CN115953730B - Intelligent traffic road surface driving condition monitoring platform based on image processing technology - Google Patents
Intelligent traffic road surface driving condition monitoring platform based on image processing technology Download PDFInfo
- Publication number
- CN115953730B CN115953730B CN202211308610.9A CN202211308610A CN115953730B CN 115953730 B CN115953730 B CN 115953730B CN 202211308610 A CN202211308610 A CN 202211308610A CN 115953730 B CN115953730 B CN 115953730B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target
- target running
- running vehicle
- driver
- 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
Classifications
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention relates to the technical field of traffic road surface running condition monitoring and analyzing, and particularly discloses an intelligent traffic road surface running condition monitoring platform based on an image processing technology.
Description
Technical Field
The invention belongs to the technical field of traffic road surface running condition monitoring and analysis, and relates to an intelligent traffic road surface running condition monitoring platform based on an image processing technology.
Background
The rural roads are often mixed 'sick vehicles' and 'black vehicles' such as agricultural vehicles, non-motor vehicles and the like, the insurance procedures are uneven, and most accidents and damages are pedestrians and non-motor vehicle drivers, so that the importance of monitoring the running conditions of the traffic pavement of the rural roads is highlighted.
At present, the traffic road surface monitoring of the rural road mainly monitors the apparent information of the road surface, lacks monitoring management on the running vehicles, has certain defects, and has the following defects in the current traffic road surface running condition monitoring: 1. the second-hand vehicles, the assembled vehicles, the abandoned vehicles and the unlicensed vehicles with poor safety performance in the rural areas occupy a larger proportion, the running vehicles in the rural roads are not monitored at present, the safety of the running vehicles cannot be ensured, the healthy development of rural passenger transport markets is affected, the life and property safety of the country and people is threatened, and potential safety hazards are buried for road passenger transport.
2. At present, no monitoring and analysis are carried out on personnel information of a running vehicle, so that the life and property safety of passengers is not guaranteed, illegal camping infringes the economic benefits and legal rights of legal operators, the normal passenger order is disturbed, meanwhile, the national tax is stolen and leaked by a black car, the economic loss is caused for the country, the legal rights of the passengers are infringed, and a plurality of social security and stability problems are further caused.
3. At present, the traffic sign line of each intersection of the rural road is not carefully monitored, so that the traffic safety of the intersection of the rural road cannot be guaranteed, the use safety of the road is low, the use efficiency of the road is reduced, and the use cost of the road is increased.
Disclosure of Invention
In view of this, in order to solve the problems set forth in the above background art, an intelligent traffic road surface driving condition monitoring platform based on an image processing technology is proposed.
The aim of the invention can be achieved by the following technical scheme: the invention provides an intelligent traffic road surface driving condition monitoring platform based on an image processing technology.
And the vehicle image monitoring module monitors the target running vehicle of the target rural road according to the high-definition cameras distributed at each intersection of the target rural road.
The vehicle information analysis module focuses the pictures of the high-definition cameras on license plates corresponding to the target running vehicles according to the high-definition cameras distributed at all intersections of the target rural roads, extracts basic information corresponding to the target running vehicles from the license plates corresponding to the target running vehicles, analyzes the vehicle information of the target rural road running vehicles, and further calculates vehicle safety evaluation coefficients corresponding to the target running vehicles, wherein the vehicle information of the target rural road running vehicles comprises license plate information and use information.
The personnel monitoring module focuses the pictures of the high-definition cameras on drivers and passengers corresponding to the target running vehicles according to the high-definition cameras distributed at all intersections of the target rural roads, and sends the acquired images of the drivers and passengers corresponding to the target running vehicles to the personnel analysis module.
The personnel analysis module is used for analyzing and processing the driver image and the passenger image corresponding to the target running vehicle according to the received driver image and the passenger image corresponding to the target running vehicle, so as to obtain the personnel safety evaluation coefficient corresponding to the target running vehicle.
And the sign line monitoring and analyzing module is used for carrying out image monitoring on traffic sign lines corresponding to all the intersections of the target rural roads according to the high-definition cameras distributed at all the intersections of the target rural roads, so as to analyze and obtain the traffic sign line safety evaluation coefficients corresponding to all the intersections of the target rural roads.
The early warning display terminal carries out early warning processing aiming at a vehicle safety evaluation coefficient corresponding to a target running vehicle of a target rural road, a personnel safety evaluation coefficient and traffic sign line safety evaluation coefficients corresponding to all intersections.
The database is used for storing reference vehicle brands corresponding to the vehicle marks, reference vehicle outlines corresponding to the vehicle types, standard service lives of the vehicle types, standard annual inspection interval duration of the vehicle types, allowable running mileage of the vehicle types and total number of reference parts of the vehicle types, and also used for storing face images of driver license owners, driving license information corresponding to the drivers and allowable riding personnel numbers of the vehicle types.
Illustratively, the basic information corresponding to the target running vehicle includes a production year, a vehicle model, a time corresponding to a past annual inspection, and a vehicle annual inspection condition corresponding to a past annual inspection.
By way of example, the specific analysis process is as follows by analyzing license information of the target rural road driving vehicle: a1, extracting license plates corresponding to target running vehicles according to high-definition cameras arranged at all intersections of the target rural roads, marking the license plates corresponding to the target running vehicles as target license plates, and extracting installation vehicle models corresponding to the target license plates from a vehicle information base.
A2, comparing the logo corresponding to the target running vehicle with the reference vehicle brands corresponding to the logos stored in the database according to the logo corresponding to the target running vehicle, further obtaining the vehicle brands corresponding to the target running vehicle, comparing the vehicle types corresponding to the target running vehicle with the reference vehicle outlines corresponding to the vehicle types stored in the database according to the vehicle types corresponding to the target running vehicle, obtaining the vehicle outlines corresponding to the target running vehicle, further combining the vehicle models corresponding to the target running vehicle, and matching the vehicle models corresponding to the target running vehicle with the installation vehicle models corresponding to the target license plate numbers, thereby obtaining the license coincidence coefficient alpha corresponding to the target running vehicle.
By way of example, the specific analysis process is as follows by analyzing the usage information of the target rural road-driving vehicle: s1, according to basic information corresponding to the target running vehicle, extracting the production year corresponding to the target running vehicle from the basic information, and according to an analysis formula, analyzing the service life corresponding to the target running vehicle and the production year corresponding to the target running vehicle according to the current corresponding year and the service life corresponding to the target running vehicle by combining the current corresponding year.
