CN117953693A - Expressway traffic intelligent monitoring system based on video ai - Google Patents
Expressway traffic intelligent monitoring system based on video ai Download PDFInfo
- Publication number
- CN117953693A CN117953693A CN202410354154.4A CN202410354154A CN117953693A CN 117953693 A CN117953693 A CN 117953693A CN 202410354154 A CN202410354154 A CN 202410354154A CN 117953693 A CN117953693 A CN 117953693A
- Authority
- CN
- China
- Prior art keywords
- value
- vehicle
- road section
- traffic
- target monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 264
- 238000004458 analytical method Methods 0.000 claims abstract description 71
- 238000011156 evaluation Methods 0.000 claims abstract description 47
- 230000002159 abnormal effect Effects 0.000 claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 7
- 238000013178 mathematical model Methods 0.000 claims description 3
- 230000003449 preventive effect Effects 0.000 claims description 2
- 230000002265 prevention Effects 0.000 abstract description 5
- 230000005856 abnormality Effects 0.000 description 12
- 101100518501 Mus musculus Spp1 gene Proteins 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000007123 defense Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000009863 secondary prevention Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 238000009736 wetting Methods 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of expressway traffic intelligent monitoring, in particular to an expressway traffic intelligent monitoring system based on a video ai, which comprises a monitoring point distribution module, a traffic monitoring primary analysis module, a traffic monitoring deep analysis module, a traffic prediction module, an execution processing module and a display terminal; the traffic image of the target monitoring road section is obtained by arranging monitoring points, the abnormal traffic state is identified by utilizing the primary analysis module, after the abnormal state is judged, the traffic jam influence information is further analyzed by the deep analysis module to obtain road conditions, vehicle driving and road surface evaluation values, the traffic prediction module analyzes traffic jam trends based on the evaluation values and sends corresponding jam trend type signals to the execution processing module, and the execution processing module triggers a prevention instruction according to the signals to realize automatic processing and display notification, so that the intelligent and automatic level of traffic monitoring management is improved, and effective decision support is provided for management departments and travelers.
Description
Technical Field
The invention belongs to the technical field of expressway traffic intelligent monitoring, and particularly relates to an expressway traffic intelligent monitoring system based on a video ai.
Background
Along with the rapid development of society and the continuous acceleration of urban process, the traffic flow of expressways is continuously increased, the real-time monitoring and management of the traffic condition of the expressways are increasingly important, and whether the expressways are smooth or not is directly related to the economic development of cities and the daily travel of residents as important hubs of urban traffic;
However, although the existing highway monitoring systems have realized the whole-course video information transmission, so that traffic monitoring departments can acquire the traffic conditions of the highways in real time, the systems often only can provide basic video information, lack the capability of deep analysis and prediction of the video information, which means that when emergency conditions such as traffic flow dissimilarity, congestion and the like occur on the highways, the traffic monitoring departments often cannot quickly know the actual conditions and make effective emergency reactions, and often send relevant personnel to the scene for processing after the congestion or the accident has occurred, and the delayed reaction speed not only affects the traffic dispersion efficiency, but also can aggravate the congestion condition and even cause the traffic accident to occur;
in order to solve the above-mentioned defect, a technical scheme is provided.
Disclosure of Invention
The invention aims to solve the problem that the existing expressway monitoring system lacks the capability of depth analysis and prediction of video information, and provides an expressway traffic intelligent monitoring system based on video ai.
The aim of the invention can be achieved by the following technical scheme:
an intelligent monitoring system for highway traffic based on video ai, comprising:
The monitoring point defense distribution module is used for performing monitoring point defense distribution on the target monitoring road section so as to obtain a traffic image corresponding to the target monitoring road section;
The traffic monitoring primary analysis module is used for monitoring the vehicle state information corresponding to the target monitoring road section to obtain an abnormal value, so that the traffic state corresponding to the target monitoring road section is subjected to preliminary judgment and analysis, and if the traffic state corresponding to the target monitoring road section is judged to be the abnormal state, the traffic monitoring deep analysis module is executed;
The traffic monitoring depth analysis module is used for judging the traffic state corresponding to the target monitoring road section to be an abnormal state, so that traffic congestion influence information corresponding to the target monitoring road section is analyzed and processed to obtain a road condition evaluation value, a vehicle running evaluation value and a road surface evaluation value corresponding to the target monitoring road section, wherein the traffic monitoring depth analysis module comprises a first monitoring analysis unit, a second monitoring analysis unit and a third monitoring analysis unit;
The first monitoring analysis unit is used for monitoring and analyzing the road condition state corresponding to the target monitoring road section, so as to obtain a road condition evaluation value corresponding to the target monitoring road section;
The second monitoring analysis unit is used for monitoring and analyzing the vehicle running state corresponding to the target monitoring road section, so as to obtain a vehicle running evaluation value corresponding to the target monitoring road section;
the third monitoring and analyzing unit is used for monitoring and analyzing the road surface state corresponding to the target monitoring road section, so as to obtain a road surface evaluation value corresponding to the target monitoring road section;
The traffic prediction module is used for receiving the road condition evaluation value, the vehicle running evaluation value and the road surface evaluation value corresponding to the target monitoring road section, analyzing the traffic congestion trend state corresponding to the target monitoring road section, obtaining a congestion trend type signal according to the traffic congestion trend state, and sending the congestion trend type signal to the execution processing module, wherein the congestion trend type signal comprises a heavy congestion trend signal, a medium congestion trend signal and a light congestion trend signal;
and the execution processing module is used for receiving the congestion tendency type signal, triggering a corresponding preventive execution instruction, carrying out corresponding operation processing and carrying out display notification on the display terminal.
