CN114299726A - Highway severe weather identification method based on artificial intelligence - Google Patents
Highway severe weather identification method based on artificial intelligence Download PDFInfo
- Publication number
- CN114299726A CN114299726A CN202111673044.7A CN202111673044A CN114299726A CN 114299726 A CN114299726 A CN 114299726A CN 202111673044 A CN202111673044 A CN 202111673044A CN 114299726 A CN114299726 A CN 114299726A
- Authority
- CN
- China
- Prior art keywords
- highway
- severe weather
- artificial intelligence
- comparison
- weather
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 238000010835 comparative analysis Methods 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an artificial intelligence-based highway severe weather identification method, which comprises the following steps: s1, forming video data; s2, classifying the video data according to weather conditions, dividing the video data into five categories of sunny days, cloudy days, rainy days, foggy days and snowy days, and storing the five categories respectively; s3, forming an extracted picture, and storing the extracted picture according to the category; s4, forming an analysis model; s5, forming key point pixels; s6, forming a contrast database; s7, monitoring the highway environment in real time through a camera, setting a comparison period, and comparing and analyzing the video state and a comparison database; s8, outputting a comparison result after the weather type accords with one category; s9, identifying the type of severe weather, performing early warning prompt, performing final judgment by combining the identification result with temperature and humidity change, avoiding interference caused by misjudgment, facilitating efficient identification and early warning, ensuring the safety of highway management and use and facilitating popularization and use.
Description
Technical Field
The invention relates to the technical field of highway management, in particular to a highway severe weather identification method based on artificial intelligence.
Background
In the current social life, the use of the expressway is more and more common, and in the driving safety of the expressway, the influence range of weather is largest, and the caused consequences are the most serious, so that in order to ensure the management safety of the expressway, the severe weather of the expressway needs to be identified, and the timeliness of early warning is ensured.
However, in the existing identification method for severe weather on the highway, the pictures are shot directly through the monitoring camera and then are identified and verified manually, so that the identification range is small, the efficiency is low, the feedback time is long, the timeliness is not high, meanwhile, more manpower and time are needed, the identification cost is high, intelligent identification analysis can not be performed through images, and a new identification method needs to be provided.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides an artificial intelligence-based highway severe weather identification method.
In order to achieve the purpose, the invention adopts the following technical scheme:
an artificial intelligence-based highway severe weather identification method comprises the following steps:
s1, shooting the highway environment by a camera in different weather to form video data;
s2, classifying the video data according to weather conditions, dividing the video data into five categories of sunny days, cloudy days, rainy days, foggy days and snowy days, and storing the five categories respectively;
s3, extracting the content of the classified video data, separating out pictures with high definition to form extracted pictures, and storing the extracted pictures corresponding to the categories;
s4, modeling the content of the extracted picture to form an analysis model;
s5, separating the key points of the picture through an analysis model to form key point pixels;
s6, classifying and storing the key point pixels, and associating the key point pixels with video data and an extracted picture directory to form a comparison database;
s7, monitoring the highway environment in real time through a camera, setting a comparison period, and comparing and analyzing the video state and a comparison database;
s8, outputting a comparison result after the weather type accords with one category;
and S9, detecting the temperature and humidity of the monitoring position, judging by matching the output result, determining the identified severe weather type, and performing early warning prompt.
Preferably, the video data in S1 includes a highway pavement video and a surrounding environment video, and is a synchronous shooting file.
Preferably, the manner of forming the extracted pictures in S3 is to play the video file according to frames, check each frame of picture, and extract and separate the pictures.
Preferably, the analysis model of S4 is a picture layer three-dimensional framework model, and analyzes the key point layer of the picture.
Preferably, the method for forming the key pixel in S5 includes the following steps:
a1, separating image layers of the pictures to form a background layer, a highway layer and a key point layer;
a2, comparing the background layers, directly and completely discarding the road sections which do not conform to the identification, and continuing to process if the road sections conform to the identification;
a3, separating the expressway layer and the key point layer, separately comparing and analyzing the road surface state, and extracting obvious change characteristics to form characteristic points;
and A4, reserving the characteristic points, forming a new layer, and obtaining key pixel points.
