CN114239927A - Regional traffic accident early warning method and system based on deep learning - Google Patents

Regional traffic accident early warning method and system based on deep learning Download PDF

Info

Publication number
CN114239927A
CN114239927A CN202111438751.8A CN202111438751A CN114239927A CN 114239927 A CN114239927 A CN 114239927A CN 202111438751 A CN202111438751 A CN 202111438751A CN 114239927 A CN114239927 A CN 114239927A
Authority
CN
China
Prior art keywords
deep learning
accident
regional
traffic
vehicle
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.)
Withdrawn
Application number
CN202111438751.8A
Other languages
Chinese (zh)
Inventor
周显敬
刘虎
汪寒雨
黄银地
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Zhuoer Information Technology Co ltd
Original Assignee
Wuhan Zhuoer Information Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan Zhuoer Information Technology Co ltd filed Critical Wuhan Zhuoer Information Technology Co ltd
Priority to CN202111438751.8A priority Critical patent/CN114239927A/en
Publication of CN114239927A publication Critical patent/CN114239927A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G06Q50/265—Personal security, identity or safety
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
    • 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
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • 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
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Analytical Chemistry (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Chemical & Material Sciences (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Development Economics (AREA)
  • Mathematical Physics (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Educational Administration (AREA)
  • Probability & Statistics with Applications (AREA)
  • Emergency Management (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Security & Cryptography (AREA)

Abstract

The invention provides a regional traffic accident early warning method and system based on deep learning, wherein the method comprises the following steps: acquiring traffic accident occurrence sites within a historical period of time, and clustering the traffic accident occurrence sites based on a DBSCAN clustering algorithm to obtain regional traffic accident point clusters; extracting the characteristics of the regional traffic accidents, constructing a mapping relation between the characteristics of the traffic accidents and the accident types, and training a deep learning model based on a deep learning algorithm; and detecting regional traffic characteristic data, predicting vehicle accident risks through a deep learning model, and early warning corresponding vehicles. By the scheme, the regional vehicle risk can be predicted, the risk prompt is accurately carried out on regional drivers, and the traffic safety is guaranteed.