S2, locating the vehicle type corresponding to the target running vehicle according to the vehicle type corresponding to the target running vehicle, screening from a database to obtain the standard service life of the corresponding vehicle type, and matching and comparing the service life corresponding to the target running vehicle with the standard service life of the corresponding vehicle type, so that the service life coincidence coefficient beta corresponding to the target running vehicle is obtained.
S3, extracting the time of last annual inspection corresponding to the target running vehicle and the annual inspection condition of the vehicle corresponding to the past annual inspection from the basic information corresponding to the target running vehicle, further screening the time of last annual inspection corresponding to the target running vehicle from the time of last annual inspection corresponding to the target running vehicle, and further obtaining the number of vehicle running mileage corresponding to the last annual inspection corresponding to the target running vehicle and the number of annual inspection qualified conditions of the vehicle parts.
S4, according to the last annual inspection time corresponding to the target running vehicle, combining the current corresponding time, and utilizing a calculation formula T 0 ＝T′-T 1 Calculating the detection time length T of the target running vehicle from this year 0 Wherein T' is represented as the set current corresponding time, T 1 The last annual inspection time corresponding to the target running vehicle is represented, the standard annual inspection interval duration of the corresponding vehicle type is extracted from the database according to the vehicle type corresponding to the target running vehicle, and the annual inspection coincidence coefficient delta corresponding to the target running vehicle is obtained by comparing the annual inspection interval duration of the target running vehicle from this time with the standard annual inspection interval duration of the corresponding vehicle type.
S5, according to the number of vehicle running mileage corresponding to the last annual inspection corresponding to the target running vehicle and the number of qualified annual inspection of the vehicle parts, utilizing a calculation formulaCalculating a running safety evaluation coefficient χ corresponding to the target running vehicle, wherein a1 and a2 are respectively expressed as set running kilometers of the vehicle and influence factors corresponding to qualified parts, K and M are respectively expressed as running mileage corresponding to the target running vehicle and qualified annual inspection parts, K 'and M' are respectively expressed as allowable running mileage corresponding to the type of the vehicle and total reference parts stored in a database, and e is expressed as a natural constant.
The calculating method is characterized in that the vehicle safety evaluation coefficient corresponding to the target running vehicle is obtained through calculation, and the specific calculating process is as follows: according to the license plate coincidence coefficient, the annual inspection coincidence coefficient and the running safety evaluation coefficient corresponding to the target running vehicle, and according to an analysis formulaAnd calculating a vehicle safety evaluation coefficient epsilon corresponding to the target running vehicle, wherein b1, b2, b3 and b4 are respectively expressed as set vehicle license compliance coefficients, year compliance coefficients, annual inspection compliance coefficients and influence factors corresponding to the running safety evaluation coefficients.
The analysis processing is performed on the driver image corresponding to the target running vehicle, and the specific processing procedure is as follows: u1, focusing a picture of a high-definition camera on a driver corresponding to a target running vehicle according to the high-definition camera arranged at each intersection of the target rural road, extracting a face image of the driver corresponding to the target running vehicle from the picture, comparing the face image of the driver corresponding to the target running vehicle with face images of drivers license owners stored in a database, judging that the driver corresponding to the target running vehicle is no driver license person if the face image of the driver corresponding to the target running vehicle is failed to be compared with the face images of the drivers license owners, marking the running safety degree corresponding to the target running vehicle as phi', and extracting driver license information corresponding to the driver corresponding to the target running vehicle from the database if the face image of the driver corresponding to the target running vehicle is successfully compared with the face image of a certain driver license owner, wherein the driver license information comprises the type of the driver license running vehicle, the residual score, the effective time of the driver license and the effective year of the driver license.
U2, obtaining a vehicle running type coincidence coefficient corresponding to a driver of the target running vehicle according to annual inspection coincidence coefficient homonymous analysis corresponding to the target running vehicleAnd the license remaining score corresponds to the coefficient gamma.
U3, according to the effective time and the effective year of the driving license corresponding to the driver corresponding to the target driving vehicle, utilizing a calculation formula T=T' +T 2 Calculating out the driving license expiration time corresponding to the driver corresponding to the target driving vehicle, and matching and comparing the driving license expiration time corresponding to the driver corresponding to the target driving vehicle with the current corresponding time to obtain the targetThe driving license security evaluation coefficient eta corresponding to the driver of the target driving vehicle is calculated by a calculation formula to obtain the driving license information evaluation coefficient phi 'corresponding to the target driving vehicle, wherein T' is represented as the effective time of the driving license corresponding to the driver corresponding to the target driving vehicle, and T 2 And the driving license effective year corresponding to the driver corresponding to the target running vehicle is indicated.
And U4, obtaining a driver safety evaluation coefficient phi corresponding to the target driving vehicle, wherein the value of phi is phi 'or phi', and phi '> phi'.
The analysis processing is performed on the passenger image corresponding to the target running vehicle, and the specific processing procedure is as follows: and focusing the pictures of the high-definition cameras on the passengers corresponding to the target running vehicles according to the high-definition cameras arranged at all the intersections of the target rural roads, and extracting the number of the passengers corresponding to the target running vehicles from the pictures.
And extracting the number of the permitted passengers corresponding to the target running vehicle from the database according to the vehicle type corresponding to the target running vehicle, and calculating the passenger safety evaluation coefficient zeta corresponding to the target running vehicle by using a calculation formula.
The specific calculation process is that according to the driver safety evaluation coefficient and the passenger safety evaluation coefficient corresponding to the target running vehicle, according to an analysis formulaAnd calculating a personnel safety evaluation coefficient lambda corresponding to the target running vehicle, wherein d1 and d2 are respectively expressed as a set driver safety evaluation coefficient and an influence factor corresponding to the passenger safety evaluation coefficient.
And comparing the personnel safety evaluation coefficient corresponding to the target running vehicle with the set standard personnel safety evaluation coefficient, and if the personnel safety evaluation coefficient corresponding to the target running vehicle is smaller than the set standard personnel safety evaluation coefficient, marking the target running vehicle and further performing early warning processing.
C1, extracting the contour corresponding to the traffic sign line from the traffic sign line image corresponding to each intersection of the target rural road, dividing the traffic sign line into marking areas according to a preset sequence, extracting the chromaticity of each marking area, further obtaining the average chromaticity of the traffic sign line through mean value calculation, and simultaneously extracting the maximum chromaticity value and the minimum chromaticity value corresponding to the traffic sign line from each marking area, thereby obtaining the chromaticity uniformity corresponding to each intersection traffic sign line through calculation formula and recording as Y i Where i is denoted by the number corresponding to each intersection, i=1, 2.