Further, the monitoring point distribution is carried out on the target monitoring road section, and the specific analysis process is as follows:
Dividing the target monitoring road section according to a preset area, wherein the specific dividing mode is as follows: acquiring the length and the width of a target monitoring road section, dividing the target monitoring road section into a plurality of equal-area sub-areas according to a preset area, obtaining the sub-areas of the target monitoring road section, and arranging intelligent cameras in the sub-areas of the target monitoring road section;
The traffic videos corresponding to the target monitoring road sections in a period of time are acquired through the intelligent cameras, the traffic videos corresponding to the target monitoring road sections in a period of time are obtained, the traffic videos corresponding to the target monitoring road sections in a period of time are analyzed, and the traffic images of all monitoring time points corresponding to the target monitoring road sections in a period of time are obtained.
Further, the traffic state corresponding to the target monitoring road section is subjected to preliminary judgment and analysis, and the specific analysis process is as follows:
Extracting the number of vehicles from the traffic images of each monitoring time point corresponding to the target monitoring road section within a period of time, marking the number as a vehicle numerical value Tc h, wherein h represents each monitoring time point within a period of time, h=1, 2,3 … … n1, n1 is the total number of each monitoring time point within a period of time, and the value is a positive integer; and average analysis is carried out on the vehicle values at each monitoring time point, and the obtained vehicle number average value is recorded as And carrying out difference analysis on the vehicle numerical value and the vehicle numerical average value according to the formula: obtain the vehicle number difference value/> Wherein/>Comparing and analyzing the vehicle number difference value with a preset vehicle number difference threshold value, marking the monitoring time point as an abnormal point if the vehicle number difference value is larger than or equal to the preset vehicle number difference threshold value, marking the monitoring time point as an abnormal point if the vehicle number difference value is smaller than the preset vehicle number difference threshold value, counting the number of abnormal points in a period of time to obtain the number of abnormal points in a period of time, marking the abnormal point as an abnormal value, simultaneously comparing and analyzing the abnormal value with the preset abnormal threshold value, and judging the traffic state corresponding to the target monitoring road section as an abnormal state if the abnormal value is larger than or equal to the preset abnormal threshold value.
Further, the road condition state corresponding to the target monitoring road section is monitored and analyzed, and the specific analysis process is as follows:
Obtaining position data of each vehicle corresponding to the target monitoring road section in a period of time by obtaining the position data of each vehicle corresponding to the target monitoring road section in a period of time, wherein the position data comprises the distance between each vehicle and each surrounding vehicle, thereby obtaining a matrix formed by the position data Represents the distance between the vehicle numbered p and the surrounding vehicles numbered q, where p=1, 2,3 … … m1, m1 represents the total number of respective vehicle numbers and q=1, 2,3 … … m2, m2 represents the total number of respective vehicles corresponding to each surrounding vehicle number, according to the matrix: /(I)And extracting a distance sequence between each vehicle and each vehicle around the corresponding vehicle, and substituting the distance sequence into a matrix formula: Obtaining a matrix/>, which is formed by the vehicles and the vehicle distance safety parameter values corresponding to each surrounding vehicle And substitutes it into a preset mathematical model: /(I)Obtaining a vehicle spacing value/>, corresponding to the target monitoring road sectionWherein/>、/>、Respectively corresponding vehicle distance safety parameter values, vehicle distance safety threshold values and early warning weight factors of all vehicles;
The number of plugging times corresponding to the target monitoring road section in a period of time and the number of vehicles traveling the emergency lane are obtained, and are respectively calibrated to be plugging values Sum of deviation values/>；
Extracting the row spacing value of the vehiclePlug value/>Sum of deviation values/>The values of (2) are normalized according to the formula: /(I)And obtaining a road condition evaluation value corresponding to the target monitoring road section, wherein beta 1, beta 2 and beta 3 respectively represent weight coefficients of the vehicle road distance value, the stopover value and the deviation value.
