building structure characteristic diagram, so that water level early warning analysis can be performed in subsequent steps based on the first building structure characteristic diagram. The server 201 may be any device with processing capability, such as a computer, a microprocessor, etc., and the water level monitoring location terminal 202 may be, for example, a terminal carrying a sensor such as a water level measuring sensor or a humidity detecting sensor, which is not limited herein.
The water level early warning monitoring signal is a signal for prompting the monitoring system to start the water level early warning monitoring of the target water level monitoring position. The video monitoring equipment is arranged at a preset water level monitoring place, namely video monitoring equipment such as a camera and the like arranged at the preset water level monitoring place such as a bridge opening, a pedestrian bridge opening and the like. The first water level monitoring image of the predetermined water level monitoring place at the first time point is the first water level monitoring image of the predetermined water level monitoring place shot at the time point of receiving the water level early warning monitoring signal. Thus, the first water level monitoring image can analyze the architectural structural features such as a ditch or a pedestrian step of the predetermined water level monitoring site.
The building structure characteristic diagram in the first water level monitoring image is a block diagram of the first water level monitoring image, which only contains the outline of the building structure such as a water channel or a pedestrian step, a sewer and the like.
The end of one region can be indicated by edge detection of the image by existing image segmentation techniques, i.e. where the grey levels or structures have abrupt changes, and where another region starts. And then, the first water level monitoring image can be accurately segmented to obtain the outline of each building structure in the first water level monitoring image, and then the building structure characteristic diagram in the first water level monitoring image is obtained. Therefore, the condition of the initial building structure of the preset water level monitoring place can be clearly and simply represented through the building structure characteristic diagram.
In step S120, a second water level monitoring image of the predetermined water level monitoring location at a second time point after the first time point is obtained at a fixed time, and the second water level monitoring image is segmented to obtain a second building structure characteristic map.
In the embodiment of the present example, the architectural feature map in the second water level monitoring image is a block diagram that only includes the outline of the architectural structure, such as a canal, a pedestrian step, a sewer, and the like, in the second water level monitoring image.
And a second water level monitoring image of a preset water level monitoring place of a second time point after the first time point is obtained regularly, the monitoring image of the water level monitoring place, namely the second water level monitoring image, can be obtained regularly, and then the second water level monitoring image is segmented to obtain a second building structure characteristic diagram based on the second water level monitoring image, so that the preset water level monitoring place can be monitored in real time.
In step S130, a structural feature change area in the second architectural structural feature map relative to the first architectural structural feature map is obtained, and a structural feature initial area in the first architectural structural feature map corresponding to the structural feature change area is obtained.
In the embodiment of the present example, since the second architectural feature map is acquired at a time point after the first time point, there may be a change area with respect to the first architectural feature map due to a water level rise, a vehicle movement, or the like, that is, a structural feature change area, in the second architectural feature map. Based on the position of the structural feature change area in the second building structural feature map, the structural feature initial area corresponding to the structural feature change area can be accurately intercepted from the corresponding position in the first building structural feature map. The method for acquiring the structural feature change area in the second architectural structure feature map relative to the first architectural structure feature map may be to superimpose the second architectural structure feature map and the first architectural structure feature map, and determine an area where no building outline is overlapped in the two feature maps as the structural feature change area. Or obtaining coordinates of pixel points of the building structure outline of the second building structure characteristic diagram and the first building structure characteristic diagram, and determining an area where the pixel points without coordinate coincidence are located as a structural characteristic change area.
By acquiring the structural feature change area and the structural feature initial area, the key part for early warning analysis can be extracted from the second building structural feature graph and the first building structural feature graph, and the analysis efficiency is improved effectively according to the analysis accuracy.
In step S140, a plurality of feature change sub-domain sequences of the predetermined water level monitoring location are extracted based on the structural feature change area, the structural feature initial area, and a preset standard building structural feature map.
In the embodiment of the present example, the preset standard building structure characteristic map is a building structure characteristic map which is acquired in advance and used for safety of a predetermined water level monitoring place and is free from movement and intervention of pedestrians and the like.