C2, obtaining the contour area corresponding to the traffic sign line according to the contour corresponding to the traffic sign line of each intersection, calculating the contour integrity corresponding to the traffic sign line of each intersection through a calculation formula, and marking as G i 。
C3, according to the chromaticity uniformity and the contour integrity corresponding to the traffic sign lines of each intersection, a calculation formula is adoptedCalculating to obtain the traffic sign line safety evaluation coefficient omega corresponding to each intersection of the target rural road i Wherein f1 and f2 are respectively expressed as weight factors corresponding to chromaticity uniformity and contour integrity.
As described above, the intelligent traffic road surface driving condition monitoring platform based on the image processing technology provided by the invention has at least the following beneficial effects: according to the intelligent traffic road surface running condition monitoring platform based on the image processing technology, through monitoring and analyzing the target running vehicle, the personnel information corresponding to the target running vehicle and the traffic sign lines corresponding to all intersections of the target rural road, the vehicle safety evaluation coefficient, the personnel safety evaluation coefficient and the traffic sign line safety evaluation coefficient corresponding to all intersections of the target running vehicle are obtained, on one hand, the problem that limitation exists in the rural road running condition monitoring in the prior art is effectively solved, the safety of the running vehicle is guaranteed, the healthy development of rural passenger transport market is promoted, the life and property safety of the country and people is further guaranteed, the potential safety hazard is solved for the transportation of road passengers, on the one hand, through monitoring and analyzing the personnel information of the running vehicle, the economic benefit and legal rights of legal operators are guaranteed, the normal passenger traffic order is guaranteed, and the social security and stability problem are further guaranteed, on the other hand, the traffic safety of all intersections of the rural road is strengthened, the use safety of the rural road is enhanced, the use efficiency of the rural road is improved, and the use cost of the road is lowered.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a system module connection according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but 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.
Referring to fig. 1, the system comprises a vehicle image monitoring module, a vehicle information analysis module, a personnel monitoring module, a personnel analysis module, a sign line monitoring analysis module, an early warning display terminal and a database.
The vehicle image monitoring module is connected with the vehicle information analysis module, the personnel monitoring module is connected with the personnel analysis module, the early warning display terminal is connected with the vehicle information analysis module, the personnel analysis module and the sign line monitoring analysis module, and the database is connected with the vehicle information analysis module and the personnel analysis module.
And the vehicle image monitoring module monitors the target running vehicle of the target rural road according to the high-definition cameras distributed at each intersection of the target rural road.
The vehicle information analysis module focuses the pictures of the high-definition cameras on license plates corresponding to the target running vehicles according to the high-definition cameras distributed at all intersections of the target rural roads, extracts basic information corresponding to the target running vehicles from the license plates corresponding to the target running vehicles, analyzes the vehicle information of the target rural road running vehicles, and further calculates vehicle safety evaluation coefficients corresponding to the target running vehicles, wherein the vehicle information of the target rural road running vehicles comprises license plate information and use information.
The above-mentioned basic information corresponding to the target running vehicle includes the production year, the vehicle model, the time corresponding to the past annual inspection, and the annual inspection condition of the vehicle corresponding to the past annual inspection.
The specific analysis process of the license information of the target rural road running vehicle is as follows: a1, extracting license plates corresponding to target running vehicles according to high-definition cameras arranged at all intersections of the target rural roads, marking the license plates corresponding to the target running vehicles as target license plates, and extracting installation vehicle models corresponding to the target license plates from a vehicle information base.
A2, comparing the vehicle logo corresponding to the target running vehicle with the reference vehicle brands corresponding to the vehicle logos stored in the database according to the vehicle logo corresponding to the target running vehicle, further obtaining the vehicle brand corresponding to the target running vehicle, comparing the vehicle model corresponding to the target running vehicle with the reference vehicle contours corresponding to the vehicle types stored in the database according to the vehicle model corresponding to the target running vehicle, obtaining the vehicle contour corresponding to the target running vehicle, further combining to obtain the vehicle model corresponding to the target running vehicle, matching the vehicle model corresponding to the target running vehicle with the installation vehicle model corresponding to the target license plate, judging that the installation vehicle is the target running vehicle if the vehicle model corresponding to the target running vehicle is matched with the installation vehicle model corresponding to the target license plate, further marking the license plate coincidence degree corresponding to the target running vehicle as alpha ', and conversely marking the license plate coincidence degree corresponding to the target running vehicle as alpha ', thereby obtaining the license plate coincidence coefficient alpha corresponding to the target running vehicle, wherein the alpha takes the value as alpha ' or alpha ', and alpha ' > ' alpha '.
The above-mentioned analysis is performed on the usage information of the target rural road running vehicle, and the specific analysis process is as follows: s1, according to basic information corresponding to the target running vehicle, extracting the production year corresponding to the target running vehicle from the basic information, and according to an analysis formula, analyzing the service life corresponding to the target running vehicle and the production year corresponding to the target running vehicle according to the current corresponding year and the service life corresponding to the target running vehicle by combining the current corresponding year.
S2, locating the vehicle type corresponding to the target traveling vehicle according to the vehicle type corresponding to the target traveling vehicle, screening a standard service life of the corresponding vehicle type from a database, matching and comparing the service life of the corresponding target traveling vehicle with the standard service life of the corresponding vehicle type, judging that the target traveling vehicle is an abnormal service life vehicle if the standard service life of the corresponding vehicle type is smaller than or equal to the service life of the corresponding target traveling vehicle, so as to obtain the service life coincidence degree beta 'corresponding to the target traveling vehicle, otherwise, obtaining the service life coincidence degree beta' corresponding to the target traveling vehicle, so as to obtain the service life coincidence coefficient beta corresponding to the target traveling vehicle, wherein the value of beta is beta 'or beta', and beta '> beta'.
In a specific embodiment, the image segmentation processing technology is used for carrying out segmentation processing on the vehicle model image corresponding to the target running vehicle to obtain a vehicle model sub-image corresponding to the target running vehicle, and the vehicle model sub-image corresponding to the target running vehicle is compared with the standard vehicle model corresponding to each preset vehicle type, so that the vehicle type corresponding to the target running vehicle is obtained.