Description

Regional traffic accident early warning method and system based on deep learning
Technical Field
The invention relates to the field of traffic safety, in particular to a regional traffic accident early warning method and system based on deep learning.
Background
Generally, in a road section where a traffic accident occurs frequently, a map navigation system of a vehicle can perform voice reminding generally, and meanwhile, prompting can be performed on some extreme weather or traffic jam and other conditions. However, it is often difficult for such a common prompting method to alert the driver, and the occurrence of a safety accident is not substantially reduced.
Disclosure of Invention
In view of this, the embodiment of the invention provides a regional traffic accident early warning method and system based on deep learning, so as to solve the problem that the safety accidents are not reduced to a great extent in the existing early warning mode.
In a first aspect of the embodiments of the present invention, a regional traffic accident early warning method based on deep learning is provided, including:
acquiring traffic accident occurrence sites within a historical period of time, and clustering the traffic accident occurrence sites based on a DBSCAN clustering algorithm to obtain regional traffic accident point clusters;
extracting the characteristics of the regional traffic accidents, constructing a mapping relation between the characteristics of the traffic accidents and the accident types, and training a deep learning model based on a deep learning algorithm;
and detecting regional traffic characteristic data, predicting vehicle accident risks through a deep learning model, and early warning corresponding vehicles.
In a second aspect of the embodiments of the present invention, there is provided a regional traffic accident early warning system based on deep learning, including:
the data acquisition clustering module is used for acquiring traffic accident occurrence sites within a historical period of time, and clustering the traffic accident occurrence sites based on a DBSCAN clustering algorithm to obtain regional traffic accident point clusters;
the model training module is used for extracting the characteristics of the regional traffic accidents, constructing the mapping relation between the traffic accident characteristics and the accident types, and training the deep learning model based on a deep learning algorithm;
and the prediction early warning module is used for detecting regional traffic characteristic data, predicting vehicle accident risks through a deep learning model, and early warning corresponding vehicles.
In a third aspect of the embodiments of the present invention, there is provided an electronic device, which at least includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the method according to the first aspect of the embodiments of the present invention are implemented.
In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method provided in the first aspect of the embodiments of the present invention.
In the embodiment of the invention, the area accident frequently-occurring place is obtained by clustering the traffic accident occurrence points, and the early warning is carried out on the area vehicles through the deep learning model, so that the area vehicles can be monitored, predicted and early warned, the occurrence of the area traffic accidents can be effectively avoided, and the early warning prompt can be accurately carried out on the area drivers.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a regional traffic accident early warning method based on deep learning according to an embodiment of the present invention;
fig. 2 is another schematic flow chart of a regional traffic accident early warning method based on deep learning according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a deep learning-based regional traffic accident warning system according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below 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.
The terms "comprises" and "comprising," when used in this specification and claims, and in the accompanying drawings and figures, are intended to cover non-exclusive inclusions, such that a process, method or system, or apparatus that comprises a list of steps or elements is not limited to the listed steps or elements. In addition, "first" and "second" are used to distinguish different objects, and are not used to describe a specific order.
Referring to fig. 1, fig. 1 is a schematic flow chart of a regional traffic accident early warning method based on deep learning according to an embodiment of the present invention, including:
s101, acquiring traffic accident occurrence places in a historical period of time, and clustering the traffic accident occurrence places based on a DBSCAN clustering algorithm to obtain regional traffic accident point clusters;
and acquiring a historical accident occurrence place for a certain area or a certain line, such as a certain city or a highway. The historical data before the road surface condition or the geographic condition is greatly changed is deleted, and only the traffic accident data of which the road surface condition and the geographic condition are not changed is kept, such as the data before the change of lane change, the change of a crossroad into a T-shaped intersection, the change of straight running into turning and the like can be eliminated.
The traffic accident occurrence place can be not represented by latitude and longitude, and the accident occurrence place can be an approximate place within a certain accuracy range, and generally can be based on the position of the vehicle in collision and rollover.
A rough accident frequent region can be obtained by clustering the accident occurrence place, when the vehicle is in the region, state data can be collected, and the vehicle state can be monitored by a sensor carried by the vehicle or regional video monitoring.
The DBSCAN (sensitivity-Based Spatial Clustering of Applications with Noise) Clustering algorithm is a Density Clustering algorithm, and can divide high-Density areas into clusters. Based on density clustering, not only can the accident frequent place be determined, but also the correlation between the regional traffic environment and the accident can be analyzed and determined, and the deep learning model prediction is facilitated.
S102, extracting the characteristics of the regional traffic accidents, constructing a mapping relation between the characteristics of the traffic accidents and the accident types, and training a deep learning model based on a deep learning algorithm;
the method comprises the steps of extracting five dimensional characteristic data of weather, time intervals, space geographic environment, accident vehicle state and other vehicle state corresponding to traffic accidents.
Generally, the weather includes rainy days, foggy days, sunny days, snowing days and the like, the time periods are generally divided into morning time periods, afternoon time periods, evening time periods, night time periods and the like, the space ground environment includes traffic environments such as intersections, lane increase, lane reduction, lane merging, downhill slopes and uphill slopes, the self-vehicle state includes straight running, turning, lane changing, overtaking, accelerating, decelerating and the like, the information such as the speed and the course angle corresponding to the vehicle is also included, the other-vehicle state includes straight running, turning, lane changing and the like, and the other-vehicle speed, distance and the like are also included.
