CN108399752A - A kind of driving infractions pre-judging method, device, server and medium - Google Patents
A kind of driving infractions pre-judging method, device, server and medium Download PDFInfo
- Publication number
- CN108399752A CN108399752A CN201810400364.7A CN201810400364A CN108399752A CN 108399752 A CN108399752 A CN 108399752A CN 201810400364 A CN201810400364 A CN 201810400364A CN 108399752 A CN108399752 A CN 108399752A
- Authority
- CN
- China
- Prior art keywords
- regulations
- violating
- vehicle
- image
- time point
- 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.)
- Pending
Links
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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention discloses a kind of driving infractions pre-judging method, device, server and media.Wherein, method includes:The video captured by the rear camera of vehicle launch is obtained, and parses video is obtained with vehicle travels each time point corresponding image;Each image is input to anticipation model violating the regulations trained in advance and determines the target image for having motoring offence;The probability violating the regulations of vehicle is determined according to target image and navigation data.The embodiment of the present invention obtains picture corresponding with time point by the video during parsing vehicle driving, and judge whether the picture is the Target Photo for having motoring offence through anticipation model violating the regulations, the probability violating the regulations of vehicle is determined according to Target Photo and navigation data, solve the problems, such as that existing navigation device and automobile data recorder can not judge whether vehicle has act of violating regulations, driver can be made to predefine whether oneself act of violating regulations is occurring and the address of act of violating regulations occurring on the run, to assist user's civilization to drive.
Description
Technical field
The present embodiments relate to artificial intelligence technology more particularly to a kind of driving infractions pre-judging method, device, servers
And medium.
Background technology
In the prior art, the navigation softwares such as Baidu map, Google Maps or Amap can provide to the user
A variety of path plannings are selected, if user wants to go home from company, then navigation software can be according to Origin And Destination information, vehicle
Flow, car plate restricted driving region provide one either with or without information such as camera probes it considers that the road conditions optimized.In addition, usual vehicle
It is upper generally all to fill an automobile data recorder, prevent blackmail or record landscape, also reverse image etc. function.
But general driver drive when, can not determine line oneself whether is compacted in driving procedure, rush it is red
Whether lamp or violating the regulations, do not know oneself to have broken rules and regulations to be photographed, navigation software or automobile data recorder cannot all provide one really yet
Fixed answer.
Invention content
A kind of driving infractions pre-judging method of offer of the embodiment of the present invention, device, server and medium, can make driver advance
Determine whether oneself act of violating regulations is occurring and the address of act of violating regulations occurring on the run, to instruct later driving row
For.
In a first aspect, an embodiment of the present invention provides a kind of driving infractions pre-judging method, this method includes:
The video captured by the rear camera of vehicle launch is obtained, and parses what the video obtained travelling with the vehicle
Each time point corresponding image;
Each image is input to anticipation model violating the regulations trained in advance and determines the target image for having motoring offence;
The probability violating the regulations of the vehicle is determined according to the target image and navigation data.
Second aspect, the embodiment of the present invention additionally provide driving infractions anticipation device, which includes:
Vehicle travels image collection module, for obtaining the video captured by the rear camera of vehicle launch, and parses institute
State video is obtained with the vehicle travels each time point corresponding image;
Target image determining module, for by each image be input to trained anticipation model violating the regulations in advance determine have it is violating the regulations
The target image of driving behavior;
Probability determination module violating the regulations, for determining the violating the regulations general of the vehicle according to the target image and navigation data
Rate.
The third aspect, the embodiment of the present invention additionally provide a kind of server, which includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors so that one or more of processing
Device realizes the driving infractions pre-judging method as described in any in the embodiment of the present invention.
Fourth aspect, the embodiment of the present invention additionally provide a kind of computer readable storage medium, are stored thereon with computer
Program realizes the driving infractions pre-judging method as described in any in the embodiment of the present invention when program is executed by processor.
The embodiment of the present invention obtains picture corresponding with time point by the video during parsing vehicle driving, and passes through
Anticipation model violating the regulations judges whether the picture is the Target Photo for having motoring offence, true according to Target Photo and navigation data
The probability violating the regulations for determining vehicle, solving existing navigation device and automobile data recorder can not judge whether vehicle has act of violating regulations
Problem can make driver predefine whether oneself act of violating regulations is occurring and the ground of act of violating regulations occurring on the run
Location, to instruct later driving behavior.
