CN115755228A - Accumulated water road section prediction method - Google Patents
Accumulated water road section prediction method Download PDFInfo
- Publication number
- CN115755228A CN115755228A CN202211201570.8A CN202211201570A CN115755228A CN 115755228 A CN115755228 A CN 115755228A CN 202211201570 A CN202211201570 A CN 202211201570A CN 115755228 A CN115755228 A CN 115755228A
- Authority
- CN
- China
- Prior art keywords
- ponding
- information
- suspected
- point
- area
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for predicting a ponding road section, which comprises the following steps: s1, inspecting a plurality of road sections to be detected, and acquiring road surface information of the road sections, wherein the road surface information comprises rainfall and topography information, and the topography information comprises concave-convex conditions of the road surface and slope conditions; s2, determining a suspected ponding point and the position thereof according to the topography information to obtain ponding information of the suspected ponding point in a historical time period, and establishing a deep learning historical time period model according to the ponding information, wherein the historical time period model comprises a mapping relation between the position of the suspected ponding point and the ponding information; s3, acquiring rainfall and topographic information of suspected ponding points in a future time period according to the weather information, and predicting ponding information in the future time period; and S4, checking the water accumulation information predicted in the future time period. The prediction method disclosed by the invention is wide in application range, can be widely applied to urban waterlogging prevention and control, can be used for accurately predicting different rainfall and terrain information, and is high in prediction efficiency.
Description
Technical Field
The invention relates to the technical field of road ponding prediction, in particular to a ponding road section prediction method.
Background
With the acceleration of the urbanization process, the adverse consequences caused by urban waterlogging become more serious, and the sustainable development of cities is seriously hindered. In order to improve the monitoring level of the waterlogging, and avoid causing various losses after the waterlogging occurs, the rainfall network waterlogging monitoring station can effectively and accurately monitor the waterlogging condition after the rainstorm occurs, according to the monitoring data analysis result, through issuing early warning information, remind related personnel to make preparations in advance, avoid adverse factors caused by the waterlogging, the monitoring capability of the rainstorm waterlogging state can be improved through building the rainfall network waterlogging monitoring station, and the forecast early warning level of the rainstorm waterlogging disaster is improved. However, due to the problems of construction cost, monitoring range, practicability and the like, the urban rainfall network ponding monitoring site is generally constructed only for individual or important positions, and the urban rainfall network ponding monitoring site is not effectively monitored in a large range and high density manner for urban whole-area rainfall ponding, namely once a city rainstorm occurs, only the ponding condition near the network ponding monitoring site can be obtained, the urban rainfall monitoring site is a ponding monitoring method for discrete points, the ponding state information of the urban network cannot be obtained, and the monitoring of the ponding state of the road network is difficult to realize. The method for predicting the ponding road section is wide in applicability, can predict rainfall ponding in the whole area of a city, and has a good early warning effect.
The patent literature of China discloses a method and a device for predicting a water accumulation road section, and the publication number of the method and the device is CN106448171B, and provides the method and the device for predicting the water accumulation road section. The method comprises the following steps: obtaining the precipitation of the current time; searching a ponding road section set corresponding to the rainfall at the current time in a relation table of the rainfall and the ponding road sections, and taking the ponding road sections included in the ponding road section set as predicted ponding road sections; and the relation between the precipitation amount and the ponding road section is obtained through historical data statistics. The device is used for executing the method. However, the specific technical solution of chinese patent with publication No. CN106448171B is different from the present invention, and the prediction is not performed by means of different topography information.
Disclosure of Invention
The invention solves the problem that rainfall ponding in the whole area of a city cannot be effectively monitored due to the small application range of the conventional road section prediction, provides a ponding road section prediction method, establishes a historical time section model according to road surface information of each road section and by combining rainfall capacity and terrain information, and predicts ponding information in a future time section.