On the basis of the structural feature change area, the structural feature initial area and the preset standard building structure feature map, extracting a plurality of feature change sub-area series of a preset water level monitoring place, namely extracting sub-areas of the same position in the structural feature change area, the structural feature initial area and the preset standard building structure feature map, and then sequentially connecting the sub-areas of the same position in series to obtain a plurality of feature change sub-area sequences. Different sub pre-sequences can be extracted by setting different methods for extracting sub-extraction domains. The calculation analysis data volume of the subsequent steps can be further reduced through extraction of the sub-regions, meanwhile, the change condition of the monitoring place can be clearly reflected in real time through the characteristic change sub-region sequence, and the accuracy of water level monitoring and early warning in the subsequent steps is guaranteed.
In one embodiment of the present example, referring to fig. 3, a plurality of characteristic change subdomain series of the predetermined water level monitoring place are extracted based on the structural characteristic change region, the structural characteristic initial region and a preset standard building structural characteristic map, including
Step 310, an edge profile based on the structural feature change area is shrunk inwards to obtain a plurality of inner profiles with the same shapes as the edge profile;
step 320, extracting an outer variation subdomain between the edge profile and an outermost inner profile of the plurality of inner profiles, extracting an inner variation subdomain surrounded by an innermost inner profile of the plurality of inner profiles, and extracting other variation subdomains between two adjacent inner profiles of the plurality of inner profiles;
step 330, sequentially acquiring initial subdomains and standard subdomains of positions corresponding to the outer side change subdomain, the inner side change subdomain and the other change subdomains in the structural feature initial region and the preset standard building structural feature map;
step 340, connecting each of the outside variation sub-field, the inside variation sub-field and the other variation sub-fields in series with the initial sub-field and the standard sub-field at the corresponding positions to obtain the plurality of characteristic variation sub-field sequences.
When the edge profile of the structural feature change area is a square, for example, the side of the square is 10 cm away from the center, and 4 square inner profiles with 2 cm intervals are generated inwards from the center. Therefore, the structural feature variation region can be uniformly divided, and the feature containing quantity of each region is ensured as many as possible. Then, an outer variation subfield between the edge contour and an outermost inner contour among the plurality of inner contours, that is, for example, an area between the outermost square inner contour and the edge contour among the above-mentioned 4 square inner contours, is extracted. An inner variation subfield surrounded by the innermost inner contour among the plurality of inner contours, that is, for example, an innermost region surrounded by the innermost square inner contour among the above-mentioned 4 square inner contours, is extracted. And extracting other variation subfields between adjacent two of the plurality of inner contours. This allows uniform extraction of the changing subfields from inside to outside into multiple regions. And then the outer change subdomain, the inner change subdomain and other change subdomains corresponding to each monitoring moment point are connected with the initial subdomain and the standard subdomain at corresponding positions in series to obtain a plurality of characteristic change subdomain sequences, so that the calculation and analysis data volume of subsequent steps can be further reduced, meanwhile, the change condition of a monitoring place can be clearly reflected in real time through the characteristic change subdomain sequences, and the accuracy of water level monitoring and early warning in the subsequent steps is ensured.
In step S150, inputting a pre-trained machine learning model into a feature change sub-domain sequence of a predetermined sequence of the plurality of feature change sub-domain sequences to obtain a regular early warning risk value of the predetermined water level monitoring location.
In the embodiment of the present example, the feature change sub-field sequence of the predetermined sequence in the plurality of feature change sub-field sequences, that is, the selected at least one feature change sequence in the plurality of feature change sub-field sequences, may be set in advance to select several of the predetermined sequences, for example, only the sequence corresponding to the outermost sub-field is selected, or one feature change sub-field sequence is selected every several sequences. Then, the characteristic change subdomain sequence of the preset sequence is input into a machine learning model trained in advance, and the regular early warning risk value of the preset water level monitoring place can be automatically and accurately obtained.
In a word, the water level monitoring and early warning is efficiently and accurately carried out through the machine learning model based on the fact that the extracted water level monitoring place is a real-time characteristic change subdomain sequence.
In an implementation manner of this example, the training method of the machine learning model is:
acquiring a characteristic change subdomain sequence sample set of a predetermined sequence, wherein each sample calibrates a corresponding regular early warning risk value in advance;
Respectively inputting the data of each sample into a machine learning model to obtain a regular early warning risk value output by the machine learning model;
if the obtained regular early warning risk value is inconsistent with the regular early warning risk value calibrated in advance for the sample after the data of the sample is input into the machine learning model, adjusting the coefficient of the machine learning model until the regular early warning risk value is consistent;
and when the data of all the samples are input into the machine learning model, the obtained regular early warning risk value is consistent with the regular early warning risk value calibrated for the data sample in advance, and the training is finished.