Description of the drawings
Fig. 1 is the flow chart of the driving infractions pre-judging method in the embodiment of the present invention one;
Fig. 2 is the structural schematic diagram of the driving infractions anticipation device in the embodiment of the present invention two;
Fig. 3 is the structural schematic diagram of the server in the embodiment of the present invention three.
Specific implementation mode
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limitation of the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the flow chart for the driving infractions pre-judging method that the embodiment of the present invention one provides, and the present embodiment is applicable to sentence
Whether there are the case where act of violating regulations, this method that can be executed by driving infractions anticipation device in disconnected driving procedure, the device example
Such as it is configured in server.As shown in Figure 1, this method specifically includes:
S110, video captured by the rear camera of vehicle launch is obtained, and parses the video and obtain and the vehicle
The corresponding image of each time point of traveling.
In order to be best understood from outside vehicle situation, can at least one camera be installed on vehicle.Can be specifically
The camera of head end and/or tail end the installation record driving condition of vehicle, with shoot in vehicle travel process vehicle front and/or
The video image of rear road conditions.It is understood that in this operation, camera that vehicle is installed can be obtained in vehicle row
Captured video during sailing, as long as the external environment image in the driving process of vehicle can be understood, herein not
It limits, such as can be captured by other cameras such as the automobile data recorder that vehicle is self-contained or the later stage voluntarily installs
Video.
In driving procedure, in order to which preferably programme path generally can also provide navigation data by means of navigation device, with
Prompt user's driving path simultaneously confirms the place that there is camera device violating the regulations in traffic route and driving process.
In one embodiment, the video council captured by camera with it is preset when a length of node upload onto the server,
Such as every two minutes upload primary videos or every five minutes primary, the processing capacities and parsing that specific duration can be according to server
Efficiency determines.After server receives first video, parsing video will be started and obtain the time point phase travelled with vehicle
Corresponding image, the image such as shot at 05 seconds 10 minutes at 9 points in the morning, the position that vehicle is driven to, the image can wrap
Containing road information, the information of vehicles etc. in vehicle forward direction.If server is parsing current video, then current video it
The video uploaded afterwards then caches in the memory unit, successively etc. to be resolved.
S120, it each image is input to anticipation model violating the regulations trained in advance determines there is the target figure of motoring offence
Picture.
Wherein, motoring offence may include making a dash across the red light, crimping, driving in the wrong direction and the behaviors such as do not fasten the safety belt.Anticipation violating the regulations
Model is then a model obtained from image when being occurred according to act of violating regulations as machine learning algorithm is trained, and passes through the mould
Type can prejudge out in the image that parsing obtains content shows act of violating regulations in which piece image, so that it is determined that going out target figure
Picture.
Further, training anticipation model violating the regulations mainly includes the following steps:
Image pattern of breaking rules and regulations is obtained, and the image pattern violating the regulations is input in anticipation model violating the regulations to be trained and is obtained
Current output result.Wherein, image pattern is broken rules and regulations as photo captured under some scenes violating the regulations, can be received by Cloud Server
Collect the picture concerned of online friend's upload as training sample.
According to the error between current output result and desired output result, the anticipation ginseng of the anticipation model violating the regulations is adjusted
Number.It is less than error threshold until currently exporting the error between result and desired output result.
Optionally, before determining target image, when detecting that content matching degree reaches preset on same timing node
When at least two images of matching degree threshold value, and duplicate removal processing is carried out at least two images.Optionally, to it is described at least
Two images carry out duplicate removal processing, can be specifically that content matching degree on same timing node is reached preset matching degree threshold value
At least two images in any one Zhang Baocun, delete others images at least two images;Can also be will be same
Content matching degree reaches the highest figure of clarity at least two images of preset matching degree threshold value on one timing node
As preserving, other images at least two images described in deletion.
Due on same timing node, multiple images of matching degree threshold value are reached with matching degree, i.e., height it is similar or
Identical image is input to obtained output result in anticipation model violating the regulations and is often consistent, therefore removes the figure of repetition
Piece can improve the efficiency for judging probability violating the regulations.
S130, the probability violating the regulations that the vehicle is determined according to the target image and navigation data.
Specifically, determining that the probability violating the regulations of the vehicle includes the following steps according to the target image and navigation data:
First, the time point corresponding to the target image determines that the vehicle travels process at the time point
Target location.