Further, the vehicle running state corresponding to the target monitoring road section is monitored and analyzed, and the specific analysis process is as follows:
The running speeds of all vehicles corresponding to the target monitoring road sections in a period of time are obtained by obtaining the running speeds of all vehicles corresponding to the target monitoring road sections in a period of time, and the numerical values of the highest running speed and the lowest running speed are extracted from the running speeds to calculate the difference value to obtain the running speed difference value, and the running speed difference value is marked as Meanwhile, the preset reference running speed difference value corresponding to the target monitoring road section in a period of time is obtained, and the preset reference running speed difference value corresponding to the target monitoring road section in a period of time is obtained and marked as/>According to the formula: /(I)To obtain the running speed change value/>Wherein [ mu ] represents the set correction coefficient;
Obtaining the total overtaking times of each vehicle corresponding to the target monitoring road section in a period of time by obtaining the total overtaking times of each vehicle corresponding to the target monitoring road section in a period of time, extracting the successful overtaking times from the total overtaking times, performing duty ratio calculation on the successful overtaking times and the total overtaking times, obtaining a lane change stable value and recording the lane change stable value as ；
Obtaining the time length and the mileage of each vehicle driver corresponding to the target monitoring road section in a period of time from the start of learning to drive to the current monitoring time point by obtaining the time length and the mileage of each vehicle driver corresponding to the target monitoring road section in a period of time from the start of learning to drive to the current monitoring time point, marking the time length and the mileage as a driving value and a driving value respectively, extracting the values of the driving value and the driving value, multiplying the values by corresponding weight coefficients respectively, adding the values to obtain a driving age value, and recording the driving age value as the driving age value；
Extracting running speed change valueLane change plateau value/>And driving age value/>The values of (2) are normalized according to the formula: /(I)And obtaining a vehicle running evaluation value T2 corresponding to the target monitoring road section, wherein e represents a natural constant, eta 1, eta 2 and eta 3 respectively represent a running speed variable value, a lane change stable value and a weight coefficient of a driving age value, and eta 1 is more than eta 2 and more than eta 3.
Further, the road surface state corresponding to the target monitoring road section is monitored and analyzed, and the specific analysis process is as follows:
The slip value, the humidity value and the damage value in the road surface state information corresponding to the target monitoring road section in a period of time are obtained by obtaining the slip value, the humidity value and the damage value in the road surface state information corresponding to the target monitoring road section in a period of time, the slip value, the humidity value and the damage value are respectively marked as phz, sdd and atz, and meanwhile, the numerical values of the three are extracted for normalization processing, and the method is based on the formula: obtaining a pavement evaluation value T3 corresponding to the target monitoring road section, wherein/> And/>Respectively representing a reference slip value, a reference humidity value and a reference breakage value,And/>The slip abnormality difference value, the humidity abnormality difference value, and the breakage abnormality difference value are respectively represented, and γ1, γ2, and γ3 are respectively represented as weighting coefficients of the slip abnormality degree, the humidity abnormality degree, and the breakage abnormality degree, and γ1 > γ2 > γ3.
Further, the traffic congestion trend state corresponding to the target monitoring road section is analyzed, and the specific analysis process is as follows:
extracting the values of the road condition evaluation value T1, the vehicle running evaluation value T2 and the road surface evaluation value T3 corresponding to the target monitoring road section, and carrying out normalization processing according to the formula: obtaining a traffic congestion influence coefficient JTY, wherein δ1, δ2 and δ3 are respectively represented as set weight factors;
Setting three congestion influence gradient comparison intervals of a traffic congestion influence coefficient, namely a first gradient congestion influence interval tdsh, a second gradient congestion influence interval tdsh and a third gradient congestion influence interval tdsh3 respectively, wherein tdsh1 = Atdsh 2=2 Atdsh3, tdsh1 > tdsh2 > tdsh3, A represents a multiple of the gradient, and setting of specific numerical values of A is specifically set in specific highway traffic examples by a person skilled in the art;
When the traffic congestion influence coefficient is in a preset first gradient congestion influence interval tdsh, a heavy congestion tendency signal is generated, when the traffic congestion influence coefficient is in a preset second gradient congestion influence interval tdsh, a medium congestion tendency signal is generated, and when the traffic congestion influence coefficient is in a preset third gradient congestion influence interval tdsh, a light congestion tendency signal is generated.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the target monitoring road section is laid by the monitoring points, so that the target monitoring road section can be covered on the whole, the acquisition quality and the real-time performance of traffic images are ensured, and powerful data support is provided for subsequent analysis;
According to the invention, the abnormal traffic condition can be primarily identified by monitoring and analyzing the vehicle state information corresponding to the target monitoring road section, so that the traffic state can be more accurately judged, and an important basis is provided for subsequent deep analysis;
According to the traffic condition analysis method and the traffic condition analysis system, when the traffic condition of the target monitoring road section is judged to be abnormal, the traffic congestion influence information corresponding to the target monitoring road section is obtained, the road condition evaluation value corresponding to the target monitoring road section is analyzed, meanwhile, the vehicle running evaluation value corresponding to the target monitoring road section is analyzed, the road surface evaluation value corresponding to the target monitoring road section is analyzed, and further the traffic congestion influence coefficient is comprehensively analyzed, so that the congestion degree is quantized, a traffic management department and a traveler can know the severity degree of congestion more accurately, corresponding decisions and adjustments are made, and the situation that the traffic management department adopts blind or invalid countermeasures to cause resource waste and congestion is aggravated is avoided.