The characteristic change subdomain sequence samples of the predetermined sequence are characteristic change subdomain sequence samples of the predetermined sequence historically corresponding to monitoring image acquisition of a certain water level monitoring location. The method comprises the steps that a characteristic change subdomain sequence sample set of a preset sequence is collected to serve as the input of a machine learning model, and each sample is calibrated by an expert to serve as a corresponding regular early warning risk value to serve as the output of the machine learning model. And then, after the data of all the samples are input into the machine learning model, the obtained regular early warning risk value is consistent with the regular early warning risk value calibrated in advance for the data samples by adjusting the coefficient, and the training is finished, so that the training accuracy is effectively ensured.
In an embodiment of this example, after the obtaining, when receiving the water level early warning monitoring signal, a first water level monitoring image of a predetermined water level monitoring place at a first time point when receiving the water level early warning monitoring signal, and segmenting the first water level monitoring image to obtain a first building structure characteristic map, the method further includes:
according to the first building structure characteristic diagram, calibrating a water level early warning category for the preset water level monitoring place;
acquiring the weight of a preset water level monitoring element according to the water level early warning category, wherein the preset water level monitoring element comprises a water level rising rate, the number of people and a human moving frequency;
periodically collecting a plurality of second water level monitoring images after the first time point to form a second water level monitoring image sequence, and acquiring the water level rising rate, the number of people and the moving frequency of people based on the second water level monitoring image sequence;
and acquiring a regular early warning risk value of the preset water level monitoring place based on the water level rising rate, the number of people, the moving frequency of people and the weight of the preset water level monitoring element.
The water level early warning category is a level at which a predetermined water level monitoring place needs to be monitored according to the level of the risk of water level rising at the predetermined water level monitoring place, and for example, the predetermined water level early warning category may be a low risk of 1-60 classified according to 1-100, a medium risk of 60-80, and a high risk of 80-100. The higher the water level early warning category is, the higher the traffic risk brought by the rising of the water level is. Through first building structure characteristic diagram, can accurately reflect the building structure overall arrangement in predetermined water level control place, for example, whether have rivers or sewer etc. and then can be according to first building structure characteristic diagram, through for example the statistics typical water level rises the area of relevant river course etc. and the value that the size of the area ratio of other structures such as road surface corresponds, with the ratio of predetermineeing the early warning threshold value, according to predetermineeing the LUT, accurately judge the water level early warning classification in predetermined water level control place.
The predetermined water level monitoring elements comprise real-time water level early warning monitoring elements such as water level rising rate, number of people and human moving frequency. These water level monitoring elements may reflect real-time risks associated with a water level rise at a predetermined water level monitoring location, e.g., the more people that rise in water level, the higher the risk of passage at the predetermined water level monitoring location.
The weight of the predetermined water level monitoring elements is a coefficient reflecting the importance of each water level monitoring element to the traffic risk caused when the water level rises. Generally, the weights of the predetermined water level monitoring elements are different according to different water level early warning categories, and generally, the higher the water level early warning category is, the higher the weight of the predetermined water level monitoring element is. The weight of the preset water level monitoring element can be accurately obtained according to the water level early warning type through the preset water level early warning information table. Thus, the early warning risk value can be accurately calculated in the subsequent step.
And regularly acquiring a plurality of second water level monitoring images after the first time point to form a second water level monitoring image sequence, namely acquiring images of a plurality of time points of a preset water level monitoring place from video monitoring equipment arranged at the preset water level monitoring place according to a preset time point interval after the time point of receiving a water level early warning monitoring signal, and then sequentially connecting the images of the plurality of time points in series according to the time point sequence to obtain the second water level monitoring image sequence. Thus, dynamic data such as the water level rising rate, the number of persons, the moving frequency of persons, and the like can be analyzed based on the second water level monitoring image sequence. The water level data on each image in the second water level monitoring image sequence is obtained, and then the water level rising rate can be accurately calculated according to the time point of each image, wherein the water level data is obtained by setting a water level gauge and identifying the value on the water level gauge; the number of people on each image can be accurately identified through the portrait, and then the average value is obtained to obtain the number of people; and calculating the moving frequency of the person according to the number of the persons on the first image and the last image and the time interval. Therefore, the traffic risk of the preset water level monitoring place can be accurately judged in the subsequent steps according to the water level rising rate, the number of people and the moving frequency of people.
