CN115497036A - Waterlogging depth calculation method and system and readable storage medium - Google Patents
Waterlogging depth calculation method and system and readable storage medium Download PDFInfo
- Publication number
- CN115497036A CN115497036A CN202210979316.4A CN202210979316A CN115497036A CN 115497036 A CN115497036 A CN 115497036A CN 202210979316 A CN202210979316 A CN 202210979316A CN 115497036 A CN115497036 A CN 115497036A
- Authority
- CN
- China
- Prior art keywords
- road
- scale
- point
- area
- ponding
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention provides a waterlogging depth calculation method, a waterlogging depth calculation system and a readable storage medium, wherein the waterlogging depth calculation method comprises the steps of calibrating a plurality of entity scales at specific urban positions in advance along a road; acquiring a road monitoring image of the entity scale, and determining the position information of the entity scale in the road monitoring image; establishing a perspective projection model by combining the position information, and constructing a virtual scale; determining the pixel height of the virtual scale at any point in the road surface by combining the virtual scale; identifying the ponding area of the road monitoring image by applying a machine vision model, and segmenting to obtain the boundary range of the ponding area; constructing a road route in the model in a road area outside the ponding boundary range by combining the boundary position of the road area; determining a road surface area according to the extending direction of the road line and the boundary information of the ponding area; and constructing a virtual scale at the accumulated water monitoring point according to the pixel height of the scale of the virtual scale, and determining the depth of the target accumulated water according to the height difference between the virtual scale and the intersection point of the road surface and the accumulated water surface.
Description
Technical Field
The application relates to the technical field of accumulated water depth monitoring, in particular to a waterlogging accumulated water depth calculation method and system and a readable storage medium.
Background
At present, the method for measuring the depth of accumulated water mainly comprises the following steps: the method comprises the steps of extracting graded scale data by using a water level line image to perform early warning, monitoring the water level by using a water level sensor and simulating a runoff process by using a meteorological hydrological model. However, these methods still have the following disadvantages in practical use: (1) The first method requires a specific image with water level, but only a few places such as rivers, reservoirs or the vicinity of water conservancy facilities have water level, and cannot be applied in a large area. (2) The water accumulation sensor is a good water level monitoring device, and can accurately monitor the water level; however, the accumulated water sensor is complex in equipment and high in cost, and cannot cover the whole city; (3) The meteorological hydrological model is a common method for simulating the depth of ponding water, but is easily limited by data. Therefore, these drawbacks have a great influence on the accuracy and precision of the calculation results.
Because of the rapid development of artificial intelligence in recent years, deep learning methods can be used to assist in acquiring waterlogged area information and even depth information from existing data sources such as road monitoring. For example, (1) the invention patent applied by the university of western's safety science, "a method for monitoring urban waterlogging area based on deep learning technology", proposes a road waterlogging area calculation idea of inputting a monitoring image subjected to perspective transformation to obtain a waterlogging area recognition result and obtaining quantity information of the total area of the waterlogging area through a certain amount of linear operation under the condition of training a waterlogging area example segmentation model, and brings inspiration for calculating various road waterlogging quantity attributes, but the disadvantage is that the actual size of the waterlogging area in the method needs to be measured on site, and the work is difficult to guarantee real-time and rapid implementation. (2) The invention patent of river and sea university application, namely 'urban ponding depth monitoring method based on deep learning', provides a method for detecting automobile tires in videos by using a deep learning model, taking the tires as scales for measuring the ponding depth, and then calculating the ponding depth in traffic monitoring video data by using a formula, and points out the idea of using the scales to indicate the actual depth and avoiding actual manual measurement. The method for calculating the road water accumulation depth has the advantages of economy, high efficiency and high speed, but is also limited by the dynamic characteristics of tires in monitoring videos, and has the problems that the recognition result fluctuates, the accuracy needs to be improved and the like.
Therefore, in consideration of the existing urban road accumulated water depth monitoring methods based on deep learning, dynamic information such as tires in data sources such as monitoring images needs to be used, the calculation effect of the accumulated water depth is greatly related to the positions of the tires, the processing has certain limitation, and the calculation accuracy is not high.
