CN113296713A - Accident rating model and method for optimizing storage space of automobile data recorder - Google Patents

Accident rating model and method for optimizing storage space of automobile data recorder Download PDF

Info

Publication number
CN113296713A
CN113296713A CN202110665353.3A CN202110665353A CN113296713A CN 113296713 A CN113296713 A CN 113296713A CN 202110665353 A CN202110665353 A CN 202110665353A CN 113296713 A CN113296713 A CN 113296713A
Authority
CN
China
Prior art keywords
data
road
storage space
grade
accident
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Withdrawn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
CN202110665353.3A
Other languages
Chinese (zh)
Inventor
沈梦娜
乔宏哲
包林霞
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.)
Changzhou Vocational Institute of Mechatronic Technology
Original Assignee
Changzhou Vocational Institute of Mechatronic Technology
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 Changzhou Vocational Institute of Mechatronic Technology filed Critical Changzhou Vocational Institute of Mechatronic Technology
Priority to CN202110665353.3A priority Critical patent/CN113296713A/en
Publication of CN113296713A publication Critical patent/CN113296713A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0604—Improving or facilitating administration, e.g. storage management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0608—Saving storage space on storage systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0614—Improving the reliability of storage systems
    • 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
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention belongs to the technical field of automobiles, and particularly relates to a vehicle event data recorder system and a storage space optimizing method. The method comprises the following steps: step S1, obtaining historical traffic flow data, historical traffic flow type data, road attributes and accident conditions through road video monitoring, and dividing traffic flow grades, vehicle complexity grades and road grades of each road section in each time period; step S2, constructing an accident rating model according to the traffic flow grade, the vehicle complexity grade and the road grade of each road section in each time period; step S3, acquiring vehicle and road information of the current road section, and calculating a current road section risk index D according to the accident rating model; and step S4, obtaining the storage space of the corresponding video data according to the current road section risk degree index D. The invention divides the storage space according to the risk index, optimizes the storage method and avoids the problems that the memory card is full frequently and the newly recorded video data can cover the original video data when the cyclic recording is adopted.

