CN113823088B - Urban road ponding depth prediction and early warning method based on visual recognition technology - Google Patents
Urban road ponding depth prediction and early warning method based on visual recognition technology Download PDFInfo
- Publication number
- CN113823088B CN113823088B CN202111065131.4A CN202111065131A CN113823088B CN 113823088 B CN113823088 B CN 113823088B CN 202111065131 A CN202111065131 A CN 202111065131A CN 113823088 B CN113823088 B CN 113823088B
- Authority
- CN
- China
- Prior art keywords
- depth
- picture
- water
- scale feature
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000005516 engineering process Methods 0.000 title claims abstract description 25
- 230000000007 visual effect Effects 0.000 title claims abstract description 14
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 77
- 238000001514 detection method Methods 0.000 claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 238000010586 diagram Methods 0.000 claims abstract description 9
- 238000012937 correction Methods 0.000 claims abstract description 8
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 5
- 238000009825 accumulation Methods 0.000 claims description 20
- 238000002372 labelling Methods 0.000 claims description 13
- 239000003086 colorant Substances 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 238000013136 deep learning model Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 238000000691 measurement method Methods 0.000 abstract description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
Abstract
The invention discloses an urban road ponding depth prediction and early warning method based on a visual recognition technology, which comprises the steps of constructing a target detection model of a scale feature; collecting a traffic intersection monitoring video, preprocessing a video image, then carrying out scale feature object detection, and carrying out distortion correction and anti-perspective transformation on a detection result; calculating the depth of the dot product water at each position by using a proportional measurement and calculation method according to the target detection result of the scale feature object; displaying the depth of the accumulated water at each position on a platform in a thermodynamic diagram mode; and constructing a time series model according to the existing ponding depth data, and predicting the ponding depth of the next time period by using the collected rainfall and ponding depth data for multiple times. According to the method, the characteristic point location information is extracted through the video data of the road video monitoring system, the ponding depth of the measuring point is calculated by using a perspective analysis algorithm, and the information is displayed by being superposed with an electronic map, so that waterlogging forecasting and early warning are conveniently carried out on a meteorological part, and waterlogging disasters are reduced.
Description
Technical Field
The invention relates to the technical field of urban waterlogging monitoring and early warning, in particular to an urban road waterlogging depth prediction and early warning method based on a visual recognition technology.
Background
Due to the fact that the temperature of the earth surface is increased due to global warming, extreme weather events, particularly extreme events such as heavy rainfall, high temperature heat waves and the like, show a continuously increasing trend in the last 50 years, and the occurrence of the extreme events is expected to be more frequent in the future. Heavy rainstorm and extreme rainfall events generate huge pressure on a drainage system of a city, and road ponding and waterlogging disasters are frequent, so that serious inconvenience is brought to people for going out, and even serious loss of life and property is caused.
The traditional rainstorm waterlogging mathematical model constructed by integrating basic spatial information such as urban geography, river terrain, engineering facilities, meteorological monitoring and flood control scheduling can be used for early warning and forecasting waterlogging conditions to a certain extent, but is influenced by factors such as data integrity, accuracy and model generalization, and the mathematical model is difficult to provide real-time urban waterlogging information.
The monitoring and early warning system established based on water level rainfall sensing and the Internet of things technology and established in part of cities can provide real-time and accurate accumulated water point information, can improve the precaution level to a certain extent, and enhances the capability of resisting rainstorm disasters. The implementation of this technical scheme need rely on hardware such as a large amount of water level monitoring and sensing facility to drop into, realizes that large tracts of land covers and technique popularization has great degree of difficulty.
