CN111009127B - Urban dynamic early warning system and method based on accident risk - Google Patents
Urban dynamic early warning system and method based on accident risk Download PDFInfo
- Publication number
- CN111009127B CN111009127B CN201911350612.2A CN201911350612A CN111009127B CN 111009127 B CN111009127 B CN 111009127B CN 201911350612 A CN201911350612 A CN 201911350612A CN 111009127 B CN111009127 B CN 111009127B
- Authority
- CN
- China
- Prior art keywords
- accident
- information
- road
- vehicle
- speed
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a city dynamic early warning system and method based on accident risk, which are characterized in that position information and speed information of a vehicle are acquired through a vehicle end, driving state information, traffic flow and road condition information of the vehicle are acquired and analyzed by matching with a road section monitoring end, various parameters during accident occurrence can be accurately and comprehensively acquired, the parameters are processed through an early warning pushing end, the reason of the accident occurrence, a high-speed road section and accident characteristics are obtained through analysis, namely, under certain type of road condition information, a vehicle running speed interval with the largest accident occurrence proportion is obtained, after the vehicle enters the high-speed road section, the speed information and the road condition information of the vehicle are detected in real time, and when the accident characteristics are met, early warning is pushed to remind a driver. After the reasons of accidents are analyzed, the accident records corresponding to the accidents caused by human factors are removed, so that the noise reduction of data is realized, the accuracy of the relevance between the driving speed and the road condition state is improved, and the accuracy of early warning is further improved.
Description
Technical Field
The invention relates to the field of traffic accident early warning systems, in particular to an accident risk based urban dynamic early warning system and method.
Background
In the process of running in a vehicle, the influence of environmental factors is often caused, such as the reduction of visibility caused by rain and snow or the reduction of ground gripping performance caused by the accumulation of water and icing on the road surface, so that the reaction of a driver is not in time, accidents are caused, and the accidents can be avoided by controlling the speed of the vehicle;
the patent document with publication number CN208842326U discloses a fatigue driving state recognition and early warning system, which detects and recognizes the fatigue state of the driver and feeds back the fatigue degree in real time so that the driver can take measures in time, thereby providing a scientific and reasonable early warning for the driver, reducing traffic accidents caused by fatigue driving, and improving the driving reliability of the driver.
Patent document CN101593352 discloses a driving safety monitoring system based on face orientation and visual focus, comprising a visual sensor and an intelligent processor, wherein the intelligent processor comprises an image acquisition module, a skin color area detection module, a color image area; the edge extraction module is used for extracting edges by adopting a Canny operator to obtain a head image outline; the eye detection module is used for carrying out Hough transformation on the marginalized face and positioning eyes; the face orientation analysis module is used for determining a mouth region, positioning a mouth, respectively calculating the left area and the right area of the face by taking eyes and the mouth as references, and calculating the left area and the right area of the face; and the driver safe driving judging module is used for judging that the driver is in a non-safe driving state and sending an alarm instruction according to a preset human face left-right area ratio interval, if the calculated current human face left-right area ratio is outside the preset interval. The invention has strong anti-interference capability and high accuracy.
However, the technical scheme does not analyze each road section and real-time road condition information, only carries out early warning on accidents caused by human factors, but does not carry out early warning on accidents caused by environmental factors, so that the adaptive range is small and the early warning accuracy is not high in practical use.
Disclosure of Invention
In order to solve the above technical problems, the present invention provides a city dynamic early warning system and method based on accident risk, the position information and the speed information of the vehicle are acquired by the vehicle end, the driving state information, the traffic flow and the road condition information of the vehicle are acquired and analyzed by matching with the road section monitoring end, various parameters when an accident occurs can be accurately and comprehensively acquired, the driving state information, the traffic flow, the road condition information, the position information and the speed information are processed through the early warning pushing end, the reason of the accident occurrence, the high-speed road section and the accident characteristics are obtained through analysis, namely, under certain road condition information, the vehicle running speed interval with the largest accident ratio is obtained, and after the vehicle enters a high-speed road section, and the speed information and the road condition information of the vehicle are detected in real time, and when the accident characteristics are met, early warning is pushed to remind a driver. After the reasons of accidents are analyzed, the accident records corresponding to the accidents caused by human factors are removed, so that the noise reduction of data is realized, the accuracy of the relevance between the driving speed and the road condition state is improved, and the accuracy of early warning is further improved.