Every target image all corresponds to a time point of vehicle traveling, according in the time point enquiry navigation device
Navigation data determines the place that vehicle is driven at the time point, i.e. target location.
In one embodiment, determine that the vehicle travels the target location passed through and includes at the time point:According to
Contextual data and map datum in the target image determine at least one picture position corresponding with the target image;
Time point corresponding to the target image determines navigation data shown navigation position at the time point;It calculates at least
The range error of one described image position and the navigation position, by the range error minimum in each range error
Corresponding described image position is as target location.
In one embodiment, determine that the vehicle travels the target location passed through and includes at the time point:According to
Contextual data and map datum in the target image determine at least one picture position corresponding with the target image;
Time point corresponding to the target image determines navigation data shown navigation position at the time point;It calculates at least
The range error of one described image position and the navigation position, if the range error minimum in each range error
In preset error range, then using the navigation position as target location.
Specifically, target image Scene data can be building, mark information or traffic information in target image
Deng can determine at least one picture position corresponding with target image according to above- mentioned information.For example, when the scene of target image
Show that there are one known buildings in the target image in data, then can determine picture position institute in conjunction with information such as road signs
Road and direction.Since the image scene data shot at the different location on known road and direction of advance are more
Number is consistent, then identified picture position can be at least one different positions on known road and direction of advance
It sets.
The situation similar in view of there may be target image Scene, therefore may be determined in conjunction with map datum
Two or more picture positions corresponding with the target image, optional is navigation data, will be with navigation position most
It is a close picture position as target location.
Navigation position is that the vehicle confirmed in navigation data according to target image corresponding time point is gone at the moment
Sail by position, it is also likely to be to have error that navigation position and picture position, which may be consistent, then further, calculating
The range error of at least one described image position and the navigation position, it is contemplated that there may be delays for navigation data, will be each
The corresponding described image position of the minimum range error is as target location in the range error.In some scenes,
It, can when the range error minimum in each range error is in preset error range if range error is negligible
Using the navigation position as target location.Be advantageous in that using above-mentioned technical proposal, can fully combining target image and
Navigation data realizes accurate positionin to vehicle, so can more accurately judge vehicle this position probability violating the regulations.
Further, judge whether there is monitoring device violating the regulations in the preset range of the target location.Wherein, preset range
Can be within the scope of 10 meters, 20 meters or 25 meters of distance objective position, which shoots with video-corder range not less than monitoring device violating the regulations
, the monitoring device violating the regulations for being possible to take vehicle peccancy behavior can be found in this way.
Then, if there is monitoring device violating the regulations in the preset range of target location, the history of the target location is violating the regulations general
Rate is determined as the probability violating the regulations of the vehicle.Wherein, the history of target location probability violating the regulations is according to historical violation data
Obtained from calculating, calculation is to use the computational methods of probability violating the regulations in the prior art.
The technical solution of the present embodiment obtains figure corresponding with time point by the video during parsing vehicle driving
Piece, and judge whether the picture is the Target Photo for having motoring offence through anticipation model violating the regulations, according to Target Photo and lead
Boat data determine the probability violating the regulations of vehicle, solve existing navigation device and automobile data recorder can not judge vehicle whether against
The problem of Zhang Hangwei, can make driver predefine whether oneself act of violating regulations is occurring and row of breaking rules and regulations occurring on the run
For address, to instruct later driving behavior.
Embodiment two
Fig. 2 is the structural schematic diagram of the driving infractions anticipation device in the embodiment of the present invention two.It is disobeyed as shown in Fig. 2, driving
Chapter prejudges device:Vehicle travels image collection module 210, target image determining module 220 and probability determination module violating the regulations
230。
Wherein, vehicle travels image collection module 210, for obtaining the video captured by the rear camera of vehicle launch,
And parse the video is obtained with the vehicle travels each time point corresponding image;Target image determining module 220 is used
The target image for having motoring offence is determined in each image is input to anticipation model violating the regulations trained in advance;Probability violating the regulations
Determining module 230, the probability violating the regulations for determining the vehicle according to the target image and navigation data.
The technical solution of the present embodiment obtains figure corresponding with time point by the video during parsing vehicle driving
Piece, and judge whether the picture is the Target Photo for having motoring offence through anticipation model violating the regulations, according to Target Photo and lead
Boat data determine the probability violating the regulations of vehicle, solve existing navigation device and automobile data recorder can not judge vehicle whether against
The problem of Zhang Hangwei, can make driver predefine whether oneself act of violating regulations is occurring and row of breaking rules and regulations occurring on the run
For address, to instruct later driving behavior.