At present, with the continuous promotion of construction projects such as smart cities, safe cities and the like, monitoring networks of cities at all levels have reached higher coverage, and monitoring technology is gradually developed from analog signals to high-definition digital technology. If the urban waterlogging early warning system can be developed based on the existing urban monitoring video resources by using the computer vision technology, the artificial intelligence algorithm, the video big data processing technology and the like, the waterlogging monitoring cost can be greatly saved, a point-and-face urban area full-coverage monitoring system is built, and a new method is provided for solving the urban waterlogging problem and perfecting a drainage system.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems in the prior art, the invention provides an urban road water accumulation depth prediction and early warning method based on a visual recognition technology, which comprises the steps of collecting video data of a road video monitoring system, extracting feature point position information, recognizing scale features by using binarization processing and pixel feature recognition, calculating the water accumulation depth of a measuring point by using a ratio measuring and calculating party, superposing the information and an electronic map to realize data visualization, realizing water accumulation depth prediction by using a time sequence model, facilitating the early warning of waterlogging forecast in a meteorological part and reducing waterlogging disasters.
The technical scheme is as follows: the invention provides an urban road ponding depth prediction and early warning method based on a visual recognition technology, which comprises the following steps:
step 1: constructing a target detection model of the scale feature, wherein the detection model adopts a YOLO v3 deep learning model to construct the target detection model of the scale feature;
and 2, step: collecting a traffic intersection monitoring video, preprocessing a video image, then carrying out target detection on a scale feature, and carrying out distortion correction and anti-perspective transformation on a detection result image to obtain a front view of the scale feature;
and 3, step 3: carrying out binarization processing and pixel feature identification on the scale feature front view in the step 2, and calculating the depth of each position dot product water by using a proportional calculation method;
and 4, step 4: building a WebGIS-based accumulated water depth product analysis platform, and displaying the accumulated water depth of each position in the step 3 on the platform in a thermodynamic diagram mode;
and 5: and constructing a time series model according to the existing water accumulation depth data, and predicting the water accumulation depth of the next time period by using the collected multiple rainfall and water accumulation depth data.
Further, the method for constructing the target detection model in the step 1 comprises the following steps:
s1.1: collecting an object image with scale characteristics at an urban traffic intersection, classifying the object image into categories, and measuring the characteristic sizes of different scale characteristics, wherein the specific categories comprise warning post, traffic indication rod and signal lamp post scale characteristics, and the characteristic sizes mainly comprise the height of a color band and the distance between a top color band and the ground;
s1.2: labeling the picture by using LabelImg to obtain a labeling file in txt format matched with the picture;
s1.3: the Python script file makes the collected pictures into a training data set file 'train.txt' and a test data set file 'test.txt';
s1.4: and (4) inputting the data set file in the S1.3 into a YOLO v3 deep learning model to finish the training and testing of the target detection model.
Further, the video image preprocessing in the step 2 includes converting the video image into a frame-by-frame picture data set, and performing rain removing processing on the picture data by using a rain removing algorithm based on a GAN network.
Further, the specific method for detecting the scale feature target in the step 2 is as follows:
s2.1: reading a picture data set, transmitting the picture data set into the target detection model trained in the step 1 for detection, performing frame selection on scale feature objects in the picture, and identifying the scale category;
s2.2: capturing a local area picture of the scale feature according to the target detection result in the S2.1;
s2.3: and (3) performing distortion correction and inverse perspective transformation on the local area picture by adopting a project points function of OpenCV to obtain a front view of the scale feature.
Further, the specific method for calculating the depth of the dot product water at each position in step 3 is as follows:
s3.1: establishing local picture templates at the joint of color bands of different colors according to the front view of the scale feature in the step 2;
s3.2: reading a feature image acquired by target detection, and matching a first red-white or other color interval region position by using a cv2.Matchtemplate function of OpenCv so as to determine the position of an interval line;
s3.3: carrying out binarization processing on the picture, and circularly finding the initial position of a red-white or other color alternate region by pixel points from a first red-white or other color alternate spacing line so as to determine the height c of a first color band on the picture;
s3.4: reading the height of the whole picture through OpenCv to obtain the position of the bottom edge of the picture, and subtracting the position of the top of the color band according to the position of the top of the color band obtained in S3.3 to obtain the height x from the top to the bottom of the color band on the picture;
s3.5: and calculating the depth of the accumulated water by proportional measurement in combination with the known size of the scale features of the specific category, wherein the specific calculation formula is as follows:
wherein D is the depth of the accumulated water; h is the actual height from the top end of the captured scale feature to the ground; s is the width of a single color band of the scale feature; x is the height of the first ribbon from top to bottom in the figure; c is the height of the first color bar on the graph.