Drawings
For the convenience of those skilled in the art, the present invention will be further described with reference to the accompanying drawings;
Fig. 1 is a general block diagram of the system of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, an intelligent monitoring system for highway traffic based on video ai comprises: the system comprises a monitoring point distribution module, a traffic monitoring primary analysis module, a traffic monitoring deep analysis module, a traffic prediction module, an execution processing module and a display terminal;
the monitoring point distribution module is used for carrying out monitoring point distribution on the target monitoring road section, and the specific analysis process is as follows:
Dividing the target monitoring road section according to a preset area, wherein the specific dividing mode is as follows: acquiring the length and the width of a target monitoring road section, dividing the target monitoring road section into a plurality of equal-area sub-areas according to a preset area, obtaining the sub-areas of the target monitoring road section, and arranging intelligent cameras in the sub-areas of the target monitoring road section;
Acquiring traffic videos corresponding to the target monitoring road sections in a period of time through an intelligent camera to obtain traffic videos corresponding to the target monitoring road sections in a period of time, and analyzing the traffic videos corresponding to the target monitoring road sections in a period of time to obtain traffic images of all monitoring time points corresponding to the target monitoring road sections in a period of time;
The traffic monitoring primary analysis module is used for monitoring the vehicle state information corresponding to the target monitoring road section, so that the traffic state corresponding to the target monitoring road section is subjected to primary judgment and analysis, and the specific analysis process is as follows:
Extracting the number of vehicles from the traffic images of each monitoring time point corresponding to the target monitoring road section within a period of time, marking the number as a vehicle numerical value Tc h, wherein h represents each monitoring time point within a period of time, h=1, 2,3 … … n1, n1 is the total number of each monitoring time point within a period of time, and the value is a positive integer; and average analysis is carried out on the vehicle values at each monitoring time point, and the obtained vehicle number average value is recorded as And carrying out difference analysis on the vehicle numerical value and the vehicle numerical average value according to the formula: obtain the vehicle number difference value/> Wherein/>Comparing and analyzing the vehicle number difference value with a preset vehicle number difference threshold value, if the vehicle number difference value is larger than or equal to the preset vehicle number difference threshold value, marking the monitoring time point as an abnormal point, if the vehicle number difference value is smaller than the preset vehicle number difference threshold value, marking the monitoring time point as an abnormal point, counting the number of abnormal points in a period of time to obtain the number of abnormal points in a period of time and marking the abnormal point as an abnormal value, simultaneously comparing and analyzing the abnormal value with the preset abnormal threshold value, if the abnormal value is larger than or equal to the preset abnormal threshold value, judging the traffic state corresponding to the target monitoring road section as an abnormal state, and executing a traffic monitoring deep analysis module, otherwise, judging the traffic state corresponding to the target monitoring road section as a normal state;
The traffic monitoring deep analysis module is used for judging the traffic state corresponding to the target monitoring road section to be an abnormal state, so that traffic congestion influence information corresponding to the target monitoring road section is analyzed and processed, wherein the traffic monitoring deep analysis module comprises a first monitoring analysis unit, a second monitoring analysis unit and a third monitoring analysis unit, and the specific analysis process is as follows:
The first monitoring and analyzing unit is used for monitoring and analyzing the road condition state corresponding to the target monitoring road section, and the specific analyzing process is as follows:
Obtaining position data of each vehicle corresponding to the target monitoring road section in a period of time by obtaining the position data of each vehicle corresponding to the target monitoring road section in a period of time, wherein the position data comprises the distance between each vehicle and each surrounding vehicle, thereby obtaining a matrix formed by the position data Represents the distance between the vehicle numbered p and the surrounding vehicles numbered q, where p=1, 2,3 … … m1, m1 represents the total number of respective vehicle numbers and q=1, 2,3 … … m2, m2 represents the total number of respective vehicles corresponding to each surrounding vehicle number, according to the matrix: /(I)And extracting a distance sequence between each vehicle and each vehicle around the corresponding vehicle, and substituting the distance sequence into a matrix formula: Obtaining a matrix/>, which is formed by the vehicles and the vehicle distance safety parameter values corresponding to each surrounding vehicle And substitutes it into a preset mathematical model: obtaining a vehicle spacing value/>, corresponding to the target monitoring road section Wherein/>、/>、/>Respectively corresponding vehicle distance safety parameter values, vehicle distance safety threshold values and early warning weight factors of all vehicles;
The number of plugging times corresponding to the target monitoring road section in a period of time and the number of vehicles traveling the emergency lane are obtained, and are respectively calibrated to be plugging values Sum of deviation values/>；
Extracting the row spacing value of the vehiclePlug value/>Sum of deviation values/>The values of (2) are normalized according to the formula: /(I)Obtaining a road condition evaluation value T1 corresponding to a target monitoring road section, wherein beta 1, beta 2 and beta 3 respectively represent weight coefficients of a vehicle road distance value, a stopover value and a deviation value, and beta 1 is more than beta 2 and more than beta 3, and the weight coefficients are used for balancing the duty ratio weight of each item of data in formula calculation, so that the accuracy of a calculation result is promoted;
The second monitoring and analyzing unit is used for monitoring and analyzing the running state of the vehicle corresponding to the target monitoring road section, and the specific analysis process is as follows:
The running speeds of all vehicles corresponding to the target monitoring road sections in a period of time are obtained by obtaining the running speeds of all vehicles corresponding to the target monitoring road sections in a period of time, and the numerical values of the highest running speed and the lowest running speed are extracted from the running speeds to calculate the difference value to obtain the running speed difference value, and the running speed difference value is marked as Meanwhile, the preset reference running speed difference value corresponding to the target monitoring road section in a period of time is obtained, and the preset reference running speed difference value corresponding to the target monitoring road section in a period of time is obtained and marked as/>According to the formula: /(I)Obtaining the running speed variation valueWherein [ mu ] represents the set correction coefficient;
