CN108399778A - Swarm intelligence congestion reminding method, system and computer readable storage medium - Google Patents

Swarm intelligence congestion reminding method, system and computer readable storage medium Download PDF

Info

Publication number
CN108399778A
CN108399778A CN201810430004.1A CN201810430004A CN108399778A CN 108399778 A CN108399778 A CN 108399778A CN 201810430004 A CN201810430004 A CN 201810430004A CN 108399778 A CN108399778 A CN 108399778A
Authority
CN
China
Prior art keywords
congestion
user
clouds
onboard system
information
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
Application number
CN201810430004.1A
Other languages
Chinese (zh)
Inventor
刘新
宋朝忠
郭烽
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.)
Shenzhen Yicheng Automatic Driving Technology Co Ltd
Original Assignee
Shenzhen Yicheng Automatic Driving 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 Shenzhen Yicheng Automatic Driving Technology Co Ltd filed Critical Shenzhen Yicheng Automatic Driving Technology Co Ltd
Priority to CN201810430004.1A priority Critical patent/CN108399778A/en
Publication of CN108399778A publication Critical patent/CN108399778A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096766Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
    • G08G1/096791Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is another vehicle

Abstract

The invention discloses a kind of swarm intelligence congestion reminding method, which is applied to congestion prompt system, and congestion prompt system includes at least user's onboard system and high in the clouds, and this method includes:High in the clouds receives the traffic state information that each user's onboard system is sent, wherein traffic state information includes at least the vehicle distributed intelligence in the first position information and user's onboard system position preset range of each user's onboard system;High in the clouds determines the second position information in congestion status according to the traffic state information of reception, and sends congestion prompt message to corresponding user's onboard system according to first position information and second position information.The invention also discloses a kind of system, computer readable storage mediums.The present invention can effectively expand the area coverage of information collection, improve the timeliness of information collection, targetedly issuing traffic congestion information, improve user experience.