Preferably, the forming of the comparison database in S6 includes camera automatic shooting data, manhole input data, automatic recognition result data and manual input result data.
Preferably, in S7, the contrast period is set as a set time period, one frame of image is captured every 10 seconds for comparison, the operation is performed for 6 times continuously to form a contrast period, and then the capturing is started again at an interval of 600 seconds, and the operations are performed in a cycle.
Preferably, the comparative analysis method in S7 includes the following steps:
b1, extracting the key pixel points and associating the key pixel points with the stored data in the database;
b2, caching the associated storage data and the key pixel points to a comparison position separately to form a comparison file;
b3, analyzing a comparison file, comparing the states of the expressway layers, analyzing the reflection intensity of the pavement, judging the expressway layers to be in a sunny day and a cloudy day if the expressway layers are in normal reflection, judging the expressway layers to be in a foggy day if the expressway layers are in weak reflection, and judging the expressway layers to be in a rainy day and a snowy day if the expressway layers are in strong reflection;
and B4, performing correlation comparison with the database according to the judgment result, outputting a final result and judging the type of the severe weather.
Preferably, the output comparison result in S8 includes a weather category, a weather intensity, a local range, and a time node.
Preferably, the mode of judging the matching result in S9 is to verify the temperature, humidity and weather structure, and if the matching result obviously does not conform to the natural law, the judgment is a false judgment, and the comparison and analysis are returned to S7.
According to the artificial intelligence-based highway severe weather identification method, the highway video data are obtained through shooting, then the images are separated and extracted through frame number checking, the accuracy and the definition of the images are ensured, then the key points of the images are separated and extracted according to the image layer analysis model of the images, the weather states which are consistent with the images can be contrastively analyzed, the efficiency, the stability and the accuracy are high, intelligent extraction and analysis can be performed, the errors and the cost of artificial identification are reduced, the control and the use are facilitated, the final judgment is performed through the identification result and the temperature and humidity change, the interference caused by misjudgment is avoided, the efficient identification and early warning are facilitated, the management and the use safety of the highway is ensured, and the popularization and the use are convenient.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
An artificial intelligence-based highway severe weather identification method comprises the following steps:
s1, shooting the highway environment by a camera in different weather to form video data;
s2, classifying the video data according to weather conditions, dividing the video data into five categories of sunny days, cloudy days, rainy days, foggy days and snowy days, and storing the five categories respectively;
s3, extracting the content of the classified video data, separating out pictures with high definition to form extracted pictures, and storing the extracted pictures corresponding to the categories;
s4, modeling the content of the extracted picture to form an analysis model;
s5, separating the key points of the picture through an analysis model to form key point pixels;
s6, classifying and storing the key point pixels, and associating the key point pixels with video data and an extracted picture directory to form a comparison database;
s7, monitoring the highway environment in real time through a camera, setting a comparison period, and comparing and analyzing the video state and a comparison database;
s8, outputting a comparison result after the weather type accords with one category;
and S9, detecting the temperature and humidity of the monitoring position, judging by matching the output result, determining the identified severe weather type, and performing early warning prompt.
Preferably, the video data in S1 includes a highway pavement video and a surrounding environment video, and is a synchronous shooting file.
Preferably, in the step S3, the extracted pictures are formed by playing the video file in frames, examining each frame of picture, and performing extraction and separation.
Preferably, the analysis model in S4 is a picture layer three-dimensional framework model, and analyzes the key point layer of the picture.
Preferably, the method for forming the key pixel in S5 includes the following steps:
a1, separating image layers of the pictures to form a background layer, a highway layer and a key point layer;
a2, comparing the background layers, directly and completely discarding the road sections which do not conform to the identification, and continuing to process if the road sections conform to the identification;
a3, separating the expressway layer and the key point layer, separately comparing and analyzing the road surface state, and extracting obvious change characteristics to form characteristic points;
and A4, reserving the characteristic points, forming a new layer, and obtaining key pixel points.