Disclosure of Invention
The embodiment of the application aims to provide a waterlogging water depth calculation method, a waterlogging water depth calculation system and a readable storage medium, and the calculation accuracy can be improved.
The embodiment of the application also provides a waterlogging ponding depth calculation method, which comprises the following steps:
s1, calibrating a plurality of entity scales along a road at a specific position of a city in advance;
s2, acquiring a road monitoring image of the entity scale, and determining the position information of each entity scale in the road monitoring image;
s3, combining the position information of each entity scale, creating a corresponding perspective projection model, and constructing a virtual scale;
s4, determining the scale pixel height of the virtual scale at any point in the road surface by combining the virtual scale;
s5, identifying a ponding area in the road monitoring image by using a machine vision model, and segmenting to obtain a ponding area boundary range;
s6, constructing a corresponding road line in the model in the road area outside the ponding boundary range by combining the boundary position of the road area;
s7, determining a road surface area corresponding to the water accumulation area according to the extending direction of the road line and the boundary information of the water accumulation area;
s8, constructing a corresponding virtual scale at the accumulated water monitoring point according to the pixel height of the virtual scale, and determining the depth of the target accumulated water according to the height difference between the virtual scale and the intersection point of the road surface and the accumulated water surface.
In a second aspect, an embodiment of the present application further provides an waterlogging ponding depth calculation system, the system includes an entity calibration module, a scale positioning module, a model creation module, a virtual calibration module, a ponding region identification module, a road line construction module, a road surface region identification module, and a ponding depth calculation module, wherein:
the entity calibration module is used for calibrating a plurality of entity scales along a road at a specific position of a city in advance;
the scale positioning module is used for acquiring a road monitoring image of the entity scales and determining the position information of each entity scale in the road monitoring image;
the model creating module is used for creating a corresponding perspective projection model by combining the position information of each entity scale and constructing a virtual scale;
the virtual calibration module is used for determining the pixel height of the virtual scale at any point in the road surface by combining the virtual scale;
the ponding area identification module is used for identifying the ponding area in the road monitoring image by applying a machine vision model and obtaining the boundary range of the ponding area by segmentation;
the road route constructing module is used for constructing corresponding road lines in the model in a road area outside the ponding boundary range by combining the boundary position of the road area;
the road surface area identification module is used for determining a road surface area corresponding to the ponding area according to the extending direction of the road route and the boundary information of the ponding area;
and the accumulated water depth calculation module is used for constructing a corresponding virtual scale at an accumulated water monitoring point according to the pixel height of the virtual scale, and determining the target accumulated water depth according to the height difference between the virtual scale and the intersection point of the road surface and the accumulated water surface.
In a third aspect, an embodiment of the present application further provides a readable storage medium, where the readable storage medium includes a waterlogging depth calculation method program, and when the waterlogging depth calculation method program is executed by a processor, the method includes implementing the steps of the waterlogging depth calculation method described in any one of the above.
As can be seen from the above, the method, the system and the readable storage medium for calculating the waterlogging water depth provided by the embodiment of the application can determine the intersection point of the water accumulation area and the virtual scale in real time, calculate the water accumulation depth at the position based on the position of the intersection point, and provide first-hand data for subsequently monitoring the risk level of the water accumulation depth and making a risk early warning; the virtual scale is constructed by utilizing the fixed characteristic of a monitoring scene and combining road information of the same scene when no water is accumulated, and can be applied to water accumulation depth monitoring under different rainfall conditions, so that the monitoring range can be effectively expanded, and the monitoring efficiency and accuracy are improved; the practical height in the monitored image is determined by using the easily-set entity scale, so that the problems of large monitoring fluctuation and insufficient accuracy caused by using other dynamic objects as scales are effectively avoided, and the calculation accuracy is improved.
Additional features and advantages of the present application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a flowchart of a method for calculating waterlogging depth according to an embodiment of the present disclosure;
FIG. 2 is a schematic view of a road one-point perspective projection model;
FIG. 3 is a schematic diagram of a two-point perspective projection model of a road;
FIG. 4 is a schematic illustration of determining a height difference of an intersection of a road surface and a water surface on an image;
FIG. 5 is a schematic view of determining a road extending direction according to the lane lines obtained by the segmentation;
fig. 6 is a schematic structural diagram of a waterlogging ponding depth calculation system according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not construed as indicating or implying relative importance.