Description

Swarm intelligence congestion reminding method, system and computer readable storage medium
Technical field
The present invention relates to a kind of technical field of transportation more particularly to swarm intelligence congestion reminding method, system and computers Readable storage medium storing program for executing.
Background technology
The concept of swarm intelligence (Swarm/collection intelligence) insect populations in nature Observation, gregariousness biology are referred to as swarm intelligence by the macroscopical intelligent behavior feature shown that cooperates.In nature, have Biology but can rely on the strength of group to obtain survival advantage.It can share out the work and help one another between individual, is mutually coordinated, completing complicated appoint Business, shows relatively high intelligence, self-organizing, adaptivity with height, and it is special to show system that is non-linear, emerging in large numbers Sign.Swarm intelligence refers to without intelligence or only there is relatively easy intelligent main body to show higher intelligent behavior by cooperation Characteristic;Group's cooperation that task can be made of a large amount of simple individuals is completed, and the latter often has more robustness, flexibility Advantage economically.Wherein, traffic technique is one potential application direction of swarm intelligence.
The development of traffic technique and people’s lives are closely bound up, with the development of social economy, people's living standard Improve, the quantity of motor vehicle increases sharply, and traffic congestion has become a great problem of people's trip, influence people’s lives with Work.In the prior art, traffic state information is generally acquired by specific vehicle or crowd, then by distribution platform with The mode of broadcast carries out issuing traffic congestion information, and existing this traffic state information acquisition method area coverage is small, information Acquisition there may be delay, cannot be according to user location pointedly issuing traffic congestion information.
Invention content
The main purpose of the present invention is to provide a kind of swarm intelligence congestion reminding method, system and computer-readable storages Medium, it is intended to solve that prior art traffic state information acquisition method area coverage is small, and there may be delays for the acquisition of information, no Can according to user location pointedly issuing traffic congestion information the problem of.
To achieve the above object, the present invention provides a kind of swarm intelligence congestion reminding method, and the congestion reminding method is answered For congestion prompt system, the congestion prompt system includes at least user's onboard system and high in the clouds, the congestion prompt side Method includes:
The high in the clouds receives the traffic state information that each user's onboard system is sent, wherein the traffic state information The vehicle in first position information and user's onboard system position preset range including at least each user's onboard system Distributed intelligence;
The high in the clouds determines the second position information in congestion status according to the traffic state information of reception, and according to institute It states first position information and the second position information sends congestion prompt message to corresponding user's onboard system.
Preferably, the vehicle distributed intelligence includes the vehicle distributed image or mobile lidar of vehicle-mounted camera shooting The vehicle of acquisition is distributed point cloud data.
Preferably, the high in the clouds determines the second position information in congestion status according to the traffic state information of reception, And congestion prompt message is sent to corresponding user's onboard system according to the first position information and the second position information The step of include:
The high in the clouds is corresponding default according to traffic state information each user's onboard system of the acquisition position received The vehicle distributed intelligence of range, and traffic density distributed intelligence is obtained according to the vehicle distributed intelligence;
The high in the clouds determines the second position information in congestion status according to the traffic density distributed intelligence;
The high in the clouds is less than or equal to the shortest distance according to the first position information and the second position information pre- If user's onboard system of distance threshold establishes incidence relation with each second position information;
The high in the clouds sends congestion prompt message to each associated user's onboard system according to the incidence relation.
Preferably, the high in the clouds determines the second position information in congestion status according to the traffic density distributed intelligence The step of after further include:
The high in the clouds determines the congestion distance of each congestion position according to the second position information;
The high in the clouds sends congestion prompt message to the step of each associated user's onboard system according to the incidence relation Suddenly include:
The high in the clouds sends congestion prompt message to each according to the congestion distance of each congestion position and the incidence relation A associated user's onboard system.
Preferably, the high in the clouds determines the second position information in congestion status according to the traffic density distributed intelligence The step of after further include:
The high in the clouds determines the predicted congestion time span of each congestion position according to the second position information;
The high in the clouds sends congestion prompt message to the step of each associated user's onboard system according to the incidence relation Suddenly include:
The high in the clouds sends congestion prompt according to the predicted congestion time span of each congestion position and the incidence relation Information is to each associated user's onboard system.
Preferably, the high in the clouds determines the predicted congestion time span of each congestion position according to the second position information The step of include:
The high in the clouds determines the prediction of each congestion position according to the second position information based on big data analysis information Congestion time span.
Preferably, which is characterized in that traffic congestion prompt situation reminding method further includes:
The high in the clouds receives the path planning request that user terminal or user's onboard system are sent, wherein the path rule It includes origin information and endpoint information to draw request;
The high in the clouds carries out path planning according to path planning request and traffic congestion situation, wherein the traffic Jam situation includes at least the second position information, the congestion distance or the predicted congestion time span.
To achieve the above object, the present invention also provides a kind of congestion prompt systems, wherein the congestion prompt system is at least Including memory, processor and the congestion attention program being stored on the memory, the congestion attention program is described Processor realizes following steps when executing:
The high in the clouds receives the traffic state information that each user's onboard system is sent, wherein the traffic state information The vehicle in first position information and user's onboard system position preset range including at least each user's onboard system Distributed intelligence;
The high in the clouds determines the second position information in congestion status according to the traffic state information of reception, and according to institute It states first position information and the second position information sends congestion prompt message to corresponding user's onboard system.
Preferably, following steps are also realized when the congestion attention program is executed by the processor:
The high in the clouds is corresponding default according to traffic state information each user's onboard system of the acquisition position received The vehicle distributed intelligence of range, and traffic density distributed intelligence is obtained according to the vehicle distributed intelligence;
The high in the clouds determines the second position information in congestion status according to the traffic density distributed intelligence;
The high in the clouds is less than or equal to the shortest distance according to the first position information and the second position information pre- If user's onboard system of distance threshold establishes incidence relation with each second position information;
The high in the clouds sends congestion prompt message to each associated user's onboard system according to the incidence relation.
In addition, to achieve the above object, the present invention also provides a kind of congestions to prompt computer readable storage medium, wherein Congestion attention program is stored on the computer readable storage medium, the congestion attention program is realized when being executed by processor The step of congestion reminding method as described above.
The present invention provides a kind of swarm intelligence congestion reminding method, and the congestion reminding method is applied to congestion prompt system System, the congestion prompt system include at least user's onboard system and high in the clouds, and the congestion reminding method includes:The high in the clouds Receive the traffic state information that each user's onboard system is sent, wherein the traffic state information includes at least each user Vehicle distributed intelligence in the first position information and user's onboard system position preset range of onboard system;The high in the clouds Determine the second position information in congestion status according to the traffic state information of reception, and according to the first position information and The second position information sends congestion prompt message to corresponding user's onboard system.By the above-mentioned means, using as friendship Each user's onboard system individual in logical group acquires traffic state information, can effectively expand the covering surface of information collection Product, improves the timeliness of information collection;According to the second confidence of the first position information of user's onboard system and congestion position Breath can targetedly issuing traffic congestion information, improve user experience.
Description of the drawings
Fig. 1 is the affiliated terminal structure schematic diagram of device for the hardware running environment that the embodiment of the present invention is related to;
Fig. 2 is the flow diagram of congestion reminding method of the present invention and congestion prompt system first embodiment;
Fig. 3 is the flow diagram of congestion reminding method of the present invention and congestion prompt system second embodiment;
Fig. 4 is the flow diagram of congestion reminding method 3rd embodiment of the present invention;
Fig. 5 is the flow diagram of congestion reminding method fourth embodiment of the present invention;
Fig. 6 is the flow diagram of the 5th embodiment of congestion reminding method of the present invention;
Fig. 7 is the flow diagram of congestion reminding method sixth embodiment of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
In the prior art, traffic state information is generally acquired by specific vehicle or crowd, it is then flat by issuing Platform carries out issuing traffic congestion information, existing this traffic state information acquisition method area coverage by way of broadcast Small, the acquisition of information, cannot be targetedly according to user location pointedly issuing traffic congestion information there may be delay.
In order to solve the above technical problem, the present invention provides a kind of swarm intelligence congestion reminding methods, in the method, institute It states congestion reminding method and is applied to congestion prompt system, the congestion prompt system includes at least user's onboard system and cloud End, the high in the clouds first receive the traffic state information that each user's onboard system is sent, wherein the traffic state information is at least Vehicle distribution in first position information and user's onboard system position preset range including each user's onboard system Information determines the second position information in congestion status further according to the traffic state information of reception, and according to described first Confidence ceases and the second position information sends congestion prompt message to corresponding user's onboard system.To effectively expand information The area coverage of acquisition improves the timeliness of information collection, targetedly issuing traffic congestion information, improves user experience.
As shown in Figure 1, the system structure diagram for the hardware running environment that Fig. 1, which is the embodiment of the present invention, to be related to.
Terminal of the embodiment of the present invention can be PC, can also be smart mobile phone, tablet computer, E-book reader, MP3 (Moving Picture Experts Group Audio Layer III, dynamic image expert's compression standard audio level 3) Player, MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert's compression standard sound Frequency level 4) the packaged type terminal device with display function such as player, pocket computer.
As shown in Figure 1, the terminal may include:Processor 1001, such as CPU, network interface 1004, user interface 1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing the connection communication between these components. User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard), optional user interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 may include optionally that the wired of standard connects Mouth, wireless interface (such as WI-FI interfaces).Memory 1005 can be high-speed RAM memory, can also be stable memory (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned processor 1001 storage device.
Optionally, terminal can also include camera, RF (Radio Frequency, radio frequency) circuit, sensor, audio Circuit, WiFi module etc..Wherein, sensor such as optical sensor, motion sensor and other sensors.Specifically, light Sensor may include ambient light sensor and proximity sensor, wherein ambient light sensor can according to the light and shade of ambient light come The brightness of display screen is adjusted, proximity sensor can close display screen and/or backlight when mobile terminal is moved in one's ear.As One kind of motion sensor, gravity accelerometer can detect in all directions the size of (generally three axis) acceleration, quiet Size and the direction that can detect that gravity when only, the application that can be used to identify mobile terminal posture are (such as horizontal/vertical screen switching, related Game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.;Certainly, mobile terminal can also match The other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor are set, details are not described herein.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of terminal structure shown in Fig. 1, can wrap It includes than illustrating more or fewer components, either combines certain components or different components arrangement.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage media Believe module, Subscriber Interface Module SIM and congestion attention program.