S3, extracting the time of last annual inspection corresponding to the target running vehicle and the annual inspection condition of the vehicle corresponding to the past annual inspection from the basic information corresponding to the target running vehicle, further screening the time of last annual inspection corresponding to the target running vehicle from the time of last annual inspection corresponding to the target running vehicle, and further obtaining the number of vehicle running mileage corresponding to the last annual inspection corresponding to the target running vehicle and the number of annual inspection qualified conditions of the vehicle parts.
S4, according to the last annual inspection time corresponding to the target running vehicle, combining the current corresponding time, and utilizing a calculation formula T 0 ＝T′-T 1 Calculating the detection time length T of the target running vehicle from this year 0 Wherein T' is represented as the set current corresponding time, T 1 The last annual inspection time corresponding to the target running vehicle is represented, standard annual inspection interval duration of the corresponding vehicle type is extracted from a database according to the vehicle type corresponding to the target running vehicle, the annual inspection interval duration of the target running vehicle from this time is compared with the standard annual inspection interval duration of the corresponding vehicle type, if the annual inspection interval duration of the target running vehicle from this time is longer than the standard annual inspection interval duration of the corresponding vehicle type, the target running vehicle is judged to be an annual inspection abnormal vehicle, so as to obtain annual inspection coincidence degree delta ' corresponding to the target running vehicle, otherwise, the annual inspection coincidence degree delta ' corresponding to the target running vehicle is obtained, so as to obtain an annual inspection coincidence coefficient delta corresponding to the target running vehicle, wherein the delta takes the value of delta ' or delta ', and delta '. >δ″。
S5, according to the number of vehicle running mileage corresponding to the last annual inspection corresponding to the target running vehicle and the number of qualified annual inspection of the vehicle parts, utilizing a calculation formulaCalculating a driving safety evaluation coefficient χ corresponding to the target driving vehicle, wherein a1 and a2 are respectively expressed as set driving kilometers of the vehicle and influence factors corresponding to qualified parts, K and M are respectively expressed as driving mileage corresponding to the target driving vehicle and qualified annual inspection parts, and K 'and M' are respectively expressed asThe database stores the allowable travel mileage corresponding to the type of vehicle and the total number of reference parts, e, which are expressed as natural constants.
The calculation mentioned above obtains the vehicle safety evaluation coefficient corresponding to the target running vehicle, and the specific calculation process is as follows: according to the license plate coincidence coefficient, the annual inspection coincidence coefficient and the running safety evaluation coefficient corresponding to the target running vehicle, and according to an analysis formulaAnd calculating a vehicle safety evaluation coefficient epsilon corresponding to the target running vehicle, wherein b1, b2, b3 and b4 are respectively expressed as set vehicle license compliance coefficients, year compliance coefficients, annual inspection compliance coefficients and influence factors corresponding to the running safety evaluation coefficients.
The personnel monitoring module focuses the pictures of the high-definition cameras on drivers and passengers corresponding to the target running vehicles according to the high-definition cameras distributed at all intersections of the target rural roads, and sends the acquired images of the drivers and passengers corresponding to the target running vehicles to the personnel analysis module.
The personnel analysis module is used for analyzing and processing the driver image and the passenger image corresponding to the target running vehicle according to the received driver image and the passenger image corresponding to the target running vehicle, so as to obtain the personnel safety evaluation coefficient corresponding to the target running vehicle.
The above-mentioned analysis and processing are performed on the driver image corresponding to the target running vehicle, and the specific processing procedure is as follows: u1, focusing a picture of a high-definition camera on a driver corresponding to a target running vehicle according to the high-definition camera arranged at each intersection of the target rural road, extracting a face image of the driver corresponding to the target running vehicle from the picture, comparing the face image of the driver corresponding to the target running vehicle with face images of drivers license owners stored in a database, judging that the driver corresponding to the target running vehicle is no driver license person if the face image of the driver corresponding to the target running vehicle is failed to be compared with the face image of a driver license owner, marking the running safety degree corresponding to the target running vehicle as phi', and extracting driver license information corresponding to the driver corresponding to the target running vehicle from the database if the face image of the driver corresponding to the target running vehicle is successfully compared with the face image of the driver license owner, wherein the driver license information comprises the type of the driver license running vehicle, the residual score, the effective time of the driver license and the effective year of the driver license.
In a specific embodiment, according to the face image of the driver corresponding to the target driving vehicle, the face image corresponding to the driver corresponding to the target driving vehicle is obtained, and the eye contour, the mouth contour and the nose contour of the driver corresponding to the target driving vehicle are extracted from the face image.
And taking the eyebrow center as a center to form a perpendicular line perpendicular to the perpendicular line, forming a face rectangular coordinate system, and obtaining position coordinates corresponding to the eye center point, the mouth center point and the nose center point of a driver corresponding to the target driving vehicle according to the positions of the eye center point, the mouth center point and the nose center point of the driver corresponding to the target driving vehicle, thereby taking the position coordinates as identity characteristic information corresponding to the driver corresponding to the target driving vehicle.
And extracting eye center point position coordinates, mouth center point position coordinates and nose center point position coordinates corresponding to the driver corresponding to the target driving vehicle from the identity characteristic information corresponding to the driver corresponding to the target driving vehicle.
And acquiring face images of the drivers and owners of the drivers stored in the database, and generating identity characteristic information corresponding to the drivers and owners of the drivers and the owners of the drivers according to the generation mode of the identity characteristic information corresponding to the drivers and owners of the target running vehicles by the face images of the drivers and owners of the drivers and the licenses, so as to obtain eye center point position coordinates, mouth center point position coordinates and nose center point position coordinates of the owners of the drivers and the owners of the drivers.
Matching and comparing the identity characteristic information corresponding to the driver corresponding to the target driving vehicle with the identity characteristic information corresponding to each driving license owner to obtain the eye position coordinate difference and the mouth position coordinate of the driver corresponding to the target driving vehicle and corresponding to each driving license ownerThe difference and the nose position coordinate difference are respectively recorded as Deltal 0 j 、Δl 1 j 、Δl 2 j J represents the number corresponding to each driver's license holder, j=1, 2, &.. by calculation formulaCalculating the identity coincidence coefficient mu of the driver corresponding to the target running vehicle and the driver license owners j Wherein Deltal 0 ′、Δl 1 ′、Δl 2 ' is respectively indicated as the coordinate differences corresponding to the allowed eyes, mouth and nose of the set person, and g1, g2 and g3 are respectively indicated as the set eye position coordinate differences, mouth position coordinate differences and nose position coordinate differences.