Description

Accident rating model and method for optimizing storage space of automobile data recorder
Technical Field
The invention belongs to the technical field of automobiles, and particularly relates to an accident rating model and method for optimizing a storage space of a vehicle event data recorder.
Background
The automobile data recorder has a plurality of functions of recording videos, sounds and the like during the driving of the automobile, and can provide a driver with a plurality of convenience. The fact that the storage card is full is a problem existing in many automobile data recorders, and the storage space is insufficient, so that the automobile data recorders cannot normally record automobile images. The main methods for solving the problems at present are as follows: the mode of the automobile data recorder is changed into circular recording, so that the newly recorded video data can cover all the original video data, and the situation of insufficient capacity of the memory card can be avoided due to continuous circulation. The disadvantage of this method is that if the original video is not saved in time and the new video covers the original video, the original important video data will be lost.
Based on the above problems, an accident rating model and method for optimizing the storage space of the automobile data recorder are needed.
Disclosure of Invention
The invention aims to provide an accident rating model and method for optimizing storage space of an automobile data recorder, which are used for dividing storage spaces with different sizes according to road conditions so as to solve the problem that the automobile data recorder is always full of storage cards.
In order to solve the above technical problem, the present invention provides an accident rating model for optimizing a storage space method, including:
Figure BDA0003117136240000011
wherein ZC＝w*xCW is the normal vector of the optimal classification hyperplane, xCFor the road section data vector, mu, of the algorithm model to be constructedAData mean, mu, obtained by projection of the data without occurrence of an accident on a normal vector wBThe mean of the data obtained after the normal vector w projection for the accident data.
Furthermore, the normal vector w of the optimal classification hyperplane is calculated by the following method,
Figure BDA0003117136240000021
the muAIs calculated by
Figure BDA0003117136240000022
The muBIs calculated by
Figure BDA0003117136240000023
The above-mentioned
Figure BDA0003117136240000024
xiFor training ith data vector x ═ x (x)(1),x(2),x(3))，x(1)Is the traffic class, x(1)＝1、2……5；x(2)For the vehicle complexity level, x(2)＝1、2……5；x(3)Is road grade, x(3)＝1、2……5；yiIs corresponding to xiWhether accidents occur is marked, wherein the accidents which do not occur are marked as 1, the accidents which occur are marked as-1, and N is the number of training data; alpha is alphai *The ith element which is a solution to the dual problem in the Lagrangian multiplier vector; n is the number of training data, NAIs a category yiNumber of samples equal to 1, NBIs a category yiThe number of samples is-1.
In another aspect, the present invention provides a method for optimizing storage space for a vehicle event data recorder, comprising the following steps:
step S1, obtaining historical traffic flow data, historical traffic flow type data, road attributes and accident conditions through road video monitoring, and dividing traffic flow grades, vehicle complexity grades and road grades of each road section in each time period;
step S2, constructing the accident rating model according to the traffic flow grade, the vehicle complexity grade and the road grade of each time segment of each road section;
step S3, acquiring vehicle and road information of the current road section, and calculating a current road section risk index D according to the accident rating model;
and step S4, obtaining the storage space of the corresponding video data according to the current road section risk degree index D.
Further, the method for constructing the accident rating model of the road segment time period in the step S2 includes:
step S21, step S21, according to the historical traffic flow rate grade as x(1)Vehicle complexity class x(2)Road grade x(3)Establishing a data vector x ═ x(1),x(2),x(3))；
In step S22, a coefficient vector w is created (w ═ w(1)，w(2)，w(3))，w(j)For the corresponding feature x(j)The value of j is 1, 2 and 3;
step S23, using soft space SVM to solve the classification hyperplane with the maximum geometric space and the normal vector thereof, and expressing the problem as the constrained optimization problem
Figure BDA0003117136240000031
S.t yi(w.xi+b)≥1-ξi
ξi≥0i＝1，2，...N
Wherein, C is a penalty coefficient and takes a value of 0.9; xi is a relaxation variable; xiiRelaxation variables for the ith training data; b is an offset; by converting the original problem into a dual problem, solving the optimal solution of the dual problem by using a KKT condition, the optimal solution of the optimal classification hyperplane and a coefficient vector can be obtained, namely the normal vector of the optimal classification hyperplane:
Figure BDA0003117136240000032
αi *the i-th element, x, of the solution to the dual problem in the Lagrangian multiplier vectoriFor the ith training data vector, yiIs corresponding to xiWhether accidents occur is marked, wherein the accidents which do not occur are marked as 1, the accidents which occur are marked as-1, and N is the number of training data;
step S24, the data mean value obtained by the projection of the data without accident on the normal vector w
Figure BDA0003117136240000033
Data of accident in normal vector wMean of data obtained after projection
Figure BDA0003117136240000034
Figure BDA0003117136240000035
Wherein N isAIs a category yiNumber of samples equal to 1, NBIs a category yi-1 sample number;
in the step of S25,
Figure BDA0003117136240000041
ZC＝w*xC，xCand the time section data vector is the current road section.
Further, in step S3, the method for acquiring the vehicle information of the current road segment includes:
and acquiring the current position coordinates and the corresponding road sections through the GPS, and inquiring the corresponding traffic flow grade, the vehicle complexity grade and the road grade on the cloud server.