In terminal shown in Fig. 1, network interface 1004 is mainly used for connecting background server, is carried out with background server Data communicate;User interface 1003 is mainly used for connecting client (user terminal), with client into row data communication;And processor 1001 can be used for calling the congestion attention program stored in memory 1005, and execute following operation:
The high in the clouds receives the traffic state information that each user's onboard system is sent, wherein the traffic state information The vehicle in first position information and user's onboard system position preset range including at least each user's onboard system Distributed intelligence;
The high in the clouds determines the second position information in congestion status according to the traffic state information of reception, and according to institute It states first position information and the second position information sends congestion prompt message to corresponding user's onboard system.
Further, processor 1001 can call the congestion attention program stored in memory 1005, also execute following Operation:
The high in the clouds is corresponding default according to traffic state information each user's onboard system of the acquisition position received The vehicle distributed intelligence of range, and traffic density distributed intelligence is obtained according to the vehicle distributed intelligence;
The high in the clouds determines the second position information in congestion status according to the traffic density distributed intelligence;
The high in the clouds is less than or equal to the shortest distance according to the first position information and the second position information pre- If user's onboard system of distance threshold establishes incidence relation with each second position information;
The high in the clouds sends congestion prompt message to each associated user's onboard system according to the incidence relation.
Further, processor 1001 can call the congestion attention program stored in memory 1005, also execute following Operation:
The high in the clouds determines the congestion distance of each congestion position according to the second position information;
The high in the clouds sends congestion prompt message to each according to the congestion distance of each congestion position and the incidence relation A associated user's onboard system.
Further, processor 1001 can call the congestion attention program stored in memory 1005, also execute following Operation:
The high in the clouds determines the predicted congestion time span of each congestion position according to the second position information;
The high in the clouds sends congestion prompt according to the predicted congestion time span of each congestion position and the incidence relation Information is to each associated user's onboard system.
Further, processor 1001 can call the congestion attention program stored in memory 1005, also execute following Operation:
The high in the clouds determines the prediction of each congestion position according to the second position information based on big data analysis information Congestion time span.
Further, processor 1001 can call the congestion attention program stored in memory 1005, also execute following Operation:
The high in the clouds receives the path planning request that user terminal or user's onboard system are sent, wherein the path rule It includes origin information and endpoint information to draw request;
The high in the clouds carries out path planning according to path planning request and traffic congestion situation, wherein the traffic Jam situation includes at least the second position information, the congestion distance or the predicted congestion time span.
It is congestion reminding method first embodiment flow diagram of the present invention with reference to Fig. 2, Fig. 2.
The concept of swarm intelligence (Swarm/collection intelligence) insect populations in nature Observation, gregariousness biology are referred to as swarm intelligence by the macroscopical intelligent behavior feature shown that cooperates.In nature, have Biology but can rely on the strength of group to obtain survival advantage.It can share out the work and help one another between individual, is mutually coordinated, completing complicated appoint Business, shows relatively high intelligence, self-organizing, adaptivity with height, and it is special to show system that is non-linear, emerging in large numbers Sign.Swarm intelligence refers to without intelligence or only there is relatively easy intelligent main body to show higher intelligent behavior by cooperation Characteristic;Group's cooperation that task can be made of a large amount of simple individuals is completed, and the latter often has more robustness, flexibility Advantage economically.Wherein, traffic technique is one potential application direction of swarm intelligence.The development of traffic technique and people's It lives closely bound up, with the development of social economy, the improvement of people's living standards, the quantity of motor vehicle increases sharply, traffic Congestion has become a great problem of people's trip, influences people’s lives and work.In the prior art, generally by specific Vehicle or crowd acquire traffic state information, then carry out issuing traffic congestion letter in a broadcast manner by distribution platform Breath, existing this traffic state information acquisition method area coverage is small, the acquisition of information there may be delay, cannot according to Family position pointedly issuing traffic congestion information.The present invention provides a kind of by user's onboard system acquisition traffic behavior letter Breath, and the side of the location information progress traffic congestion prompt according to the traffic state information of the onboard system of user acquisition and user Method to according to user location pointedly issuing traffic congestion information, and solves prior art acquisition traffic state information and covers Capping is small, it is understood that there may be the problem of delay.In the present embodiment, each user's onboard system is as the individual in traffic group, The acquisition of traffic state information is completed in mutually coordinated cooperation, according to the traffic state information and use of the acquisition of the onboard system of user The location information at family carries out traffic congestion prompt, and the user of each onboard system can obtain near itself or and travel Relevant traffic state information, and pointedly evade congestion path.
In the present embodiment, the congestion reminding method is applied to congestion prompt system, and the congestion prompt system is at least Including user's onboard system and high in the clouds, in the present embodiment, onboard system includes that vehicle-mounted hardware and management and control are vehicle-mounted The programming system of hardware and vehicle-mounted software resource.In the present embodiment, vehicle-mounted hardware is in addition to including positioning device, intelligent back vision mirror Or outside the conventional vehicle-mounted hardware such as automobile data recorder, the camera shooting of the vehicle distributed image on shooting driving path can also be configured to Head or the laser radar for obtaining vehicle distributed point cloud data on driving path, and the communication mould for being interacted with high in the clouds Block.High in the clouds can be interacted with each onboard system, the traffic state information sent for receiving each user's onboard system, and root It is in the position of congestion status according to the traffic state information of reception, and sends prompt message to corresponding onboard system.This implementation The realization of example includes the following steps:
Step S10, the high in the clouds receive the traffic state information that each user's onboard system is sent, wherein the traffic Status information includes at least the first position information and user's onboard system position preset range of each user's onboard system Interior vehicle distributed intelligence;The vehicle distributed intelligence includes the vehicle distributed image or vehicle-mounted laser thunder of vehicle-mounted camera shooting Vehicle up to acquisition is distributed point cloud data.
In the present embodiment, traffic state information includes each onboard system position and position preset range Interior vehicle distributed intelligence.The vehicle distributed image that can be configured on user's onboard system on shooting driving path is taken the photograph As the laser radar of vehicle distributed point cloud data on head or acquisition driving path, vehicle can utilize vehicle during traveling It carries camera and periodically obtains current location information, i.e. first position information by positioning device, meanwhile, shooting vehicle is current Vehicle distributed image in the preset range of position preferably can only shoot the vehicle distributed image of vehicle forward direction.Each use The first position information of itself is associated with by family onboard system with the image of shooting, is generated traffic state information and is sent out by communication module Send traffic state information to high in the clouds.Camera shooting range can by control cradle head control camera pitch angle or deflection Angle controls.When being configured with mobile lidar on onboard system, it is current vehicle can be obtained by mobile lidar Vehicle in the preset range of position is distributed point cloud data.Each user's onboard system by the first position information of itself and obtain Vehicle distributed point cloud data correlation generates traffic state information, and traffic state information is sent to high in the clouds by communication module.At this In embodiment, vehicle can be set and periodically obtain traffic state information during the process of traveling and be sent to high in the clouds, It periodically obtains traffic state information when the speed of vehicle can also be set less than some pre-set velocity threshold value and is sent to high in the clouds.
Step S20, the high in the clouds determine the second position information in congestion status according to the traffic state information of reception, And congestion prompt message is sent to corresponding user's onboard system according to the first position information and the second position information.
Based on above-mentioned steps, when above-mentioned high in the clouds receives the traffic state information that each onboard system is sent, to receiving Traffic state information handled.The location information and corresponding vehicle point of onboard system are first obtained from traffic state information Cloth information, i.e. location information and vehicle distributed image or vehicle are distributed point cloud data.The present embodiment is by taking vehicle distributed image as an example It illustrates, high in the clouds can use training image in advance, train vehicle identification model.Different object recognition systems is different Training method.Many methods derive from bare metal learning art, such as boost, Winnow, support vector machines, RVM, shellfish The technologies such as leaf this theory, gauss hybrid models, EM algorithms, decision tree, decision stub.Training method is broadly divided into two major classes: The method of seeking difference (discriminative approach) and extensive method (generative approach).The method of seeking difference attempts in feature A decision boundary is found in space, and characteristic vector is classified, and judges whether it belongs to certain type objects.Sliding window model frequently with Method of seeking difference training pattern, SVM, decision tree, decision stub and boost class technologies are usually used in the extensive rule of the method for seeking difference as much as possible The feature for finding certain class object judges object according to the probability that these features occur using bayesian theory, gauss hybrid models Classification.Be arranged frequently with extensive method based on the method for component, Optimized model parameter, EM algorithms be commonly used to processing component and its it Between relationship, the problem of this method is a kind of method of iterative estimate parameter, it can handle shortage of data, but cannot be guaranteed Find global maximum.It specifically, can be according to figure after the vehicle distributed image that the onboard system A of high in the clouds acquisition vehicle A is sent As in the distributing position of vehicle and camera configuration configuration pitch angle or deflection angle and geometrical principle determine in image vehicle with Clap vehicle A relative position or image in relative position general between vehicle, so that it is determined that in image corresponding position vehicle Distribution density, then determines whether the position of jam situation and congestion further according to vehicle distribution density.Certainly also may be used To set vehicle fleet size threshold value, when vehicle fleet size is more than vehicle fleet size threshold value in the image of vehicle shooting, judge that the position goes out Existing jam situation.In the present embodiment, when more different vehicles are in similar position, the image of shooting may exist The part of overlapping, it is also possible to which in same paths but distance is farther out without being overlapped, can be based on the location information of position vehicle Distance or the unimpeded distance of congestion position and congestion are more accurately determined in conjunction with the image information of multiple vehicles.In this reality It applies in example, second position information refers to the location information of congestion regions, is the location information of a position range, may include Congestion starting point and congestion terminal.After determining the second position information in congestion status, further according to each user's onboard system First position information determine in congestion position or user's onboard system of the neighbouring preset range in congestion position, and it is corresponding The location information of congestion position and user's onboard system within a preset range are established into incidence relation, sent according to incidence relation The prompt message of traffic congestion is to associated user's onboard system.It in the present embodiment, can also be according to user's onboard system position Confidence breath determines the travel direction of corresponding vehicle, and the congestion road of vehicle front is determined further according to the vehicle distributed intelligence of vehicle front Journey or congestion time send prompt message to corresponding user's onboard system so that user according to congestion distance or congestion time Clear specific jam situation.Certainly in the present embodiment, determining can also be by broadcast after the second information of congestion position Jam situation is sent to the onboard system in bigger preset range by mode, for example, when the cities section A highway gets congestion, it will Congestion prompt message is sent to all onboard systems within the scope of the cities A.