In order to achieve the purpose, the invention adopts the following technical scheme: a ponding road section prediction method comprises the following steps:
s1, inspecting a plurality of road sections to be detected to obtain road surface information of the road sections, wherein the road surface information comprises rainfall and topography information, and the topography information comprises concave-convex conditions of the road surface and slope conditions;
s2, determining a suspected ponding point and the position thereof according to the topography information, obtaining ponding information of the suspected ponding point in a historical time period, and establishing a deep learning historical time period model according to the ponding information, wherein the historical time period model comprises a mapping relation between the position of the suspected ponding point and the ponding information;
s3, acquiring rainfall and topographic information of suspected ponding points in a future time period according to the weather information, and predicting ponding information in the future time period;
and S4, checking the ponding information predicted in the future time period, and updating the historical time period model if the check value exceeds a preset value.
Firstly, determining a road section to be detected, wherein the road section to be detected can be selected by self, and respectively acquiring road surface information of the road section to be detected, namely rainfall and terrain information, wherein the terrain information is the concave-convex road surface condition and the slope condition of the whole road section; then, determining each suspected accumulated water point, corresponding position and accumulated water information, establishing a historical time period model, and predicting by using the historical time period model to obtain the accumulated water information in a future time period; and finally, checking the prediction result to ensure the accuracy of the prediction.
Preferably, the topography information is acquired by using an acquisition device, and the method specifically comprises the following steps:
s11, acquiring the overall road surface concave-convex condition of the road section to be detected, and preliminarily screening road section points with the flatness larger than the set flatness;
and S12, collecting image information of each screened road section point, mapping points with different shooting distances in the image information into different gray values according to the relation between the shooting distance and the depth of field to obtain gray map information, and judging the slope condition according to the gray map information.
In the invention, in the process of acquiring terrain information, the concave-convex condition of the road surface of the road section to be detected is firstly acquired, the road section points with larger concave-convex degree, namely large flatness, are preliminarily screened, the set flatness index is a fixed numerical value, the screened road section points are respectively subjected to image acquisition processing, and the obtained gray value information can well identify the concave-convex condition and the slope breaking condition in the single road section point.
Preferably, the step S2 includes the steps of:
s21, screening suspected accumulated water points according to the gray-scale image information, and marking the positions of the suspected accumulated water points;
s22, sequentially collecting ponding information of the suspected ponding points according to the marking sequence, wherein the area of the suspected ponding points is obtained according to the ponding information; according to the area of the suspected ponding point and the terrain information, the maximum depth of the suspected ponding point is obtained;
and S23, respectively establishing a historical period model of the position of the suspected water accumulation point, the area of the suspected water accumulation point, the position of the suspected water accumulation point and the maximum depth of the suspected water accumulation point, wherein the area of the suspected water accumulation point and the maximum depth of the suspected water accumulation point are used as characteristic input.
In the invention, after the suspected accumulated water points are selected, marking and numbering are required; and acquiring infrared image information after marking to obtain the area and the maximum depth of the suspected accumulated water point, finally establishing a historical time period model, and establishing a mapping relation between the position of the suspected accumulated water point and the area of the suspected accumulated water point and between the position of the suspected accumulated water point and the maximum depth of the suspected accumulated water point under different rainfall conditions.
Preferably, the step S22 includes the steps of:
s221, acquiring infrared image information of suspected accumulated water points, wherein the temperature of the accumulated water area is lower than that of a non-accumulated water area according to the fact that the specific heat of water in the accumulated water area is higher than that of the non-accumulated water area;
s222, carrying out interval division on the temperature, setting a plurality of temperature intervals, respectively corresponding to different pixels in the infrared image, wherein the area of the pixel higher than the set value is a non-ponding area, the area of the pixel lower than the set value is a ponding area, and calculating the area of the ponding area in the infrared image information;
s223, calculating the area of the actual water accumulation region according to the area relation between the area of the water accumulation region in the infrared image information and the area of the actual water accumulation region, namely the area of the suspected water accumulation point;
and S224, obtaining the space volume information of the suspected ponding point according to the area and the topography information of the suspected ponding point, establishing a space ponding depth model, and solving the maximum depth of the suspected ponding point.