And sequencing the identity coincidence coefficients of the driver corresponding to the target driving vehicle and the driver corresponding to each driving license owner according to the sequence from large to small, and further taking the driving license owner corresponding identity of the first ranked identity coincidence coefficient as the driver corresponding identity corresponding to the target driving vehicle.
U2, obtaining a vehicle running type coincidence coefficient corresponding to a driver of the target running vehicle according to annual inspection coincidence coefficient homonymous analysis corresponding to the target running vehicle And the license remaining score corresponds to the coefficient gamma.
In a specific embodiment, a driver corresponding to a target running vehicle is marked as a target driver, a vehicle type corresponding to the target running vehicle is compared with a driving license running vehicle type corresponding to a driver corresponding to a set target running vehicle, and if the vehicle type corresponding to the target running vehicle is inconsistent with the driving license running vehicle type corresponding to the target driver, the target running vehicle is judged to be abnormally driven, so that driving compliance corresponding to the target driver is obtainedOtherwise, it willDriving compliance corresponding to target driver +.>Thus, the vehicle driving type corresponding to the target driver is obtained as the coincidence coefficient +.>Wherein (1)>The value is +.>Or->And->
In a specific embodiment, the driving residual score corresponding to the target driving person is compared with the set standard minimum driving score, if the driving residual score corresponding to the target driving person is smaller than or equal to the set standard minimum driving score, the driving license corresponding to the target driving person is judged to be marked as a dead driving license, so as to obtain the driving license compliance gamma″ corresponding to the target driving person, otherwise, the driving license compliance gamma ' corresponding to the target driving person is obtained, so as to obtain the driving license residual score compliance coefficient gamma corresponding to the target driving person, wherein the gamma is gamma ' or gamma ', and the gamma ' > gamma '.
In one specific embodiment, the standard minimum driving score is set to 0 point.
U3, according to the effective time and the effective year of the driving license corresponding to the driver corresponding to the target driving vehicle, utilizing a calculation formula T=T' +T 2 Calculating the driving license expiration time corresponding to the driver corresponding to the target driving vehicle, matching and comparing the driving license expiration time corresponding to the driver corresponding to the target driving vehicle with the current corresponding time, and if the target driving vehicle is matched with the driving license expiration time corresponding to the driver corresponding to the target driving vehicleIf the expiration time of the driving license corresponding to the driver is larger than the current corresponding time, judging that the driving license corresponding to the driver corresponding to the target driving vehicle is an expired driving license, thereby obtaining the driving license security evaluation degree eta 'of the driving license corresponding to the driver corresponding to the target driving vehicle, otherwise, obtaining the driving license security evaluation degree eta' of the driving license corresponding to the driver corresponding to the target driving vehicle, thereby obtaining the driving license security evaluation coefficient eta corresponding to the driver of the target driving vehicle, wherein the eta takes the value of eta 'or eta', and eta 'is the value of eta'.>η ", wherein T" represents the validation time of the driver's license corresponding to the target traveling vehicle, T 2 And the driving license effective year corresponding to the driver corresponding to the target running vehicle is indicated.
U4, according to the analysis formulaAnd calculating a driver information evaluation coefficient phi' corresponding to the target running vehicle, wherein c1, c2 and c3 are respectively expressed as weight factors corresponding to the driving license running type, the driving license remaining fraction and the driving license effective time corresponding to the driver of the target running vehicle.
U5, obtaining a driver safety evaluation coefficient phi corresponding to the target driving vehicle, wherein the value of phi is phi 'or phi', and phi '> phi'.
The above-mentioned analysis processing is performed on the passenger image corresponding to the target running vehicle, and the specific processing procedure is as follows: and focusing the picture of the high-definition camera on the corresponding passengers of the target running vehicle according to the high-definition camera arranged at each intersection of the target rural road, extracting the number of the passengers corresponding to the target running vehicle from the picture, and marking the number as E.
Extracting the number of permitted passengers corresponding to the target running vehicle from the database according to the type of the vehicle corresponding to the target running vehicle, and utilizing a calculation formulaCalculating an occupant safety evaluation coefficient zeta corresponding to the target running vehicle, wherein E' is expressed as a passenger safety evaluation coefficient zeta corresponding to the target running vehicleThe number of passengers is permitted.
The specific calculation process is as follows, according to the driver safety evaluation coefficient and the passenger safety evaluation coefficient corresponding to the target running vehicle, according to the analysis formulaAnd calculating a personnel safety evaluation coefficient lambda corresponding to the target running vehicle, wherein d1 and d2 are respectively expressed as a set driver safety evaluation coefficient and an influence factor corresponding to the passenger safety evaluation coefficient.
According to the embodiment of the invention, through monitoring and analyzing the personnel information of the running vehicle, the economic benefit and legal rights of legal operators are ensured, the normal passenger order is ensured, and the social security and stability problems are further ensured.
And the sign line monitoring and analyzing module is used for carrying out image monitoring on traffic sign lines corresponding to all the intersections of the target rural roads according to the high-definition cameras distributed at all the intersections of the target rural roads, so as to analyze and obtain the traffic sign line safety evaluation coefficients corresponding to all the intersections of the target rural roads.
C1, extracting the contour corresponding to the traffic sign line from the traffic sign line image corresponding to each intersection of the target rural road, dividing the traffic sign line into marking areas according to a preset sequence, extracting the chromaticity of each marking area, further obtaining the average chromaticity of the traffic sign line through mean value calculation, and simultaneously extracting the maximum chromaticity value and the minimum chromaticity value corresponding to the traffic sign line from each marking area, thereby obtaining the chromaticity uniformity corresponding to each intersection traffic sign line through calculation formula and recording as Y i Where i is denoted by the number corresponding to each intersection, i=1, 2.
C2, obtaining the contour area corresponding to the traffic sign line according to the contour corresponding to the traffic sign line of each intersection, and calculating the traffic sign of each intersection through a calculation formulaThe line-corresponding profile integrity, and is denoted as G i 。
C3, according to the chromaticity uniformity and the contour integrity corresponding to the traffic sign lines of each intersection, a calculation formula is adoptedCalculating to obtain the traffic sign line safety evaluation coefficient omega corresponding to each intersection of the target rural road i Wherein f1 and f2 are respectively expressed as weight factors corresponding to chromaticity uniformity and contour integrity.
The traffic sign line of each intersection of the rural road is carefully monitored, so that the traffic safety of the intersection of the rural road is enhanced, the use safety of the road is enhanced, the use efficiency of the road is improved, and the use cost of the road is reduced.