Further, probability determination module 230 violating the regulations includes:
Target location confirmation unit, for the time point corresponding to the target image determine the vehicle this when
Between point travel process target location;
Whether monitoring device judging unit violating the regulations has monitoring dress violating the regulations in the preset range for judging the target location
It sets;
Probability determining unit violating the regulations, when for having monitoring device violating the regulations in the preset range of the target location, by this
The history of target location determine the probability violating the regulations is the probability violating the regulations of the vehicle.
Preferably, driving infractions anticipation device further includes deduplication module, for being trained in advance each image to be input to
Anticipation model violating the regulations before, when detecting that content matching degree reaches preset matching degree threshold value at least on same timing node
When two images, and duplicate removal processing is carried out at least two images.
Further, driving infractions anticipation device further includes model training module, which is specifically used for:
Image pattern of breaking rules and regulations is obtained, and the image pattern violating the regulations is input in anticipation model violating the regulations to be trained and is obtained
Current output result;
According to the error between current output result and desired output result, the anticipation ginseng of the anticipation model violating the regulations is adjusted
Number.
Further, target location confirmation unit is specifically used for:
According to the contextual data in the target image at least one and target image pair is determined with map datum
The picture position answered;
Time point corresponding to the target image determines navigation data shown navigation position at the time point;
The range error for calculating at least one described image position and the navigation position, by each range error most
The corresponding described image position of the small range error is as target location.
Further, target location confirmation unit can be additionally used in:
According to the contextual data in the target image at least one and target image pair is determined with map datum
The picture position answered;
Time point corresponding to the target image determines navigation data shown navigation position at the time point;
The range error of at least one described image position and the navigation position is calculated, if in each range error most
The small range error is in preset error range, then using the navigation position as target location.
What the executable any embodiment of the present invention of driving infractions anticipation device that the embodiment of the present invention is provided was provided drives
Pre-judging method violating the regulations is sailed, has the corresponding function module of execution method and advantageous effect.
Embodiment three
Fig. 3 is the structural schematic diagram of the server in the embodiment of the present invention three.Fig. 3 is shown suitable for being used for realizing the present invention
The block diagram of the exemplary servers 312 of embodiment.The server 312 that Fig. 3 is shown is only an example, should not be to the present invention
The function and use scope of embodiment bring any restrictions.
As shown in figure 3, server 312 is showed in the form of universal computing device.The component of server 312 may include but
It is not limited to:One or more processor or processing unit 316, system storage 328, connection different system component (including
System storage 328 and processing unit 316) bus 318.
Bus 318 indicates one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using the arbitrary bus structures in a variety of bus structures.It lifts
For example, these architectures include but not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Server 312 typically comprises a variety of computer system readable media.These media can be it is any being capable of bedding and clothing
The usable medium that business device 312 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 328 may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 330 and/or cache memory 332.Server 312 may further include it is other it is removable/can not
Mobile, volatile/non-volatile computer system storage medium.Only as an example, storage system 334 can be used for reading and writing not
Movably, non-volatile magnetic media (Fig. 3 do not show, commonly referred to as " hard disk drive ").It, can be with although being not shown in Fig. 3
It provides for the disc driver to moving non-volatile magnetic disk (such as " floppy disk ") read-write, and to removable non-volatile
The CD drive of CD (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 318.Memory 328 may include at least one program
There is one group of (for example, at least one) program module, these program modules to be configured to perform the present invention for product, the program product
The function of each embodiment.
Program/utility 340 with one group of (at least one) program module 332, can be stored in such as memory
In 328, such program module 332 includes but not limited to operating system, one or more application program, other program modules
And program data, the realization of network environment may be included in each or certain combination in these examples.Program module 342
Usually execute the function and/or method in embodiment described in the invention.
Server 312 can also be with one or more external equipments 314 (such as keyboard, sensing equipment, display 324 etc.)
Communication, can also be enabled a user to one or more equipment interact with the server 312 communicate, and/or with make the clothes
Any equipment (such as network interface card, modem etc.) that business device 312 can be communicated with one or more of the other computing device
Communication.This communication can be carried out by input/output (I/O) interface 322.Also, server 312 can also be suitable by network
Orchestration 320 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public network, such as because of spy
Net) communication.As shown, network adapter 320 is communicated by bus 318 with other modules of server 312.It should be understood that
Although being not shown in Fig. 3, other hardware and/or software module can be used in conjunction with server 312, including but not limited to:Micro- generation
Code, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup are deposited
Storage system etc..