In the present embodiment, the high in the clouds receives the traffic state information that each user's onboard system is sent, wherein described Traffic state information includes at least the first position information of each user's onboard system and user's onboard system position is preset Vehicle distributed intelligence in range;The high in the clouds determines the second position in congestion status according to the traffic state information of reception Information, and it is vehicle-mounted to corresponding user according to the first position information and second position information transmission congestion prompt message System.By the above-mentioned means, using traffic state information is acquired as each user's onboard system individual in traffic group, The area coverage that information collection can effectively be expanded, improves the timeliness of information collection;According to the first of user's onboard system Confidence cease and the second position information of congestion position can targetedly issuing traffic congestion information, improve user experience.
Further, it is congestion reminding method second embodiment flow diagram of the present invention with reference to Fig. 3, Fig. 3, based on above-mentioned Congestion reminding method embodiment of the present invention proposes the second embodiment of the present invention.
Based on above-described embodiment, in the present embodiment, step S20 includes:
Step S30, the high in the clouds obtain each user's onboard system position pair according to the traffic state information received The vehicle distributed intelligence for the preset range answered, and traffic density distributed intelligence is obtained according to the vehicle distributed intelligence;
Step S40, the high in the clouds determine the second confidence in congestion status according to the traffic density distributed intelligence Breath;
Step S50, the high in the clouds are less than the shortest distance according to the first position information and the second position information Or establish incidence relation equal to user's onboard system of pre-determined distance threshold value and each second position information;
Step S60, the high in the clouds are vehicle-mounted to each associated user according to incidence relation transmission congestion prompt message System.
Based on above-described embodiment, in the present embodiment, high in the clouds receives the traffic behavior that each user's onboard system is sent After information, the first position information of each onboard system and corresponding vehicle distributed image are first obtained from traffic state information, The vehicle distribution density information of user's onboard system position within a preset range, Ke Yigen are determined according to vehicle distributed image The shooting image less than or equal to multiple onboard systems of pre-determined distance position is combined according to the location information of user's onboard system Obtain more complete traffic density distributed intelligence.The present embodiment is illustrated by taking vehicle distributed image as an example, and high in the clouds can be pre- Training image is first used, vehicle identification model is trained.Different object recognition systems has different training methods.Many methods From bare metal learning art, such as boost, Winnow, support vector machines, RVM, bayesian theory, Gaussian Mixture mould The technologies such as type, EM algorithms, decision tree, decision stub.Training method is broadly divided into two major classes:The method of seeking difference (discriminative approach) and extensive method (generative approach).The method of seeking difference attempts to look in feature space To a decision boundary, characteristic vector is classified, judges whether it belongs to certain type objects.Sliding window model is frequently with the method for seeking difference Training pattern, SVM, decision tree, decision stub and boost class technologies are usually used in the extensive rule of the method for seeking difference and find certain as much as possible The feature of class object judges the class of object using bayesian theory, gauss hybrid models according to the probability that these features occur Not.Be arranged frequently with extensive method based on the method for component, Optimized model parameter, EM algorithms be commonly used to processing component and its between The problem of relationship, this method are a kind of methods of iterative estimate parameter, it can handle shortage of data, but cannot be guaranteed to find Global maximum.It specifically, can be according in image after the vehicle distributed image that the onboard system A of high in the clouds acquisition vehicle A is sent Distributing position and camera configuration the configuration pitch angle or deflection angle and geometrical principle of vehicle determine vehicle and bat vehicle in image Relative position general between vehicle in the relative position or image of A, can also be big according to the imaging of vehicle in the picture The actual range of vehicle and vehicle A in small determining image, so that it is determined that the distributing position of vehicle.So that it is determined that corresponding in image The vehicle distribution density of position, then determines whether the position of jam situation and congestion further according to vehicle distribution density. Vehicle fleet size threshold value can certainly be set, the quantity of vehicle is as in preset range near user's onboard system using in image Traffic density distributed intelligence.When vehicle fleet size is more than vehicle fleet size threshold value in the image of vehicle shooting, judge that the position occurs Jam situation.In the present embodiment, when more different vehicles are in similar position, the image of shooting may have weight Folded part, it is also possible to which in same paths but distance is farther out without being overlapped, can be based on the location information knot of position vehicle The image information for closing multiple vehicles more accurately determines distance or the unimpeded distance of congestion position and congestion.Specifically, The camera of user's onboard system A can only be shot to the vehicle distributed image in direction of advance coverage, the vehicle-mounted system of user The image of the shooting of system A is sent to high in the clouds and obtains vehicle when high in the clouds receives the vehicle distributed image that user's onboard system A is sent The first position information of distributed image and user's onboard system A identifies the vehicle in vehicle distributed image, and determining can in image Identify vehicle quantity, judge can recognize that vehicle quantity whether be greater than or equal to preset quantity threshold value n, if more than or be equal to, Then determine that the camera sites user onboard system A are in congestion status, and congestion road is determined with the shooting distance of user's vehicle onboard system Journey.Then it determines to be less than or equal at a distance from each congestion position further according to the first position information of user's onboard system and preset User's onboard system of distance, and the second information and user's vehicle in congestion status by distance less than or equal to pre-determined distance Loading system establishes incidence relation, for example, user's onboard system A and the shortest distance of congestion position first are less than pre-determined distance, user Onboard system B and the shortest distance of congestion position second are less than pre-determined distance, then respectively by user's onboard system A and congestion position first Incidence relation is established, user's onboard system B establishes incidence relation with congestion position second.High in the clouds sends congestion feelings according to incidence relation Condition prompt message will be sent to user to corresponding user's onboard system about the prompt message of congestion position first jam situation Onboard system A will be sent to user's onboard system B about the prompt message of congestion position second jam situation.
In the present embodiment, the high in the clouds obtains each user's onboard system institute in place according to the traffic state information received The vehicle distributed intelligence of corresponding preset range is set, and traffic density distributed intelligence is obtained according to the vehicle distributed intelligence;Institute It states high in the clouds and the second position information in congestion status is determined according to the traffic density distributed intelligence;
The high in the clouds is less than or equal to the shortest distance according to the first position information and the second position information pre- If user's onboard system of distance threshold establishes incidence relation with each second position information;It is closed according to the association in the high in the clouds System sends congestion prompt message to each associated user's onboard system.It is distributed according to traffic density by the above-mentioned means, realizing Information determines the position in congestion status, and may according to user's onboard system and the determination at a distance from congestion status position The user's onboard system that can be influenced by cur-rent congestion situation, and established with the location information in congestion status having an impact Incidence relation pointedly sends the prompt message of traffic congestion situation according to incidence relation to associated user's onboard system.
Further, it is congestion reminding method 3rd embodiment flow diagram of the present invention with reference to Fig. 4, Fig. 4, based on above-mentioned Congestion reminding method embodiment of the present invention proposes the third embodiment of the present invention.
Based on above-described embodiment, in the present embodiment, further include after step S40:
Step S70, the high in the clouds determine the congestion distance of each congestion position according to the second position information;
Step S60 includes:
Step S80, the high in the clouds send congestion according to the congestion distance of each congestion position and the incidence relation and prompt Information is to each associated user's onboard system.
Based on above-described embodiment, in the present embodiment, high in the clouds obtains the vehicle distribution map that the onboard system A of vehicle A is sent As after, configuration pitch angle or deflection angle can be configured according to the distributing position and camera of vehicle in image and geometrical principle is true Determine relative position general between vehicle in the relative position or image of vehicle and bat vehicle A in image, it can also be according to vehicle Imaging size in the picture determines the actual range of vehicle and vehicle A in image, so that it is determined that the distributing position of vehicle. So that it is determined that in image corresponding position vehicle distribution density, then determine whether congestion feelings further according to vehicle distribution density The position of condition and congestion.Vehicle fleet size threshold value can certainly be set, the quantity of vehicle is as the vehicle-mounted system of user using in image Traffic density distributed intelligence near system in preset range.When vehicle fleet size is more than vehicle fleet size threshold value in the image of vehicle shooting When, judge that jam situation occurs in the position.In the present embodiment, when more different vehicles are in similar position, shooting Image may exist overlapping part, it is also possible to same paths but distance farther out without be overlapped, position can be based on Set vehicle location information combine the image information of multiple vehicles more accurately determine congestion position and congestion distance or Unimpeded distance.Specifically, the camera of user's onboard system A can only be shot to the vehicle in direction of advance coverage point The image of cloth image, the shooting of user's onboard system A is sent to high in the clouds, and high in the clouds receives the vehicle that user's onboard system A is sent When distributed image, the first position information of vehicle distributed image and user's onboard system A is obtained, is identified in vehicle distributed image Vehicle determines the quantity that can recognize that vehicle in image, judges can recognize that whether the quantity of vehicle is greater than or equal to preset quantity threshold Value n, if more than or be equal to, it is determined that the camera sites user onboard system A are in congestion status, with the bat of user's vehicle onboard system Photographic range determines congestion distance.Then further according to the first position information of user's onboard system determine with each congestion position away from From user's onboard system less than or equal to pre-determined distance, and by distance be less than or equal to pre-determined distance in congestion status Second information and user's onboard system establish incidence relation, for example, user's onboard system A and the shortest distance of congestion position first are small In pre-determined distance, user's onboard system B and the shortest distance of congestion position second are less than pre-determined distance, then respectively by the vehicle-mounted system of user System A establishes incidence relation with congestion position first, and user's onboard system B establishes incidence relation with congestion position second.High in the clouds is according to pass Connection relationship sends jam situation prompt message to corresponding user's onboard system, i.e., by carrying about congestion position first jam situation Show that information is sent to user onboard system A, the vehicle-mounted system of user will be sent to about the prompt message of congestion position second jam situation Unite B.In the present embodiment, it when determining the second position information in congestion status, is determined according to second position information each Then the distance of the congestion distance of congestion position, i.e. congestion covering sends congestion feelings according to determining congestion distance and incidence relation Condition prompt message is to corresponding user's onboard system.Specifically, it is based on above-described embodiment, when the congestion distance of congestion position first is When L1, then sends prompt position first and jam situation prompt message that congestion distance is L1 occur to user's onboard system A.In this reality It applies in example, path and the travel direction of user's traveling can also be determined according to the change in location of user's onboard system, for user The jam situation in the front of travel direction sends prompt message, such case can also be according to can also be according to second confidence Breath and first position information determine travel distance of user's onboard system apart from congestion position, and congestion feelings are sent according to operating range Condition prompt message.Specifically, position current vehicle A is position third, according to position third and vehicle A runs track and is prestored Cartographic information determines the pathname of vehicle A runs, when congestion road occurs in the front position first in the path vehicle A runs direction When journey is the jam situation of L1, according to the cartographic information to prestore determine position and and position first travel distance S, then basis Position first, travel distance S and congestion distance L1 send jam situation prompt message to user onboard system A, for example, prompt letter Breath can be " jam situation that congestion distance is L1 occurs in position first at S in front of current path ", and onboard system can pass through language Sound prompts or directly shows the relevant information of jam situation on navigator display to prompt user.