Preferably, the forming of the comparison database in S6 includes camera auto-shooting data, manhole input data, auto-recognition result data and manual input result data.
Preferably, in S7, the contrast period is set as a set time period, one frame of image is cut every 10 seconds for comparison, the operation is performed for 6 times continuously to form a contrast period, and then the cutting is started again at an interval of 600 seconds, and the operations are sequentially and cyclically performed.
Preferably, the comparative analysis method in S7 includes the steps of:
b1, extracting the key pixel points and associating the key pixel points with the stored data in the database;
b2, caching the associated storage data and the key pixel points to a comparison position separately to form a comparison file;
b3, analyzing a comparison file, comparing the states of the expressway layers, analyzing the reflection intensity of the pavement, judging the expressway layers to be in a sunny day and a cloudy day if the expressway layers are in normal reflection, judging the expressway layers to be in a foggy day if the expressway layers are in weak reflection, and judging the expressway layers to be in a rainy day and a snowy day if the expressway layers are in strong reflection;
and B4, performing correlation comparison with the database according to the judgment result, outputting a final result and judging the type of the severe weather.
Preferably, the output comparison result in S8 includes a weather type, a weather intensity, a local range, and a time node.
Preferably, the matching result in S9 is determined by mutually verifying the temperature, humidity and weather structure, and if the result obviously does not conform to the natural law, the result is determined as a false determination, and the result returns to S7 for re-comparison and analysis.
According to the artificial intelligence-based highway severe weather identification method, the highway video data are obtained through shooting, then the images are separated and extracted through frame number checking, the accuracy and the definition of the images are ensured, then the key points of the images are separated and extracted according to the image layer analysis model of the images, the weather states which are consistent with the images can be contrastively analyzed, the efficiency, the stability and the accuracy are high, intelligent extraction and analysis can be performed, the errors and the cost of artificial identification are reduced, the control and the use are facilitated, the final judgment is performed through the identification result and the temperature and humidity change, the interference caused by misjudgment is avoided, the efficient identification and early warning are facilitated, the management and the use safety of the highway is ensured, and the popularization and the use are convenient.
Claims (10)
1. An artificial intelligence-based method for identifying severe weather of a highway is characterized by comprising the following steps: the method for identifying the severe weather of the expressway based on artificial intelligence comprises the following steps:
s1, shooting the highway environment by a camera in different weather to form video data;
s2, classifying the video data according to weather conditions, dividing the video data into five categories of sunny days, cloudy days, rainy days, foggy days and snowy days, and storing the five categories respectively;
s3, extracting the content of the classified video data, separating out pictures with high definition to form extracted pictures, and storing the extracted pictures corresponding to the categories;
s4, modeling the content of the extracted picture to form an analysis model;
s5, separating the key points of the picture through an analysis model to form key point pixels;
s6, classifying and storing the key point pixels, and associating the key point pixels with video data and an extracted picture directory to form a comparison database;
s7, monitoring the highway environment in real time through a camera, setting a comparison period, and comparing and analyzing the video state and a comparison database;
s8, outputting a comparison result after the weather type accords with one category;
and S9, detecting the temperature and humidity of the monitoring position, judging by matching the output result, determining the identified severe weather type, and performing early warning prompt.
2. The artificial intelligence based highway severe weather identification method according to claim 1, wherein: the video data in S1 includes a highway pavement video and a surrounding environment video, and is a synchronous shooting file.
3. The artificial intelligence based highway severe weather identification method according to claim 1, wherein: the manner of forming the extracted pictures in S3 is to play the video file according to frames, check each frame of picture, and extract and separate.
4. The artificial intelligence based highway severe weather identification method according to claim 1, wherein: and the analysis model of the S4 is a picture layer three-dimensional framework model, and is used for analyzing the key point layer of the picture.