Referring to fig. 1, fig. 1 is a flow chart of a method for calculating water-logging depth according to some embodiments of the present disclosure. The method comprises the following steps:
step S1, calibrating a plurality of entity scales along a road at a specific position of a city in advance.
And S2, acquiring a road monitoring image of the entity scales, and determining the position information of each entity scale in the road monitoring image.
And S3, combining the position information of each entity scale to create a corresponding perspective projection model and construct a virtual scale.
And S4, determining the pixel height of the virtual scale at any point in the road surface by combining the virtual scale.
And S5, identifying the ponding area in the road monitoring image by applying a machine vision model, and segmenting to obtain the boundary range of the ponding area.
And S6, constructing a corresponding road line in the model in the road area outside the ponding boundary range by combining the boundary position of the road area.
And S7, determining a road surface area corresponding to the ponding area according to the extending direction of the road line and the boundary information of the ponding area.
And S8, constructing a corresponding virtual scale at the accumulated water monitoring point according to the pixel height of the virtual scale, and determining the target accumulated water depth according to the height difference between the virtual scale and the intersection point of the road surface and the accumulated water surface.
Therefore, the calculation method for the waterlogging ponding depth can determine the intersection point of the ponding area and the virtual scale in real time, calculate the ponding depth at the position based on the position of the intersection point, and provide first-hand data for subsequent risk level monitoring of the ponding depth and risk early warning; the virtual scale is constructed by utilizing the fixed characteristic of a monitoring scene and combining road information of the same scene when no water is accumulated, and can be applied to water accumulation depth monitoring under different rainfall conditions, so that the monitoring range can be effectively expanded, and the monitoring efficiency and accuracy are improved; the practical height in the monitored image is determined by using the easily-set entity scale, so that the problems of large monitoring fluctuation and insufficient accuracy caused by using other dynamic objects as scales are effectively avoided, and the calculation accuracy is improved.
In one embodiment, in step S2, the determining the position information of each of the physical scales in the road monitoring image includes:
and S21, determining a target road monitoring video which corresponds to a specific position of a city and is calibrated with a plurality of entity scales along a road in advance.
And S22, segmenting a plurality of road monitoring images from the target road monitoring video according to a preset image segmentation rule.
Specifically, in the current implementation step, the required road monitoring image is segmented from the target road monitoring video according to an image segmentation rule segmented frame by frame. Of course, different embodiments are not limited to the image segmentation method, and the image segmentation method may be dynamically adjusted according to actual situations.
And S23, calling a pre-trained target detection model, identifying the entity scales from the road monitoring images, and determining the pixel coordinates and the pixel heights of the entity scales in the road monitoring images based on the pixel coordinates of the upper edge and the lower edge of the identification frame calibrated in the identification process.
Specifically, the training step of the target detection model includes:
(1) And acquiring a target monitoring image to be subjected to scale identification, and labeling the scale set in the target monitoring image to obtain corresponding labeling data.
It should be noted that, in practical application, the tagging data may be added to the preset txt file, so as to facilitate subsequent data call.
(2) And constructing an initial detection model, and inputting the target monitoring image serving as training data into the initial detection model for model training. In the training process, whether the training end condition is reached is judged based on the deviation value between the corresponding associated labeling data and the recognition data output through the model.
It should be noted that, in practical applications, the currently created training data, the preset label, and the verification data may be respectively added to the preset images folder and the labels folder. The two folders are equally divided into a training set train and a verification set val, and the pictures and the labels keep a one-to-one correspondence relationship.
(3) After the training is finished, a target detection model for stably identifying the artificial scale from the monitoring image can be obtained.
In the embodiment, before the model training, the training is performed by finding the characteristics of the data set or checking the results of the data processing and data enhancement operations in advance and continuously adjusting various configurations according to the data analysis results. Meanwhile, by combining the data loading and debugging function, the influence of data operation on the data set can be further analyzed, the analysis accuracy of the algorithm model is further improved, and the execution effect is improved.