Processing unit 316 is stored in program in system storage 328 by operation, to perform various functions using with
And data processing, such as realize the driving infractions pre-judging method that the embodiment of the present invention is provided, this method includes mainly:
The video captured by the rear camera of vehicle launch is obtained, and parses what the video obtained travelling with the vehicle
Each time point corresponding image;
Each image is input to anticipation model violating the regulations trained in advance and determines the target image for having motoring offence;
The probability violating the regulations of the vehicle is determined according to the target image and navigation data.
Example IV
The embodiment of the present invention four additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should
Realize that the driving infractions pre-judging method provided such as the embodiment of the present invention, this method include mainly when program is executed by processor:
The video captured by the rear camera of vehicle launch is obtained, and parses what the video obtained travelling with the vehicle
Each time point corresponding image;
Each image is input to anticipation model violating the regulations trained in advance and determines the target image for having motoring offence;
The probability violating the regulations of the vehicle is determined according to the target image and navigation data.
The arbitrary of one or more computer-readable media may be used in the computer storage media of the embodiment of the present invention
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or the arbitrary above combination.The more specific example (non exhaustive list) of computer readable storage medium includes:Tool
There are one or the electrical connection of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium, which can be any, includes or the tangible medium of storage program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as the data-signal that a carrier wave part is propagated,
Wherein carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By instruction execution system, device either device use or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
It can be write with one or more programming languages or combinations thereof for executing the computer that operates of the present invention
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " such as " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partly executes or executed on a remote computer or server completely on the remote computer on the user computer.
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (LAN) or
The domain wide area network (WAN) is connected to subscriber computer, or, it may be connected to outer computer (such as carried using Internet service
It is connected by internet for quotient).
Note that above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The present invention is not limited to specific embodiments described here, can carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out to the present invention by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
May include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of driving infractions pre-judging method, which is characterized in that including:
Obtain vehicle launch rear camera captured by video, and parse the video obtain with the vehicle travel it is each when
Between put corresponding image;
Each image is input to anticipation model violating the regulations trained in advance and determines the target image for having motoring offence;
The probability violating the regulations of the vehicle is determined according to the target image and navigation data.
2. according to the method described in claim 1, it is characterized in that, described determine institute according to the target image and navigation data
The probability violating the regulations of vehicle is stated, including:
Time point corresponding to the target image determines that the vehicle travels the target location passed through at the time point;
Judge whether there is monitoring device violating the regulations in the preset range of the target location;
If so, by the probability violating the regulations that the history of target location determine the probability violating the regulations is the vehicle.
3. according to the method described in claim 1, it is characterized in that, each image is input to advance trained anticipation violating the regulations
Before model, the method further includes:
When detecting that content matching degree reaches at least two images of preset matching degree threshold value on same timing node, and it is right
At least two images carry out duplicate removal processing.
4. according to the method described in claim 1, it is characterized in that, further including:
Anticipation model violating the regulations is trained;
Correspondingly, described pair of anticipation model violating the regulations be trained including:
Image pattern of breaking rules and regulations is obtained, and the image pattern violating the regulations is input in anticipation model violating the regulations to be trained and is obtained currently
Export result;
According to the error between current output result and desired output result, the anticipation parameter of the anticipation model violating the regulations is adjusted.
5. according to the method described in claim 2, it is characterized in that, the time point corresponding to the target image determine institute
It states vehicle and travels the target location passed through at the time point, including:
According in the target image contextual data and map datum determine it is at least one corresponding with the target image
Picture position;
Time point corresponding to the target image determines navigation data shown navigation position at the time point;
The range error for calculating at least one described image position and the navigation position, will be minimum in each range error
The corresponding described image position of the range error is as target location.
6. according to the method described in claim 2, it is characterized in that, the time point corresponding to the target image determine institute
It states vehicle and travels the target location passed through at the time point, including:
According in the target image contextual data and map datum determine it is at least one corresponding with the target image
Picture position;
Time point corresponding to the target image determines navigation data shown navigation position at the time point;
The range error of at least one described image position and the navigation position is calculated, if minimum in each range error
The range error is in preset error range, then using the navigation position as target location.