The early warning display terminal performs early warning processing aiming at a vehicle safety evaluation coefficient corresponding to a target running vehicle of a target rural road, a personnel safety evaluation coefficient and traffic sign line safety evaluation coefficients corresponding to all intersections.
In a specific embodiment, the vehicle safety evaluation coefficient corresponding to the target running vehicle of the target rural road is compared with the set standard vehicle safety coefficient, if the vehicle safety evaluation coefficient corresponding to the target running vehicle of the target rural road is smaller than the set standard vehicle safety coefficient, the target running vehicle is marked, and the interception processing is carried out on the target running vehicle at the next intersection.
In a specific embodiment, comparing the personnel safety evaluation coefficient corresponding to the target running vehicle of the target rural road with the set standard personnel safety evaluation coefficient, if the personnel safety evaluation coefficient corresponding to the target running vehicle is smaller than the set standard personnel safety evaluation coefficient, marking the target running vehicle, and intercepting the target running vehicle at the next intersection.
In a specific embodiment, the traffic sign line safety evaluation coefficient corresponding to each intersection of the target rural road is compared with the set standard traffic sign line safety coefficient, and if the traffic sign line safety evaluation coefficient corresponding to a certain intersection of the target rural road is smaller than the set standard traffic sign line safety coefficient, the intersection is marked as an obstacle intersection, and then related personnel are arranged to process and repair.
The database is used for storing reference vehicle brands corresponding to the vehicle marks, reference vehicle outlines corresponding to the vehicle types, standard service lives of the vehicle types, standard annual inspection interval duration of the vehicle types, allowable running mileage of the vehicle types and total number of reference parts of the vehicle types, and also used for storing face images of driver license owners, driving license information corresponding to the drivers and allowable riding personnel numbers of the vehicle types.
The foregoing is merely illustrative and explanatory of the principles of the invention, as various modifications and additions may be made to the specific embodiments described, or similar thereto, by those skilled in the art, without departing from the principles of the invention or beyond the scope of the appended claims.
Claims (2)
1. An intelligent traffic road surface driving condition monitoring platform based on an image processing technology is characterized in that: the system comprises a vehicle image monitoring module, a vehicle information analysis module, a personnel monitoring module, a personnel analysis module, a sign line monitoring analysis module, an early warning display terminal and a database;
the vehicle image monitoring module monitors a target running vehicle of the target rural road according to high-definition cameras distributed at all intersections of the target rural road;
the vehicle information analysis module focuses the pictures of the high-definition cameras on license plates corresponding to the target running vehicles according to the high-definition cameras distributed at all intersections of the target rural roads, extracts basic information corresponding to the target running vehicles from the license plates corresponding to the target running vehicles, analyzes the vehicle information of the target rural road running vehicles, and further calculates vehicle safety evaluation coefficients corresponding to the target running vehicles, wherein the vehicle information of the target rural road running vehicles comprises license plate information and use information;
The personnel monitoring module focuses the pictures of the high-definition cameras on drivers and passengers corresponding to the target running vehicles according to the high-definition cameras distributed at all intersections of the target rural roads, and sends the acquired images of the drivers and passengers corresponding to the target running vehicles to the personnel analysis module;
the personnel analysis module is used for analyzing and processing the driver image and the passenger image corresponding to the target running vehicle according to the received driver image and the passenger image corresponding to the target running vehicle, so as to obtain a personnel safety evaluation coefficient corresponding to the target running vehicle;
the sign line monitoring and analyzing module is used for carrying out image monitoring on traffic sign lines corresponding to all intersections of the target rural roads according to the high-definition cameras distributed at all the intersections of the target rural roads, so as to analyze and obtain traffic sign line safety evaluation coefficients corresponding to all the intersections of the target rural roads;
the early warning display terminal performs early warning processing aiming at a vehicle safety evaluation coefficient corresponding to a target running vehicle of a target rural road, a personnel safety evaluation coefficient and traffic sign line safety evaluation coefficients corresponding to all intersections;
The database is used for storing a reference vehicle brand corresponding to each vehicle logo, a reference vehicle contour corresponding to each vehicle type, a standard service life of each vehicle type, a standard annual inspection interval duration of each vehicle type, a permitted running mileage number of each vehicle type and a total number of reference parts of each vehicle type, and also used for storing a face image of a driver license owner, driving license information corresponding to each driver and a permitted riding personnel number of each vehicle type;
the basic information corresponding to the target running vehicle comprises production year, vehicle type logo, time corresponding to the past annual inspection and vehicle annual inspection condition corresponding to the past annual inspection;
the license information of the target rural road running vehicle is analyzed, and the specific analysis process is as follows:
a1, extracting license plates corresponding to target running vehicles according to high-definition cameras arranged at all intersections of the target rural roads, marking the license plates corresponding to the target running vehicles as target license plates, and extracting installation vehicle models corresponding to the target license plates from a vehicle information base;
a2, comparing the logo corresponding to the target running vehicle with the reference vehicle brands corresponding to the logos stored in the database according to the logo corresponding to the target running vehicle, further obtaining the vehicle brands corresponding to the target running vehicle, comparing the vehicle types corresponding to the target running vehicle with the reference vehicle contours corresponding to the vehicle types stored in the database according to the vehicle types corresponding to the target running vehicle, obtaining the vehicle contours corresponding to the target running vehicle, further combining the vehicle models corresponding to the target running vehicle, and matching the vehicle models corresponding to the target running vehicle with the installation vehicle models corresponding to the target license plate numbers, thereby obtaining the license coincidence coefficient alpha corresponding to the target running vehicle;