The technical problem to be solved by the invention is as follows:
A. how to select the high-risk road section and enable the vehicle to obtain accurate early warning by combining the road condition information when the vehicle drives into the high-risk road section.
The purpose of the invention can be realized by the following technical scheme:
a city dynamic early warning system based on accident risk comprises a road section monitoring end, an early warning pushing end and a vehicle end arranged in a vehicle, wherein the vehicle end comprises a positioning module, a speed recording module and an associated uploading module; the positioning module is used for recording the position information of the vehicle at the frequency f 1; the speed recording module is used for recording the speed information of the vehicle at a frequency f 1; the correlation uploading module is used for correlating the position information of the accident with the average speed information t1 before the accident happens after receiving the running information acquisition instruction, generating the running information of the accident vehicle and uploading the running information to the road section monitoring terminal;
the road section monitoring end comprises a driver state detection module, a road condition detection module, a traffic flow recording module and an accident monitoring module; the driver state detection module is used for acquiring driving state information of a driver at a frequency f2, wherein the driving state information comprises a normal driving state and a dangerous driving state; the traffic flow recording module is used for recording the traffic flow of the road section in a time period t2, and the road condition detection module is used for detecting the road condition information of the road section at a frequency f 3; the accident monitoring module is used for detecting whether an accident occurs or not, acquiring accident vehicle information used for determining a vehicle end corresponding to the accident vehicle, generating a driving information acquisition instruction according to the accident vehicle information, and sending the driving information acquisition instruction to the vehicle end corresponding to the accident vehicle; after receiving the returned driving information, the accident monitoring module generates accident road section information according to the position information, associates the accident road section information, the accident vehicle information, the driving state information, the traffic flow of the time period when the accident occurs and the road condition information when the accident occurs, generates an accident record together, and uploads the accident record to the early warning pushing end;
the early warning pushing end comprises a high-speed road section screening module, an accident characteristic extraction module and an early warning generation module; the high-speed road section screening module is used for screening road sections with accident occurrence frequency higher than the average value according to all accident records as high-speed road sections; the accident feature extraction module is used for extracting accident features containing road condition information and driving information according to the accident record; the early warning generation module is used for acquiring real-time driving state information from a road section monitoring end, real-time road condition information of the high-speed road section and driving information of a vehicle end corresponding to the vehicle from the vehicle end when the vehicle drives into the high-speed road section, and sending early warning push to the vehicle end when the accident characteristics corresponding to the same time period are met.
Further, the driver state detection module comprises a collection unit installed in the vehicle and a receiving and processing unit in wireless communication connection with the collection unit, wherein the collection unit comprises high-definition camera equipment and an alcohol concentration sensor arranged in the vehicle, the high-definition camera equipment is used for collecting facial information of the driver, and the alcohol concentration sensor is used for detecting whether the driver drives after drinking; the receiving and processing unit is arranged in the road section monitoring terminal and used for receiving the facial information and the detected alcohol concentration, carrying out intelligent image recognition on the facial information, and recognizing the state of the driver as a normal driving state or a dangerous driving state, wherein the dangerous driving state comprises suspected drunk driving, fatigue driving and attention transfer.
Further, the road condition detection module comprises a visibility detection unit, a surface water detection unit, an icing detection unit and a road condition information generation unit; the visibility detection unit is used for detecting the visibility of the road section and dividing the visibility into n1 grades; the road surface ponding detection unit is used for detecting the ponding state of a road section and dividing the ponding state into n2 grades according to the ponding depth, and the road surface icing detection unit is used for detecting the road surface icing state and dividing the icing state into n3 grades according to the icing area on the road of unit area; the road condition information generating unit is used for generating road condition information containing visibility, a ponding state and an icing state.
A city dynamic early warning method based on accident risk comprises the following specific steps:
s1, screening a road section with the accident occurrence frequency higher than the average value as a high-speed road section by a high-speed road section screening module of the early warning pushing end according to all accident records in a time period t 2;
s2, an accident feature extraction module of the early warning pushing end extracts accident features from all accident records in a time period t2 of the high-speed road section;
s3, screening a vehicle end entering a high-speed road section as a monitoring vehicle according to the position information by an early warning generation module of the early warning push end, acquiring real-time road condition information and driving state information of the high-speed road section where the monitoring vehicle is located from the road section monitoring end, and acquiring driving information of the vehicle end corresponding to the vehicle from the vehicle end;
and S4, comparing the driving state information, the road condition information and the driving information with the accident characteristics of the road section by the early warning generation module of the early warning pushing end, and sending early warning pushing to the vehicle end when the driving state information, the road condition information and the driving information accord with the accident characteristics corresponding to the same time period.