In the invention, for collecting the accumulated water information of the suspected accumulated water point, specifically, a relationship between temperature and pixels is established according to the condition that the temperature of the accumulated water area is different from that of the non-accumulated water area in an infrared image collection mode, the accumulated water area and the non-accumulated water area are distinguished, and the area of the accumulated water area is used as the area of the suspected accumulated water point.
Preferably, the step S3 includes the steps of:
s31, acquiring weather information in a future time period, acquiring rainfall in the future time period, and determining a suspected accumulated water point and a position;
and S32, traversing the historical period model, finding out the relation between the position of the suspected ponding point and the ponding information under the condition of the closest rainfall, and respectively determining the area of the suspected ponding point and the maximum depth of the suspected ponding point in the future period.
According to the method, for a specific prediction process, prediction is mainly carried out according to a historical time period model, the closest rainfall condition is selected, if the same rainfall condition exists, direct calling is carried out, if the same rainfall does not exist, error analysis and trend analysis are carried out, the two conditions respectively correspond to different weights, and the condition with the minimum value is taken for calling after the weights of the two conditions are superposed.
Preferably, the step S4 includes the steps of:
s41, predicting the water accumulation information of the future time period, wherein the water accumulation information of the future time period comprises the predicted area of the suspected water accumulation point of the future time period and the maximum depth of the suspected water accumulation point, and comparing the area with the water accumulation information of the actual future time period;
and S42, comparing and solving the error rate of the accumulated water information in the predicted future time period and the accumulated water information in the actual future time period, if the error rate is more than 0.1%, failing to predict, updating the historical time period model, and if the error rate is less than 0.1%, determining that the prediction is accurate.
In the invention, the verification of the prediction result is mainly compared with the water accumulation information in the actual future time period, when the comparison error rate is overlarge, the prediction result needs to be updated, and the water accumulation information in the future time period is predicted under the safety principle under the normal condition, namely, the area and the maximum depth of a suspected water accumulation point are properly increased on the final prediction result, but the increased area and the maximum depth of the suspected water accumulation point are only used for the early warning process after the prediction result, and the recording of the prediction result is not influenced.
Preferably, the spatial water accumulation depth model records spatial volume information of suspected water accumulation points, each suspected water accumulation point corresponds to one spatial volume information, the spatial volume information in the spatial water accumulation depth model exists in an image form, corresponding parameters of the spatial volume information are input, corresponding spatial volume information is found out, and the maximum depth of the suspected water accumulation points is output.
In the invention, the space ponding depth model can be stored in a computer, can be found out by a traversal method, and can also be called by inputting corresponding parameters, and the more accurate the input corresponding parameters are, the more accurate the maximum depth of the corresponding suspected ponding point is.
Preferably, the gradation map information includes different gradations corresponding to the imaging distance, and the state of unevenness and the state of gradient slope of the road surface can be specified from the gradation map information.
In the invention, the gray-scale map can also be converted into a form of combining a plurality of numerical matrixes, so that the determination of the concave-convex condition and the gradient slope condition is facilitated.
Preferably, the step S21 is specifically: in the grayscale map information, the position with the largest grayscale value is the pit, and if the grayscale values around the pit are significantly reduced, that is, if the grayscale value change rate between the grayscale values around the pit and the position with the largest grayscale value exceeds 10%, the position with the largest grayscale value is the suspected accumulated water point.
In the invention, after the suspected accumulated water point is determined by the gray-scale image information, the position of the suspected accumulated water point is marked so as to facilitate the subsequent collection of a plurality of suspected accumulated water point images.
Preferably, the space water accumulation depth model is updated at fixed time intervals, and the updating of the space water accumulation depth model is synchronous with the updating of the road information of the road section.