In one embodiment, in step S21, the determining a target road monitoring video corresponding to a specific city position and calibrated with a plurality of physical scales along a road in advance includes:
step S211, obtaining an initial road monitoring video corresponding to a specific position of a city, and identifying a straight road section from the initial road monitoring video.
Step S212, when the corresponding road straight section is identified, calibrating a plurality of entity scales with clear height information along the boundary of the road straight section, enabling the entity scales to appear in the monitoring video range of the road, and determining the required target road monitoring video according to the entity scales.
Specifically, after a straight road section within the monitoring range is identified, a plurality of entity scales (such as traffic barrels, road poles and the like) with clear height information can be set along the road boundary, so that the entity scales appear in the road monitoring video range. It should be noted that the aforementioned physical scale can be understood as a "highly known indicating object" which needs to be arranged along the road in the actual scene.
According to the embodiment, the actual height of the monitored image is determined by using the easily-established entity scale, and the problems of large monitoring fluctuation and insufficient accuracy caused by using other dynamic objects as scales are effectively avoided.
In one embodiment, there are a plurality of vanishing points in the created perspective projection model, which are determined from the aggregate points obtained by stretching and aggregating the parallel lines represented by each of the solid scales to the far horizon.
Referring to fig. 2-3, a one-point perspective projection model or a two-point perspective projection model may be selectively constructed according to the extending direction of the road. For example, when the perspective projection model is constructed by a computer device, when it is determined that the road extending direction substantially coincides with the screen of the computer device, the construction of the one-point perspective projection model may be performed (as shown in fig. 2). Otherwise, the construction of the two-point perspective projection model can be performed (as shown in fig. 3).
It should be noted that the principle that parallel lines can be pushed together at vanishing points in reality is also based on the phenomenon observed by the naked eye, for example, two rails of a railway seem to be exactly merged together on a horizon. There may be one or two vanishing points in the picture, depending on the coordinate position and orientation of the composition; all vanishing points may fall on the horizon or on an extended line out of the plane of the drawing.
Compared with the calculation of the depth of the accumulated water by using the dynamic solid ruler, the embodiment has the advantages that the stability of the perspective model is higher, and extra errors caused by large fluctuation generated by the movement of the object in the monitoring process are avoided.
In one embodiment, in step S4, the determining the virtual scale pixel height of any point in the road surface by combining the virtual scale includes:
step S41, calculating the pixel coordinates of each vanishing point according to the position information of each entity scale by the following formula:
(y 2 -y 0 )(x 1 -x 0 )＝(y 1 -y 0 )(x 2 -x 0 )； (1)
wherein (x) 1 ，y 1 )、(x 2 ，y 2 ) Pixel coordinates (x) corresponding to two preset solid scales 0 ，y 0 ) The pixel coordinates of the corresponding vanishing point.
Specifically, assuming a vanishing point along the road direction, the coordinate of the vanishing point pixel along the road axis direction on the image is known as (x) 0 ，y 0 ) In the image (x) 1 ，y 1 ) Has a pixel height of h 1 A solid scale of (1). Then the scale is moved to another position (x) in the image along the axis 2 ，y 2 ) Then, the pixel coordinate (x) of the vanishing point can be calculated by the above formula (1) according to the position between the two scales 0 ，y 0 )。
Step S42, at the index point (x) 1 ，y 1 ) And constructing a virtual scale on the road surface where the vehicle is located.
Step S43, according to the longitudinal pixel coordinate y of vanishing point 0 The longitudinal pixel coordinate y of the index point 1 And the height h of a display pixel corresponding to a scale on the virtual scale v1 Calculating the height h of the pixel of the virtual scale at any point in the road surface by the following formula v ：
h v ＝h v1 (y-y 0 )/(y 1 -y 0 )； (2)
h v1 ＝(h 1* h r0 )/h c ； (3)
Y is a longitudinal pixel coordinate of any point in the road surface; h is a total of 1 Is the pixel height of the solid scale at the index point, h r0 Actual unit height, h, indicated for the scale of the virtual scale c Is the actual height of the solid scale.