7. a kind of driving infractions prejudge device, which is characterized in that including:
Vehicle travels image collection module, for obtaining the video captured by the rear camera of vehicle launch, and is regarded described in parsing
Frequency obtains image corresponding with each time point that the vehicle travels;
Target image determining module has the traffic violation for each image to be input to anticipation model determination violating the regulations trained in advance
The target image of behavior;
Probability determination module violating the regulations, the probability violating the regulations for determining the vehicle according to the target image and navigation data.
8. device according to claim 7, which is characterized in that the probability determination module violating the regulations includes:
Target location confirmation unit determines the vehicle at the time point for the time point corresponding to the target image
Travel the target location passed through;
Whether monitoring device judging unit violating the regulations has monitoring device violating the regulations in the preset range for judging the target location;
Probability determining unit violating the regulations, when for having monitoring device violating the regulations in the preset range of the target location, by the target
The history of position determine the probability violating the regulations is the probability violating the regulations of the vehicle.
9. a kind of server, which is characterized in that the server includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors so that one or more of processors are real
The now driving infractions pre-judging method as described in any in claim 1-6.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The driving infractions pre-judging method as described in any in claim 1-6 is realized when execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810400364.7A CN108399752A (en) | 2018-04-28 | 2018-04-28 | A kind of driving infractions pre-judging method, device, server and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810400364.7A CN108399752A (en) | 2018-04-28 | 2018-04-28 | A kind of driving infractions pre-judging method, device, server and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108399752A true CN108399752A (en) | 2018-08-14 |
Family
ID=63100721
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810400364.7A Pending CN108399752A (en) | 2018-04-28 | 2018-04-28 | A kind of driving infractions pre-judging method, device, server and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108399752A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109410582A (en) * | 2018-11-27 | 2019-03-01 | 易念科技(深圳)有限公司 | Traffic condition analysis method and terminal device |
CN110264730A (en) * | 2019-06-05 | 2019-09-20 | 上海易点时空网络有限公司 | The method and system of tracking escape vehicle based on driving recording |
CN110796883A (en) * | 2019-11-06 | 2020-02-14 | 山东浪潮人工智能研究院有限公司 | Electric bicycle violation reminding method and device based on image recognition |
CN110851652A (en) * | 2019-11-29 | 2020-02-28 | 京东方科技集团股份有限公司 | Method and device for assisting in viewing driving record video |
CN111340811A (en) * | 2020-02-19 | 2020-06-26 | 浙江大华技术股份有限公司 | Method and device for splitting violation synthetic graph and computer storage medium |
CN111339337A (en) * | 2019-12-18 | 2020-06-26 | 贵州智诚科技有限公司 | Method for labeling penalty treatment based on road traffic law-violation behaviors |
CN111383457A (en) * | 2018-12-30 | 2020-07-07 | 浙江宇视科技有限公司 | Parking space state detection method and device, equipment and storage medium |
CN111798358A (en) * | 2020-07-01 | 2020-10-20 | 北京梧桐车联科技有限责任公司 | Method and device for determining route calculation time, electronic equipment and readable storage medium |
CN111832376A (en) * | 2019-07-18 | 2020-10-27 | 北京骑胜科技有限公司 | Vehicle reverse running detection method and device, electronic equipment and storage medium |
CN112466003A (en) * | 2019-09-06 | 2021-03-09 | 顺丰科技有限公司 | Vehicle state detection method, device, server and storage medium |
CN112632412A (en) * | 2020-12-30 | 2021-04-09 | 北京嘀嘀无限科技发展有限公司 | Method, device, equipment and medium for processing traffic violation information |
CN112735148A (en) * | 2020-12-24 | 2021-04-30 | 上海上大鼎正软件股份有限公司 | Method and device for judging overspeed of vehicle in camp, electronic equipment and storage medium |