According to the method and the device, the space water accumulation depth model is updated along with the updating of the road information of the road section, so that the problem of inaccurate prediction caused by the change of the road information is solved.
The invention has the beneficial effects that: the method for predicting the ponding road sections can be used for establishing a historical time section model according to the road surface information of each road section and combining rainfall and terrain information to predict the ponding information in a future time section.
Drawings
Fig. 1 is a flowchart of a method for predicting a water accumulation section according to the present invention.
Detailed Description
The embodiment is as follows:
the embodiment provides a method for predicting a water accumulation section, which includes a plurality of steps with reference to fig. 1.
The method comprises the following steps of S1, polling a plurality of road sections to be detected, and acquiring road surface information of the road sections, wherein the road surface information comprises rainfall and topography information, and the topography information comprises concave-convex conditions of the road surface and slope conditions; specifically, the accessible is patrolled and examined the vehicle and is patrolled and examined, is provided with various collection system on patrolling and examining the vehicle.
The method comprises a step S11 of acquiring the overall road surface concave-convex condition of the road section to be detected after acquisition, and preliminarily screening out road section points with the flatness larger than a set flatness. Specifically, the collection is performed by detecting the overall road surface unevenness by using a laser detector or other equipment, and screening is performed according to the flatness.
And S12, acquiring image information of each screened road section point, mapping points with different shooting distances in the image information into different gray values according to the relation between the shooting distance and the depth of field to obtain gray map information, and judging the slope condition according to the gray map information. Specifically, in the gradation map information, different gradations are associated with the shooting distance, and the unevenness condition and the gradient/slope condition of the road surface can be specified based on the gradation map information.
And S2, determining the suspected ponding point and the position thereof according to the topography information, obtaining ponding information of the suspected ponding point in a historical time period, and establishing a deep learning historical time period model according to the ponding information, wherein the historical time period model comprises a mapping relation between the position of the suspected ponding point and the ponding information. Specifically, the historical period model is established based on different rainfall conditions in the historical period.
Step S21, screening out suspected accumulated water points from the gray-scale image information, and marking the positions of the suspected accumulated water points; in this embodiment, for a specific marking mode, the marking may be directly marked on the road segment map, but the marking mode is not limited to this mode.
In step S21, the specific process of screening the grayscale map information is as follows: in the gray map information, firstly, the position with the maximum gray value is determined, namely the pit, and if the gray values around the pit are obviously reduced, namely the gray value change rate of the gray value around the pit and the position with the maximum gray value exceeds 10%, the position with the maximum gray value is a suspected water accumulation point. In this embodiment, after the suspected ponding point is determined by the grayscale map information, the position of the suspected ponding point needs to be marked, so as to facilitate the subsequent collection of multiple suspected ponding point images.
Step S22, sequentially collecting ponding information of the suspected ponding points according to the marking sequence, wherein the area of the suspected ponding points is obtained according to the ponding information; and obtaining the maximum depth of the suspected water accumulation point according to the area of the suspected water accumulation point and the topography information. Specifically, for the method of acquiring the area and the maximum depth of the suspected accumulated water point, the substep is referred to.
Step S221, acquiring infrared image information of suspected ponding points, wherein the temperature of the ponding area is lower than that of the non-ponding area according to the fact that the specific heat of water in the ponding area is higher than that of the non-ponding area; in this embodiment, an infrared camera is used for acquisition, and image processing is performed in the controller. The controller is a computer.
Step S222, dividing the temperature into sections, setting a plurality of temperature sections, and calculating the area of the water accumulation region in the infrared image information, where the different pixels in the infrared image correspond to each other, and the region where the pixel is higher than the set value is a non-water accumulation region and the region where the pixel is lower than the set value is a water accumulation region. Specifically, the area of the water accumulation region can be obtained by only calculating the pixel distribution.