In one embodiment, in step S7, the determining, according to the extending direction of the road line and the boundary information of the water accumulation area, a road surface area corresponding to the water accumulation area:
and S71, identifying a ponding area from the road monitoring image, and screening out ponding monitoring points needing to monitor the depth of the ponding from the ponding area.
Specifically, referring to fig. 4, the water accumulation area is a gray area indicated in the figure, and the water accumulation monitoring point is a point P indicated in the figure s (x s ，y s ) The vanishing point is a point P indicated in the figure 0 (x 0 ，y 0 )，P s And the vertical distance delta h relative to the road extension track is the ponding depth required to be obtained.
And step S72, identifying a connecting line between the ponding monitoring point and the vanishing point, and determining an intersection point obtained by intersecting the connecting line and the boundary of the ponding area.
In particular, a water accumulation monitoring point P s And vanishing point P 0 The connection lines therebetween can be further determined from fig. 4, and after the boundary position of each lane (i.e. the road boundary) is currently determined, a corresponding road line is constructed based on the extending direction of the road boundary (specifically, refer to fig. 5).
And S73, according to the extending direction of the road line, making a road extending track below the water accumulation area along the intersection point.
And S74, taking a point on the road extending track, which is positioned right below the ponding monitoring point, as a road surface point, and determining a road surface area corresponding to the ponding area based on an area correspondingly covered by the road surface point.
Specifically, the determination method of the road surface point is to make a road extending direction track at the intersection point-B, wherein a point right below the point B on the track is the required road surface point-C.
In one embodiment, in step S8, constructing a corresponding virtual scale at the water accumulation monitoring point according to the virtual scale pixel height includes:
and S81, acquiring the pixel height of a target virtual scale of the ponding monitoring point, and establishing a virtual scale with the pixel height of the target virtual scale between the ponding monitoring point and the corresponding road surface point.
In step S8, determining a target water accumulation depth according to a height difference between the virtual scale and an intersection of the road surface and the water accumulation surface, includes:
and S82, obtaining corresponding initial ponding depth based on the difference value between the longitudinal pixel coordinates of the ponding monitoring points and the longitudinal pixel coordinates of the corresponding road surface points.
Specifically, the longitudinal pixel coordinate of the known water accumulation monitoring point is y s The longitudinal pixel coordinate of the corresponding road point is y f And then the initial water accumulation depth is as follows: y is s -y f 。
And S83, converting the actual height of the initial water accumulation depth according to the pixel height of the target virtual scale to obtain the corresponding target water accumulation depth.
Specifically, let y s -y f As h in formula (3) r0 After substituting this into the formula (2), the formula (2) can be converted into the following formula (4). Subsequently, under the condition of knowing relevant parameters according to the formula (4), the required target water accumulation depth Δ h can be calculated:
referring to fig. 6, the system 600 disclosed in the present application includes an entity calibration module 601, a scale positioning module 602, a model creation module 603, a virtual calibration module 604, a water accumulation region identification module 605, a road line construction module 606, a road surface region identification module 607, and a water accumulation depth calculation module 608, where:
the entity calibration module 601 is used for calibrating a plurality of entity scales along a road at a specific position of a city in advance;
the scale positioning module 602 is configured to obtain a road monitoring image of the entity scales, and determine position information of each entity scale in the road monitoring image;
the model creating module 603 is configured to create a corresponding perspective projection model in combination with the position information of each entity scale, and construct a virtual scale;
the virtual calibration module 604 is configured to determine, in combination with the virtual scale, a virtual scale pixel height of any point in the road surface;
the ponding area identification module 605 is configured to identify a ponding area in the road monitoring image by applying a machine vision model, and obtain a ponding area boundary range by segmentation;
the road line construction module 606 is configured to construct a corresponding road line in the model in a road area outside the ponding boundary range by combining the boundary position of the road area;
the road surface area identification module 607 is configured to determine a road surface area corresponding to the water accumulation area according to an extending direction of a road route and boundary information of the water accumulation area;
the ponding depth calculation module 608 is configured to construct a corresponding virtual scale at a ponding monitoring point according to the virtual scale pixel height, and determine a target ponding depth according to a height difference between the virtual scale and an intersection point of the road surface and the ponding surface.