5. The artificial intelligence based highway severe weather identification method according to claim 1, wherein: the method for forming the key pixel point in the step S5 includes the following steps:
a1, separating image layers of the pictures to form a background layer, a highway layer and a key point layer;
a2, comparing the background layers, directly and completely discarding the road sections which do not conform to the identification, and continuing to process if the road sections conform to the identification;
a3, separating the expressway layer and the key point layer, separately comparing and analyzing the road surface state, and extracting obvious change characteristics to form characteristic points;
and A4, reserving the characteristic points, forming a new layer, and obtaining key pixel points.
6. The artificial intelligence based highway severe weather identification method according to claim 1, wherein: the step S6, forming a contrast database, includes camera automatic shooting data, manhole input data, automatic recognition result data and manual input result data.
7. The artificial intelligence based highway severe weather identification method according to claim 1, wherein: and in the step S7, setting a contrast period as a set time period, intercepting one frame of image every 10 seconds for contrast, continuously operating for 6 times to form a contrast period, then beginning interception again at an interval of 600 seconds, and sequentially and circularly performing.
8. The artificial intelligence based highway severe weather identification method according to claim 1, wherein: the comparative analysis method in S7 includes the steps of:
b1, extracting the key pixel points and associating the key pixel points with the stored data in the database;
b2, caching the associated storage data and the key pixel points to a comparison position separately to form a comparison file;
b3, analyzing a comparison file, comparing the states of the expressway layers, analyzing the reflection intensity of the pavement, judging the expressway layers to be in a sunny day and a cloudy day if the expressway layers are in normal reflection, judging the expressway layers to be in a foggy day if the expressway layers are in weak reflection, and judging the expressway layers to be in a rainy day and a snowy day if the expressway layers are in strong reflection;
and B4, performing correlation comparison with the database according to the judgment result, outputting a final result and judging the type of the severe weather.
9. The artificial intelligence based highway severe weather identification method according to claim 1, wherein: the output comparison result in S8 includes a weather category, a weather intensity, a local range, and a time node.
10. The artificial intelligence based highway severe weather identification method according to claim 1, wherein: and judging the matching result in the S9 in a mode of mutually verifying the temperature, humidity and weather structures, judging to be misjudged if the matching result obviously does not accord with the natural rule, and returning to the S7 for contrastive analysis again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111673044.7A CN114299726B (en) | 2021-12-31 | 2021-12-31 | Expressway bad weather identification method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111673044.7A CN114299726B (en) | 2021-12-31 | 2021-12-31 | Expressway bad weather identification method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114299726A true CN114299726A (en) | 2022-04-08 |
| CN114299726B CN114299726B (en) | 2024-07-19 |
Family
ID=80974650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111673044.7A Active CN114299726B (en) | 2021-12-31 | 2021-12-31 | Expressway bad weather identification method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299726B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115310519A (en) * | 2022-07-11 | 2022-11-08 | 广州国交润万交通信息有限公司 | Method for weather discrimination by combining video and audio |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002162343A (en) * | 2000-11-24 | 2002-06-07 | Natl Inst For Land & Infrastructure Management Mlit | Judgement method of road surface condition by visual picture type road surface condition finding equipment |
| CN103034862A (en) * | 2012-12-14 | 2013-04-10 | 北京诚达交通科技有限公司 | Road snow and rain state automatic identification method based on feature information classification |
| CN104463196A (en) * | 2014-11-11 | 2015-03-25 | 中国人民解放军理工大学 | Video-based weather phenomenon recognition method |
| CN110866593A (en) * | 2019-11-05 | 2020-03-06 | 西南交通大学 | Highway severe weather identification method based on artificial intelligence |
| CN111340151A (en) * | 2020-05-25 | 2020-06-26 | 南京信息工程大学 | Weather phenomenon recognition system and method for assisting automatic driving of vehicle |