Obtaining the total overtaking times of each vehicle corresponding to the target monitoring road section in a period of time by obtaining the total overtaking times of each vehicle corresponding to the target monitoring road section in a period of time, extracting the successful overtaking times from the total overtaking times, performing duty ratio calculation on the successful overtaking times and the total overtaking times, obtaining a lane change stable value and recording the lane change stable value as ；
Obtaining the time length and the mileage of each vehicle driver corresponding to the target monitoring road section in a period of time from the start of learning to drive to the current monitoring time point by obtaining the time length and the mileage of each vehicle driver corresponding to the target monitoring road section in a period of time from the start of learning to drive to the current monitoring time point, marking the time length and the mileage as a driving value and a driving value respectively, extracting the values of the driving value and the driving value, multiplying the values by corresponding weight coefficients respectively, adding the values to obtain a driving age value, and recording the driving age value as the driving age value；
Extracting running speed change valueLane change plateau value/>And driving age value/>The values are normalized according to the formula: /(I)Obtaining a vehicle running evaluation value T2 corresponding to a target monitoring road section, wherein e represents a natural constant, eta 1, eta 2 and eta 3 represent weight coefficients of a running speed change value, a lane change stability value and a driving age value respectively, eta 1 is more than eta 2 and eta 3, and the weight coefficients are used for balancing the duty ratio weight of each item of data in formula calculation so as to promote the accuracy of a calculation result;
The third monitoring and analyzing unit is used for monitoring and analyzing the road surface state corresponding to the target monitoring road section, and the specific analysis process is as follows:
The slip value, the humidity value and the damage value in the road surface state information corresponding to the target monitoring road section in a period of time are obtained by obtaining the slip value, the humidity value and the damage value in the road surface state information corresponding to the target monitoring road section in a period of time, the slip value, the humidity value and the damage value are respectively marked as phz, sdd and atz, and meanwhile, the numerical values of the three are extracted for normalization processing, and the method is based on the formula: obtaining a pavement evaluation value T3 corresponding to the target monitoring road section, wherein/> And/>Respectively representing a reference slip value, a reference humidity value and a reference breakage value,And/>The sliding abnormality difference value, the humidity abnormality difference value and the breakage abnormality difference value are respectively represented, and gamma 1, gamma 2 and gamma 3 are respectively represented as weight coefficients of the sliding abnormality degree, the humidity abnormality degree and the breakage abnormality degree, wherein gamma 1 is more than gamma 2 and more than gamma 3, and the weight coefficients are used for balancing the duty ratio weights of various data in formula calculation, so that the accuracy of calculation results is promoted;
The slip value refers to the snow depth of the road surface, the humidity value refers to the wetting degree of the road surface, the humidity value can be obtained by direct measurement of a humidity sensor, and the breakage value refers to the breakage area of the road surface;
transmitting the generated road condition evaluation value T1, the vehicle running evaluation value T2 and the road surface evaluation value T3 corresponding to the target monitoring road section to a traffic prediction module;
the traffic prediction module is used for receiving the road condition evaluation value T1, the vehicle running evaluation value T2 and the road surface evaluation value T3 corresponding to the target monitoring road section, so as to analyze the traffic jam trend state corresponding to the target monitoring road section, and the specific analysis process is as follows:
extracting the values of the road condition evaluation value T1, the vehicle running evaluation value T2 and the road surface evaluation value T3 corresponding to the target monitoring road section, and carrying out normalization processing according to the formula: obtaining a traffic congestion influence coefficient JTY, wherein δ1, δ2 and δ3 are respectively represented as set weight factors;
Setting three congestion influence gradient comparison intervals of a traffic congestion influence coefficient, namely a first gradient congestion influence interval tdsh, a second gradient congestion influence interval tdsh and a third gradient congestion influence interval tdsh3 respectively, wherein tdsh1 = Atdsh 2=2 Atdsh3, tdsh1 > tdsh2 > tdsh3, A represents a multiple of the gradient, and setting of specific numerical values of A is specifically set in specific highway traffic examples by a person skilled in the art;
When the traffic congestion influence coefficient is in a preset first gradient congestion influence interval tdsh, a heavy congestion tendency signal is generated, when the traffic congestion influence coefficient is in a preset second gradient congestion influence interval tdsh, a medium congestion tendency signal is generated, and when the traffic congestion influence coefficient is in a preset third gradient congestion influence interval tdsh, a light congestion tendency signal is generated;
Transmitting the generated congestion tendency type signal to an execution processing module, wherein the congestion tendency type signal comprises a heavy congestion tendency signal, a medium congestion tendency signal and a light congestion tendency signal;
The execution processing module is used for receiving the congestion tendency type signal, and executing operation processing on the target monitoring road section, wherein the specific processing procedure is as follows:
If the light congestion tendency signal is captured, triggering a first-stage prevention execution instruction, and providing voice broadcasting for a running vehicle corresponding to the target monitoring road section according to the triggered first-stage prevention execution instruction to remind the driver of running safety;
If the medium congestion tendency signal is captured, triggering a secondary prevention execution instruction, and carrying out selection analysis on a target closing inlet corresponding to a target monitoring road section according to the triggered secondary prevention execution instruction, wherein the specific analysis is as follows: obtaining entrance influence information corresponding to a target monitoring road section by obtaining the entrance influence information corresponding to the target monitoring road section, wherein the entrance influence information comprises a vehicle flow and a vehicle duty ratio, extracting numerical values of the vehicle flow and the vehicle duty ratio from the vehicle flow and the vehicle duty ratio, multiplying the numerical values by corresponding proportional coefficients respectively, adding the numerical values to obtain an entrance influence value, comparing and analyzing the entrance influence value with a preset entrance influence threshold, judging the entrance as a target closed entrance when the entrance influence value is larger than or equal to the preset entrance influence threshold, and displaying a notice on a display terminal;