In one embodiment, each module in the system is further configured to perform the method in any optional implementation manner of the above embodiment.
Therefore, the waterlogging ponding depth calculating system disclosed by the application can determine the intersection point of the ponding area and the virtual scale in real time, calculate the ponding depth at the position based on the position of the intersection point, and provide first-hand data for subsequent risk level monitoring of the ponding depth and risk early warning; the virtual scale is constructed by utilizing the fixed characteristic of a monitoring scene and combining road information of the same scene when no water is accumulated, and can be applied to water accumulation depth monitoring under different rainfall conditions, so that the monitoring range can be effectively expanded, and the monitoring efficiency and accuracy are improved; the practical height in the monitored image is determined by using the easily-set entity scale, so that the problems of large monitoring fluctuation and insufficient accuracy caused by using other dynamic objects as scales are effectively avoided, and the calculation accuracy is improved.
The embodiment of the present application provides a readable storage medium, and the computer program, when executed by a processor, performs the method in any optional implementation manner of the above embodiment. The storage medium may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as a Static Random Access Memory (SRAM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), an Erasable Programmable Read-Only Memory (EPROM), a Programmable Read-Only Memory (PROM), a Read-Only Memory (ROM), a magnetic Memory, a flash Memory, a magnetic disk, or an optical disk.
The readable storage medium can determine the intersection point of the ponding area and the virtual scale in real time, and calculate the ponding depth at the position based on the position of the intersection point, so as to provide first-hand data for subsequently monitoring the risk level of the ponding depth and making a risk early warning; the characteristic of fixed monitoring scenes is utilized, the construction of the virtual scale is realized by combining the road information of the same scene when no water is accumulated, and the virtual scale can be applied to the depth monitoring of the water accumulation under different rainfall conditions, so that the monitoring range can be effectively expanded, and the monitoring efficiency and the monitoring accuracy are improved; the practical height in the monitored image is determined by using the easily-set entity scale, so that the problems of large monitoring fluctuation and insufficient accuracy caused by using other dynamic objects as scales are effectively avoided, and the calculation accuracy is improved.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (9)
1. A waterlogging water depth calculation method is characterized by comprising the following steps:
s1, calibrating a plurality of entity scales along a road at a specific position of a city in advance;
s2, acquiring a road monitoring image of the entity scale, and determining the position information of each entity scale in the road monitoring image;
s3, combining the position information of each entity scale, creating a corresponding perspective projection model, and constructing a virtual scale;
s4, determining the pixel height of the virtual scale at any point in the road surface by combining the virtual scale;
s5, identifying a ponding area in the road monitoring image by using a machine vision model, and segmenting to obtain a ponding area boundary range;
s6, constructing a corresponding road line in the model in the road area outside the ponding boundary range by combining the boundary position of the road area;
s7, determining a road surface area corresponding to the water accumulation area according to the extending direction of the road line and the boundary information of the water accumulation area;
s8, constructing a corresponding virtual scale at the accumulated water monitoring point according to the pixel height of the virtual scale, and determining the depth of the target accumulated water according to the height difference between the virtual scale and the intersection point of the road surface and the accumulated water surface.
2. The method according to claim 1, wherein in step S2, the determining the position information of each of the physical scales in the road monitoring image includes:
s21, determining a target road monitoring video corresponding to a specific position of a city and calibrating a plurality of entity scales along a road in advance;
s22, segmenting a plurality of road monitoring images from the target road monitoring video according to a preset image segmentation rule;
s23, calling a pre-trained target detection model, identifying the entity scales from the road monitoring images, and determining the pixel coordinates and the pixel heights of the entity scales in the road monitoring images based on the pixel coordinates of the upper edge and the lower edge of the identification frame calibrated in the identification process.