Further, the method for obtaining the storage space of the corresponding video data according to the current road segment risk index D in step S4 includes: setting a threshold value K; when D is larger than or equal to K, the automobile data recorder adopts the camera module to record in high resolution; when D is less than K, the automobile data recorder adopts low-resolution recording; and distributing the storage space of the corresponding video data according to the high resolution and the low resolution.
The method has the advantages that the historical traffic flow data, the historical traffic flow category data, the road attributes and the accident situation are obtained through road video monitoring to divide the traffic flow grade, the vehicle complexity grade and the road grade of each road section in each time period, the accident rating model is constructed through the traffic flow grade, the vehicle complexity grade and the road grade, the road section danger index is calculated through the accident rating model, the storage space is divided according to the danger index, the storage method is optimized, and the problems that a memory card is full frequently and newly recorded video data can cover original video data when circular recording is adopted are solved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method of optimizing memory space of the present invention;
fig. 2 is a flowchart of the sub-steps of step S2 in fig. 1.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. 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.
Examples
As shown in fig. 1, this embodiment 1 provides a method for optimizing a storage space for a vehicle event data recorder, which may include: step S1, obtaining historical traffic flow data, historical traffic flow type data, road attributes and accident conditions through road video monitoring, and dividing traffic flow grades, vehicle complexity grades and road grades of each road section in each time period; step S2, constructing an accident rating model according to the traffic flow grade, the vehicle complexity grade and the road grade of each road section in each time period; step S3, acquiring vehicle information of the current road section, and calculating a current road section risk index D according to the accident rating model; and step S4, obtaining the storage space of the corresponding video data according to the current road section risk degree index D. The method for optimizing the storage space provided by the embodiment can realize the optimization of the storage space and simultaneously avoid the loss of data.
As shown in fig. 2, in the present example, the method of constructing the accident rating model for the link time period at step S2 includes:
step S21, traffic flow data and traffic flow type data in each hour time period are obtained according to video monitoring, and traffic flow grades are divided into x according to historical traffic flow data(1)，x(1)1, 2 … … 5; dividing the complexity level of the vehicle into x according to the historical traffic flow category data(2)，x(2)1, 2 … … 5; classifying the road grade as x according to the road attribute(3)，x(3)1, 2 … … 5, optional, x(3)The value can be 1, 2, 3 and 4 on the first-level, second-level, third-level and fourth-level roads and 5 on the expressway according to the technical standard of highway engineering in China. Establish data vector x ═ x(1),x(2),x(3))；
In step S22, a coefficient vector w is created (w ═ w(1)，w(2)，w(3))，w(j)For the corresponding feature x(j)The value of j is 1, 2 and 3;
step S23, using soft space SVM to solve the classification hyperplane with the maximum geometric space, and expressing the problem as a constraint optimization problem
Figure BDA0003117136240000061
S.t yi(w.xi+b)≥1-ξi
ξi≥0i＝1，2，...N；
Wherein C is a penalty coefficient; xi is a relaxation variable; xiiRelaxation variables for the ith training data; b is an offset; by converting the original problem into a dual problem, solving the optimal solution of the dual problem by using a KKT condition, namely a Carrocon-Kuen-Tack condition, the optimal solution of the optimal classification hyperplane and a coefficient vector can be solved, namely the normal vector of the optimal classification hyperplane:
Figure BDA0003117136240000062
αi *the i-th element, x, of the solution to the dual problem in the Lagrangian multiplier vectoriFor the ith training data vector, yiIs corresponding to xiWhether accidents occur is marked, wherein the accidents which do not occur are marked as 1, the accidents which occur are marked as-1, and N is the number of training data;
step S24, the data mean value obtained by the projection of the data without accident on the normal vector w
Figure BDA0003117136240000071
Mean value of data obtained after projection of accident data on normal vector w
Figure BDA0003117136240000072
Figure BDA0003117136240000073
Wherein N isAIs a category yiNumber of samples equal to 1, NBIs a category yiThe number of samples is-1.
In the step of S25,
Figure BDA0003117136240000074
in the present embodiment, in order to obtain more timely information, the method of acquiring the vehicle information of the current link in step S3 is: and acquiring the current position coordinates and the corresponding road sections through the GPS, and inquiring the corresponding traffic flow grade, the vehicle complexity grade and the road grade on the cloud server.
In this embodiment, in order to store videos as needed, the method of obtaining a storage space of corresponding video data according to the current link risk degree index D in S4 includes: setting a threshold value K; when D is larger than or equal to K, the automobile data recorder adopts the camera module to record in high resolution; and when D is less than K, the automobile data recorder adopts low-resolution recording. A
In summary, in the embodiment, an accident rating model is constructed through the historical traffic flow data, the historical traffic flow category data, the road attributes and the accident situation, the current road risk index is calculated through the accident rating model, and the resolution is selected according to the comparison result between the risk index and the threshold, so that the storage space can be effectively optimized.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.