Step S223, calculating the area of the actual water-accumulating area, that is, the area of the suspected water-accumulating point, according to the area relationship between the area of the water-accumulating area in the infrared image information and the area of the actual water-accumulating area, specifically, the area of the water-accumulating area in the infrared image information and the area relationship of the actual water-accumulating area are in a direct proportion relationship, and the proportional system of the direct proportion relationship is a fixed numerical value.
Step S224, according to the area and the relief information of the suspected ponding point, space volume information of the suspected ponding point is obtained, a space ponding depth model is built, and the maximum depth of the suspected ponding point is obtained. Specifically, the maximum depth of the suspected ponding point is the output of the space ponding depth model.
And for the space water accumulation depth model, inputting the space volume information of the suspected water accumulation points, wherein each suspected water accumulation point corresponds to one space volume information, the space volume information in the space water accumulation depth model exists in an image form, inputting corresponding parameters of the space volume information, finding out the corresponding space volume information, and outputting the maximum depth of the suspected water accumulation points. In this embodiment, the spatial ponding depth model can be stored in a computer, and can be found out by a traversal method, or can be retrieved by inputting corresponding parameters, and the more accurate the input corresponding parameters are, the more accurate the maximum depth of the corresponding suspected ponding point is.
S3, acquiring rainfall and topographic information of suspected ponding points in a future time period according to the weather information, and predicting ponding information in the future time period; specifically, the prediction process includes the following sub-steps.
In step S31, weather information in a future time period is acquired, rainfall in the future time period is obtained, and a suspected accumulated water point and a location are determined. Specifically, the acquisition mode is to acquire data from the weather station.
Step S32, traversing the historical time period model, finding out the relation between the position of the suspected ponding point and the ponding information under the condition of the closest rainfall, and respectively determining the area of the suspected ponding point and the maximum depth of the suspected ponding point in the future time period. Specifically, the prediction result is stored and transmitted to the verification end for verification.
And S4, checking the ponding information of the predicted future time period, and updating the historical time period model if the check value exceeds a preset value. The specific verification method is a comparison of error rates, and the following steps are specifically referred to.
Step S41, predicting that the ponding information in the future time period comprises the area of the suspected ponding point and the maximum depth of the suspected ponding point in the predicted future time period, and comparing the area with the ponding information in the actual future time period; specifically, the area of the suspected ponding point and the maximum depth of the suspected ponding point are compared respectively.
And S42, comparing and solving the error rate of the accumulated water information in the predicted future time period and the accumulated water information in the actual future time period, if the error rate is more than 0.1%, failing to predict, updating the historical time period model, and if the error rate is less than 0.1%, determining that the prediction is accurate. In this embodiment, the verification of the prediction result is mainly compared with the water accumulation information in an actual future time period, when the comparison error rate is too large, the prediction result needs to be updated, and the water accumulation information in the future time period is predicted under a safety principle under a normal condition, that is, the area and the maximum depth of the suspected water accumulation point are appropriately increased on the final prediction result, but the increased area and the maximum depth of the suspected water accumulation point are only used in an early warning process after the prediction result, and the recording of the prediction result is not influenced.
In addition, the space water accumulation depth model is updated at fixed time intervals, and the updating of the space water accumulation depth model is synchronous with the updating of the road information of the road section. In this embodiment, the spatial water accumulation depth model is updated along with the update of the road information of the road section, so that the problem of inaccurate prediction caused by the change of the road information is prevented.
Firstly, determining a road section to be detected, wherein the road section to be detected can be selected by self, and respectively acquiring road surface information of the road section to be detected, namely rainfall and terrain information, wherein the terrain information is the concave-convex road surface condition and the slope condition of the whole road section; then, determining each suspected accumulated water point, corresponding position and accumulated water information, establishing a historical time period model, and predicting by using the historical time period model to obtain accumulated water information in a future time period; and finally, checking the prediction result to ensure the accuracy of the prediction.