Further, the concrete method for displaying the ponding depth product analysis platform in the thermodynamic diagram mode comprises the following steps:
s4.1: ID marking is carried out on the scaly structure, site water depth data are matched with site IDs, and site water depth display is carried out on a WebGIS through java calling of sites and site attributes;
s4.2: based on the site water depth data, carrying out water accumulation amount simulation operation by utilizing a site fitting technology to realize grid point interpolation of any region and different levels, storing the grid point data in a JavaScript Object Notation data format, carrying out segmentation marking on the road, matching the road section with the attribute according to the road section ID, finally constructing a WebGIS frame by adopting technologies such as Leafflet, canvas and the like, and uniformly displaying the water depth site data and the road grid point data in a superimposed geographic information manner.
Further, the method for performing station water depth display on the WebGIS in the step S4.1 includes: the dots with colors are used for representing accumulated water with different degrees, and the accumulated water is divided into different grades according to the depth of the accumulated water:
1) Slightly accumulating water for 0-10 cm, and labeling with blue;
2) Slightly accumulating water for 10-15 cm, and labeling with yellow;
3) Moderate water accumulation of 15-30 cm is marked by orange;
4) Severe ponding >30cm, red was used.
Has the beneficial effects that:
1. the method disclosed by the invention is mainly used for carrying out urban accumulated water depth identification based on the existing urban monitoring image, and does not need to build hardware facilities such as a newly-added rainfall sensor, so that the cost can be greatly reduced, the large-area coverage of a monitoring system can be realized, and the method has the advantages of good applicability, easiness in popularization and the like.
2. The invention utilizes the scale feature identified in the monitoring system to carry out scale extraction and anti-perspective correction, determines the height c on the image of the first color band and the height x on the image from the top end to the bottom of the color band in the image through binarization and pixel feature extraction methods according to the image data of the scale feature, and measures and calculates the depth of the accumulated water at any time by utilizing ratio measurement, thereby having high real-time performance.
3. The forecasting precision is continuously improved along with the accumulation of basic data based on the time series model, the forecasting precision is gradually improved, and the practicability and the commercial value of the method are gradually improved after the method is put into operation.
Drawings
FIG. 1 is a technical route chart of the accumulated water depth prediction and early warning method of the present invention;
FIG. 2 is a schematic view of target detection of a scale feature of the present invention;
FIG. 3 is a water depth marker plot of a scale feature of the present invention;
FIG. 4 is a thermodynamic diagram showing the road water depth electronic map of the present invention;
FIG. 5 is a water accumulation depth warning visualization display diagram according to the present invention;
FIG. 6 is a schematic diagram of an alarm when the depth of water accumulated on the electronic map exceeds a threshold value.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The invention discloses an urban road ponding depth prediction and early warning method based on a visual identification technology, which comprises the following steps:
step 1: and constructing a target detection model of the scale feature, wherein the detection model adopts a YOLO v3 deep learning model to construct the target detection model of the scale feature.
S1.1: the method comprises the steps of collecting an object image with scale characteristics at an urban traffic intersection, carrying out classification division, and measuring the characteristic sizes of different scale characteristics, wherein the characteristic sizes mainly comprise the height of a color ribbon and the distance between a top color ribbon and the ground, and referring to the attached drawing 2, the method adopts video image data collected based on the existing urban monitoring system, and the scale characteristics mainly comprise a traffic sign warning pole, a signal lamp pole and the like.