Further, the specific steps of screening the high-speed road section in S1 are as follows:
s1.1, denoising the accident record; the method specifically comprises the following steps: all accident records in a time period t2 are obtained, and accident records with driving state information being a normal driving state are screened out to be used as sample accidents;
s1.2, grouping the sample accidents according to road sections to obtain a sample accident set of each road section, and recording as Ai as a sample accident set of the ith road section { Ai1, Ai2, …, aij, … and aiki }, wherein Ai is the sample accident set of the ith road section, aij is the jth sample accident in the set Ai, aiki is the last sample accident in the set Ai, and ki is the element number of the set Ai;
s1.3, obtaining the traffic flow Ci of a road section corresponding to the sample accident set Ai in a time period t 2; calculating the accident occurrence rate Pi of each road section as ki/Ci, and calculating the average accident probability of all road sections, wherein n is the number of sample accident sets;
s1.4, comparing the Pi with the average accident probability, screening the road sections with the accident occurrence rate larger than the average accident probability, and marking the road sections as high-speed road sections;
further, the concrete steps of extracting the accident characteristics in S2 are as follows:
s2.1, selecting a corresponding sample accident set Ai in a time period t2 of the high-speed road section, and acquiring road condition information and driving information of each element in the sample accident set Ai;
s2.2, generating all kinds of road condition information through permutation and combination, recording the kinds as X1, X2, X3 and …, dividing the kinds into n4 speed sections from small to large according to the section range L, recording the speed sections as Y1, Y2, Y3 and …, and establishing a road condition information-speed section table; counting the number of accidents of each item in the table according to the sample accident set Ai;
s2.3, extracting each item of data in any column in the table to form a group of arrays, calculating standard deviation of the arrays, recording the standard deviation as accident characteristic standard deviation of the road condition information, and so on to obtain accident characteristic standard deviation of all the road condition information to form a standard deviation array, calculating average value of the standard deviation array, and screening out road condition information types corresponding to all the accident characteristic standard deviations which are larger than the average value to serve as alternative road condition information types;
s2.4, calculating the total number Mq of the accidents in each row in the table corresponding to the alternative road condition information types, calculating the proportion G between the number of the accidents in each speed interval and the Mq, at least arranging the accidents from multiple speed intervals, screening a plurality of speed intervals in sequence until the sum of the proportions G in the screened speed intervals exceeds 50%, and marking the screened speed intervals and the corresponding road condition information types as accident characteristics;
and S2.5, marking the dangerous driving state as an accident characteristic.
The invention has the beneficial effects that:
(1) the position information and the speed information of the vehicle are acquired through the vehicle end, the driving state information, the traffic flow and the road condition information of the vehicle are acquired and analyzed through the road section monitoring end in a matched mode, all parameters in the accident occurrence can be accurately and comprehensively acquired, the driving state information, the traffic flow, the road condition information, the position information and the speed information are processed through the early warning pushing end, the reason of the accident occurrence, the high-speed road section and the accident characteristics are obtained through analysis, namely under the road condition information of a certain type, the vehicle running speed interval with the largest accident occurrence proportion is formed, after the vehicle enters the high-speed road section, the speed information and the road condition information of the vehicle are detected in real time, and when the accident characteristics are met, early warning is pushed, and a driver is.
(2) After the reasons of accidents are analyzed, the accident records corresponding to the accidents caused by human factors are removed, so that the noise reduction of data is realized, the accuracy of the relevance between the driving speed and the road condition state is improved, and the accuracy of early warning is further improved.
Drawings
The invention will be further described with reference to the accompanying drawings.
