CN101226688A - System and method for monitoring traffic congestion status based on cluster - Google Patents
System and method for monitoring traffic congestion status based on cluster Download PDFInfo
- Publication number
- CN101226688A CN101226688A CNA2008100560991A CN200810056099A CN101226688A CN 101226688 A CN101226688 A CN 101226688A CN A2008100560991 A CNA2008100560991 A CN A2008100560991A CN 200810056099 A CN200810056099 A CN 200810056099A CN 101226688 A CN101226688 A CN 101226688A
- Authority
- CN
- China
- Prior art keywords
- cluster
- module
- cluster piece
- piece
- highway section
- 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.)
- Granted
Links
Images
Abstract
Disclosed are a system for monitoring traffic jams conditions based on clustering and a method thereof, wherein the system comprises a road network modeling module, a clustering block creation module, a forecasting module, an accident processing module and a monitoring module, wherein the road network modeling module is used to model the road network, the clustering block creation module is used to form the clustering blocks of vehicles in the road network according to motion state of objects and the distance between the objects, the forecasting module is used to forecast the splitting time of each clustering block and generate the accidents of splitting and merging, the accident processing module is used to process the accidents of splitting and merging of the clustering blocks, and to merge the clustering blocks, the distance of which is close into a dense region, and the monitoring module is used to monitor the dense region in road network.
Description
Technical field
The present invention relates to the problem that mobile object close quarters is found.Specifically, relate to a kind of system and method thereof that is used for coming the monitoring and controlling traffic congestion based on cluster.
Background technology
Cluster analysis is just the data object to be divided into groups, and make to have higher similarity between the object in same group, and the object difference on the same group is not bigger.Cluster analysis has constituted basic data analysis function, is applied in widely in many application, comprises Flame Image Process, data compression, pattern identification and market survey.Can identify intensive and sparse zone by cluster, thereby find the distribution pattern of the overall situation.We regard the vehicle that moves on the road network as mobile object, and so mobile object is carried out cluster analysis can predicted city traffic congestion situation.
Existing mobile object cluster working hypothesis object motion utilizes several clusters in Europe between object to define the similarity of object in free space.In real world, object moves in the limited space network, and for example, automobile moves on road network.Therefore, utilize the more realistic requirement of similarity of network distance definition object between object.Here, network distance refers in the network shortest path distance between object.
When the target of cluster when the spatial object of static state changes to the mobile object of motion road network, the complicacy of cluster will increase greatly.On the one hand continuous change can take place along with the time in huge and their position of the mobile number of objects on the road network, make clustering result also may be along with the time, change along with mobile motion of objects, even the very little position change of object also may cause diverse cluster result.Mobile motion of objects is also complicated unusually on the road network simultaneously, the feasible trend that is difficult to catch object.On the other hand on the classic method when the similarity of calculating between the mobile object, the method that is adopted is several distances of directly calculating between the mobile object in Europe, and under the situation of road network, should consider to use network distance to calculate similarity between the mobile object.
Summary of the invention
In order to solve above-mentioned traditional problem, so one object of the present invention is exactly to have proposed a kind of system and method thereof that is used for coming based on cluster the monitoring and controlling traffic congestion.
In one aspect of the invention, proposed a kind ofly to come the system of monitoring and controlling traffic congestion based on cluster, this system comprises: the road network MBM is used for the road network modeling; The cluster piece is set up module, is used for according to motion of objects state and the distance between them, forms the cluster piece of vehicle in road network; Prediction module is used to predict the splitting time of each cluster piece, and produces division and merging incident; Event processing module is used to handle the division and the merging incident of cluster piece, and the cluster piece close mutual distance is merged into close quarters; And monitoring modular, be used for monitoring the close quarters of road network.
In aspect this, wherein the cluster piece is set up module mutual distance is close and object that motion state is similar and is constituted cluster piece one by one.
In aspect this, wherein prediction module further comprises: load module is used to import the cluster piece; Judge module is used to judge cluster piece position, judges that promptly the cluster piece is in the middle of end, highway section or highway section; Splitting time obtains module, is used for judging the cluster piece at judge module and obtains the time that splitting time is first object arrival crossing of cluster piece under the situation in the middle of the highway section; Computing module is used for judging the cluster piece under the situation at end, highway section at judge module, calculates two earliest time t that object meets in the cluster piece
mComparison module, be used for the ultimate range of every pair of contiguous object with compare apart from threshold values ε with up to t
mConstantly; Update module does not all surpass apart from threshold values ε, then from t if comparison module is judged the ultimate range of every pair of contiguous object
mObject-order after the upgating object order also will be upgraded is constantly sent into computing module; And the splitting time computing module, if sometime, the ultimate range that comparison module is judged every pair of contiguous object surpasses apart from threshold values ε, then will surpass the splitting time that be recorded as the cluster piece apart from the moment the earliest of threshold values ε.
In aspect this, wherein processing module further comprises: computing module is used for calculating the time that each object of each cluster piece arrives the end, highway section; Judge module is used for judging whether first object of cluster piece arrives the end, highway section; Grouping module is used for when first object of a cluster piece arrives the end, highway section, the direction grouping of object in this cluster piece according to object; And the merging module, be used for every group objects being merged to the cluster piece in next highway section according to distance threshold values ε.