Specifically, the dimensional characteristic data of the traffic accident is represented by a numerical value, and a mapping matrix corresponding to the same type of traffic accident is constructed.
And (3) expressing the dimensional characteristics by specific numerical values, wherein in weather, 1 represents sunny days, 2 represents rainy days, 3 represents foggy days, and the like, so as to construct a mapping relation from a matrix to an accident type. The matrix also comprises numerical values corresponding to the characteristics, such as rainfall levels represented by 1, 2 and 3 in rainy days, and vehicle speeds with specific numerical values are corresponding to different states in the vehicle state.
The deep learning model comprises 5 convolutional layers, 5 anti-convolutional layers and 1 full-connection layer; the activation functions of the convolution layer and the deconvolution layer are tanh functions, and the activation function of the full-connection layer is a sigmoid function.
The deep learning model is trained and tested through historical traffic accident data to obtain a corresponding traffic accident prediction model, and accident prediction can be performed on input characteristic data.
S103, detecting regional traffic characteristic data, predicting vehicle accident risks through a deep learning model, and early warning corresponding vehicles.
The regional vehicle characteristics are monitored, vehicle state information is obtained, and accident prediction can be carried out through the model through networking query or automatic input due to the fact that the current weather, the time period and the regional space geographic environment characteristics are known.
The method comprises the steps of acquiring the real-time state of vehicles in a traffic accident point cluster region in real time through video monitoring, and predicting the accident risk of the vehicles in the region through a deep learning model by combining the characteristics of regional weather and geographic environment; and giving early warning prompt to the corresponding vehicle through regional traffic broadcast or a navigation map.
The method comprises the steps of obtaining the real-time state of a vehicle through a vehicle-mounted sensor, predicting the accident risk of the vehicle in a region through a deep learning model by combining the characteristics of regional weather and geographic environment, and carrying out early warning prompt through a voice system or a navigation map in the vehicle.
Specifically, as shown in fig. 2, when the vehicle state is monitored by the regional traffic monitoring camera, data collection and prediction need to be performed by the server, and a result is broadcasted by regional broadcasting or accessing a navigation map for prompting; when the state of the self vehicle and other vehicles is collected through the vehicle sensor, the vehicle end predicts the accident of the self vehicle according to the collected information, the weather acquired through networking and the current regional traffic environment characteristics, and when the accident risk is judged to exist, the voice system in the vehicle is used for broadcasting and prompting so as to take measures in advance to avoid the accident.
The method provided by the embodiment can be used for extracting and determining the places with multiple accidents, accurately and effectively prompting the corresponding safe operation of the driver through the accident risk prediction of the region, and can guarantee the driving safety of the vehicle.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, but should not constitute any limitation to the implementation process of the embodiments of the present invention,
fig. 3 is a schematic structural diagram of a regional traffic accident early warning system based on deep learning according to an embodiment of the present invention, where the system includes:
the data acquisition clustering module 310 is used for acquiring traffic accident occurrence sites within a historical period of time, and clustering the traffic accident occurrence sites based on a DBSCAN clustering algorithm to obtain regional traffic accident point clusters;
the model training module 320 is used for extracting the characteristics of the regional traffic accidents, constructing the mapping relation between the traffic accident characteristics and the accident types, and training a deep learning model based on a deep learning algorithm;
the method comprises the steps of extracting five dimensional characteristic data of weather, time intervals, space geographic environment, accident vehicle state and other vehicle state corresponding to traffic accidents.
Furthermore, the dimension characteristic data of the traffic accidents are represented through numerical values, and mapping matrixes corresponding to the same type of traffic accidents are constructed.
The deep learning model comprises 5 convolutional layers, 5 anti-convolutional layers and 1 full-connection layer; the activation functions of the convolution layer and the deconvolution layer are tanh functions, and the activation function of the full-connection layer is a sigmoid function.
And the prediction early warning module 330 is used for detecting regional traffic characteristic data, predicting vehicle accident risks through a deep learning model, and early warning corresponding vehicles.
Optionally, the real-time state of the vehicles in the traffic accident point cluster region is obtained in real time through video monitoring, and the accident risk of the vehicles in the region is predicted through a deep learning model by combining the characteristics of regional weather and geographic environment; and giving early warning prompt to the corresponding vehicle through regional traffic broadcast or a navigation map.
Optionally, the real-time state of the vehicle is acquired through the vehicle-mounted sensor, the regional vehicle accident risk is predicted through the deep learning model by combining regional weather and geographic environment characteristics, and early warning prompt is carried out through an in-vehicle voice system or a navigation map.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the module described above may refer to corresponding processes in the foregoing method embodiments, and are not described herein again.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic equipment is used for predicting and early warning regional traffic accidents. As shown in fig. 4, the electronic apparatus 4 of this embodiment includes: a memory 410, a processor 420, and a system bus 430, the memory 410 including an executable program 4101 stored thereon, it being understood by those skilled in the art that the electronic device configuration shown in fig. 4 does not constitute a limitation of electronic devices and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
The following describes each component of the electronic device in detail with reference to fig. 4:
the memory 410 may be used to store software programs and modules, and the processor 420 executes various functional applications and data processing of the electronic device by operating the software programs and modules stored in the memory 410. The memory 410 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as cache data) created according to the use of the electronic device, and the like. Further, the memory 410 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