In this embodiment, in the acquisition process of relief information, at first acquire the unsmooth situation in road surface of the highway section that awaits measuring, to the unsmooth degree great, the highway section point that the roughness is big promptly, carry out preliminary screening, the roughness index of setting for fixed numerical value carries out the collection processing of image respectively to the highway section point of selecting, and the unsmooth situation and the broken situation of slope in the independent highway section point can be fine discerned to the grey scale value information that obtains.
In this embodiment, after the suspected accumulated water point is selected, the suspected accumulated water point needs to be marked and numbered; and acquiring infrared image information after marking to obtain the area and the maximum depth of the suspected accumulated water point, finally establishing a historical time period model, and establishing a mapping relation between the position of the suspected accumulated water point and the area of the suspected accumulated water point and between the position of the suspected accumulated water point and the maximum depth of the suspected accumulated water point under different rainfall conditions.
In this embodiment, specifically, for collecting the accumulated water information of the suspected accumulated water point, a relationship between temperature and pixels is established according to a condition that the temperature of the accumulated water area is different from that of the non-accumulated water area in an infrared image collection manner, the accumulated water area and the non-accumulated water area are distinguished, and the area of the accumulated water area is used as the area of the suspected accumulated water point.
In this embodiment, for a specific prediction process, prediction is mainly performed according to a historical time period model, a closest rainfall condition is selected, if the same rainfall condition exists, the prediction is directly performed, if the same rainfall condition does not exist, error analysis and trend analysis are performed, the two conditions correspond to different weights respectively, and the condition with the minimum value is taken for calling after the weights of the two conditions are superposed.
In this embodiment, the gray scale map may also be converted into a form of a combination of a plurality of numerical matrices, which facilitates determination of the concave-convex condition and the slope condition.
The above embodiments are further illustrated and described in order to facilitate understanding of the invention, and no unnecessary limitations are to be understood therefrom, and any modifications, equivalents, and improvements made within the spirit and principle of the invention should be included therein.
Claims (10)
1. The accumulated water road section prediction method is characterized by comprising the following steps of:
s1, inspecting a plurality of road sections to be detected to obtain road surface information of the road sections, wherein the road surface information comprises rainfall and topography information, and the topography information comprises concave-convex conditions of the road surface and slope conditions;
s2, determining a suspected ponding point and the position thereof according to the topography information, obtaining ponding information of the suspected ponding point in a historical time period, and establishing a deep learning historical time period model according to the ponding information, wherein the historical time period model comprises a mapping relation between the position of the suspected ponding point and the ponding information;
s3, acquiring rainfall and topographic information of suspected ponding points in a future time period according to the weather information, and predicting ponding information in the future time period;
and S4, checking the accumulated water information of the predicted future time period, and updating the historical time period model if the checked value exceeds a preset value.
2. The ponding road section prediction method according to claim 1, wherein the topography information is acquired by using an acquisition device, and the method specifically comprises the following steps:
s11, acquiring the overall concave-convex road surface condition of the road section to be detected, and preliminarily screening road section points with the flatness larger than the set flatness;
and S12, collecting image information of each screened road section point, mapping points with different shooting distances in the image information into different gray values according to the relation between the shooting distance and the depth of field to obtain gray map information, and judging the slope condition according to the gray map information.
3. The ponding road section prediction method according to claim 2, characterized in that the step S2 comprises the steps of:
s21, screening suspected accumulated water points according to the gray-scale image information, and marking the positions of the suspected accumulated water points;
s22, sequentially collecting ponding information of the suspected ponding points according to the marking sequence, wherein the area of the suspected ponding points is obtained according to the ponding information; according to the area of the suspected ponding point and the terrain information, the maximum depth of the suspected ponding point is obtained;
and S23, respectively establishing a historical period model of the position of the suspected water accumulation point, the area of the suspected water accumulation point, the position of the suspected water accumulation point and the maximum depth of the suspected water accumulation point, wherein the area of the suspected water accumulation point and the maximum depth of the suspected water accumulation point are used as characteristic input.