The regular early warning risk value of the preset water level monitoring place is a risk value of the traffic early warning of the preset water level monitoring place after the water level monitoring signal is received through calculation according to the water level monitoring factors such as the water level rising rate, the number of people, the moving frequency of people and the like and the weight of the preset water level monitoring factors, and the higher the regular early warning risk value is, the higher the traffic risk of the preset water level monitoring place is.
In an embodiment of this example, the calibrating, according to the first architectural feature map, a water level early warning category for the predetermined water level monitoring place includes:
acquiring the areas of all buildings on the first building structure characteristic diagram according to the first building structure characteristic diagram;
acquiring water level rise contribution factors of all buildings from a preset water level monitoring building information table;
acquiring the water level rise rate of the preset water level monitoring place according to the areas of all the buildings and the water level rise contribution factors;
and calibrating the water level early warning category for the preset water level monitoring place according to the water level rising rate.
The first building structure feature map is divided into a plurality of areas with outlines, a plurality of similarities between each area and the various kinds of outline maps of the building structures stored in the database can be obtained by comparing the outline of each area with the various kinds of outline maps of the building structures stored in the database, and when the average value of the similarities is larger than a preset threshold value, the building structure corresponding to each area is determined. Further, the area of the building of each area can be accurately acquired by image detection.
Then, in a preset water level monitoring building information table, water level rising contribution factors of all buildings in the first building structure characteristic diagram, such as 70% of river contribution factor, minus 35% of sewer, and the like, are obtained. And then, acquiring the water level rise rate of the preset water level monitoring place according to the areas of all the buildings and the water level rise contribution factors, namely acquiring the water level rise rate of all the buildings by taking the contribution factors of all the buildings as building area weight coefficients. And then, the water level early warning type can be accurately calibrated for the preset water level monitoring place according to the preset rising rate and the water level early warning type comparison table.
In an embodiment of this example, the obtaining, according to the water level early warning category, a weight of a predetermined water level monitoring element, where the predetermined water level monitoring element includes a water level rising rate, a number of people, and a moving frequency of people, includes:
according to the water level early warning type, searching a target early warning type corresponding to the water level early warning type from a preset water level early warning information table;
and acquiring the weight of a preset water level monitoring element associated with the target early warning category, wherein the preset water level monitoring element comprises a water level rising rate, the number of people and the moving frequency of people.
The preset water level early warning information table stores risk weights of various water level monitoring elements including water level rising rate, number of people and human moving frequency, and the weights of the preset water level monitoring elements related to the target early warning types can be efficiently and accurately acquired after target early warning types corresponding to the water level early warning types are searched from the preset water level early warning information table according to the water level early warning types.
In an embodiment of this example, the obtaining of the periodic early warning risk value of the predetermined water level monitoring location based on the water level rising rate, the number of people, the moving frequency of people, and the weight of the predetermined water level monitoring element includes:
and obtaining the regular early warning risk value according to a formula U ═ mX nY)/wV, wherein U is the regular early warning risk value, X is the water level rising rate, Y is the number of people, V is the moving frequency of people, and m, n and w are the weights of the preset water level monitoring elements associated with the target early warning category respectively.
The mX nY can judge the conditions of two risk factors of the water level rising rate and the number of people in real time, for example, the water level rises quickly and the number of people at the place is large; then, the water level rising rate and the influence of the number of people in the place on the movement of people can be accurately judged through (mX nY)/wV, namely, the regular early warning risk value is obtained, and the real-time risk of the place is more serious the higher the regular risk value is.
The application also provides a water level early warning monitoring device. Referring to fig. 4, the water level early warning monitoring apparatus may include: a first acquisition module 410, a second acquisition module 420, a third acquisition module 430, an extraction module 440, and a prediction module 450. Wherein:
the first obtaining module 410 may be configured to, when receiving a water level early warning monitoring signal, obtain a first water level monitoring image of a predetermined water level monitoring location at a first time point when receiving the water level early warning monitoring signal, and segment the first water level monitoring image to obtain a first building structure feature map;