If the heavy congestion tendency signal is captured, triggering a three-level prevention execution instruction, and performing scheduling analysis on a target traffic police corresponding to a target monitoring road section according to the triggered three-level prevention execution instruction, wherein the specific analysis is as follows: the method comprises the steps of obtaining position coordinates of each on-duty traffic police through positioning scanning of position information of the on-duty traffic police, obtaining distances between a target monitoring road section and each on-duty traffic police, marking the distances as distance values, comparing and analyzing the distance values with preset distance thresholds, and judging the on-duty traffic police with the distance values smaller than the preset distance thresholds as schedulable personnel; meanwhile, the traffic jam influence coefficient corresponding to the target monitoring road section is called, the traffic jam influence coefficient corresponding to the target monitoring road section is compared and analyzed with a preset reference section of the traffic jam influence coefficient, when the traffic jam influence coefficient corresponding to the target monitoring road section is within the reference section, the on-duty traffic police K1 is dispatched to the target monitoring road section to execute tasks, when the traffic jam influence coefficient corresponding to the target monitoring road section is beyond the reference section, the on-duty traffic police K2 is dispatched to the target monitoring road section to execute tasks, scheduling personnel are sequentially sent to scheduling signals according to the distance value from small to large, and display notification is carried out on a display terminal.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (5)
1. An intelligent monitoring system for highway traffic based on video ai, which is characterized by comprising:
The monitoring point distribution module is used for carrying out monitoring point distribution on the target monitoring road section, and the specific analysis process is as follows:
Dividing the target monitoring road section according to a preset area, wherein the specific dividing mode is as follows: acquiring the length and the width of a target monitoring road section, dividing the target monitoring road section into a plurality of equal-area sub-areas according to a preset area, obtaining the sub-areas of the target monitoring road section, and arranging intelligent cameras in the sub-areas of the target monitoring road section;
Acquiring traffic videos corresponding to the target monitoring road sections in a period of time through an intelligent camera to obtain traffic videos corresponding to the target monitoring road sections in a period of time, and analyzing the traffic videos corresponding to the target monitoring road sections in a period of time to obtain traffic images of all monitoring time points corresponding to the target monitoring road sections in a period of time;
The traffic monitoring primary analysis module is used for monitoring the vehicle state information corresponding to the target monitoring road section, so that the traffic state corresponding to the target monitoring road section is primarily judged and analyzed, and the specific analysis process is as follows:
Extracting the number of vehicles from the traffic images of each monitoring time point corresponding to the target monitoring road section within a period of time, marking the number as a vehicle numerical value Tc h, wherein h represents each monitoring time point within a period of time, h=1, 2,3 … … n1, n1 is the total number of each monitoring time point within a period of time, and the value is a positive integer; and average analysis is carried out on the vehicle values at each monitoring time point, and the obtained vehicle number average value is recorded as And carrying out difference analysis on the vehicle numerical value and the vehicle numerical average value according to the formula: obtain the vehicle number difference value/> Wherein/>Comparing and analyzing the vehicle number difference value with a preset vehicle number difference threshold value, marking the monitoring time point as an abnormal point if the vehicle number difference value is larger than or equal to the preset vehicle number difference threshold value, marking the monitoring time point as an abnormal point if the vehicle number difference value is smaller than the preset vehicle number difference threshold value, counting the number of abnormal points in a period of time to obtain the number of abnormal points in a period of time and marking the abnormal point as an abnormal value, simultaneously comparing and analyzing the abnormal value with the preset abnormal threshold value, judging the traffic state corresponding to the target monitoring road section as an abnormal state if the abnormal value is larger than or equal to the preset abnormal threshold value, and executing a traffic monitoring deep analysis module;
The traffic monitoring depth analysis module is used for judging the traffic state corresponding to the target monitoring road section to be an abnormal state, so that traffic congestion influence information corresponding to the target monitoring road section is analyzed and processed to obtain a road condition evaluation value, a vehicle running evaluation value and a road surface evaluation value corresponding to the target monitoring road section, wherein the traffic monitoring depth analysis module comprises a first monitoring analysis unit, a second monitoring analysis unit and a third monitoring analysis unit;
The first monitoring analysis unit is used for monitoring and analyzing the road condition state corresponding to the target monitoring road section, so as to obtain a road condition evaluation value corresponding to the target monitoring road section;
The second monitoring analysis unit is used for monitoring and analyzing the vehicle running state corresponding to the target monitoring road section, so as to obtain a vehicle running evaluation value corresponding to the target monitoring road section;
the third monitoring and analyzing unit is used for monitoring and analyzing the road surface state corresponding to the target monitoring road section, so as to obtain a road surface evaluation value corresponding to the target monitoring road section;
The traffic prediction module is used for receiving the road condition evaluation value, the vehicle running evaluation value and the road surface evaluation value corresponding to the target monitoring road section, analyzing the traffic congestion trend state corresponding to the target monitoring road section, obtaining a congestion trend type signal according to the traffic congestion trend state, and sending the congestion trend type signal to the execution processing module, wherein the congestion trend type signal comprises a heavy congestion trend signal, a medium congestion trend signal and a light congestion trend signal;
and the execution processing module is used for receiving the congestion tendency type signal, triggering a corresponding preventive execution instruction, carrying out corresponding operation processing and carrying out display notification on the display terminal.