An executable program 4101 of a signboard extraction method is contained on a memory 410, the executable program 4101 can be divided into one or more modules/units, the one or more modules/units are stored in the memory 410 and executed by a processor 420 to realize prediction and early warning of regional vehicle traffic accident risk, etc., and the one or more modules/units can be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used for describing the execution process of the computer program 4101 in the electronic device 4. For example, the computer program 4101 may be segmented into a data collection clustering module, a model training module, and a predictive alert module.
The processor 420 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, performs various functions of the electronic device and processes data by operating or executing software programs and/or modules stored in the memory 410 and calling data stored in the memory 410, thereby performing overall status monitoring of the electronic device. Alternatively, processor 420 may include one or more processing units; preferably, the processor 420 may integrate an application processor, which mainly handles operating systems, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 420.
The system bus 430 is used to connect functional units inside the computer, and can transmit data information, address information, and control information, and may be, for example, a PCI bus, an ISA bus, a VESA bus, etc. The instructions of the processor 420 are transmitted to the memory 410 through the bus, the memory 410 feeds data back to the processor 420, and the system bus 430 is responsible for data and instruction interaction between the processor 420 and the memory 410. Of course, the system bus 430 may also access other devices such as network interfaces, display devices, and the like.
In this embodiment of the present invention, the executable program executed by the process 420 included in the electronic device includes:
acquiring traffic accident occurrence sites within a historical period of time, and clustering the traffic accident occurrence sites based on a DBSCAN clustering algorithm to obtain regional traffic accident point clusters;
extracting the characteristics of the regional traffic accidents, constructing a mapping relation between the characteristics of the traffic accidents and the accident types, and training a deep learning model based on a deep learning algorithm;
and detecting regional traffic characteristic data, predicting vehicle accident risks through a deep learning model, and early warning corresponding vehicles.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A regional traffic accident early warning method based on deep learning is characterized by comprising the following steps:
acquiring traffic accident occurrence sites within a historical period of time, and clustering the traffic accident occurrence sites based on a DBSCAN clustering algorithm to obtain regional traffic accident point clusters;
extracting the characteristics of the regional traffic accidents, constructing a mapping relation between the characteristics of the traffic accidents and the accident types, and training a deep learning model based on a deep learning algorithm;
and detecting regional traffic characteristic data, predicting vehicle accident risks through a deep learning model, and early warning corresponding vehicles.
2. The method of claim 1, wherein the characterizing regional traffic accidents comprises:
and extracting five dimensional characteristic data of weather, time interval, space geographic environment, accident vehicle state and other vehicle state corresponding to the traffic accident.
3. The method of claim 1, wherein constructing a mapping of traffic accident characteristics to accident types comprises:
and representing the dimension characteristic data of the traffic accidents through numerical values, and constructing a mapping matrix corresponding to the same type of traffic accidents.
4. The method of claim 1, wherein the deep learning model comprises 5 convolutional layers, 5 anti-convolutional layers, and 1 fully-connected layer;
the activation functions of the convolution layer and the deconvolution layer are tanh functions, and the activation function of the full-connection layer is a sigmoid function.
5. The method of claim 1, wherein the detecting regional traffic characteristic data, predicting vehicle accident risk through a deep learning model, and pre-warning a corresponding vehicle comprises:
the real-time state of vehicles in a traffic accident point cluster region is obtained in real time through video monitoring, and the risk of vehicle accidents in the region is predicted through a deep learning model by combining the characteristics of regional weather and geographic environment;
and giving early warning prompt to the corresponding vehicle through regional traffic broadcast or a navigation map.
6. The method of claim 1, wherein the detecting regional traffic characteristic data, predicting vehicle accident risk through a deep learning model, and pre-warning a corresponding vehicle comprises:
the real-time state of the vehicle is acquired through the vehicle-mounted sensor, the regional vehicle accident risk is predicted through the deep learning model by combining regional weather and geographic environment characteristics, and early warning prompt is carried out through an in-vehicle voice system or a navigation map.
7. A regional traffic accident early warning system based on deep learning is characterized by comprising:
the data acquisition clustering module is used for acquiring traffic accident occurrence sites within a historical period of time, and clustering the traffic accident occurrence sites based on a DBSCAN clustering algorithm to obtain regional traffic accident point clusters;
the model training module is used for extracting the characteristics of the regional traffic accidents, constructing the mapping relation between the traffic accident characteristics and the accident types, and training the deep learning model based on a deep learning algorithm;
and the prediction early warning module is used for detecting regional traffic characteristic data, predicting vehicle accident risks through a deep learning model, and early warning corresponding vehicles.
8. The system of claim 7, wherein the characterizing regional traffic accidents comprises:
and extracting five dimensional characteristic data of weather, time interval, space geographic environment, accident vehicle state and other vehicle state corresponding to the traffic accident.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of a deep learning based regional traffic accident warning method according to any one of claims 1 to 6.
10. A computer-readable storage medium storing a computer program, wherein the computer program is configured to implement the steps of the deep learning-based regional traffic accident warning method according to any one of claims 1 to 6 when executed.
CN202111438751.8A 2021-11-25 2021-11-25 Regional traffic accident early warning method and system based on deep learning Withdrawn CN114239927A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111438751.8A CN114239927A (en) 2021-11-25 2021-11-25 Regional traffic accident early warning method and system based on deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111438751.8A CN114239927A (en) 2021-11-25 2021-11-25 Regional traffic accident early warning method and system based on deep learning