4. The ponding road section prediction method according to claim 3, characterized in that the step S22 includes the steps of:
s221, acquiring infrared image information of the suspected ponding point, wherein the temperature of the ponding area is lower than that of the non-ponding area according to the fact that the specific heat of water in the ponding area is higher than that of the non-ponding area;
s222, carrying out interval division on the temperature, setting a plurality of temperature intervals, respectively corresponding to different pixels in the infrared image, wherein the area of the pixel higher than the set value is a non-ponding area, the area of the pixel lower than the set value is a ponding area, and calculating the area of the ponding area in the infrared image information;
s223, calculating the area of the actual water accumulation area according to the area relation between the area of the water accumulation area in the infrared image information and the actual water accumulation area, namely, the area of the suspected water accumulation point;
and S224, obtaining the space volume information of the suspected ponding point according to the area and the topography information of the suspected ponding point, establishing a space ponding depth model, and solving the maximum depth of the suspected ponding point.
5. The ponding road section prediction method according to claim 3 or 4, characterized in that the step S3 comprises the steps of:
s31, acquiring weather information in a future time period, acquiring rainfall in the future time period, and determining a suspected accumulated water point and a position;
and S32, traversing the historical period model, finding out the relation between the position of the suspected ponding point and the ponding information under the condition of the closest rainfall, and respectively determining the area of the suspected ponding point and the maximum depth of the suspected ponding point in the future period.
6. The ponding road section prediction method according to claim 1, characterized in that the step S4 comprises the steps of:
s41, predicting that the ponding information in the future time period comprises the area of a suspected ponding point and the maximum depth of the suspected ponding point in the predicted future time period, and comparing the area with the ponding information in the actual future time period;
and S42, comparing and solving the error rate of the accumulated water information in the predicted future time period with the error rate of the accumulated water information in the actual future time period, if the error rate is more than 0.1%, the prediction fails, updating the historical time period model, and if the error rate is less than 0.1%, the prediction is accurate.
7. The water accumulation section prediction method according to claim 4, wherein the spatial water accumulation depth model records spatial volume information of suspected water accumulation points, each suspected water accumulation point corresponds to one spatial volume information, the spatial volume information in the spatial water accumulation depth model exists in the form of an image, corresponding parameters of the spatial volume information are input, corresponding spatial volume information is found, and the maximum depth of the suspected water accumulation point is output.
8. The accumulated water road section prediction method according to claim 2, wherein the gray scale map information is obtained by corresponding to different gray scales of the shooting distance, and the concave-convex condition and the gradient slope condition of the road surface can be determined according to the gray scale map information.
9. The accumulated water section prediction method according to claim 3, wherein the step S21 specifically comprises: in the grayscale map information, the position with the largest grayscale value is the pit, and if the grayscale value around the pit is significantly reduced, that is, if the grayscale value change rate between the grayscale value around the pit and the position with the largest grayscale value exceeds 10%, the position with the largest grayscale value is the suspected accumulated water point.