2. The intelligent monitoring system for highway traffic based on video ai according to claim 1, wherein the road condition state corresponding to the target monitoring road section is monitored and analyzed, and the specific analysis process is as follows:
Obtaining position data of each vehicle corresponding to the target monitoring road section in a period of time by obtaining the position data of each vehicle corresponding to the target monitoring road section in a period of time, wherein the position data comprises the distance between each vehicle and each surrounding vehicle, thereby obtaining a matrix formed by the position data Represents the distance between the vehicle numbered p and the surrounding vehicles numbered q, where p=1, 2,3 … … m1, m1 represents the total number of respective vehicle numbers and q=1, 2,3 … … m2, m2 represents the total number of respective vehicles corresponding to each surrounding vehicle number, according to the matrix: /(I)And extracting a distance sequence between each vehicle and each vehicle around the corresponding vehicle, and substituting the distance sequence into a matrix formula: Obtaining a matrix/>, which is formed by the vehicles and the vehicle distance safety parameter values corresponding to each surrounding vehicle And substitutes it into a preset mathematical model: /(I)Obtaining a vehicle spacing value/>, corresponding to the target monitoring road sectionWherein/>、/>、Respectively corresponding vehicle distance safety parameter values, vehicle distance safety threshold values and early warning weight factors of all vehicles;
The number of plugging times corresponding to the target monitoring road section in a period of time and the number of vehicles traveling the emergency lane are obtained, and are respectively calibrated to be plugging values Sum of deviation values/>；
Extracting the row spacing value of the vehiclePlug value/>Sum of deviation values/>The values of (2) are normalized according to the formula: And obtaining a road condition evaluation value corresponding to the target monitoring road section, wherein beta 1, beta 2 and beta 3 respectively represent weight coefficients of the vehicle road distance value, the stopover value and the deviation value.
3. The intelligent monitoring system for highway traffic based on video ai according to claim 1, wherein the monitoring analysis is performed on the running state of the vehicle corresponding to the target monitoring road section, and the specific analysis process is as follows:
Obtaining the running speed of each vehicle corresponding to the target monitoring road section in a period of time by obtaining the running speed of each vehicle corresponding to the target monitoring road section in a period of time, extracting the numerical value of the highest running speed and the lowest running speed from the running speed to obtain a running speed difference value by difference calculation, and obtaining the preset reference running speed difference value corresponding to the target monitoring road section in a period of time to obtain the preset reference running speed difference value corresponding to the target monitoring road section in a period of time and calculating according to a formula to obtain a running speed variation value;
Obtaining the total overtaking times of each vehicle corresponding to the target monitoring road section in a period of time by obtaining the total overtaking times of each vehicle corresponding to the target monitoring road section in a period of time, extracting the successful overtaking times from the total overtaking times, and carrying out duty ratio calculation on the successful overtaking times and the total overtaking times to obtain a lane change stability value;
Obtaining the time length and the mileage which are passed by each vehicle driver corresponding to the target monitoring road section in a period of time from the start of learning to the current monitoring time point by marking the time length and the mileage as a driving value and a driving value respectively, extracting the values of the driving value and the driving value, multiplying the values by corresponding weight coefficients respectively, and adding the values to obtain a driving age value;
And extracting the values of the running speed change value, the lane change stability value and the driving age value, and carrying out normalization calculation processing to obtain a vehicle running evaluation value corresponding to the target monitoring road section.
4. The intelligent monitoring system for highway traffic based on video ai according to claim 1, wherein the monitoring analysis is performed on the road surface state corresponding to the target monitoring road section, and the specific analysis process is as follows:
The method comprises the steps of obtaining the slip value, the humidity value and the damage value in the road surface state information corresponding to the target monitoring road section in a period of time, extracting the values of the slip value, the humidity value and the damage value, and carrying out normalization calculation processing to obtain the road surface evaluation value corresponding to the target monitoring road section.