S1.2: labeling the picture by using LabelImg to obtain a labeling file in txt format matched with the picture;
s1.3: the Python script file makes the collected pictures into a training data set file 'train.txt' and a testing data set file 'test.txt';
s1.4: and (4) inputting the data set file in the S1.3 into a YOLO v3 deep learning model to finish the training and testing of the target detection model.
Step 2: collecting traffic intersection monitoring videos, preprocessing video images, then carrying out target detection on the scale feature objects, and carrying out distortion correction and anti-perspective transformation on the detection result images to obtain the front view of the scale feature objects.
The pretreatment thereon comprises: and converting the video image into a frame-by-frame picture data set, and carrying out rain removing treatment on the picture data by using a rain removing algorithm based on a GAN network.
S2.1: reading a picture data set, transmitting the picture data set into the target detection model trained in the step 1 for detection, performing frame selection on the scale feature objects in the picture, and identifying the scale types of the scale feature objects, referring to the attached figures 2 and 3.
S2.2: and (4) capturing a local area picture of the scale feature according to the target detection result in the S2.1, and referring to the attached figure 3.
S2.3: and performing distortion correction and inverse perspective transformation on the local area picture by adopting a project points function of OpenCV to obtain a front view of the scale feature.
And step 3: and (4) calculating the depth of the dot product water at each position by using a proportional measurement and calculation method according to the target detection result of the standard ruler feature object in the step (2).
The specific method for calculating the depth of the dot product water at each position in the step 3 comprises the following steps:
s3.1: and establishing local picture templates at the joint of color bands of different colors according to the scale features.
S3.2: and reading a feature image acquired by target detection, and matching the region position (or other colors) of the first red and white interval by using the cv2.Matchtemplate function of OpenCv, thereby determining the position of the interval line.
S3.3: the picture is subjected to binarization processing, and from a first interval line with red and white intervals (or other colors, in the figure, the warning rods with red and white intervals are taken as an example), the pixel points circularly find the initial position of the red and white area, so that the height c of the first color band on the picture is determined.
S3.4: and reading the height of the whole picture through OpenCv to obtain the position of the bottom edge of the picture, and subtracting the position of the top of the color band obtained according to S3.3 to obtain the height x from the top to the bottom of the color band on the picture.
S3.5: and calculating the depth of the ponding water by proportional measurement and calculation by combining the known size of the scale features of the specific category, wherein the specific calculation formula is as follows:
wherein D is the depth of the accumulated water; h is the actual height from the top end of the grabbed scale feature to the ground; s is the width of a single color band of the scale feature; x is the height of the first color band from top to bottom in the figure; c is the height of the first color bar on the graph.
And 4, step 4: and (4) constructing a water accumulation depth product analysis platform based on the WebGIS, and displaying the water accumulation depth at each position in the step (3) on the platform in a thermodynamic diagram mode.
S4.1: and (4) performing ID labeling on the scaly structure, matching the site water depth data with the site ID, and displaying the site water depth on the WebGIS by calling the site and the site attributes through java.
The dots with colors are used for representing accumulated water with different degrees, and the accumulated water is divided into different grades according to the depth of the accumulated water:
1) Slightly accumulating water for 0-10 cm, and labeling with blue;
2) Slightly accumulating water for 10-15 cm, and labeling with yellow;
3) Moderate water accumulation of 15-30 cm is marked by orange;
4) Severe ponding >30cm, red was used.
Referring to fig. 5 and fig. 6, the water depth result is matched with the map point location, different water depths are classified and displayed on the map in different colors, and data between intersections are filled by difference calculation. And displaying a warning signal for the point position with the water accumulation depth exceeding 30 cm.
S4.2: based on site water depth data, carrying out water accumulation amount simulation operation by utilizing a site fitting technology, realizing lattice point interpolation of any region and different levels, storing the lattice point data in a JavaScript Object Notation data format, carrying out segmentation marking on a road, matching the road section with attributes according to road section ID, finally constructing a WebGIS framework by adopting technologies such as Leafflet, canvas and the like, and uniformly displaying water depth site data and road lattice point data by superposing geographic information.