the second obtaining module 420 may be configured to obtain a second water level monitoring image of the predetermined water level monitoring location at a second time point after the first time point in a timing manner, and segment the second water level monitoring image to obtain a second architectural structure feature map;
the third obtaining module 430 may be configured to obtain a structural feature change area in the second architectural structural feature map relative to the first architectural structural feature map, and obtain a structural feature initial area in the first architectural structural feature map corresponding to the structural feature change area;
the extraction module 440 may be configured to extract a plurality of feature change sub-domain sequences of the predetermined water level monitoring location based on the structural feature change region, the structural feature initial region, and a preset standard building structural feature map;
The prediction module 450 may be configured to input a feature change sub-domain sequence of a predetermined sequence of the plurality of feature change sub-domain sequences into a pre-trained machine learning model, so as to obtain a regular early warning risk value of the predetermined water level monitoring location.
The specific details of each module in the water level early warning and monitoring device have been described in detail in the corresponding water level early warning and monitoring method, and therefore are not described herein again.
It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Moreover, although the steps of the methods herein are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.
In an exemplary embodiment of the present application, there is also provided an electronic device capable of implementing the above method.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
An electronic device 500 according to this embodiment of the invention is described below with reference to fig. 5. The electronic device 500 shown in fig. 5 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 5, the electronic device 500 is embodied in the form of a general purpose computing device. The components of the electronic device 500 may include, but are not limited to: the at least one processing unit 510, the at least one memory unit 520, and a bus 530 that couples various system components including the memory unit 520 and the processing unit 510.
Wherein the storage unit stores program code that is executable by the processing unit 510 to cause the processing unit 510 to perform steps according to various exemplary embodiments of the present invention as described in the above section "exemplary methods" of the present specification. For example, the processing unit 510 may execute step S110 as shown in fig. 1: when a water level early warning monitoring signal is received, acquiring a first water level monitoring image of a preset water level monitoring place at a first time point when the water level early warning monitoring signal is received, and segmenting the first water level monitoring image to obtain a first building structure characteristic diagram; s120: acquiring a second water level monitoring image of the preset water level monitoring place of a second time point after the first time point in a timing mode, and dividing the second water level monitoring image to obtain a second building structure characteristic diagram; step S130: acquiring a structural feature change area in the second building structural feature map relative to the first building structural feature map, and acquiring a structural feature initial area in the first building structural feature map corresponding to the structural feature change area; step S140: extracting a plurality of characteristic change subdomain sequences of the preset water level monitoring place based on the structural characteristic change area, the structural characteristic initial area and a preset standard building structural characteristic diagram; step S150: and inputting the characteristic change subdomain sequences of the preset sequences in the plurality of characteristic change subdomain sequences into a pre-trained machine learning model to obtain the regular early warning risk value of the preset water level monitoring place.
The memory unit 520 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)5201 and/or a cache memory unit 5202, and may further include a read-only memory unit (ROM) 5203.
Storage unit 520 may also include a program/utility 5204 having a set (at least one) of program modules 5205, such program modules 5205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
Bus 530 may be one or more of any of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
The electronic device 500 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a client to interact with the electronic device 500, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 500 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interface 550, which may include display unit 540 coupled to input/output (I/O) interface 550. Also, the electronic device 500 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 560. As shown, the network adapter 560 communicates with the other modules of the electronic device 500 over the bus 530. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, and may also be implemented by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present application.
In an exemplary embodiment of the present application, there is also provided a computer readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps according to various exemplary embodiments of the invention described in the above section "exemplary method" of this description, when said program product is run on said terminal device.
Referring to fig. 6, a program product 600 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the client computing device, partly on the client device, as a stand-alone software package, partly on the client computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the client computing device over any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., over the internet using an internet service provider).
Furthermore, the above-described figures are merely schematic illustrations of processes involved in methods according to exemplary embodiments of the invention, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