In the present embodiment, the high in the clouds determines the congestion distance of each congestion position according to the second position information; The high in the clouds sends congestion prompt message to each associated according to the congestion distance of each congestion position and the incidence relation User's onboard system.The congestion distance information that congestion position occurs is sent to user's onboard system by the above-mentioned means, realizing, User can obtain more detailed jam situation, improve user experience.
Further, it is congestion reminding method fourth embodiment flow diagram of the present invention with reference to Fig. 5, Fig. 5.Based on above-mentioned Embodiment proposes the fourth embodiment of the present invention.
Based on above-described embodiment, in the present embodiment, further include after step S40:
Step S90, the high in the clouds determine that the predicted congestion time of each congestion position is long according to the second position information Degree;
Step S60 further includes:
Step S100, the high in the clouds are sent according to the predicted congestion time span of each congestion position and the incidence relation Congestion prompt message is to each associated user's onboard system.
Based on above-described embodiment, in the present embodiment, high in the clouds can obtain the congestion position, right of each traffic congestion situation Tailback quantity, corresponding congestion distance or the congestion coverage area answered and corresponding congestion time span, and be stored in In presetting database, to one large database concept of structure.In the present embodiment, the second position congestion in congestion status is determined After information, place and the congestion coverage area of congestion can be determined according to second position information, it can be by user's congestion ahead The history jam situation stored in the information and dates library such as place and congestion coverage area is matched or is compared, to predict The time duration of current each congestion position congestion, that is, determine the predicted time length of each congestion position, then in root It is predicted that congestion time span and incidence relation transmission jam situation prompt message are vehicle-mounted to each associated user in congestion position System.It certainly, in the present embodiment, can also rule of thumb or data with existing analysis determines specific congestion covering surface or congestion The predicted congestion time span of distance simultaneously stores, straight after determining congestion distance or congestion covering surface according to second position information The congestion covering surface or congestion distance for connecing and prestoring carry out comparison matching, determine predicted congestion time span.In the present embodiment, It can also rule of thumb or the calculating of data with existing analysis congestion covering surface or congestion distance and predicted congestion time span is public Formula determines predicted congestion time span according to calculation formula.
In the present embodiment, when the high in the clouds determines the predicted congestion of each congestion position according to the second position information Between length;The high in the clouds sends congestion prompt letter according to the predicted congestion time span of each congestion position and the incidence relation It ceases to each associated user's onboard system.By the above-mentioned means, realizing the predicted congestion time span information of congestion position It is sent to user's onboard system, user can obtain more detailed jam situation, improve user experience.
Further, it is the 5th embodiment flow diagram of congestion reminding method of the present invention with reference to Fig. 6, Fig. 6, based on above-mentioned Congestion reminding method embodiment of the present invention proposes the fifth embodiment of the present invention.
Based on above-described embodiment, in the present embodiment, step S90 includes:
Step S110, the high in the clouds determine each congestion position according to the second position information based on big data analysis information The predicted congestion time span set.
Based on above-described embodiment, in this embodiment, high in the clouds can obtain the congestion position of each traffic congestion situation, correspondence Tailback quantity, corresponding congestion distance or congestion coverage area and corresponding congestion time span, and be stored in pre- If in database, to one large database concept of structure.In the present embodiment, the second position congestion letter in congestion status is determined After breath, place and the congestion coverage area of congestion can be determined according to second position information, it can be by the ground of user's congestion ahead The history jam situation stored in the information and dates library such as point and congestion coverage area is matched or is compared, to which prediction is worked as The time duration of preceding each congestion position congestion determines the predicted time length of each congestion position, then in basis Predicted congestion time span and incidence relation send jam situation prompt message to the vehicle-mounted system of each associated user in congestion position System.
In the present embodiment, the high in the clouds determines each gather around according to the second position information based on big data analysis information The predicted congestion time span of stifled position.By the above-mentioned means, can more accurately be predicted using big data analysis information each The congestion time duration of congestion position.
Further, it is congestion reminding method sixth embodiment flow diagram of the present invention with reference to Fig. 7, Fig. 7, based on above-mentioned Congestion reminding method embodiment of the present invention proposes the sixth embodiment of the present invention.
Based on above-described embodiment, in the present embodiment, the congestion reminding method further includes:
Step S120, the high in the clouds receive the path planning request that user terminal or user's onboard system are sent, wherein institute It includes origin information and endpoint information to state path planning request;
Step S130, the high in the clouds carry out path planning according to path planning request and traffic congestion situation, wherein The traffic congestion situation includes at least the second position information, the congestion distance or the predicted congestion time span.
Based on above-described embodiment, in the present embodiment, user, can be vehicle-mounted by user terminal or user in trip Systematic difference program set out path planning request, set out request when, first input beginning and end information, certainly, Yong Huke To select current position location as starting point.When inputting beginning and end information and determining, user's onboard system passes through communication The planning of module transmitting path is asked to high in the clouds, wherein further includes the mark of user's onboard system or user terminal in path planning request Know information, high in the clouds asked according to path planning in beginning and end information and the cartographic information that prestores determine one or more A feasible path, and be sent to corresponding user's onboard system or user terminal, user's onboard system or user terminal can be with Feasible way is shown on navigation map.High in the clouds can be carried out when determining feasible path according to the jam situation of each path Screening, such as the long path of congestion overlong time or congestion distance is given up, retain unimpeded path, naturally it is also possible to will go out The path of existing jam situation retains, in transmitting path planning information to user terminal or user's onboard system, by congestion path Jam situation be also sent to user terminal or user's onboard system so that user terminal or user's onboard system are according to by road The presentation of information of diameter jam situation is on corresponding path.
In the present embodiment, user is by user terminal or user's onboard system when checking route planning information, can be with Suitable path is selected, when user selectes path, user terminal or user's onboard system send choosing according to the path that user selectes Routing information is determined to high in the clouds.Before instruction or replacement path are reached home in user's triggering, high in the clouds monitors the traffic shape in the path State, it is according to the location information of user that jam situation prompt message is whole to corresponding user when jam situation occurs in the path End or user's onboard system, can also re-start path planning according to user's onboard system current location and jam situation, send out Send path planning advisory information to user terminal or user's onboard system.
In the present embodiment, the high in the clouds receives the path planning request that user terminal or user's onboard system are sent, In, the path planning request includes origin information and endpoint information;The high in the clouds is asked according to the path planning and traffic Jam situation carries out path planning, wherein the traffic congestion situation includes at least the second position information, the congestion road Journey or the predicted congestion time span.By the above-mentioned means, can be according to the travel information of user and jam situation into walking along the street Diameter is planned, is helped user to evade the path in congestion status, is improved the usage experience of user.
In addition, the present invention also provides a kind of congestion prompt systems.
With reference to figure 2, the first embodiment of congestion prompt system of the present invention is proposed.In the present embodiment, the congestion prompt System includes at least memory, processor and the congestion attention program being stored on the memory, and the congestion prompts journey Sequence realizes following steps when being executed by the processor:
Step S10, the high in the clouds receive the traffic state information that each user's onboard system is sent, wherein the traffic Status information includes at least the first position information and user's onboard system position preset range of each user's onboard system Interior vehicle distributed intelligence;
In the present embodiment, the congestion reminding method is applied to congestion prompt system, and the congestion prompt system is at least Including user's onboard system and high in the clouds, in the present embodiment, onboard system includes that vehicle-mounted hardware and management and control are vehicle-mounted The programming system of hardware and vehicle-mounted software resource.In the present embodiment, vehicle-mounted hardware is in addition to including positioning device, intelligent back vision mirror Or outside the conventional vehicle-mounted hardware such as automobile data recorder, the camera shooting of the vehicle distributed image on shooting driving path can also be configured to Head or the laser radar for obtaining vehicle distributed point cloud data on driving path, and the communication mould for being interacted with high in the clouds Block.High in the clouds can be interacted with each onboard system, the traffic state information sent for receiving each user's onboard system, and root It is in the position of congestion status according to the traffic state information of reception, and sends prompt message to corresponding onboard system.
In the present embodiment, traffic state information includes each onboard system position and position preset range Interior vehicle distributed intelligence.The vehicle distributed image that can be configured on user's onboard system on shooting driving path is taken the photograph As the laser radar of vehicle distributed point cloud data on head or acquisition driving path, vehicle can utilize vehicle during traveling It carries camera and periodically obtains current location information, i.e. first position information by positioning device, meanwhile, shooting vehicle is current Vehicle distributed image in the preset range of position preferably can only shoot the vehicle distributed image of vehicle forward direction.Each use The first position information of itself is associated with by family onboard system with the image of shooting, is generated traffic state information and is sent out by communication module Send traffic state information to high in the clouds.Camera shooting range can by control cradle head control camera pitch angle or deflection Angle controls.When being configured with mobile lidar on onboard system, it is current vehicle can be obtained by mobile lidar Vehicle in the preset range of position is distributed point cloud data.Each user's onboard system by the first position information of itself and obtain Vehicle distributed point cloud data correlation generates traffic state information, and traffic state information is sent to high in the clouds by communication module. In the present embodiment, vehicle can be arranged periodically to obtain traffic state information during the process of traveling and be sent to cloud End periodically obtains traffic state information and is sent to cloud when the speed of vehicle can also be arranged less than some pre-set velocity threshold value End.
Step S20, the high in the clouds determine the second position information in congestion status according to the traffic state information of reception, And congestion prompt message is sent to corresponding user's onboard system according to the first position information and the second position information.