CN112818726A (en) * | 2019-11-15 | 2021-05-18 | 杭州海康威视数字技术股份有限公司 | Vehicle violation early warning method, device, system and storage medium |
CN113380021A (en) * | 2020-03-10 | 2021-09-10 | 深圳市丰驰顺行信息技术有限公司 | Vehicle state detection method, device, server and computer-readable storage medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100955712B1 (en) * | 2009-09-14 | 2010-05-03 | 장성원 | Information interworking system of intelligent bus and bus stop using infrared communication |
CN101739840A (en) * | 2009-11-26 | 2010-06-16 | 西北工业大学 | Poly GPS/INS and transportation image fusion and positioning method |
KR20110000780U (en) * | 2011-01-06 | 2011-01-24 | 주식회사 하이드 | Traffic regulations devices by panoramic imaging IP camera |
JP2012010036A (en) * | 2010-06-23 | 2012-01-12 | Toshiba Corp | Camera calibration system, and measuring vehicle and roadside device for the same |
CN204596167U (en) * | 2015-04-03 | 2015-08-26 | 吴振华 | A kind of intelligent system realizing early warning violating the regulations |
CN105469102A (en) * | 2014-07-29 | 2016-04-06 | 小米科技有限责任公司 | Vehicle driving information recording method and vehicle driving information recording device |
CN105957347A (en) * | 2016-06-16 | 2016-09-21 | 大连海事大学 | Navigation-automobile-data-recorder-based detection method for illegal turning around of vehicle |
CN106652467A (en) * | 2016-11-29 | 2017-05-10 | 浙江广厦建设职业技术学院 | Traffic information collection system and method thereof |
CN106875721A (en) * | 2017-01-23 | 2017-06-20 | 斑马信息科技有限公司 | Violation information management system and its path of navigation generation method |
CN206773925U (en) * | 2017-06-15 | 2017-12-19 | 河南中安占海控股集团有限公司 | Make a dash across the red light identification disposal plant |
-
2018
- 2018-04-28 CN CN201810400364.7A patent/CN108399752A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100955712B1 (en) * | 2009-09-14 | 2010-05-03 | 장성원 | Information interworking system of intelligent bus and bus stop using infrared communication |
CN101739840A (en) * | 2009-11-26 | 2010-06-16 | 西北工业大学 | Poly GPS/INS and transportation image fusion and positioning method |
JP2012010036A (en) * | 2010-06-23 | 2012-01-12 | Toshiba Corp | Camera calibration system, and measuring vehicle and roadside device for the same |
KR20110000780U (en) * | 2011-01-06 | 2011-01-24 | 주식회사 하이드 | Traffic regulations devices by panoramic imaging IP camera |
CN105469102A (en) * | 2014-07-29 | 2016-04-06 | 小米科技有限责任公司 | Vehicle driving information recording method and vehicle driving information recording device |
CN204596167U (en) * | 2015-04-03 | 2015-08-26 | 吴振华 | A kind of intelligent system realizing early warning violating the regulations |
CN105957347A (en) * | 2016-06-16 | 2016-09-21 | 大连海事大学 | Navigation-automobile-data-recorder-based detection method for illegal turning around of vehicle |
CN106652467A (en) * | 2016-11-29 | 2017-05-10 | 浙江广厦建设职业技术学院 | Traffic information collection system and method thereof |
CN106875721A (en) * | 2017-01-23 | 2017-06-20 | 斑马信息科技有限公司 | Violation information management system and its path of navigation generation method |
CN206773925U (en) * | 2017-06-15 | 2017-12-19 | 河南中安占海控股集团有限公司 | Make a dash across the red light identification disposal plant |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109410582B (en) * | 2018-11-27 | 2021-11-16 | 易念科技(深圳)有限公司 | Traffic condition analysis method and terminal equipment |
CN109410582A (en) * | 2018-11-27 | 2019-03-01 | 易念科技(深圳)有限公司 | Traffic condition analysis method and terminal device |
CN111383457A (en) * | 2018-12-30 | 2020-07-07 | 浙江宇视科技有限公司 | Parking space state detection method and device, equipment and storage medium |
CN111383457B (en) * | 2018-12-30 | 2021-02-09 | 浙江宇视科技有限公司 | Parking space state detection method and device, equipment and storage medium |
CN110264730A (en) * | 2019-06-05 | 2019-09-20 | 上海易点时空网络有限公司 | The method and system of tracking escape vehicle based on driving recording |
CN111832376A (en) * | 2019-07-18 | 2020-10-27 | 北京骑胜科技有限公司 | Vehicle reverse running detection method and device, electronic equipment and storage medium |
CN112466003A (en) * | 2019-09-06 | 2021-03-09 | 顺丰科技有限公司 | Vehicle state detection method, device, server and storage medium |
CN112466003B (en) * | 2019-09-06 | 2023-11-28 | 顺丰科技有限公司 | Vehicle state detection method, device, computer equipment and storage medium |
CN110796883A (en) * | 2019-11-06 | 2020-02-14 | 山东浪潮人工智能研究院有限公司 | Electric bicycle violation reminding method and device based on image recognition |