Claims (9)

1. A water level early warning monitoring method is characterized by comprising the following steps:
when a water level early warning monitoring signal is received, acquiring a first water level monitoring image of a preset water level monitoring place at a first time point when the water level early warning monitoring signal is received, and segmenting the first water level monitoring image to obtain a first building structure characteristic diagram;
Acquiring a second water level monitoring image of the preset water level monitoring place of a second time point after the first time point in a timing mode, and dividing the second water level monitoring image to obtain a second building structure characteristic diagram;
acquiring a structural feature change area in the second building structural feature map relative to the first building structural feature map, and acquiring a structural feature initial area in the first building structural feature map corresponding to the structural feature change area;
extracting a plurality of characteristic change subdomain sequences of the preset water level monitoring place based on the structural characteristic change area, the structural characteristic initial area and a preset standard building structural characteristic diagram;
a plurality of inner contours which are the same as the edge contours in shape are obtained based on the inward shrinkage of the edge contours of the structural feature change areas;
extracting an outer variation subfield between the edge profile and an outermost inner profile of a plurality of inner profiles, extracting an inner variation subfield surrounded by an innermost inner profile of the plurality of inner profiles, and extracting other variation subfields between adjacent two inner profiles of the plurality of inner profiles;
sequentially acquiring initial subdomains and standard subdomains of positions corresponding to the outer side change subdomain, the inner side change subdomain and the other change subdomains in the structural feature initial region and the preset standard building structural feature map;
Each of the outer side variation sub-domain, the inner side variation sub-domain and the other variation sub-domains are connected with the initial sub-domain and the standard sub-domain at the corresponding positions in series to obtain a plurality of characteristic variation sub-domain sequences;
acquiring a characteristic change subdomain sequence sample set of a predetermined sequence, wherein each sample calibrates a corresponding regular early warning risk value in advance; and respectively inputting the data of each sample into a machine learning model to obtain a periodic early warning risk value output by the machine learning model, when the data of all the samples are input into the machine learning model, the obtained periodic early warning risk value is consistent with a periodic early warning risk value calibrated in advance for the data samples, after training is finished, inputting a characteristic change subdomain sequence of a preset sequence in the characteristic change subdomain sequences into the machine learning model trained in advance to obtain the periodic early warning risk value of the preset water level monitoring place.
2. The method of claim 1, wherein the training method of the machine learning model is:
and if the obtained regular early warning risk value is inconsistent with the regular early warning risk value calibrated in advance for the sample after the data of the sample is input into the machine learning model, adjusting the coefficient of the machine learning model until the obtained regular early warning risk value is consistent with the regular early warning risk value calibrated in advance for the sample.
3. The method of claim 1, wherein after the obtaining a first water level monitoring image of a predetermined water level monitoring place at a first time point when the water level early warning monitoring signal is received and segmenting the first water level monitoring image to obtain a first architectural feature map when the water level early warning monitoring signal is received, the method further comprises:
according to the first building structure characteristic diagram, calibrating a water level early warning type for the preset water level monitoring place;
acquiring the weight of a preset water level monitoring element according to the water level early warning category, wherein the preset water level monitoring element comprises a water level rising rate, the number of people and the moving frequency of people;
regularly collecting a plurality of second water level monitoring images after the first time point to form a second water level monitoring image sequence so as to obtain the water level rising rate, the number of people and the moving frequency of people based on the second water level monitoring image sequence;
and acquiring a regular early warning risk value of the preset water level monitoring place based on the water level rising rate, the number of people, the moving frequency of people and the weight of the preset water level monitoring element.
4. The method according to claim 3, wherein said calibrating a water level early warning category for said predetermined water level monitoring location based on said first building structure characteristic map comprises:
acquiring the areas of all buildings on the first building structure characteristic diagram according to the first building structure characteristic diagram;
acquiring water level rise contribution factors of all buildings from a preset water level monitoring building information table;
acquiring the water level rise rate of the preset water level monitoring place according to the areas of all the buildings and the water level rise contribution factors;
and according to the water level rising rate, calibrating the water level early warning category for the preset water level monitoring place.