Based on above-mentioned steps, when above-mentioned high in the clouds receives the traffic state information that each onboard system is sent, to receiving Traffic state information handled.The location information and corresponding vehicle point of onboard system are first obtained from traffic state information Cloth information, i.e. location information and vehicle distributed image or vehicle are distributed point cloud data.The present embodiment is by taking vehicle distributed image as an example It illustrates, high in the clouds can use training image in advance, train vehicle identification model.Different object recognition systems is different Training method.Many methods derive from bare metal learning art, such as boost, Winnow, support vector machines, RVM, shellfish The technologies such as leaf this theory, gauss hybrid models, EM algorithms, decision tree, decision stub.Training method is broadly divided into two major classes: The method of seeking difference (discriminative approach) and extensive method (generative approach).The method of seeking difference attempts in feature A decision boundary is found in space, and characteristic vector is classified, and judges whether it belongs to certain type objects.Sliding window model frequently with Method of seeking difference training pattern, SVM, decision tree, decision stub and boost class technologies are usually used in the extensive rule of the method for seeking difference as much as possible The feature for finding certain class object judges object according to the probability that these features occur using bayesian theory, gauss hybrid models Classification.Be arranged frequently with extensive method based on the method for component, Optimized model parameter, EM algorithms be commonly used to processing component and its it Between relationship, the problem of this method is a kind of method of iterative estimate parameter, it can handle shortage of data, but cannot be guaranteed Find global maximum.It specifically, can be according to figure after the vehicle distributed image that the onboard system A of high in the clouds acquisition vehicle A is sent As in the distributing position of vehicle and camera configuration configuration pitch angle or deflection angle and geometrical principle determine in image vehicle with Clap vehicle A relative position or image in relative position general between vehicle, so that it is determined that in image corresponding position vehicle Distribution density, then determines whether the position of jam situation and congestion further according to vehicle distribution density.Certainly also may be used To set vehicle fleet size threshold value, when vehicle fleet size is more than vehicle fleet size threshold value in the image of vehicle shooting, judge that the position goes out Existing jam situation.In the present embodiment, when more different vehicles are in similar position, the image of shooting may exist The part of overlapping, it is also possible to which in same paths but distance is farther out without being overlapped, can be based on the location information of position vehicle Distance or the unimpeded distance of congestion position and congestion are more accurately determined in conjunction with the image information of multiple vehicles.In this reality It applies in example, second position information refers to the location information of congestion regions, is the location information of a position range, may include Congestion starting point and congestion terminal.After determining the second position information in congestion status, further according to each user's onboard system First position information determine in congestion position or user's onboard system of the neighbouring preset range in congestion position, and it is corresponding The location information of congestion position and user's onboard system within a preset range are established into incidence relation, sent according to incidence relation The prompt message of traffic congestion is to associated user's onboard system.It in the present embodiment, can also be according to user's onboard system position Confidence breath determines the travel direction of corresponding vehicle, and the congestion road of vehicle front is determined further according to the vehicle distributed intelligence of vehicle front Journey or congestion time send prompt message to corresponding user's onboard system so that user according to congestion distance or congestion time Clear specific jam situation.Certainly in the present embodiment, determining can also be by broadcast after the second information of congestion position Jam situation is sent to the onboard system in bigger preset range by mode, for example, when the cities section A highway gets congestion, it will Congestion prompt message is sent to all onboard systems within the scope of the cities A.
In the present embodiment, the high in the clouds receives the traffic state information that each user's onboard system is sent, wherein described Traffic state information includes at least the first position information of each user's onboard system and user's onboard system position is preset Vehicle distributed intelligence in range;The high in the clouds determines the second position in congestion status according to the traffic state information of reception Information, and it is vehicle-mounted to corresponding user according to the first position information and second position information transmission congestion prompt message System.By the above-mentioned means, using traffic state information is acquired as each user's onboard system individual in traffic group, The area coverage that information collection can effectively be expanded, improves the timeliness of information collection;According to the first of user's onboard system Confidence cease and the second position information of congestion position can targetedly issuing traffic congestion information, improve user experience.
With reference to figure 3, the second embodiment of congestion prompt system of the present invention is proposed.In the present embodiment, the congestion prompt Program also realizes following steps when being executed by the processor:
Step S30, the high in the clouds obtain each user's onboard system position pair according to the traffic state information received The vehicle distributed intelligence for the preset range answered, and traffic density distributed intelligence is obtained according to the vehicle distributed intelligence;
Step S40, the high in the clouds determine the second confidence in congestion status according to the traffic density distributed intelligence Breath;
Step S50, the high in the clouds are less than the shortest distance according to the first position information and the second position information Or establish incidence relation equal to user's onboard system of pre-determined distance threshold value and each second position information;
Step S60, the high in the clouds are vehicle-mounted to each associated user according to incidence relation transmission congestion prompt message System.
Based on above-described embodiment, in the present embodiment, high in the clouds receives the traffic behavior that each user's onboard system is sent After information, the first position information of each onboard system and corresponding vehicle distributed image are first obtained from traffic state information, The vehicle distribution density information of user's onboard system position within a preset range, Ke Yigen are determined according to vehicle distributed image The shooting image less than or equal to multiple onboard systems of pre-determined distance position is combined according to the location information of user's onboard system Obtain more complete traffic density distributed intelligence.The present embodiment is illustrated by taking vehicle distributed image as an example, and high in the clouds can be pre- Training image is first used, vehicle identification model is trained.Different object recognition systems has different training methods.Many methods From bare metal learning art, such as boost, Winnow, support vector machines, RVM, bayesian theory, Gaussian Mixture mould The technologies such as type, EM algorithms, decision tree, decision stub.Training method is broadly divided into two major classes:The method of seeking difference (discriminative approach) and extensive method (generative approach).The method of seeking difference attempts to look in feature space To a decision boundary, characteristic vector is classified, judges whether it belongs to certain type objects.Sliding window model is frequently with the method for seeking difference Training pattern, SVM, decision tree, decision stub and boost class technologies are usually used in the extensive rule of the method for seeking difference and find certain as much as possible The feature of class object judges the class of object using bayesian theory, gauss hybrid models according to the probability that these features occur Not.Be arranged frequently with extensive method based on the method for component, Optimized model parameter, EM algorithms be commonly used to processing component and its between The problem of relationship, this method are a kind of methods of iterative estimate parameter, it can handle shortage of data, but cannot be guaranteed to find Global maximum.It specifically, can be according in image after the vehicle distributed image that the onboard system A of high in the clouds acquisition vehicle A is sent Distributing position and camera configuration the configuration pitch angle or deflection angle and geometrical principle of vehicle determine vehicle and bat vehicle in image Relative position general between vehicle in the relative position or image of A, can also be big according to the imaging of vehicle in the picture The actual range of vehicle and vehicle A in small determining image, so that it is determined that the distributing position of vehicle.So that it is determined that corresponding in image The vehicle distribution density of position, then determines whether the position of jam situation and congestion further according to vehicle distribution density. Vehicle fleet size threshold value can certainly be set, the quantity of vehicle is as in preset range near user's onboard system using in image Traffic density distributed intelligence.When vehicle fleet size is more than vehicle fleet size threshold value in the image of vehicle shooting, judge that the position occurs Jam situation.In the present embodiment, when more different vehicles are in similar position, the image of shooting may have weight Folded part, it is also possible to which in same paths but distance is farther out without being overlapped, can be based on the location information knot of position vehicle The image information for closing multiple vehicles more accurately determines distance or the unimpeded distance of congestion position and congestion.Specifically, The camera of user's onboard system A can only be shot to the vehicle distributed image in direction of advance coverage, the vehicle-mounted system of user The image of the shooting of system A is sent to high in the clouds and obtains vehicle when high in the clouds receives the vehicle distributed image that user's onboard system A is sent The first position information of distributed image and user's onboard system A identifies the vehicle in vehicle distributed image, and determining can in image Identify vehicle quantity, judge can recognize that vehicle quantity whether be greater than or equal to preset quantity threshold value n, if more than or be equal to, Then determine that the camera sites user onboard system A are in congestion status, and congestion road is determined with the shooting distance of user's vehicle onboard system Journey.Then it determines to be less than or equal at a distance from each congestion position further according to the first position information of user's onboard system and preset User's onboard system of distance, and the second information and user's vehicle in congestion status by distance less than or equal to pre-determined distance Loading system establishes incidence relation, for example, user's onboard system A and the shortest distance of congestion position first are less than pre-determined distance, user Onboard system B and the shortest distance of congestion position second are less than pre-determined distance, then respectively by user's onboard system A and congestion position first Incidence relation is established, user's onboard system B establishes incidence relation with congestion position second.High in the clouds sends congestion feelings according to incidence relation Condition prompt message will be sent to user to corresponding user's onboard system about the prompt message of congestion position first jam situation Onboard system A will be sent to user's onboard system B about the prompt message of congestion position second jam situation.
In the present embodiment, the high in the clouds obtains each user's onboard system institute in place according to the traffic state information received The vehicle distributed intelligence of corresponding preset range is set, and traffic density distributed intelligence is obtained according to the vehicle distributed intelligence;Institute It states high in the clouds and the second position information in congestion status is determined according to the traffic density distributed intelligence;
The high in the clouds is less than or equal to the shortest distance according to the first position information and the second position information pre- If user's onboard system of distance threshold establishes incidence relation with each second position information;It is closed according to the association in the high in the clouds System sends congestion prompt message to each associated user's onboard system.It is distributed according to traffic density by the above-mentioned means, realizing Information determines the position in congestion status, and may according to user's onboard system and the determination at a distance from congestion status position The user's onboard system that can be influenced by cur-rent congestion situation, and established with the location information in congestion status having an impact Incidence relation pointedly sends the prompt message of traffic congestion situation according to incidence relation to associated user's onboard system.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium.
Congestion attention program is stored on computer readable storage medium of the present invention, the congestion attention program is by processor The step of congestion reminding method as described above is realized when execution.
Wherein, the congestion attention program run on the processor is performed realized method and can refer to the present invention The each embodiment of congestion reminding method, details are not described herein again.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to non-row His property includes, so that process, method, article or system including a series of elements include not only those elements, and And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this There is also other identical elements in the process of element, method, article or system.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases The former is more preferably embodiment.Based on this understanding, technical scheme of the present invention substantially in other words does the prior art Going out the part of contribution can be expressed in the form of software products, which is stored in one as described above In storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions use so that a station terminal equipment (can be mobile phone, Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills Art field, is included within the scope of the present invention.