The specific analysis process is as follows by analyzing the use information of the target rural road running vehicle:
s1, extracting the production year corresponding to the target running vehicle from the basic information corresponding to the target running vehicle, combining the current corresponding year, and analyzing the service life corresponding to the target running vehicle according to an analysis formula of the service life = the current corresponding year-the production year corresponding to the target running vehicle;
s2, locating the vehicle type corresponding to the target running vehicle according to the vehicle type corresponding to the target running vehicle, screening from a database to obtain the standard service life of the corresponding vehicle type, and matching and comparing the service life corresponding to the target running vehicle with the standard service life of the corresponding vehicle type, so as to obtain the service life coincidence coefficient beta corresponding to the target running vehicle;
s3, extracting the time of last annual inspection corresponding to the target running vehicle and the annual inspection condition of the vehicle corresponding to the past annual inspection from the basic information corresponding to the target running vehicle, further screening the time of last annual inspection corresponding to the target running vehicle from the time of last annual inspection corresponding to the target running vehicle, and further obtaining the number of vehicle running mileage corresponding to the last annual inspection corresponding to the target running vehicle and the number of annual inspection qualified conditions of the vehicle parts;
S4, according to the last annual inspection time corresponding to the target running vehicle, combining the current corresponding time, and utilizing a calculation formula T 0 ＝T′-T 1 Calculating the detection time length T of the target running vehicle from this year 0 Wherein T' is represented as the set current corresponding time, T 1 The last annual inspection time corresponding to the target running vehicle is represented, standard annual inspection interval duration of the corresponding vehicle type is extracted from the database according to the vehicle type corresponding to the target running vehicle, and the annual inspection interval duration of the target running vehicle from this annual inspection duration is compared with the standard annual inspection interval duration of the corresponding vehicle type, so that an annual inspection coincidence coefficient delta corresponding to the target running vehicle is obtained;
s5, according to the number of vehicle running mileage corresponding to the last annual inspection corresponding to the target running vehicle and the number of qualified annual inspection of the vehicle parts, utilizing a calculation formulaCalculating a running safety evaluation coefficient χ corresponding to a target running vehicle, wherein a1 and a2 are respectively expressed as set running kilometers of the vehicle and influence factors corresponding to qualified parts, K and M are respectively expressed as running mileage corresponding to the target running vehicle and qualified annual inspection parts, K 'and M' are respectively expressed as allowable running mileage corresponding to the type of the vehicle and total reference parts stored in a database, and e is expressed as a natural constant;
The vehicle safety evaluation coefficient corresponding to the target running vehicle is obtained through calculation, and the specific calculation process is as follows:
according to the license plate coincidence coefficient, the annual inspection coincidence coefficient and the running safety evaluation coefficient corresponding to the target running vehicle, and according to an analysis formulaCalculating a vehicle safety evaluation coefficient epsilon corresponding to the target running vehicle, wherein b1, b2, b3 and b4 are respectively expressed as set vehicle license platesThe influence factors corresponding to the evidence coincidence coefficient, the annual inspection coincidence coefficient and the driving safety evaluation coefficient;
the passenger image corresponding to the target running vehicle is analyzed and processed, and the specific processing process is as follows:
focusing the pictures of the high-definition cameras on the passengers corresponding to the target running vehicles according to the high-definition cameras arranged at all the intersections of the target rural roads, and extracting the number of the passengers corresponding to the target running vehicles from the pictures;
extracting the number of permitted passengers corresponding to the target running vehicle from a database according to the type of the vehicle corresponding to the target running vehicle, and calculating to obtain a passenger safety evaluation coefficient zeta corresponding to the target running vehicle by using a calculation formula;
the personnel safety evaluation coefficient corresponding to the target running vehicle is obtained, and the specific calculation process is as follows:
According to the corresponding driver safety evaluation coefficient and passenger safety evaluation coefficient of the target running vehicle and according to an analysis formulaCalculating a personnel safety evaluation coefficient lambda corresponding to the target running vehicle, wherein d1 and d2 are respectively expressed as a set driver safety evaluation coefficient and an influence factor corresponding to the passenger safety evaluation coefficient;
comparing the personnel safety evaluation coefficient corresponding to the target running vehicle with the set standard personnel safety evaluation coefficient, and if the personnel safety evaluation coefficient corresponding to the target running vehicle is smaller than the set standard personnel safety evaluation coefficient, marking the target running vehicle, and further performing early warning treatment;
the definition of the traffic sign line of each intersection of the target rural road is obtained through analysis, and the specific analysis process is as follows:
c1, extracting outlines corresponding to traffic sign lines from traffic sign line images corresponding to all intersections of a target rural road, dividing the traffic sign lines into marking areas according to a preset sequence, extracting chromaticity of the marking areas, and uniformly passingCalculating the average chromaticity of the traffic sign lines, extracting the maximum chromaticity value and the minimum chromaticity value corresponding to the traffic sign lines from each marking area, calculating the chromaticity uniformity corresponding to each intersection traffic sign line according to a calculation formula, and marking as Y i Wherein i is denoted as the number corresponding to each intersection, i=1, 2.
C2, obtaining the contour area corresponding to the traffic sign line according to the contour corresponding to the traffic sign line of each intersection, calculating the contour integrity corresponding to the traffic sign line of each intersection through a calculation formula, and marking as G i ；
C3, according to the chromaticity uniformity and the contour integrity corresponding to the traffic sign lines of each intersection, a calculation formula is adoptedCalculating to obtain the traffic sign line safety evaluation coefficient omega corresponding to each intersection of the target rural road i Wherein f1 and f2 are respectively expressed as weight factors corresponding to chromaticity uniformity and contour integrity.