Publications (1)

Publication Number Publication Date
CN114239927A true CN114239927A (en) 2022-03-25

Family

ID=80752046

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111438751.8A Withdrawn CN114239927A (en) 2021-11-25 2021-11-25 Regional traffic accident early warning method and system based on deep learning

Country Status (1)

Country Link
CN (1) CN114239927A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115240408A (en) * 2022-06-15 2022-10-25 中国第一汽车股份有限公司 Vehicle accident early warning method and system based on block chain technology, electronic device and storage medium
CN116403403A (en) * 2023-04-12 2023-07-07 西藏金采科技股份有限公司 Traffic early warning method, system, equipment and medium based on big data analysis
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
CN117609867A (en) * 2024-01-17 2024-02-27 北京全路通信信号研究设计院集团有限公司 Regional track traffic safety grade determining method, device, equipment and medium
CN116030627B (en) * 2022-12-31 2024-04-30 东南大学 Road traffic accident analysis method integrating predicted traffic risk variables

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115240408A (en) * 2022-06-15 2022-10-25 中国第一汽车股份有限公司 Vehicle accident early warning method and system based on block chain technology, electronic device and storage medium
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
CN116030627B (en) * 2022-12-31 2024-04-30 东南大学 Road traffic accident analysis method integrating predicted traffic risk variables
CN116403403A (en) * 2023-04-12 2023-07-07 西藏金采科技股份有限公司 Traffic early warning method, system, equipment and medium based on big data analysis
CN116403403B (en) * 2023-04-12 2024-02-02 西藏金采科技股份有限公司 Traffic early warning method, system, equipment and medium based on big data analysis
CN117609867A (en) * 2024-01-17 2024-02-27 北京全路通信信号研究设计院集团有限公司 Regional track traffic safety grade determining method, device, equipment and medium

Similar Documents

Publication Publication Date Title
CN114239927A (en) Regional traffic accident early warning method and system based on deep learning
US10451425B2 (en) Autonomous navigation system
CN111354187B (en) Method for assisting a driver of a vehicle and driver assistance system
US9165477B2 (en) Systems and methods for building road models, driver models, and vehicle models and making predictions therefrom
US6995663B2 (en) Driving workload estimation
US8688369B2 (en) Data mining in a digital map database to identify blind intersections along roads and enabling precautionary actions in a vehicle
CN107389085B (en) Method and device for determining road traffic attributes, computer and storage medium
US11170639B2 (en) Transportation threat detection system
DE102018131646A1 (en) DRIVER WARNING SYSTEMS AND METHOD
DE102019114595B4 (en) Method for controlling the operation of a motor vehicle and for deriving road segment speed limits
CN111464972A (en) Prioritized vehicle messaging
CN112785835A (en) Method and device for acquiring road condition information and vehicle-mounted device
DE102015223656A1 (en) Driver assistance system and method for lane recommendation
EP4141816A1 (en) Scene security level determination method, device and storage medium
JP2023067970A (en) Information processor
JP2024530216A (en) SYSTEM AND METHOD FOR MONITORING A VEHICLE - Patent application
CN116434523A (en) Vehicle active safety control method and device based on constraint degree in information perception scene
DE102015222033A1 (en) Method and device for analyzing a driving style of a driver of a vehicle
CN117195065A (en) Driving assistance method, driving assistance device, vehicle, electronic device and storage medium
CN114274980B (en) Track control method, track control device, vehicle and storage medium
CN111483463B (en) Vehicle-mounted unit and road side unit based pre-judging overtaking method and storage medium
CN116264034A (en) Dangerous road section identification method and device, edge side platform and road side equipment
CN113160567A (en) Vehicle driving assistance method, device, vehicle, server and storage medium
EP4282723A1 (en) Method and apparatus for determining vehicle speed control model training sample
CN115114729B (en) Design method of driving assistance system user case and storage medium

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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20220325