Claims (10)

1. a kind of swarm intelligence congestion reminding method, which is characterized in that the congestion reminding method is applied to congestion prompt system, The congestion prompt system includes at least user's onboard system and high in the clouds, and the congestion reminding method includes:
The high in the clouds receives the traffic state information that each user's onboard system is sent, wherein the traffic state information is at least Vehicle distribution in first position information and user's onboard system position preset range including each user's onboard system Information;
The high in the clouds determines the second position information in congestion status according to the traffic state information of reception, and according to described the One location information and the second position information send congestion prompt message to corresponding user's onboard system.
2. swarm intelligence congestion reminding method as described in claim 1, which is characterized in that the vehicle distributed intelligence includes vehicle The vehicle of the vehicle distributed image or mobile lidar acquisition that carry camera shooting is distributed point cloud data.
3. swarm intelligence congestion reminding method as described in claim 1, which is characterized in that the high in the clouds is according to the traffic of reception Status information determines the second position information in congestion status, and according to the first position information and the second confidence Breath send congestion prompt message to the step of corresponding user's onboard system include:
The high in the clouds obtains the corresponding preset range in each user's onboard system position according to the traffic state information received Vehicle distributed intelligence, and according to the vehicle distributed intelligence obtain traffic density distributed intelligence;
The high in the clouds determines the second position information in congestion status according to the traffic density distributed intelligence;
The high in the clouds according to the first position information and the second position information to the shortest distance be less than or equal to it is default away from User's onboard system from threshold value establishes incidence relation with each second position information;
The high in the clouds sends congestion prompt message to each associated user's onboard system according to the incidence relation.
4. swarm intelligence congestion reminding method as claimed in claim 3, which is characterized in that the high in the clouds is close according to the vehicle Further include after the step of degree distributed intelligence determines the second position information in congestion status:
The high in the clouds determines the congestion distance of each congestion position according to the second position information;
The high in the clouds according to the incidence relation send congestion prompt message to the step of each associated user's onboard system wrap It includes:
The high in the clouds sends congestion prompt message to each pass according to the congestion distance of each congestion position and the incidence relation User's onboard system of connection.
5. swarm intelligence congestion reminding method as claimed in claim 3, which is characterized in that the high in the clouds is close according to the vehicle Further include after the step of degree distributed intelligence determines the second position information in congestion status:
The high in the clouds determines the predicted congestion time span of each congestion position according to the second position information;
The high in the clouds according to the incidence relation send congestion prompt message to the step of each associated user's onboard system wrap It includes:
The high in the clouds sends congestion prompt message according to the predicted congestion time span of each congestion position and the incidence relation To each associated user's onboard system.
6. swarm intelligence congestion reminding method as claimed in claim 5, which is characterized in that the high in the clouds is according to the second The step of confidence breath determines the predicted congestion time span of each congestion position include:
The high in the clouds determines the predicted congestion of each congestion position according to the second position information based on big data analysis information Time span.
7. such as swarm intelligence congestion reminding method according to any one of claims 1 to 6, which is characterized in that the traffic is gathered around Blocking up prompt situation reminding method further includes:
The high in the clouds receives the path planning request that user terminal or user's onboard system are sent, wherein the path planning is asked It asks including origin information and endpoint information;
The high in the clouds carries out path planning according to path planning request and traffic congestion situation, wherein the traffic congestion Situation includes at least the second position information, the congestion distance or the predicted congestion time span.
8. a kind of congestion prompt system, which is characterized in that the congestion prompt system includes at least memory, processor and deposits The congestion attention program on the memory is stored up, following step is realized when the congestion attention program is executed by the processor Suddenly:
The high in the clouds receives the traffic state information that each user's onboard system is sent, wherein the traffic state information is at least Vehicle distribution in first position information and user's onboard system position preset range including each user's onboard system Information;
The high in the clouds determines the second position information in congestion status according to the traffic state information of reception, and according to described the One location information and the second position information send congestion prompt message to corresponding user's onboard system.
9. congestion prompt system as claimed in claim 8, which is characterized in that the congestion attention program is held by the processor Following steps are also realized when row:
The high in the clouds obtains the corresponding preset range in each user's onboard system position according to the traffic state information received Vehicle distributed intelligence, and according to the vehicle distributed intelligence obtain traffic density distributed intelligence;
The high in the clouds determines the second position information in congestion status according to the traffic density distributed intelligence;
The high in the clouds according to the first position information and the second position information to the shortest distance be less than or equal to it is default away from User's onboard system from threshold value establishes incidence relation with each second position information;
The high in the clouds sends congestion prompt message to each associated user's onboard system according to the incidence relation.
10. a kind of computer readable storage medium, which is characterized in that be stored with congestion on the computer readable storage medium and carry Show program, the congestion prompt as described in any one of claim 1 to 7 is realized when the congestion attention program is executed by processor The step of method.
CN201810430004.1A 2018-05-08 2018-05-08 Swarm intelligence congestion reminding method, system and computer readable storage medium Pending CN108399778A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810430004.1A CN108399778A (en) 2018-05-08 2018-05-08 Swarm intelligence congestion reminding method, system and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810430004.1A CN108399778A (en) 2018-05-08 2018-05-08 Swarm intelligence congestion reminding method, system and computer readable storage medium