Claims (6)

1. An event rating model for tachograph storage space optimization, comprising:
Figure FDA0003117136230000011
wherein
D is a risk index, the value range is 0-1, and the larger the D value is, the higher the accident probability is;
ZC＝w*xCw is the normal vector of the optimal classification hyperplane, xCThe road section data vector of the algorithm model to be constructed is obtained;
μAobtaining a data mean value by projecting the data without accidents on a normal vector w; and
μBthe mean of the data obtained after the normal vector w projection for the accident data.
2. The incident rating model of claim 1,
the normal vector
Figure FDA0003117136230000012
Figure FDA0003117136230000013
Figure FDA0003117136230000014
Wherein
Figure FDA0003117136230000015
And
xifor training ith data vector x ═ x (x)(1),x(2),x(3))，x(1)Is the traffic class, x(1)＝1、2……5；x(2)For the vehicle complexity level, x(2)＝1、2……5；x(3)Is road grade, x(3)＝1、2……5；
yiIs corresponding to xiWhether accidents occur is marked, wherein the accidents which do not occur are marked as 1, the accidents which occur are marked as-1, and N is the number of training data;
αi *the ith element which is a solution to the dual problem in the Lagrangian multiplier vector;
n is the number of training data, NAIs a category yiNumber of samples equal to 1, NBIs a category yiThe number of samples is-1.
3. A method for optimizing the storage space of a vehicle event data recorder is characterized by comprising the following steps:
step S1, obtaining historical traffic flow data, historical traffic flow type data, road attributes and accident conditions through road video monitoring, and dividing traffic flow grades, vehicle complexity grades and road grades of each road section in each time period;
step S2, constructing an accident rating model according to the traffic flow grade, the vehicle complexity grade and the road grade of each road section in each time period;
step S3, acquiring vehicle and road information of the current road section, and calculating a current road section risk index D according to the accident rating model;
and step S4, obtaining the storage space of the corresponding video data according to the current road section risk degree index D.
4. A method for optimizing storage space according to claim 3, wherein the method for constructing the accident rating model in step S2 comprises:
step S21, according to the historical traffic flow rate grade as x(1)Vehicle complexity class x(2)Road grade x(3)Establishing a data vector x ═ x(1),x(2),x(3))；
In step S22, a coefficient vector w is created (w ═ w(1)，w(2)，w(3))，w(j)For the corresponding feature x(j)The value of j is 1, 2 and 3;
step S23, using soft space SVM to calculate the classification hyperplane with the maximum geometric space and the normal vector thereof,
Figure FDA0003117136230000021
Figure FDA0003117136230000022
wherein, C is a penalty coefficient and takes a value of 0.9; xi is a relaxation variable; xiiRelaxation variables for the ith training data; b is an offset; by converting the original problem into a dual problemSolving the optimal solution of the dual problem by using the KKT condition to obtain the optimal solution of the optimal classification hyperplane and the coefficient vector, namely the normal vector of the optimal classification hyperplane:
Figure FDA0003117136230000023
αi *the i-th element, x, of the solution to the dual problem in the Lagrangian multiplier vectoriFor the ith training data vector, yiIs corresponding to xiWhether accidents occur is marked, wherein the accidents which do not occur are marked as 1, the accidents which occur are marked as-1, and N is the number of training data;
step S24, the data mean value obtained by the projection of the data without accident on the normal vector w
Figure FDA0003117136230000031
Mean value of data obtained after projection of accident data on normal vector w
Figure FDA0003117136230000032
Figure FDA0003117136230000033
Wherein N isAIs a category yiNumber of samples equal to 1, NBIs a category yiThe number of samples is-1.
In the step of S25,
Figure FDA0003117136230000034
ZC＝w*xC，xCand the time section data vector is the current road section.
5. The method for optimizing storage space according to claim 3, wherein the method for obtaining the vehicle information of the current road segment in the step S3 is:
and acquiring the current position coordinates and the corresponding road sections through the GPS, and inquiring the corresponding traffic flow grade, the vehicle complexity grade and the road grade on the cloud server.
6. The method for optimizing storage space according to claim 3, wherein the method for obtaining the storage space of the corresponding video data according to the current road segment risk degree index D in the step S4 comprises:
setting a threshold value K;
when D is larger than or equal to K, the automobile data recorder adopts the camera module to record in high resolution;
when D is less than K, the automobile data recorder adopts low-resolution recording;
and distributing the storage space of the corresponding video data according to the high resolution and the low resolution.
CN202110665353.3A 2021-06-16 2021-06-16 Accident rating model and method for optimizing storage space of automobile data recorder Withdrawn CN113296713A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110665353.3A CN113296713A (en) 2021-06-16 2021-06-16 Accident rating model and method for optimizing storage space of automobile data recorder