FIG. 1 is a system block diagram of the present invention;
fig. 2 is a schematic diagram of establishing a traffic information-speed interval table according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the embodiment provides an urban dynamic early warning system based on accident risk, including a road section monitoring end, an early warning pushing end, and a vehicle end arranged in a vehicle, where the vehicle end includes a positioning module, a speed recording module, and an associated uploading module; the positioning module is used for recording the position information of the vehicle at the frequency f 1; the speed recording module is used for recording the speed information of the vehicle at a frequency f 1; if f1 is 10Hz, the correlation uploading module is used for correlating the position information of the accident with the average speed information of t1 before the accident happens after the driving information acquisition instruction is received, and if t1 is 10s, the driving information of the accident vehicle is generated and uploaded to the road section monitoring terminal;
the road section monitoring end comprises a driver state detection module, a road condition detection module, a traffic flow recording module and an accident monitoring module; the driver state detection module is used for acquiring driving state information of a driver at a frequency f2, such as f 2-2 Hz, wherein the driving state information comprises a normal driving state and a dangerous driving state; the traffic flow recording module is configured to record a traffic flow of the road segment in a time period t2, and if t2 is 6:00 to 7:00, the road condition detecting module is configured to detect the road condition information of the road segment with a frequency f3, for example, f3 is 2 times/hour; the accident monitoring module is used for detecting whether an accident occurs or not, acquiring accident vehicle information used for determining a vehicle end corresponding to the accident vehicle, generating a driving information acquisition instruction according to the accident vehicle information, and sending the driving information acquisition instruction to the vehicle end corresponding to the accident vehicle; after receiving the returned driving information, the accident monitoring module generates accident road section information according to the position information, associates the accident road section information, the accident vehicle information, the driving state information, the traffic flow of the time period when the accident occurs and the road condition information when the accident occurs, generates an accident record together, and uploads the accident record to the early warning pushing end;
the early warning pushing end comprises a high-speed road section screening module, an accident characteristic extraction module and an early warning generation module; the high-speed road section screening module is used for screening road sections with accident occurrence frequency higher than the average value according to all accident records as high-speed road sections; the accident feature extraction module is used for extracting accident features containing road condition information and driving information according to the accident record; the early warning generation module is used for acquiring real-time driving state information from a road section monitoring end, real-time road condition information of the high-speed road section and driving information of a vehicle end corresponding to the vehicle from the vehicle end when the vehicle drives into the high-speed road section, and sending early warning push to the vehicle end when the accident characteristics corresponding to the same time period are met. Namely, the time period of vehicle driving belongs to the time period of 6:00-7:00, the acquired accident characteristics are the accident characteristics obtained by the data of the time period of 6:00-7: 00. I.e., t2 is the time period to which the vehicle belongs. For example, the division of time periods may divide a day into 24 time periods.
The driver state detection module comprises a collection unit arranged in the vehicle and a receiving and processing unit in wireless communication connection with the collection unit, wherein the collection unit comprises high-definition camera equipment and an alcohol concentration sensor arranged in the vehicle, the high-definition camera equipment is used for collecting facial information of a driver, and the alcohol concentration sensor is used for detecting whether the driver drives after drinking or not; the receiving and processing unit is arranged in the road section monitoring terminal and used for receiving the facial information and the detected alcohol concentration, carrying out intelligent image recognition on the facial information, and recognizing the state of the driver as a normal driving state or a dangerous driving state, wherein the dangerous driving state comprises suspected drunk driving, fatigue driving and attention transfer.
The road condition detection module comprises a visibility detection unit, a surface water accumulation detection unit, a road icing detection unit and a road condition information generation unit; the visibility detection unit is used for detecting the visibility of the road section and dividing the visibility into n1 grades; for example, n1 is equal to 3, the visibility is low, medium and high respectively. The surface water detection unit is used for detecting the water accumulation state of the road section, and dividing the water accumulation state into n2 grades according to the water accumulation depth, wherein the water accumulation state is none, low and high if n1 is 3. The icing detection unit is used for detecting the icing state of the road and dividing the icing state into n3 grades according to the icing area on the road of unit area; for example, if n1 is 3, the icing state is classified as none, local and large area. The road condition information generating unit is used for generating road condition information containing visibility, a ponding state and an icing state. Since these three physical quantities may exist simultaneously, the traffic information may include one of visibility, a ponding state, and an icing state, or may include two or three of these physical quantities.
The working process is as follows: the position information and the speed information of the vehicle are acquired through the vehicle end, the driving state information, the traffic flow and the road condition information of the vehicle are acquired and analyzed through the road section monitoring end in a matched mode, all parameters in the accident occurrence can be accurately and comprehensively acquired, the driving state information, the traffic flow, the road condition information, the position information and the speed information are processed through the early warning pushing end, the reason of the accident occurrence, the high-speed road section and the accident characteristics are obtained through analysis, namely under the road condition information of a certain type, the vehicle running speed interval with the largest accident occurrence proportion is formed, after the vehicle enters the high-speed road section, the speed information and the road condition information of the vehicle are detected in real time, and when the accident characteristics are met, early warning is pushed, and a driver is.