And 5: and constructing a time series model according to the existing water accumulation depth data, and predicting the water accumulation depth of the next time period by using the collected multiple rainfall and water accumulation depth data.
The above embodiments are merely illustrative of the technical concepts and features of the present invention, and the purpose of the embodiments is to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the protection scope of the present invention. All equivalent changes and modifications made according to the spirit of the present invention should be covered in the protection scope of the present invention.
Claims (7)
1. A method for predicting and early warning urban road ponding depth based on a visual identification technology is characterized by comprising the following steps:
step 1: constructing a target detection model of the scale feature, wherein the detection model adopts a YOLO v3 deep learning model to construct the target detection model of the scale feature;
step 2: collecting a traffic intersection monitoring video, preprocessing a video image, then carrying out target detection on a scale feature, and carrying out distortion correction and anti-perspective transformation on a detection result image to obtain a front view of the scale feature;
and step 3: carrying out binarization processing and pixel feature identification on the scale feature front view in the step 2, and calculating the depth of each position dot product water by using a proportional calculation method;
the specific method for calculating the depth of the dot product water at each position in the step 3 comprises the following steps:
s3.1: establishing local picture templates at the joint of color bands of different colors according to the front view of the scale feature in the step 2;
s3.2: reading a feature image acquired by target detection, and matching a first red-white or other color interval region position by using a cv2.Matchtemplate function of OpenCv so as to determine the position of an interval line;
s3.3: carrying out binarization processing on the picture, and circularly finding the initial position of a red-white or other color alternate region by pixel points from a first red-white alternate or other color alternate spacing line so as to determine the height c of a first color band on the picture;
s3.4: reading the height of the whole picture through OpenCv to obtain the position of the bottom edge of the picture, and subtracting the position of the top of the color band obtained according to S3.3 to obtain the height x from the top to the bottom of the color band on the picture;
s3.5: and calculating the depth of the ponding water by proportional measurement and calculation by combining the known size of the scale features of the specific category, wherein the specific calculation formula is as follows:
wherein D is the depth of accumulated water; h is the actual height from the top end of the grabbed scale feature to the ground; s is the width of a single color band of the scale feature; x is the height of the first color band from top to bottom in the figure; c is the on-image height of the first color band;
and 4, step 4: constructing a WebGIS-based ponding depth product analysis platform, and displaying the ponding depth of each position in the step 3 on the platform in a thermodynamic diagram mode;
and 5: and constructing a time series model according to the existing ponding depth data, and predicting the ponding depth of the next time period by using the collected rainfall and ponding depth data for multiple times.
2. The urban road ponding depth prediction and early warning method based on the visual recognition technology as claimed in claim 1, wherein the target detection model and the basic method established in step 1 are as follows:
s1.1: collecting an object image with scale characteristics at an urban traffic intersection, classifying the object image into classes, and measuring the characteristic sizes of different scale characteristics, wherein the specific classes comprise warning post, traffic indicating rod and signal lamp post scale characteristics, and the characteristic sizes mainly comprise ribbon height and distance between a top ribbon and the ground;
s1.2: labeling the picture by using LabelImg to obtain a tagged file in txt format matched with the picture;
s1.3: the Python script file makes the collected pictures into a training data set file 'train.txt' and a test data set file 'test.txt';
s1.4: and (4) inputting the data set file in the S1.3 into a YOLO v3 deep learning model to finish the training and testing of the target detection model.
3. The urban road ponding depth prediction and early warning method based on the visual recognition technology as claimed in claim 1, wherein the video image preprocessing in the step 2 comprises converting the video image into a frame-by-frame picture data set, and performing rain removing processing on the picture data by using a rain removing algorithm based on a GAN network.