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110665353.3A CN113296713A (en) 2021-06-16 2021-06-16 Accident rating model and method for optimizing storage space of automobile data recorder

Publications (1)

Publication Number Publication Date
CN113296713A true CN113296713A (en) 2021-08-24

Family

ID=77328313

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110665353.3A Withdrawn CN113296713A (en) 2021-06-16 2021-06-16 Accident rating model and method for optimizing storage space of automobile data recorder

Country Status (1)

Country Link
CN (1) CN113296713A (en)

Similar Documents

Publication Publication Date Title
US20200164891A1 (en) Intelligent vehicle action decisions
US20200134735A1 (en) Enhancement using analytics based on vehicle kinematic data
US10852150B2 (en) Methods and apparatuses for fuel consumption prediction
CN111340026B (en) Training method of vehicle annual payment identification model and vehicle annual payment identification method
CN115080638B (en) Multi-source data fusion analysis method for microscopic simulation, electronic equipment and storage medium
JP2017071333A (en) Drive assisting device
CN109379563B (en) Method and system for monitoring video data storage management
CN112733047B (en) Vehicle foothold generation method, device, equipment and computer storage medium
CN118196573A (en) Vehicle detection method and system based on deep learning
CN113296713A (en) Accident rating model and method for optimizing storage space of automobile data recorder
CN103116986A (en) Vehicle identification method
CN118425917A (en) System for identifying and auditing railway assets and system for auditing railway assets
CN114492544B (en) Model training method and device and traffic incident occurrence probability evaluation method and device
CN113393593A (en) Non-replaceable memory-saving driving recording system
US11507286B2 (en) Performing storage provision operations on a file system
CN112016534B (en) Neural network training method for vehicle parking violation detection, detection method and device
Alemazkoor et al. Efficient collection of connected vehicles data with precision guarantees
CN114118230A (en) Method and system for identifying congestion of bottleneck road section of expressway based on end edge cloud fusion
CN113592341A (en) Measurement loss function, sector complexity evaluation method and system
CN118629216B (en) Road target identification method and system based on radar fusion
CN112277958B (en) Driver braking behavior analysis method
CN114973693B (en) Vehicle queuing length calculation method, computer equipment and computer storage medium
Milardo et al. An unsupervised approach for driving behavior analysis of professional truck drivers
CN116225323A (en) Data storage method and device
CN116994213A (en) Vehicle identification method, apparatus, device, storage medium, and program product

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: 20210824