A city dynamic early warning method based on accident risk can be based on the early warning system, and the method comprises the following specific steps:
s1, screening a road section with the accident occurrence frequency higher than the average value as a high-speed road section by a high-speed road section screening module of the early warning pushing end according to all accident records in a time period t 2;
s2, an accident feature extraction module of the early warning pushing end extracts accident features from all accident records in a time period t2 of the high-speed road section;
s3, screening a vehicle end entering a high-speed road section as a monitoring vehicle according to the position information by an early warning generation module of the early warning push end, acquiring real-time road condition information and driving state information of the high-speed road section where the monitoring vehicle is located from the road section monitoring end, and acquiring driving information of the vehicle end corresponding to the vehicle from the vehicle end;
and S4, comparing the driving state information, the road condition information and the driving information with the accident characteristics of the road section by the early warning generation module of the early warning pushing end, and sending early warning pushing to the vehicle end when the driving state information, the road condition information and the driving information accord with the accident characteristics corresponding to the same time period.
The accident occurrence reasons can be generally divided into environmental factors and human factors, the human factors have a great influence, the accuracy of the correlation between the driving speed and the road condition is affected, and in order to improve the accuracy of the correlation between the driving speed and the road condition, the accident caused by the human factors needs to be removed, so the specific steps for screening the high-frequency road section in S1 are as follows:
s1.1, denoising the accident record; the method specifically comprises the following steps: all accident records in a time period t2 are obtained, and accident records with driving state information being a normal driving state are screened out to be used as sample accidents; the accident record corresponding to the accident caused by human factors can be eliminated.
S1.2, grouping the sample accidents according to road sections to obtain a sample accident set of each road section, and recording as Ai as a sample accident set of the ith road section { Ai1, Ai2, …, aij, … and aiki }, wherein Ai is the sample accident set of the ith road section, aij is the jth sample accident in the set Ai, aiki is the last sample accident in the set Ai, and ki is the element number of the set Ai; each road segment corresponds to a sample set of incidents.
S1.3, obtaining the traffic flow Ci of a road section corresponding to the sample accident set Ai in a time period t 2; calculating the accident occurrence rate Pi of each road section as ki/Ci, and calculating the average accident probability of all road sections, wherein n is the number of sample accident sets;
s1.4, comparing the Pi with the average accident probability, screening the road sections with the accident occurrence rate larger than the average accident probability, and marking the road sections as high-speed road sections; the high-speed road section extracted at the moment is a road section with high accident frequency caused by environmental factors, the data is more objective, and the early warning accuracy is further improved.
In order to accurately extract the relation between the road condition information and the speed and screen out the safe speed under various road condition information according to the relation; the concrete steps adopted for extracting the accident characteristics in the step S2 are as follows:
s2.1, selecting a corresponding sample accident set Ai in a time period t2 of the high-speed road section, and acquiring road condition information and driving information of each element in the sample accident set Ai; t2 is the time period during which the vehicle is running.
As shown in fig. 2, S2.2, generating all the road condition information types by permutation and combination, that is, the number of the types is N1 × N2 × N3, which is denoted as X1, X2, X3, …, and dividing the range of the types into N4 speed sections from small to large, for example, N4 is 10km/h, that is, the first speed section is 10-20, the second speed section is 20-30, and so on, which is denoted as Y1, Y2, Y3, …, and establishing a road condition information-speed section table; counting the number of accidents of each item in the table according to the sample accident set Ai;
each column in the table corresponds to the number of accidents of one road condition information in different speed intervals.
And S2.3, extracting each item of data in any column in the table to form a group of arrays, calculating the standard deviation of the arrays, recording the standard deviation as the accident characteristic standard deviation of the road condition information, and representing the dispersion degree of the number of accidents corresponding to each speed interval under the road condition information.
By analogy, obtaining accident characteristic standard deviations of all road condition information to form a standard deviation array, calculating an average value of the standard deviation array, and screening out road condition information types corresponding to all accident characteristic standard deviations larger than the average value to serve as alternative road condition information types; the type of the alternative traffic information is influenced by speed more than other types of traffic information, that is, speed has an important influence on safety under the traffic information, and therefore, the safe driving speed of the vehicle under the traffic information needs to be determined.