4. The urban road ponding depth prediction and early warning method based on the visual recognition technology as claimed in claim 1, wherein the specific method for detecting the scale feature object in step 2 is as follows:
s2.1: reading a picture data set, transmitting the picture data set into the target detection model trained in the step 1 for detection, performing frame selection on the scale feature objects in the picture, and identifying the scale category of the scale feature objects;
s2.2: capturing a local area picture of the scale feature according to the target detection result in the S2.1;
s2.3: and (3) performing distortion correction and inverse perspective transformation on the local area picture by adopting a project points function of OpenCV to obtain a front view of the scale feature.
5. The urban road ponding depth prediction and early warning method based on the visual recognition technology as claimed in claim 1, wherein the specific method for calculating the ponding depth at each position in step 3 is as follows:
s3.1: establishing local picture templates at the joint of color bands of different colors according to the front view of the scale feature in the step 2;
s3.2: reading a feature image acquired by target detection, and matching a first red-white or other color interval region position by using a cv2.Matchtemplate function of OpenCv so as to determine the position of an interval line;
s3.3: carrying out binarization processing on the picture, and circularly finding the initial position of a red-white or other color alternate region by pixel points from a first red-white or other color alternate spacing line so as to determine the height c of a first color band on the picture;
s3.4: reading the height of the whole picture through OpenCv to obtain the position of the bottom edge of the picture, and subtracting the position of the top of the color band obtained according to S3.3 to obtain the height x from the top to the bottom of the color band on the picture;
s3.5: and calculating the depth of the ponding water by proportional measurement and calculation by combining the known size of the scale features of the specific category, wherein the specific calculation formula is as follows:
wherein D is the depth of the accumulated water; h is the actual height from the top end of the grabbed scale feature to the ground; s is the width of a single color band of the scale feature; x is the height of the first color band from top to bottom in the figure; c is the height of the first color bar on the graph.
6. The urban road ponding depth prediction and early warning method based on the visual recognition technology as claimed in any one of claims 1 to 5, wherein the concrete method for displaying the ponding depth product analysis platform in a thermodynamic diagram manner is as follows:
s4.1: performing ID labeling on the scaly structure, matching site water depth data with site IDs, calling sites and site attributes through java, and displaying the site water depth on a WebGIS;
s4.2: based on site water depth data, carrying out water accumulation amount simulation operation by utilizing a site fitting technology, realizing lattice point interpolation of any region and different levels, storing the lattice point data in a JavaScript Object Notation data format, carrying out segmentation marking on a road, matching the road section with attributes according to road section ID, finally constructing a WebGIS framework by adopting technologies such as Leafflet, canvas and the like, and uniformly displaying water depth site data and road lattice point data by superposing geographic information.
7. The urban road ponding depth prediction and early warning method based on the visual recognition technology as claimed in claim 6, wherein the method for performing site water depth display on the WebGIS in the step S4.1 is as follows: the dots with colors are used for representing accumulated water with different degrees, and the accumulated water is divided into different grades according to the depth of the accumulated water:
1) Slightly accumulating water for 0-10 cm, and labeling with blue;
2) Slightly accumulating water for 10-15 cm, and labeling with yellow;
3) Moderate water accumulation of 15-30 cm is marked by orange;
4) Severe ponding >30cm, red was used.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111065131.4A CN113823088B (en) | 2021-09-11 | 2021-09-11 | Urban road ponding depth prediction and early warning method based on visual recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111065131.4A CN113823088B (en) | 2021-09-11 | 2021-09-11 | Urban road ponding depth prediction and early warning method based on visual recognition technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113823088A CN113823088A (en) | 2021-12-21 |