10. The water accumulation section prediction method according to claim 7, wherein the space water accumulation depth model is updated at fixed time intervals, and the updating of the space water accumulation depth model is synchronized with the updating of the road information of the section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211201570.8A CN115755228A (en) | 2022-09-29 | 2022-09-29 | Accumulated water road section prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211201570.8A CN115755228A (en) | 2022-09-29 | 2022-09-29 | Accumulated water road section prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115755228A true CN115755228A (en) | 2023-03-07 |
Family
ID=85350604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211201570.8A Pending CN115755228A (en) | 2022-09-29 | 2022-09-29 | Accumulated water road section prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115755228A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116469013A (en) * | 2023-06-20 | 2023-07-21 | 云途信息科技(杭州)有限公司 | Road ponding prediction method, device, computer equipment and storage medium |
| CN116955964A (en) * | 2023-09-19 | 2023-10-27 | 江苏省气象服务中心 | Continuous pavement meteorological condition analysis and deduction method |
| CN116952943A (en) * | 2023-09-19 | 2023-10-27 | 吉林省林业科学研究院(吉林省林业生物防治中心站) | Forest land slope soil erosion measurement system based on oblique photography |
-
2022
- 2022-09-29 CN CN202211201570.8A patent/CN115755228A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116469013A (en) * | 2023-06-20 | 2023-07-21 | 云途信息科技(杭州)有限公司 | Road ponding prediction method, device, computer equipment and storage medium |
| CN116469013B (en) * | 2023-06-20 | 2023-09-08 | 云途信息科技(杭州)有限公司 | Road ponding prediction method, device, computer equipment and storage medium |
| CN116955964A (en) * | 2023-09-19 | 2023-10-27 | 江苏省气象服务中心 | Continuous pavement meteorological condition analysis and deduction method |
| CN116952943A (en) * | 2023-09-19 | 2023-10-27 | 吉林省林业科学研究院(吉林省林业生物防治中心站) | Forest land slope soil erosion measurement system based on oblique photography |
| CN116952943B (en) * | 2023-09-19 | 2023-12-08 | 吉林省林业科学研究院(吉林省林业生物防治中心站) | Forest land slope soil erosion measurement system based on oblique photography |
| CN116955964B (en) * | 2023-09-19 | 2023-12-12 | 江苏省气象服务中心 | Continuous pavement meteorological condition analysis and deduction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115755228A (en) | Accumulated water road section prediction method | |
| CN107829452B (en) | Deep foundation pit construction monitoring and early warning technology integrating multiple sensors and foundation SAR | |
| CN112364802B (en) | Deformation monitoring method for collapse landslide disaster body | |
| US20200149888A1 (en) | Method and device for monitoring water volume change, computer device and storage medium | |
| CN111896721B (en) | Municipal road engineering quality intelligent acceptance detection management system based on big data | |
| KR20210030031A (en) | Early warning method and system for landslide integrated with weather forecasting information | |
| CN111784070A (en) | Intelligent landslide short-term early warning method based on XGboost algorithm | |
| CN110705759B (en) | Water level early warning monitoring method and device, storage medium and electronic equipment | |
| CN112329582B (en) | Road ponding depth monitoring method and system based on big data analysis and mechanism model cooperation | |
| CN113593191A (en) | Visual urban waterlogging monitoring and early warning system based on big data | |
| CN115035182B (en) | Landslide hazard early warning method and system | |
| CN116908942A (en) | Urban waterlogging warning device and method based on rainfall forecast | |
| CN116989679A (en) | Highway high slope displacement integrated monitoring method based on image processing | |
| CN115719164A (en) | Urban waterlogging-prone point identification method and device | |
| CN108364129A (en) | A kind of region ecology safety early alarming and forecasting method based on remote sensing big data | |
| CN110631547B (en) | Roadbed monitoring and early warning system based on Internet of things | |
| CN117372629A (en) | Reservoir visual data supervision control system and method based on digital twinning | |
| CN117196302A (en) | Regional waterlogging risk prediction method and system based on catchment partition | |
| CN116629602A (en) | Dynamic monitoring and disaster early warning system for earth-rock dam seepage safety based on digital twin technology and construction method thereof | |
| CN116129611A (en) | River bank collapse monitoring system and monitoring device | |
| CN214372603U (en) | Intelligent road safety monitoring and operation management system | |
| CN115438547A (en) | Overall evaluation method and system based on pavement service state | |
| US20230135343A1 (en) | Degradation display system, degradation display method, and recording medium | |
| JPH0972965A (en) | Method of forecasting disturbance of weather | |
| CN110533698A (en) | A kind of foundation pit construction stake detection control method of view-based access control model detection |
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 |