S2.4, the total number Mq of the accidents in each column in the table corresponding to the types of the alternative road condition information is calculated, the occupation ratio G between the number of the accidents in each speed interval and the Mq is calculated, at least a plurality of speed intervals are sequentially screened according to the sequence from the maximum number to the minimum number until the sum of the occupation ratios G in the screened speed intervals exceeds 50 percent, and the accident rate in the speed intervals is more than half, so that the screened speed intervals and the corresponding types of the road condition information can be marked as accident characteristics;
and S2.5, marking the dangerous driving state as an accident characteristic.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (1)
1. A city dynamic early warning system based on accident risk comprises a road section monitoring end, an early warning pushing end and a vehicle end arranged in a vehicle, and is characterized in that the vehicle end comprises a positioning module, a speed recording module and an associated uploading module; the positioning module is used for recording the position information of the vehicle at the frequency f 1; the speed recording module is used for recording the speed information of the vehicle at a frequency f 1; the correlation uploading module is used for correlating the position information of the accident with the average speed information t1 before the accident happens after receiving the running information acquisition instruction, generating the running information of the accident vehicle and uploading the running information to the road section monitoring terminal;
the road section monitoring end comprises a driver state detection module, a road condition detection module, a traffic flow recording module and an accident monitoring module; the driver state detection module is used for acquiring driving state information of a driver at a frequency f2, wherein the driving state information comprises a normal driving state and a dangerous driving state; the traffic flow recording module is used for recording the traffic flow of the road section in a time period t2, and the road condition detection module is used for detecting the road condition information of the road section at a frequency f 3; the accident monitoring module is used for detecting whether an accident occurs or not, acquiring accident vehicle information used for determining a vehicle end corresponding to the accident vehicle, generating a driving information acquisition instruction according to the accident vehicle information, and sending the driving information acquisition instruction to the vehicle end corresponding to the accident vehicle; after receiving the returned driving information, the accident monitoring module generates accident road section information according to the position information, associates the accident road section information, the accident vehicle information, the driving state information, the traffic flow of the time period when the accident occurs and the road condition information when the accident occurs, generates an accident record together, and uploads the accident record to the early warning pushing end;
the early warning pushing end comprises a high-speed road section screening module, an accident characteristic extraction module and an early warning generation module; the high-speed road section screening module is used for screening road sections with accident occurrence frequency higher than the average value according to all accident records as high-speed road sections; the accident feature extraction module is used for extracting accident features containing road condition information and driving information according to the accident record; the early warning generation module is used for acquiring real-time driving state information from a road section monitoring end, real-time road condition information of a high-speed road section and driving information of a vehicle end corresponding to the vehicle from the vehicle end when the vehicle drives into the high-speed road section, and sending early warning push to the vehicle end when the accident characteristics corresponding to the same time period are met;
the driver state detection module comprises a collection unit arranged in the vehicle and a receiving and processing unit in wireless communication connection with the collection unit, wherein the collection unit comprises high-definition camera equipment and an alcohol concentration sensor arranged in the vehicle, the high-definition camera equipment is used for collecting facial information of a driver, and the alcohol concentration sensor is used for detecting whether the driver drives after drinking or not; the receiving and processing unit is arranged in the road section monitoring terminal and used for receiving the facial information and the detected alcohol concentration, carrying out intelligent image recognition on the facial information, and recognizing the state of the driver as a normal driving state or a dangerous driving state, wherein the dangerous driving state comprises suspected drunk driving, fatigue driving and attention transfer;