3. The method according to claim 2, wherein in step S21, the determining a target road monitoring video corresponding to a specific city position and having a plurality of physical scales calibrated along a road in advance comprises:
s211, obtaining an initial road monitoring video corresponding to a specific position of a city, and identifying a straight road section from the initial road monitoring video;
s212, when the corresponding road straight section is identified, calibrating a plurality of entity scales with clear height information along the boundary of the road straight section, enabling the entity scales to appear in the monitoring video range of the road, and determining the required target road monitoring video.
4. The method of claim 1, wherein there are a plurality of vanishing points in the created perspective projection model, the vanishing points being determined from the aggregate points of the parallel lines represented by each of the solid scales spread out to a far horizon.
5. The method of claim 4, wherein in step S4, said determining a virtual scale pixel height of any point in the road surface in combination with the virtual scale comprises:
s41, calculating the pixel coordinates of each vanishing point according to the position information of each entity scale by the following formula:
(y 2 -y 0 )(x 1 -x 0 )＝(y 1 -y 0 )(x 2 -x 0 )；(1)
wherein (x) 1 ，y 1 )、(x 2 ，y 2 ) For the pixel coordinates corresponding to the two preset solid scales respectively, (x) 0 ，y 0 ) Pixel coordinates for the corresponding vanishing point;
s42, at the calibration point (x) 1 ，y 1 ) Constructing a virtual scale on the road surface;
s43, according to the longitudinal pixel coordinate y of the vanishing point 0 The longitudinal pixel coordinate y of the index point 1 And the height h of a display pixel corresponding to a scale on the virtual scale v1 Calculating the height h of the pixel of the virtual scale at any point in the road surface by the following formula v ：
h v ＝h v1 (y-y 0 )/(y 1 -y 0 )；(2)
h v1 ＝(h 1* h r0 )/h c ；(3)
Y is a longitudinal pixel coordinate of any point in the road surface; h is 1 Is the pixel height of the solid scale at the index point, h r0 Actual unit height, h, indicated for the scale of the virtual scale c Is the actual height of the physical scale.
6. The method according to claim 4, wherein in step S7, determining the road surface area corresponding to the ponding area according to the extending direction of the road route and the boundary information of the ponding area comprises:
s71, identifying a ponding area from the road monitoring image, and screening ponding monitoring points needing to monitor ponding depth from the ponding area;
s72, identifying a connecting line between the accumulated water monitoring point and a vanishing point, and determining an intersection point obtained by intersecting the connecting line with the boundary of the accumulated water area;
s73, according to the extending direction of the road route, along the intersection point, making a corresponding road extending track below the water accumulation area;
and S74, taking a point on the road extending track, which is positioned right below the accumulated water monitoring point, as a road surface point, and determining a road surface area corresponding to the accumulated water area based on an area correspondingly covered by the road surface point.
7. The method according to claim 1, wherein in step S8, constructing a corresponding virtual scale at the waterlogging monitoring point according to the virtual scale pixel height comprises:
s81, acquiring the pixel height of a target virtual ruler scale of the accumulated water monitoring point, and establishing a virtual ruler with the pixel height of the target virtual ruler scale between the accumulated water monitoring point and the corresponding road surface point;
in step S8, determining a target water accumulation depth according to a height difference between the virtual scale and an intersection of the road surface and the water accumulation surface, includes:
s82, obtaining corresponding initial water accumulation depth based on the difference value between the longitudinal pixel coordinate of the water accumulation monitoring point and the longitudinal pixel coordinate of the corresponding road surface point;
and S83, converting the actual height of the initial water accumulation depth according to the pixel height of the target virtual scale to obtain the corresponding target water accumulation depth.