5. The method as claimed in claim 3, wherein the obtaining of the weight of the predetermined water level monitoring elements according to the water level early warning category includes:
according to the water level early warning type, searching a target early warning type corresponding to the water level early warning type from a preset water level early warning information table;
and acquiring the weight of a preset water level monitoring element associated with the target early warning category, wherein the preset water level monitoring element comprises a water level rising rate, the number of people and the moving frequency of people.
6. The method of claim 3, wherein the obtaining of the periodic early warning risk value of the predetermined water level monitoring site based on the water level rising rate, the number of people, the moving frequency of people and the weight of the predetermined water level monitoring element comprises:
and obtaining the regular early warning risk value according to a formula U ═ mX nY)/wV, wherein U is the regular early warning risk value, X is the water level rising rate, Y is the number of people, V is the moving frequency of people, and m, n and w are the weights of the preset water level monitoring elements associated with the target early warning category respectively.
7. The utility model provides a water level early warning monitoring device which characterized in that includes:
the system comprises a first acquisition module, a first display module and a second acquisition module, wherein the first acquisition module is used for acquiring a first water level monitoring image of a preset water level monitoring place at a first time point when a water level early warning monitoring signal is received, and segmenting the first water level monitoring image to obtain a first building structure characteristic diagram;
the second acquisition module is used for acquiring a second water level monitoring image of the preset water level monitoring place at a second time point after the first time point in a timing manner, and segmenting the second water level monitoring image to obtain a second building structure characteristic diagram;
A third obtaining module, configured to obtain a structural feature change area in the second architectural structural feature map, where the structural feature change area is relative to the first architectural structural feature map, and obtain a structural feature initial area in the first architectural structural feature map, where the structural feature initial area corresponds to the structural feature change area;
the extraction module is used for extracting a plurality of characteristic change subdomain sequences of the preset water level monitoring place based on the structural characteristic change area, the structural characteristic initial area and a preset standard building structural characteristic diagram; a plurality of inner contours which are the same as the edge contours in shape are obtained based on the inward shrinkage of the edge contours of the structural feature change areas; extracting an outer variation subfield between the edge profile and an outermost inner profile of a plurality of inner profiles, extracting an inner variation subfield surrounded by an innermost inner profile of the plurality of inner profiles, and extracting other variation subfields between adjacent two inner profiles of the plurality of inner profiles; sequentially acquiring initial subdomains and standard subdomains of positions corresponding to the outer side variation subdomain, the inner side variation subdomain and the other variation subdomains in the structural feature initial region and the preset standard building structural feature graph; each of the outer side variation subdomain, the inner side variation subdomain and the other variation subdomains are connected in series with the initial subdomain and the standard subdomain at the corresponding positions to obtain a plurality of characteristic variation subdomain sequences;
The prediction module is used for acquiring a characteristic change subdomain sequence sample set of a predetermined sequence, wherein each sample calibrates a corresponding regular early warning risk value in advance; and respectively inputting the data of each sample into a machine learning model to obtain a periodic early warning risk value output by the machine learning model, when the data of all the samples are input into the machine learning model, the obtained periodic early warning risk value is consistent with a periodic early warning risk value calibrated in advance for the data samples, after training is finished, inputting a characteristic change subdomain sequence of a preset sequence in the characteristic change subdomain sequences into the machine learning model trained in advance to obtain the periodic early warning risk value of the preset water level monitoring place.
8. A computer-readable storage medium having a water level warning monitoring program stored thereon, wherein the water level warning monitoring program, when executed by a processor, implements the method of any one of claims 1-6.
9. An electronic device, comprising:
a processor; the memory is used for storing a water level early warning monitoring program of the processor; wherein the processor is configured to perform the method of any one of claims 1-6 via execution of the water level warning monitoring program.
CN201910879437.XA 2019-09-18 2019-09-18 Water level early warning monitoring method and device, storage medium and electronic equipment Active CN110705759B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201910879437.XA CN110705759B (en) 2019-09-18 2019-09-18 Water level early warning monitoring method and device, storage medium and electronic equipment
PCT/CN2020/092807 WO2021051863A1 (en) 2019-09-18 2020-05-28 Water level pre-warning and monitoring method and apparatus, and storage medium and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910879437.XA CN110705759B (en) 2019-09-18 2019-09-18 Water level early warning monitoring method and device, storage medium and electronic equipment