5. The intelligent monitoring system for highway traffic based on video ai according to claim 1, wherein the analysis of traffic congestion tendency states corresponding to the target monitored road section is performed by the following specific analysis process:
extracting the values of the road condition evaluation value, the vehicle running evaluation value and the road surface evaluation value corresponding to the target monitoring road section, and carrying out normalization calculation processing to obtain a traffic jam influence coefficient;
Setting three congestion influence gradient comparison intervals of a traffic congestion influence coefficient, namely a first gradient congestion influence interval tdsh, a second gradient congestion influence interval tdsh and a third gradient congestion influence interval tdsh3 respectively, wherein tdsh1 = Atdsh 2=2 Atdsh3, tdsh1 > tdsh2 > tdsh3, A represents a multiple of the gradient, and setting of specific numerical values of A is specifically set in specific highway traffic examples by a person skilled in the art;
When the traffic congestion influence coefficient is in a preset first gradient congestion influence interval tdsh, a heavy congestion tendency signal is generated, when the traffic congestion influence coefficient is in a preset second gradient congestion influence interval tdsh, a medium congestion tendency signal is generated, and when the traffic congestion influence coefficient is in a preset third gradient congestion influence interval tdsh, a light congestion tendency signal is generated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410354154.4A CN117953693B (en) | 2024-03-27 | 2024-03-27 | Expressway traffic intelligent monitoring system based on video ai |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410354154.4A CN117953693B (en) | 2024-03-27 | 2024-03-27 | Expressway traffic intelligent monitoring system based on video ai |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117953693A true CN117953693A (en) | 2024-04-30 |
| CN117953693B CN117953693B (en) | 2024-07-09 |
Family
ID=90805203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410354154.4A Active CN117953693B (en) | 2024-03-27 | 2024-03-27 | Expressway traffic intelligent monitoring system based on video ai |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117953693B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118155153A (en) * | 2024-05-10 | 2024-06-07 | 深圳市海飞高科技术有限公司 | Image acquisition and recognition system based on CMOS double-plate module |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200226922A1 (en) * | 2019-01-15 | 2020-07-16 | Waycare Technologies Ltd. | System and method for detection and quantification of irregular traffic congestion |
| CN116564079A (en) * | 2023-04-23 | 2023-08-08 | 赵冰心 | Road section traffic jam identification method, device and equipment and readable storage medium |
| CN117315934A (en) * | 2023-09-25 | 2023-12-29 | 阜阳交通能源投资有限公司 | Expressway traffic flow real-time monitoring and congestion prediction system based on unmanned aerial vehicle |
| CN117392852A (en) * | 2023-12-11 | 2024-01-12 | 大作(江苏)云科技有限公司 | Cloud computing resource scheduling optimization system oriented to big data analysis |
| CN117746626A (en) * | 2023-12-18 | 2024-03-22 | 河南省智慧交通研究院有限公司 | Intelligent traffic management method and system based on traffic flow |
-
2024
- 2024-03-27 CN CN202410354154.4A patent/CN117953693B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200226922A1 (en) * | 2019-01-15 | 2020-07-16 | Waycare Technologies Ltd. | System and method for detection and quantification of irregular traffic congestion |
| CN116564079A (en) * | 2023-04-23 | 2023-08-08 | 赵冰心 | Road section traffic jam identification method, device and equipment and readable storage medium |
| CN117315934A (en) * | 2023-09-25 | 2023-12-29 | 阜阳交通能源投资有限公司 | Expressway traffic flow real-time monitoring and congestion prediction system based on unmanned aerial vehicle |
| CN117392852A (en) * | 2023-12-11 | 2024-01-12 | 大作(江苏)云科技有限公司 | Cloud computing resource scheduling optimization system oriented to big data analysis |
| CN117746626A (en) * | 2023-12-18 | 2024-03-22 | 河南省智慧交通研究院有限公司 | Intelligent traffic management method and system based on traffic flow |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118155153A (en) * | 2024-05-10 | 2024-06-07 | 深圳市海飞高科技术有限公司 | Image acquisition and recognition system based on CMOS double-plate module |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117953693B (en) | 2024-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117953693B (en) | Expressway traffic intelligent monitoring system based on video ai | |
| CN111325978B (en) | Whole-process monitoring and warning system and method for abnormal behaviors of vehicles on expressway | |
| CN116644373B (en) | Automobile flow data analysis management system based on artificial intelligence | |
| CN103456024B (en) | A kind of moving target gets over line determination methods | |
| CN111882858B (en) | Multi-source data-based method for predicting queuing length of highway abnormal event | |
| CN111898491B (en) | Identification method and device for reverse driving of vehicle and electronic equipment | |
| CN113055649A (en) | Tunnel intelligent video monitoring method and device, intelligent terminal and storage medium | |
| CN114155706B (en) | Service area vehicle distinguishing method and device, electronic equipment and storage medium | |
| CN113436432A (en) | Method for predicting short-term traffic risk of road section by using road side observation data | |
| CN113359673B (en) | Automatic driving automobile performance judgment system based on big data | |
| CN112749630A (en) | Intelligent video monitoring method and system for road conditions | |
| CN116721549A (en) | Traffic flow detection system and detection method | |
| CN116631186A (en) | Expressway traffic accident risk assessment method and system based on dangerous driving event data | |
| CN117173899B (en) | Smart city traffic travel quality evaluation method | |
| CN110705854A (en) | Driving level evaluation method and system | |
| CN114333331B (en) | Method and system for identifying vehicle passing information and vehicle weight of multi-lane bridge | |
| CN116631187A (en) | Intelligent acquisition and analysis system for case on-site investigation information | |
| CN113919571A (en) | Dangerous chemical transportation premium estimation method based on edge calculation | |
| CN112802333A (en) | AI video analysis-based highway network safety situation analysis system and method | |
| CN113128847A (en) | Entrance ramp real-time risk early warning system and method based on laser radar | |
| CN113888864B (en) | Image data processing method and system | |
| CN113688687B (en) | Traffic jam state rapid identification and prediction method based on electric warning data | |
| CN116978234B (en) | Road condition data dynamic acquisition method and system based on automobile data recorder | |
| CN117523840B (en) | Intelligent lane information management system and method based on digital analysis | |
| US12027041B1 (en) | Systems and methods for detecting stop sign vehicle compliance |
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 |