| CN113823088B true CN113823088B (en) | 2023-01-13 |
Family
ID=78914355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111065131.4A Active CN113823088B (en) | 2021-09-11 | 2021-09-11 | Urban road ponding depth prediction and early warning method based on visual recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113823088B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116071656B (en) * | 2023-03-06 | 2023-06-06 | 河北工业大学 | Intelligent alarm method and system for infrared image ponding detection of underground transformer substation |
| CN116778696B (en) * | 2023-08-14 | 2023-11-14 | 易启科技(吉林省)有限公司 | Visual-based intelligent urban waterlogging early warning method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522889A (en) * | 2018-09-03 | 2019-03-26 | 中国人民解放军国防科技大学 | Hydrological ruler water level identification and estimation method based on image analysis |
| CN109448382B (en) * | 2018-12-20 | 2021-10-26 | 天地伟业技术有限公司 | Road accumulated water depth monitoring and early warning method |
| CN109801327B (en) * | 2018-12-21 | 2020-07-21 | 杭州电子科技大学 | Urban waterlogging depth information extraction method based on video data |
| CN111353380A (en) * | 2020-01-08 | 2020-06-30 | 广州华工中云信息技术有限公司 | Urban road ponding image recognition system based on machine image recognition technology |
-
2021
- 2021-09-11 CN CN202111065131.4A patent/CN113823088B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113823088A (en) | 2021-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jain et al. | Flood inundation mapping using NOAA AVHRR data | |
| CN113823088B (en) | Urban road ponding depth prediction and early warning method based on visual recognition technology | |
| Sarvestani et al. | Three decades of urban growth in the city of Shiraz, Iran: A remote sensing and geographic information systems application | |
| Sheng et al. | Quantitative dynamic flood monitoring with NOAA AVHRR | |
| Jafari et al. | Real-time water level monitoring using live cameras and computer vision techniques | |
| CN109801327B (en) | Urban waterlogging depth information extraction method based on video data | |
| CN110532952A (en) | Flood disaster risk early warning and evacuation system based on GIS location technology | |
| Turner et al. | CZM applications of Argus coastal imaging at the Gold Coast, Australia | |
| CN109186706B (en) | Method for early warning of urban rainfall flood inundated area | |
| CN102842130B (en) | Method for detecting buildings and extracting number information from synthetic aperture radar image | |
| CN115169771B (en) | Method for quickly evaluating efficiency damage of traffic network under influence of flood disasters | |
| CN110070012A (en) | A kind of refinement extracted applied to remote sensing image road network and global connection method | |
| CN108846402A (en) | The terraced fields raised path through fields based on multi-source data automates extracting method | |
| CN112906455A (en) | Coastal zone ecological system remote sensing identification method | |
| CN116246181A (en) | Extra-high voltage dense channel drift monitoring method based on satellite remote sensing technology | |
| CN114067245A (en) | Method and system for identifying hidden danger of external environment of railway | |
| CN113128579B (en) | Method for rapidly and visually measuring ground buried depth of tower pole of power transmission line | |
| CN115471980B (en) | Mud-rock flow disaster early warning method | |
| CN112232303B (en) | Grassland road information extraction method based on high-resolution remote sensing image | |
| CN113420670A (en) | Environment-friendly supervision method for changing power transmission and transformation line migration based on high-resolution remote sensing | |
| CN111340668B (en) | Typhoon disaster assessment system | |
| Callaghan et al. | The use of Landsat and aerial photography for the assessment of coastal erosion and erosion susceptibility in False Bay, South Africa | |
| CN115293262B (en) | Shoreline function and structure long time sequence detection method | |
| CN114529814B (en) | Loess plateau silt dam extraction method based on multi-source data | |
| CN115546917A (en) | Hydraulic engineering intelligent patrol method and device based on video monitoring and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231222 Address after: No. 22-15, Unit 2, No. 19 Dapingzheng Street, Yuzhong District, Chongqing, 400000 Patentee after: Chongqing Weather Online Technology Co.,Ltd. Address before: 223005 Jiangsu Huaian economic and Technological Development Zone, 1 East Road. Patentee before: HUAIYIN INSTITUTE OF TECHNOLOGY |
|
| TR01 | Transfer of patent right |