Publications (2)

Publication Number Publication Date
CN110705759A CN110705759A (en) 2020-01-17
CN110705759B true CN110705759B (en) 2022-06-03

Family

ID=69194496

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910879437.XA Active CN110705759B (en) 2019-09-18 2019-09-18 Water level early warning monitoring method and device, storage medium and electronic equipment

Country Status (2)

Country Link
CN (1) CN110705759B (en)
WO (1) WO2021051863A1 (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110705759B (en) * 2019-09-18 2022-06-03 平安科技（深圳）有限公司 Water level early warning monitoring method and device, storage medium and electronic equipment
CN112101778B (en) * 2020-09-14 2023-04-28 湖南大学 Early warning method, system, device and storage medium
CN112329787B (en) * 2020-12-07 2023-06-30 北京同方软件有限公司 Water level character positioning method based on information attention degree
CN114550037A (en) * 2022-02-18 2022-05-27 福建水口发电集团有限公司 Hydropower station video data digital safety early warning method and device
CN114860982A (en) * 2022-06-02 2022-08-05 河北兰科网络工程集团有限公司 Water accumulation information early warning method and early warning system

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108765238A (en) * 2018-05-25 2018-11-06 浙江知水信息技术有限公司 A method of it is calculated by grid model and realizes grid water early warning

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI594212B (en) * 2015-11-06 2017-08-01 Remote monitoring of water conservancy facilities
KR20170101519A (en) * 2016-02-29 2017-09-06 한국전자통신연구원 Apparatus and method for disaster monitoring using unmanned aerial vehicle
CN106228579B (en) * 2016-08-25 2019-05-10 河海大学 A kind of video image dynamic water table information extracting method based on geographical space-time scene
US11080526B2 (en) * 2017-08-15 2021-08-03 Regents Of The University Of Minnesota Satellite image classification across multiple resolutions and time using ordering constraint among instances
CN108509980B (en) * 2018-03-08 2022-07-01 南京邮电大学 Water level monitoring method based on dictionary learning
CN109255778B (en) * 2018-07-27 2021-11-09 北京市商汤科技开发有限公司 Image processing method and apparatus, electronic device, storage medium, and program product
CN109269556A (en) * 2018-09-06 2019-01-25 深圳市中电数通智慧安全科技股份有限公司 A kind of equipment Risk method for early warning, device, terminal device and storage medium
CN109816040B (en) * 2019-02-01 2022-10-14 四创科技有限公司 Deep learning-based urban inland inundation water depth detection method
CN110705759B (en) * 2019-09-18 2022-06-03 平安科技（深圳）有限公司 Water level early warning monitoring method and device, storage medium and electronic equipment

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108765238A (en) * 2018-05-25 2018-11-06 浙江知水信息技术有限公司 A method of it is calculated by grid model and realizes grid water early warning

Also Published As

Publication number Publication date
CN110705759A (en) 2020-01-17
WO2021051863A1 (en) 2021-03-25

Similar Documents

Publication Publication Date Title
CN110705759B (en) Water level early warning monitoring method and device, storage medium and electronic equipment
CN109509260B (en) Labeling method, equipment and readable medium of dynamic obstacle point cloud
CN110929565B (en) Risk monitoring method and device based on machine learning, storage medium and electronic equipment
CN115035182B (en) Landslide hazard early warning method and system
CN116612609B (en) Disaster early warning method and system based on landslide hazard prediction
US20120315920A1 (en) Systems and methods for analyzing spatiotemporally ambiguous events
CN112434260A (en) Road traffic state detection method and device, storage medium and terminal
CN115359471A (en) Image processing and joint detection model training method, device, equipment and storage medium
KR20220117341A (en) Training method, apparatus, electronic device and storage medium of lane detection model
KR102337687B1 (en) Artificial neural network-based target region extraction apparatus, method and learning method thereof
CN117351241B (en) Intelligent detection and assessment method, device, terminal and storage medium for tunnel defect
CN113705693A (en) Power grid lightning early warning method, device, recording medium and system
CN113496182B (en) Road extraction method and device based on remote sensing image, storage medium and equipment
KR102616571B1 (en) System and method for providing road traffic information based on image analysis using artificial intelligence
CN112529315B (en) Landslide prediction method, landslide prediction device, landslide prediction equipment and storage medium
CN115980690A (en) Clear sky echo recognition model construction method, clear sky echo filtering method and clear sky echo filtering device
CN115311522A (en) Target detection method and device for automatic driving, electronic equipment and medium
CN115879594A (en) Urban settlement population distribution trend prediction method based on geographic detector
CN109543610A (en) Vehicle detecting and tracking method, device, equipment and storage medium
CN115171031A (en) Method and device for detecting surface water accumulation based on vehicle reference object and application
CN109740518A (en) The determination method and device of object in a kind of video
CN115294536B (en) Violation detection method, device, equipment and storage medium based on artificial intelligence
CN114445711B (en) Image detection method, image detection device, electronic equipment and storage medium
CN113806361B (en) Method, device and storage medium for associating electronic monitoring equipment with road
CN117022264B (en) Obstacle detection method and device based on radar fusion

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