2. The intelligent traffic road surface driving condition monitoring platform based on the image processing technology as set forth in claim 1, wherein: the driver image corresponding to the target running vehicle is analyzed and processed, and the specific processing process is as follows:
u1, focusing a picture of a high-definition camera on a driver corresponding to a target running vehicle according to the high-definition camera arranged at each intersection of the target rural road, extracting a face image of the driver corresponding to the target running vehicle from the picture, comparing the face image of the driver corresponding to the target running vehicle with face images of drivers license owners stored in a database, judging that the driver corresponding to the target running vehicle is no driver license person if the face image of the driver corresponding to the target running vehicle is failed to be compared with the face images of the drivers license owners, marking the running safety degree corresponding to the target running vehicle as phi', and extracting driver license information corresponding to the driver corresponding to the target running vehicle from the database if the face image of the driver corresponding to the target running vehicle is successfully compared with the face images of a certain driver license owner, wherein the driver license information comprises the type of the driver license running vehicle, the residual fraction, the effective time of the driver license and the effective year of the driver license;
U2, obtaining a vehicle running type coincidence coefficient corresponding to a driver of the target running vehicle according to annual inspection coincidence coefficient homonymous analysis corresponding to the target running vehicleAnd the remaining fraction of the driving license conforms to a coefficient gamma;
u3, according to the effective time and the effective year of the driving license corresponding to the driver corresponding to the target driving vehicle, utilizing a calculation formula T=T' +T 2 Calculating a driving license expiration time T corresponding to a driver corresponding to the target driving vehicle, matching and comparing the driving license expiration time T corresponding to the driver corresponding to the target driving vehicle with the current corresponding time, thereby obtaining a driving license safety evaluation coefficient eta corresponding to the driver of the target driving vehicle, and calculating a driving license information evaluation coefficient phi 'corresponding to the target driving vehicle by using a calculation formula, wherein T' is represented as the driving license effective time T corresponding to the driver corresponding to the target driving vehicle 2 The driving license effective year corresponding to the driver corresponding to the target driving vehicle is expressed;
and U4, obtaining a driver safety evaluation coefficient phi corresponding to the target driving vehicle, wherein the value of phi is phi 'or phi', and phi '> phi'.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211308610.9A CN115953730B (en) | 2022-10-25 | 2022-10-25 | Intelligent traffic road surface driving condition monitoring platform based on image processing technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211308610.9A CN115953730B (en) | 2022-10-25 | 2022-10-25 | Intelligent traffic road surface driving condition monitoring platform based on image processing technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115953730A CN115953730A (en) | 2023-04-11 |
| CN115953730B true CN115953730B (en) | 2023-08-08 |
Family
ID=87288054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211308610.9A Active CN115953730B (en) | 2022-10-25 | 2022-10-25 | Intelligent traffic road surface driving condition monitoring platform based on image processing technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115953730B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116229765B (en) * | 2023-05-06 | 2023-07-21 | 贵州鹰驾交通科技有限公司 | Vehicle-road cooperation method based on digital data processing |
| CN116279522B (en) * | 2023-05-25 | 2023-07-21 | 鹰驾科技（深圳）有限公司 | In-vehicle behavior safety vehicle-mounted monitoring management system based on feature analysis |
| CN117710909B (en) * | 2024-02-02 | 2024-04-12 | 多彩贵州数字科技股份有限公司 | Rural road intelligent monitoring system based on target detection and instance segmentation |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013117119A1 (en) * | 2012-02-07 | 2013-08-15 | 厦门金龙机动车检测有限公司 | Driving evaluation system and method |
| CN104477167A (en) * | 2014-11-26 | 2015-04-01 | 浙江大学 | Intelligent driving system and control method thereof |
| CN107393304A (en) * | 2017-09-11 | 2017-11-24 | 安徽实运信息科技有限责任公司 | A kind of traffic condition detection system passed through based on bayonet socket |
| CN112561282A (en) * | 2020-12-07 | 2021-03-26 | 李强 | Big data-based automatic bus trip risk safety assessment system |
| CN112770293A (en) * | 2020-12-18 | 2021-05-07 | 杭州宣迅电子科技有限公司 | Vehicle driving environment safety analysis early warning management cloud platform based on artificial intelligence |
| CN114529131A (en) * | 2022-01-04 | 2022-05-24 | 武汉路特斯汽车有限公司 | Risk assessment method and device, electronic equipment and storage medium |
| CN115240176A (en) * | 2022-04-27 | 2022-10-25 | 浪潮通信技术有限公司 | Method, device and system for managing and controlling vehicles in risk area |
-
2022
- 2022-10-25 CN CN202211308610.9A patent/CN115953730B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013117119A1 (en) * | 2012-02-07 | 2013-08-15 | 厦门金龙机动车检测有限公司 | Driving evaluation system and method |
| CN104477167A (en) * | 2014-11-26 | 2015-04-01 | 浙江大学 | Intelligent driving system and control method thereof |
| CN107393304A (en) * | 2017-09-11 | 2017-11-24 | 安徽实运信息科技有限责任公司 | A kind of traffic condition detection system passed through based on bayonet socket |
| CN112561282A (en) * | 2020-12-07 | 2021-03-26 | 李强 | Big data-based automatic bus trip risk safety assessment system |
| CN112770293A (en) * | 2020-12-18 | 2021-05-07 | 杭州宣迅电子科技有限公司 | Vehicle driving environment safety analysis early warning management cloud platform based on artificial intelligence |
| CN114529131A (en) * | 2022-01-04 | 2022-05-24 | 武汉路特斯汽车有限公司 | Risk assessment method and device, electronic equipment and storage medium |
| CN115240176A (en) * | 2022-04-27 | 2022-10-25 | 浪潮通信技术有限公司 | Method, device and system for managing and controlling vehicles in risk area |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115953730A (en) | 2023-04-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115953730B (en) | Intelligent traffic road surface driving condition monitoring platform based on image processing technology | |
| CN110136447B (en) | Method for detecting lane change of driving and identifying illegal lane change | |
| CN109637151B (en) | Method for identifying illegal driving of emergency lane on highway | |
| Laureshyn et al. | The Swedish Traffic Conflict technique: observer's manual | |
| CN100565555C (en) | Peccancy parking detector based on computer vision | |
| US20140222323A1 (en) | Rogue vehicle detection | |
| CN105654730B (en) | A kind of fake-licensed car identification for crossing vehicle big data analysis based on bayonet | |
| US20150286883A1 (en) | Robust windshield detection via landmark localization | |
| CN111369801B (en) | Vehicle identification method, device, equipment and storage medium | |
| CN111899517B (en) | Expressway fatigue driving illegal behavior determination method | |
| CN115035491A (en) | Driving behavior road condition early warning method based on federal learning | |
| CN114926824A (en) | Method for judging bad driving behavior | |
| KR20220138894A (en) | Prediction and recognition method of road marking information and road maintenance method | |
| Safaei et al. | Weighing criteria and prioritizing strategies to reduce motorcycle-related injuries using combination of fuzzy TOPSIS and AHP methods | |
| CN114724122A (en) | Target tracking method and device, electronic equipment and storage medium | |
| Doycheva et al. | Computer vision and deep learning for real-time pavement distress detection | |
| CN114693722B (en) | Vehicle driving behavior detection method, detection device and detection equipment | |
| CN115440071A (en) | Automatic driving illegal parking detection method | |
| CN115731707A (en) | Highway vehicle traffic control method and system | |
| CN114612731A (en) | Intelligent identification method and system for road flatness detection | |
| CN109191855B (en) | Method and system for identifying motor vehicle reflecting mark not stuck according to regulations and storage medium | |
| CN112348206A (en) | Comprehensive pavement treatment system for maintaining pavement | |
| CN114201530A (en) | Suspected abnormal operation passenger car early discrimination and preventive supervision method | |
| CN112989069A (en) | Traffic violation analysis method based on knowledge graph and block chain | |
| CN113516343A (en) | Vehicle early warning system, method and storage medium based on map and track data |
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 |