the road condition detection module comprises a visibility detection unit, a surface water accumulation detection unit, a road icing detection unit and a road condition information generation unit; the visibility detection unit is used for detecting the visibility of the road section and dividing the visibility into n1 grades; the road surface ponding detection unit is used for detecting the ponding state of a road section and dividing the ponding state into n2 grades according to the ponding depth, and the road surface icing detection unit is used for detecting the road surface icing state and dividing the icing state into n3 grades according to the icing area on the road of unit area; the road condition information generating unit is used for generating road condition information comprising visibility, a ponding state and an icing state;
the city dynamic early warning method based on the accident risk comprises the following specific steps:
s1, screening a road section with the accident occurrence frequency higher than the average value as a high-speed road section by a high-speed road section screening module of the early warning pushing end according to all accident records in a time period t 2;
s2, an accident feature extraction module of the early warning pushing end extracts accident features from all accident records in a time period t2 of the high-speed road section;
s3, screening a vehicle end entering a high-speed road section as a monitoring vehicle according to the position information by an early warning generation module of the early warning push end, acquiring real-time road condition information and driving state information of the high-speed road section where the monitoring vehicle is located from the road section monitoring end, and acquiring driving information of the vehicle end corresponding to the vehicle from the vehicle end;
s4, the early warning generation module of the early warning push end compares the driving state information, the road condition information and the driving information with the accident characteristics of the road section, and sends out early warning push to the vehicle end when the driving state information, the road condition information and the driving information accord with the corresponding accident characteristics in the same time period;
the specific steps of screening the high-speed road section in the step S1 are as follows:
s1.1, denoising the accident record; the method specifically comprises the following steps: all accident records in a time period t2 are obtained, and accident records with driving state information being a normal driving state are screened out to be used as sample accidents;
s1.2, grouping the sample accidents according to road sections to obtain a sample accident set of each road section, and recording as Ai as a sample accident set of the ith road section { Ai1, Ai2, …, aij, … and aiki }, wherein Ai is the sample accident set of the ith road section, aij is the jth sample accident in the set Ai, aiki is the last sample accident in the set Ai, and ki is the element number of the set Ai;
s1.3, obtaining the traffic flow Ci of a road section corresponding to the sample accident set Ai in a time period t 2; calculating the accident rate Pi of each road section as ki/Ci, and calculating the average accident probability of all road sections
Wherein n is the number of sample incident sets;
s1.4, comparing Pi and
screening the road sections with the accident occurrence rate larger than the average accident probability, and marking the road sections as high-speed road sections;
the concrete steps of extracting the accident characteristics in the step S2 are as follows:
s2.1, selecting a corresponding sample accident set Ai in a time period t2 of the high-speed road section, and acquiring road condition information and driving information of each element in the sample accident set Ai;
s2.2, generating all kinds of road condition information through permutation and combination, recording the kinds as X1, X2, X3 and …, dividing the kinds into n4 speed sections from small to large according to the section range L, recording the speed sections as Y1, Y2, Y3 and …, and establishing a road condition information-speed section table; counting the number of accidents of each item in the table according to the sample accident set Ai;
s2.3, extracting each item of data in any column in the table to form a group of arrays, calculating standard deviation of the arrays, recording the standard deviation as accident characteristic standard deviation of the road condition information, and so on to obtain accident characteristic standard deviation of all the road condition information to form a standard deviation array, calculating average value of the standard deviation array, and screening out road condition information types corresponding to all the accident characteristic standard deviations which are larger than the average value to serve as alternative road condition information types;
s2.4, calculating the total number Mq of the accidents in each row in the table corresponding to the alternative road condition information types, calculating the proportion G between the number of the accidents in each speed interval and the Mq, at least arranging the accidents from multiple speed intervals, screening a plurality of speed intervals in sequence until the sum of the proportions G in the screened speed intervals exceeds 50%, and marking the screened speed intervals and the corresponding road condition information types as accident characteristics;
and S2.5, marking the dangerous driving state as an accident characteristic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911350612.2A CN111009127B (en) | 2019-12-24 | 2019-12-24 | Urban dynamic early warning system and method based on accident risk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911350612.2A CN111009127B (en) | 2019-12-24 | 2019-12-24 | Urban dynamic early warning system and method based on accident risk |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111009127A CN111009127A (en) | 2020-04-14 |