Publications (1)

Publication Number Publication Date
CN108399778A true CN108399778A (en) 2018-08-14

Family

ID=63101605

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810430004.1A Pending CN108399778A (en) 2018-05-08 2018-05-08 Swarm intelligence congestion reminding method, system and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN108399778A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109670431A (en) * 2018-12-11 2019-04-23 北京小马智行科技有限公司 A kind of behavioral value method and device
CN110047305A (en) * 2019-04-04 2019-07-23 安徽中交汇能网络科技有限公司 Reminding method, device, system and the road monitoring device of congestion in road
CN110363991A (en) * 2019-07-16 2019-10-22 珠海市杰理科技股份有限公司 Road condition analyzing method, apparatus, processing equipment, road condition analyzing system and vehicle
CN111640321A (en) * 2020-05-29 2020-09-08 深圳市元征科技股份有限公司 Congestion relieving method based on edge calculation and related equipment
CN113870548A (en) * 2020-06-30 2021-12-31 奥迪股份公司 Traffic management apparatus, corresponding method, server, computer device, and medium
CN114241746A (en) * 2021-11-08 2022-03-25 广西北投交通养护科技集团有限公司 Expressway tandem rear-end collision accident safety early warning device and method

Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101391589A (en) * 2008-10-30 2009-03-25 上海大学 Vehicle intelligent alarming method and device
CN101523459A (en) * 2006-10-13 2009-09-02 爱信艾达株式会社 Traffic information distributing apparatus
CN102663894A (en) * 2012-05-20 2012-09-12 杭州妙影微电子有限公司 Road traffic condition foreknowing system and method based on internet of things
CN102930735A (en) * 2012-10-25 2013-02-13 安徽科力信息产业有限责任公司 City real-time traffic and road condition information issuing method based on traffic video
CN104952123A (en) * 2015-05-27 2015-09-30 关晓芙 Vehicle-mounted equipment installed on vehicle as well as related equipment and method
CN105390009A (en) * 2015-11-17 2016-03-09 广东好帮手电子科技股份有限公司 Dynamic traffic information release method and dynamic traffic information release system
CN105474285A (en) * 2013-09-06 2016-04-06 奥迪股份公司 Method, evaluation system and vehicle for predicting at least one congestion parameter
CN105488454A (en) * 2015-11-17 2016-04-13 天津工业大学 Monocular vision based front vehicle detection and ranging method
CN105513378A (en) * 2015-12-21 2016-04-20 宇龙计算机通信科技(深圳)有限公司 Vehicle networking method, vehicle networking device and vehicle networking system
CN105574552A (en) * 2014-10-09 2016-05-11 东北大学 Vehicle ranging and collision early warning method based on monocular vision
CN106469503A (en) * 2015-08-14 2017-03-01 高德软件有限公司 A kind of method and apparatus of prediction traffic events coverage
CN106679633A (en) * 2016-12-07 2017-05-17 东华大学 Vehicle-mounted distance measuring system and vehicle-mounted distance measuring method
CN106683401A (en) * 2015-11-11 2017-05-17 丰田自动车株式会社 Vehicle image data transmission device
CN106981212A (en) * 2016-01-19 2017-07-25 霍尼韦尔国际公司 Traffic visualization system
CN107038885A (en) * 2017-05-23 2017-08-11 奇瑞汽车股份有限公司 Traffic reminding method and device
CN107045794A (en) * 2017-01-16 2017-08-15 百度在线网络技术(北京)有限公司 Road conditions processing method and processing device
CN207008863U (en) * 2017-08-11 2018-02-13 李硕 A kind of road traffic monitoring system based on drive recorder
CN107945557A (en) * 2017-12-21 2018-04-20 江西爱驰亿维实业有限公司 Real-time road display methods, device, computing device and computer-readable storage medium

Patent Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101523459A (en) * 2006-10-13 2009-09-02 爱信艾达株式会社 Traffic information distributing apparatus
CN101391589A (en) * 2008-10-30 2009-03-25 上海大学 Vehicle intelligent alarming method and device
CN102663894A (en) * 2012-05-20 2012-09-12 杭州妙影微电子有限公司 Road traffic condition foreknowing system and method based on internet of things
CN102930735A (en) * 2012-10-25 2013-02-13 安徽科力信息产业有限责任公司 City real-time traffic and road condition information issuing method based on traffic video
CN105474285A (en) * 2013-09-06 2016-04-06 奥迪股份公司 Method, evaluation system and vehicle for predicting at least one congestion parameter
CN105574552A (en) * 2014-10-09 2016-05-11 东北大学 Vehicle ranging and collision early warning method based on monocular vision
CN104952123A (en) * 2015-05-27 2015-09-30 关晓芙 Vehicle-mounted equipment installed on vehicle as well as related equipment and method
CN106469503A (en) * 2015-08-14 2017-03-01 高德软件有限公司 A kind of method and apparatus of prediction traffic events coverage
CN106683401A (en) * 2015-11-11 2017-05-17 丰田自动车株式会社 Vehicle image data transmission device
JP2017091250A (en) * 2015-11-11 2017-05-25 トヨタ自動車株式会社 Vehicular image data transfer apparatus
CN105488454A (en) * 2015-11-17 2016-04-13 天津工业大学 Monocular vision based front vehicle detection and ranging method
CN105390009A (en) * 2015-11-17 2016-03-09 广东好帮手电子科技股份有限公司 Dynamic traffic information release method and dynamic traffic information release system
CN105513378A (en) * 2015-12-21 2016-04-20 宇龙计算机通信科技(深圳)有限公司 Vehicle networking method, vehicle networking device and vehicle networking system
CN106981212A (en) * 2016-01-19 2017-07-25 霍尼韦尔国际公司 Traffic visualization system
CN106679633A (en) * 2016-12-07 2017-05-17 东华大学 Vehicle-mounted distance measuring system and vehicle-mounted distance measuring method
CN107045794A (en) * 2017-01-16 2017-08-15 百度在线网络技术(北京)有限公司 Road conditions processing method and processing device
CN107038885A (en) * 2017-05-23 2017-08-11 奇瑞汽车股份有限公司 Traffic reminding method and device
CN207008863U (en) * 2017-08-11 2018-02-13 李硕 A kind of road traffic monitoring system based on drive recorder
CN107945557A (en) * 2017-12-21 2018-04-20 江西爱驰亿维实业有限公司 Real-time road display methods, device, computing device and computer-readable storage medium

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109670431A (en) * 2018-12-11 2019-04-23 北京小马智行科技有限公司 A kind of behavioral value method and device
CN110047305A (en) * 2019-04-04 2019-07-23 安徽中交汇能网络科技有限公司 Reminding method, device, system and the road monitoring device of congestion in road
CN110047305B (en) * 2019-04-04 2021-07-06 安徽中交汇能网络科技有限公司 Road congestion prompting method, device and system and road monitoring device
CN110363991A (en) * 2019-07-16 2019-10-22 珠海市杰理科技股份有限公司 Road condition analyzing method, apparatus, processing equipment, road condition analyzing system and vehicle
CN111640321A (en) * 2020-05-29 2020-09-08 深圳市元征科技股份有限公司 Congestion relieving method based on edge calculation and related equipment
CN111640321B (en) * 2020-05-29 2021-11-12 深圳市元征科技股份有限公司 Congestion relieving method based on edge calculation and related equipment
CN113870548A (en) * 2020-06-30 2021-12-31 奥迪股份公司 Traffic management apparatus, corresponding method, server, computer device, and medium
CN114241746A (en) * 2021-11-08 2022-03-25 广西北投交通养护科技集团有限公司 Expressway tandem rear-end collision accident safety early warning device and method

Similar Documents

Publication Publication Date Title
CN108399778A (en) Swarm intelligence congestion reminding method, system and computer readable storage medium
US11302031B2 (en) System, apparatus and method for indoor positioning
JP6784854B2 (en) Providing traffic warnings to users based on return delays
US10849543B2 (en) Focus-based tagging of sensor data
US20210201070A1 (en) Systems and methods for semantic map-based adaptive auto-exposure
WO2021133789A1 (en) Systems and methods for incident detection using inference models
US11162806B2 (en) Learning and predictive navigation system
EP3037782A1 (en) Method and apparatus for providing a steering reliability map based on driven curvatures and geometry curvature
CN108475057A (en) The method and system of one or more tracks of situation prediction vehicle based on vehicle periphery
CN110239562A (en) The real-time perception adjustment based on surrounding vehicles behavior of automatic driving vehicle is adjusted with driving
US20210191394A1 (en) Systems and methods for presenting curated autonomy-system information of a vehicle
US10243867B2 (en) Vehicle security system
CN109246364A (en) Photographic device method of adjustment and relevant device
WO2022105395A1 (en) Data processing method, apparatus, and system, computer device, and non-transitory storage medium
JP2020535549A (en) Systems and methods for matching autonomous vehicles to passengers
US10254123B2 (en) Navigation system with vision augmentation mechanism and method of operation thereof
JP2020535540A (en) Systems and methods for determining whether an autonomous vehicle can provide the requested service for passengers
CN111192341A (en) Method and device for generating high-precision map, automatic driving equipment and storage medium
CN113205088B (en) Obstacle image presentation method, electronic device, and computer-readable medium
US11186289B2 (en) Concealment system for improved safe driving
US11874118B2 (en) Crowdsourcing map maintenance
KR20240047408A (en) Detected object path prediction for vision-based systems
CN117130298A (en) Method, device and storage medium for evaluating an autopilot system
EP3040682B1 (en) Learning and predictive navigation system
US20220194426A1 (en) Method and apparatus for increasing passenger safety based on accident/road link correlation

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180814