CN112818726A (en) * | 2019-11-15 | 2021-05-18 | 杭州海康威视数字技术股份有限公司 | Vehicle violation early warning method, device, system and storage medium |
CN110851652A (en) * | 2019-11-29 | 2020-02-28 | 京东方科技集团股份有限公司 | Method and device for assisting in viewing driving record video |
CN111339337A (en) * | 2019-12-18 | 2020-06-26 | 贵州智诚科技有限公司 | Method for labeling penalty treatment based on road traffic law-violation behaviors |
CN111340811A (en) * | 2020-02-19 | 2020-06-26 | 浙江大华技术股份有限公司 | Method and device for splitting violation synthetic graph and computer storage medium |
CN111340811B (en) * | 2020-02-19 | 2023-08-11 | 浙江大华技术股份有限公司 | Resolution method, device and computer storage medium for violation synthetic graph |
CN113380021A (en) * | 2020-03-10 | 2021-09-10 | 深圳市丰驰顺行信息技术有限公司 | Vehicle state detection method, device, server and computer-readable storage medium |
CN113380021B (en) * | 2020-03-10 | 2023-10-10 | 深圳市丰驰顺行信息技术有限公司 | Vehicle state detection method, device, server and computer readable storage medium |
CN111798358A (en) * | 2020-07-01 | 2020-10-20 | 北京梧桐车联科技有限责任公司 | Method and device for determining route calculation time, electronic equipment and readable storage medium |
CN111798358B (en) * | 2020-07-01 | 2024-05-31 | 北京梧桐车联科技有限责任公司 | Method and device for determining path time, electronic equipment and readable storage medium |
CN112735148A (en) * | 2020-12-24 | 2021-04-30 | 上海上大鼎正软件股份有限公司 | Method and device for judging overspeed of vehicle in camp, electronic equipment and storage medium |
CN112632412A (en) * | 2020-12-30 | 2021-04-09 | 北京嘀嘀无限科技发展有限公司 | Method, device, equipment and medium for processing traffic violation information |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108399752A (en) | A kind of driving infractions pre-judging method, device, server and medium | |
US20230385481A1 (en) | Simulation Traffic Scenario File Generation Method and Apparatus | |
CN109188457A (en) | Generation method, device, equipment, storage medium and the vehicle of object detection frame | |
KR20190090393A (en) | Lane determining method, device and storage medium | |
CN109213134A (en) | The method and apparatus for generating automatic Pilot strategy | |
CN109145680A (en) | A kind of method, apparatus, equipment and computer storage medium obtaining obstacle information | |
CN109035831A (en) | Recognition methods, device, equipment, storage medium and the vehicle of traffic light | |
CN109255341A (en) | Extracting method, device, equipment and the medium of barrier perception wrong data | |
US11361555B2 (en) | Road environment monitoring device, road environment monitoring system, and road environment monitoring program | |
CN109358627A (en) | Based on unpiloted driving assistance method, device, equipment, medium and vehicle | |
CN110095126A (en) | Map-matching method, device, equipment and medium | |
CN113535569B (en) | Control effect determination method for automatic driving | |
CN109213144A (en) | Man-machine interface (HMI) framework | |
CN115616937B (en) | Automatic driving simulation test method, device, equipment and computer readable medium | |
CN109376664A (en) | Machine learning training method, device, server and medium | |
CN110097121A (en) | A kind of classification method of driving trace, device, electronic equipment and storage medium | |
CN108268831A (en) | The robustness test method and system of a kind of unmanned vehicle vision-based detection | |
CN110533795A (en) | Data recording equipment | |
CN113392793A (en) | Method, device, equipment, storage medium and unmanned vehicle for identifying lane line | |
CN111366374B (en) | Vehicle testing method and device, electronic equipment and storage medium | |
CN111816022A (en) | Simulation method and device for simulation scene, storage medium and electronic equipment | |
CN112230632A (en) | Method, apparatus, device and storage medium for automatic driving | |
CN111881121A (en) | Automatic driving data filling method and device | |
CN107878325A (en) | Determine that parking system re-scales the method, apparatus and automatic calibration system on opportunity | |
CN114419758B (en) | Vehicle following distance calculation method and device, vehicle 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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180814 |
|
WD01 | Invention patent application deemed withdrawn after publication |