| CN111753610A (en) * | 2019-08-13 | 2020-10-09 | 上海高德威智能交通系统有限公司 | Weather identification method and device |
| CN113392818A (en) * | 2021-08-17 | 2021-09-14 | 江苏省气象服务中心 | Expressway severe weather identification method based on multi-scale fusion network |
| CN113850123A (en) * | 2021-08-18 | 2021-12-28 | 广州国交润万交通信息有限公司 | Video-based road monitoring method and device, storage medium and monitoring system |
-
2021
- 2021-12-31 CN CN202111673044.7A patent/CN114299726B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002162343A (en) * | 2000-11-24 | 2002-06-07 | Natl Inst For Land & Infrastructure Management Mlit | Judgement method of road surface condition by visual picture type road surface condition finding equipment |
| CN103034862A (en) * | 2012-12-14 | 2013-04-10 | 北京诚达交通科技有限公司 | Road snow and rain state automatic identification method based on feature information classification |
| CN104463196A (en) * | 2014-11-11 | 2015-03-25 | 中国人民解放军理工大学 | Video-based weather phenomenon recognition method |
| CN111753610A (en) * | 2019-08-13 | 2020-10-09 | 上海高德威智能交通系统有限公司 | Weather identification method and device |
| CN110866593A (en) * | 2019-11-05 | 2020-03-06 | 西南交通大学 | Highway severe weather identification method based on artificial intelligence |
| CN111340151A (en) * | 2020-05-25 | 2020-06-26 | 南京信息工程大学 | Weather phenomenon recognition system and method for assisting automatic driving of vehicle |
| CN113392818A (en) * | 2021-08-17 | 2021-09-14 | 江苏省气象服务中心 | Expressway severe weather identification method based on multi-scale fusion network |
| CN113850123A (en) * | 2021-08-18 | 2021-12-28 | 广州国交润万交通信息有限公司 | Video-based road monitoring method and device, storage medium and monitoring system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115310519A (en) * | 2022-07-11 | 2022-11-08 | 广州国交润万交通信息有限公司 | Method for weather discrimination by combining video and audio |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114299726B (en) | 2024-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109977812B (en) | Vehicle-mounted video target detection method based on deep learning | |
| CN111767927A (en) | Lightweight license plate recognition method and system based on full convolution network | |
| CN105321350B (en) | Fake-licensed car detection method and device | |
| CN110415233A (en) | Pavement crack rapid extracting method based on two step convolutional neural networks | |
| KR102035592B1 (en) | A supporting system and method that assist partial inspections of suspicious objects in cctv video streams by using multi-level object recognition technology to reduce workload of human-eye based inspectors | |
| CN107330373A (en) | A kind of parking offense monitoring system based on video | |
| CN111340151B (en) | Weather phenomenon recognition system and method for assisting automatic driving of vehicle | |
| CN111832398B (en) | Unmanned aerial vehicle image distribution line pole tower ground wire broken strand image detection method | |
| CN114937033A (en) | Rural highway pavement disease intelligent detection method based on deep convolutional neural network | |
| CN107688830B (en) | Generation method of vision information correlation layer for case serial-parallel | |
| CN111723656B (en) | Smog detection method and device based on YOLO v3 and self-optimization | |
| CN111583180B (en) | Image tampering identification method and device, computer equipment and storage medium | |
| CN113780132A (en) | Lane line detection method based on convolutional neural network | |
| CN111008608B (en) | Night vehicle detection method based on deep learning | |
| CN114972177A (en) | Road disease identification management method and device and intelligent terminal | |
| CN114299726B (en) | Expressway bad weather identification method based on artificial intelligence | |
| CN113158969A (en) | Apple appearance defect identification system and method | |
| CN114359196A (en) | Fog detection method and system | |
| CN116363567B (en) | Wafer defect identification method and system based on AOI visual inspection | |
| CN113221823A (en) | Traffic signal lamp countdown identification method based on improved lightweight YOLOv3 | |
| CN116563543A (en) | All-weather river scene panorama segmentation method and model building method | |
| CN112686105B (en) | Fog concentration grade identification method based on video image multi-feature fusion | |
| CN111339834A (en) | Method for recognizing vehicle traveling direction, computer device, and storage medium | |
| CN116129327A (en) | Infrared vehicle detection method based on improved YOLOv7 algorithm | |
| CN114821370A (en) | Single-tree crown detection and segmentation method based on unmanned aerial vehicle image and U-Net |
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 |