| CN111009127B true CN111009127B (en) | 2021-06-01 |
Family
ID=70116241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911350612.2A Active CN111009127B (en) | 2019-12-24 | 2019-12-24 | Urban dynamic early warning system and method based on accident risk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111009127B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI810723B (en) * | 2021-11-01 | 2023-08-01 | 財團法人資訊工業策進會 | Warning system and method |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583638B (en) * | 2020-04-30 | 2021-08-31 | 长安大学 | Active triggering type multi-mode risk self-help correction and differentiation intervention method |
| CN111898878A (en) * | 2020-07-14 | 2020-11-06 | 扬州大学 | Vehicle risk space-time distribution analysis method based on early warning big data |
| CN111986464A (en) * | 2020-07-15 | 2020-11-24 | 遵义同望智能科技有限公司 | System for forecasting road icing based on dynamic method |
| CN112270836B (en) * | 2020-10-15 | 2023-11-21 | 腾讯科技（深圳）有限公司 | Traffic flow control method, device, equipment and storage medium |
| CN112598905B (en) * | 2020-12-14 | 2021-10-26 | 苏州智能交通信息科技股份有限公司 | Passenger flow dynamic analysis early warning method, system and storage medium |
| CN112885081A (en) * | 2021-01-11 | 2021-06-01 | 浙江海峡创新科技有限公司 | Urban emergency safety protection early warning system |
| CN113129461A (en) * | 2021-04-06 | 2021-07-16 | 深圳市沃特沃德信息有限公司 | Automatic charging method and device for highway section and computer equipment |
| CN113178052A (en) * | 2021-04-08 | 2021-07-27 | 甄十信息科技（上海）有限公司 | Method and wearable device for water falling alarm |
| CN113178082A (en) * | 2021-04-14 | 2021-07-27 | 河北锐驰交通工程咨询有限公司 | Intelligent identification method and system for safety risks of expressway |
| CN114187752B (en) * | 2022-02-14 | 2022-04-15 | 西南交通大学 | Early warning system and method for dangerous chemical vehicle in cross-sea bridge transportation |
| CN114627643B (en) * | 2022-02-28 | 2023-07-14 | 青岛海信网络科技股份有限公司 | Highway accident risk prediction method, device, equipment and medium |
| CN115171385B (en) * | 2022-07-06 | 2022-12-27 | 合肥雷能信息技术有限公司 | Traffic incident detection system based on millimeter wave radar and video linkage |
| CN116778733A (en) * | 2022-11-26 | 2023-09-19 | 武汉广旺科技有限公司 | Highway navigation voice early warning method and system based on big data |
| CN117995021A (en) * | 2024-04-07 | 2024-05-07 | 交通运输部公路科学研究所 | Vehicle safety early warning method and system based on multi-source data fusion algorithm |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105741590B (en) * | 2016-03-29 | 2018-09-07 | 福建工程学院 | The method and system of section early warning |
| CN106448149B (en) * | 2016-05-16 | 2019-08-09 | 江苏智通交通科技有限公司 | Road traffic accident method for early warning |
| KR101937085B1 (en) * | 2018-02-27 | 2019-01-09 | (주)체리네트웍스 | Safety monitoring system for Accident prevention of tower crane |
-
2019
- 2019-12-24 CN CN201911350612.2A patent/CN111009127B/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI810723B (en) * | 2021-11-01 | 2023-08-01 | 財團法人資訊工業策進會 | Warning system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111009127A (en) | 2020-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111009127B (en) | Urban dynamic early warning system and method based on accident risk | |
| CN106446926A (en) | Transformer station worker helmet wear detection method based on video analysis | |
| CN102164270A (en) | Intelligent video monitoring method and system capable of exploring abnormal events | |
| CN105744232A (en) | Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology | |
| CN103824420A (en) | Fatigue driving identification system based on heart rate variability non-contact measuring | |
| EP2747431B1 (en) | Device and method for detecting whether camera is interfered with, and video monitoring system | |
| CN102830404B (en) | Method for identifying laser imaging radar ground target based on range profile | |
| CN112437280A (en) | Intelligent monitoring security data processing management system based on big data analysis | |
| CN103700220A (en) | Fatigue driving monitoring device | |
| CN102193918A (en) | Video retrieval method and device | |
| CN106331605A (en) | Video-based flood detection device and method | |
| CN104123557A (en) | Method for detecting car safety belt fastening state based on road monitoring device | |
| CN106910334B (en) | Method and device for predicting road section conditions based on big data | |
| CN109272760B (en) | Online detection method for abnormal data value of SCATS system detector | |
| CN112580531B (en) | Identification detection method and system for true and false license plates | |
| CN112700473B (en) | Carriage congestion degree judging system based on image recognition | |
| CN210666820U (en) | Pedestrian abnormal behavior detection system based on DSP edge calculation | |
| CN103208010A (en) | Traffic state quantitative identification method based on visual features | |
| CN116778460A (en) | Fatigue driving identification method based on image identification | |
| CN116630891A (en) | Traffic abnormal event detection system and method | |
| CN110807444A (en) | Pedestrian abnormal behavior detection system and method based on DSP edge calculation | |
| CN114120250B (en) | Video-based motor vehicle illegal manned detection method | |
| CN104504713A (en) | Automatic trouble identification method based on TEDS (trouble of moving EMU detection system) | |
| CN111025288B (en) | Security radar monitoring device and system | |
| CN114387586A (en) | Driver concentration detection method based on YOLO neural network |
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 |