8. The utility model provides an waterlogging ponding depth calculation system, a serial communication port, the system includes that the entity marks module, scale orientation module, model and establishes module, virtual mark module, ponding region identification module, road line structure module, road surface region identification module, ponding depth calculation module, wherein:
the entity calibration module is used for calibrating a plurality of entity scales along a road at a specific position of a city in advance;
the scale positioning module is used for acquiring a road monitoring image of the entity scales and determining the position information of each entity scale in the road monitoring image;
the model creating module is used for creating a corresponding perspective projection model by combining the position information of each entity scale and constructing a virtual scale;
the virtual calibration module is used for determining the pixel height of the virtual scale at any point in the road surface by combining the virtual scale;
the ponding area identification module is used for identifying the ponding area in the road monitoring image by applying a machine vision model and obtaining the boundary range of the ponding area by segmentation;
the road route constructing module is used for constructing corresponding road lines in the model in a road area outside the ponding boundary range by combining the boundary position of the road area;
the road surface area identification module is used for determining a road surface area corresponding to the ponding area according to the extending direction of the road route and the boundary information of the ponding area;
and the accumulated water depth calculation module is used for constructing a corresponding virtual scale at an accumulated water monitoring point according to the pixel height of the virtual scale, and determining the target accumulated water depth according to the height difference between the virtual scale and the intersection point of the road surface and the accumulated water surface.
9. Readable storage medium, comprising a waterlogging water depth calculation method program which, when executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210979316.4A CN115497036A (en) | 2022-08-15 | 2022-08-15 | Waterlogging depth calculation method and system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210979316.4A CN115497036A (en) | 2022-08-15 | 2022-08-15 | Waterlogging depth calculation method and system and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115497036A true CN115497036A (en) | 2022-12-20 |
Family
ID=84466414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210979316.4A Pending CN115497036A (en) | 2022-08-15 | 2022-08-15 | Waterlogging depth calculation method and system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115497036A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116399418A (en) * | 2023-05-29 | 2023-07-07 | 陕西省水利电力勘测设计研究院 | Water level identification method and system based on fixed camera |
-
2022
- 2022-08-15 CN CN202210979316.4A patent/CN115497036A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116399418A (en) * | 2023-05-29 | 2023-07-07 | 陕西省水利电力勘测设计研究院 | Water level identification method and system based on fixed camera |
| CN116399418B (en) * | 2023-05-29 | 2023-10-27 | 陕西省水利电力勘测设计研究院 | Water level identification method and system based on fixed camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Radopoulou et al. | Automated detection of multiple pavement defects | |
| CN115424232B (en) | Method for identifying and evaluating pavement pit, electronic equipment and storage medium | |
| CN111179152B (en) | Road identification recognition method and device, medium and terminal | |
| US9129163B2 (en) | Detecting common geographic features in images based on invariant components | |
| CN107430815A (en) | Method and system for automatic identification parking area | |
| CN109271861B (en) | Multi-scale fusion point cloud traffic signboard automatic extraction method | |
| CN111288890A (en) | Road sign dimension and height automatic measurement method based on binocular photogrammetry technology | |
| CN112432650B (en) | High-precision map data acquisition method, vehicle control method and device | |
| CN110647886A (en) | Interest point marking method and device, computer equipment and storage medium | |
| CN113034566A (en) | High-precision map construction method and device, electronic equipment and storage medium | |
| CN112634260A (en) | Map evaluation method and device, electronic equipment and storage medium | |
| EP4202365A1 (en) | Method, apparatus, and computer program product for identifying and correcting lane geometry in map data | |
| CN115497036A (en) | Waterlogging depth calculation method and system and readable storage medium | |
| CN109115232B (en) | Navigation method and device | |
| Jiang et al. | Development of a pavement evaluation tool using aerial imagery and deep learning | |
| CN115393319A (en) | Method and device for evaluating map elements | |
| CN113420109B (en) | Method for measuring permeability of street interface, computer and storage medium | |
| CN113255578B (en) | Traffic identification recognition method and device, electronic equipment and storage medium | |
| CN111460861A (en) | Road traffic sign identification method, device and identification equipment | |
| Widyantoro et al. | Fuzzy traffic congestion model based on speed and density of vehicle | |
| CN113496182A (en) | Road extraction method and device based on remote sensing image, storage medium and equipment | |
| CN113435350A (en) | Traffic marking detection method, device, equipment and medium | |
| CN114299247A (en) | Rapid detection and problem troubleshooting method for road traffic sign lines | |
| CN114140518A (en) | Water level height monitoring method and device, electronic equipment and storage medium | |
| CN114119389A (en) | Image restoration method, system and storage module |
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 |