In aspect this, wherein in the one-tenth figure of road networking modeling, the limit in the corresponding diagram of highway section, the node in the intersection corresponding diagram.
In aspect this, wherein to liking the vehicle that moves on the road network.
In aspect this, wherein the physical location of cluster piece is the physical location of border object.
In aspect this, wherein motion vector is the slope of boundary straight line.
In aspect this, wherein the enough near cluster piece of distance merges between any two, finds the close quarters on the road net.
In another aspect of the present invention, proposed a kind ofly to come the method for monitoring and controlling traffic congestion based on cluster, this method comprises: A, road network is carried out modeling; B, according to motion of objects state and the distance between them, in road network, form the cluster piece of vehicle; C, predict the splitting time of each cluster piece, and produce division and merging incident; The division and the merging incident of D, processing cluster piece, the cluster piece close mutual distance is merged into close quarters; And the close quarters among the E, monitoring road network.
In aspect this, wherein mutual distance is close and object that motion state is similar constitutes cluster piece one by one in step B.
In aspect this, wherein step C further comprises: input cluster piece; Judge cluster piece position, judge that promptly the cluster piece is in the middle of end, highway section or highway section; To obtain splitting time under the situation of cluster piece in the middle of the highway section be the time that first object of cluster piece arrives the crossing judging; Judge the cluster piece under the situation at end, highway section, calculating two earliest time t that object meets in the cluster piece
mThe ultimate range of every pair of contiguous object with compare apart from threshold values ε with up to t
mConstantly; If comparing the ultimate range of every pair of contiguous object does not all surpass apart from threshold values ε, then from t
mObject-order after the upgating object order also will be upgraded is constantly sent into computing module; And if sometime, the ultimate range that compares every pair of contiguous object surpasses apart from threshold values ε, then will surpass the splitting time that be recorded as the cluster piece apart from the moment the earliest of threshold values ε.
In aspect this, wherein step D further comprises: the time of calculating each object arrival end, highway section in each cluster piece; Judge whether first object in the cluster piece arrives the end, highway section; When first object of a cluster piece arrives the end, highway section, the direction grouping of object in this cluster piece according to object; And every group objects is merged in the cluster piece in next highway section according to distance threshold values ε.
In aspect this, wherein in the one-tenth figure of road networking modeling, the limit in the corresponding diagram of highway section, the node in the intersection corresponding diagram.
In aspect this, wherein to liking the vehicle that moves on the road network.
In aspect this, wherein the physical location of cluster piece is the physical location of border object.
In aspect this, wherein motion vector is the slope of boundary straight line.
In aspect this, wherein the enough near cluster piece of distance merges between any two, finds the close quarters on the road net.
Description of drawings
In conjunction with accompanying drawing subsequently, what may be obvious that from following detailed description draws above-mentioned and other purpose of the present invention, feature and advantage.In the accompanying drawings:
Fig. 1 has provided the block scheme according to traffic congestion condition monitoring of the present invention system;
Fig. 2 has provided the process flow diagram according to traffic congestion condition monitoring of the present invention system;
Fig. 3 has provided the process flow diagram according to prediction module prediction splitting time of the present invention;
Fig. 4 has provided the exemplary plot according to prediction splitting time of the present invention;
Fig. 5 has provided the more detailed block diagram according to prediction module of the present invention;
Fig. 6 has provided the process flow diagram according to event processing module of the present invention;
Fig. 7 has provided the exemplary plot of handling according to the time of the present invention;
Fig. 8 has provided the more detailed block diagram according to event processing module of the present invention; And
Fig. 9 has provided according to the mobile object close quarters example that distributes on the road network of the present invention.
Embodiment
Along with GPS, development of wireless communication devices, and the widespread use of wireless device, the data management technique in the research mobile computing environment, i.e. move database research has become a new direction.Mobile object database is meant the database that mobile object (as vehicle, aircraft, mobile subscriber etc.) and position thereof are managed.Mobile object database has represented wide application prospect in a lot of fields.Militarily, mobile object database can be answered the routine data unanswerable inquiry in storehouse; At civil area, utilizing mobile object database technology to realize can only transportation system, the automatic dispatch system of taxi/policeman, the logistics distribution system of intelligent society safeguards system and high intelligence.In addition, mobile object database also has a wide range of applications in e-commerce field.Mobile object database research mainly comprises two aspects: move database technical research and the research of mobile Object Management group.The present invention promptly will move exactly and to being applied to as database research the traffic congestion situation be monitored.
Fig. 1 is the block scheme of traffic congestion condition monitoring system.In Fig. 1, in actual applications, mobile object can be a taxi.Yet moving picture can be other other mobile objects also.As shown in Figure 1, this system comprises: the road network MBM, be used for the road network modeling, wherein become among the figure at the road networking of institute's modeling, limit in the corresponding diagram of highway section, node in the intersection corresponding diagram, the physical location of cluster piece is the physical location of border object, and motion vector is the slope of boundary straight line; The cluster piece is set up module, according to the motion state of vehicle and the distance between them, forms the cluster piece of vehicle in road network, that is to say that mutual distance is close and object that motion state is similar constitutes cluster piece one by one; Prediction module is used to predict the splitting time of each cluster piece, and produces division and merging incident; Event processing module, the division and the merging incident of processing cluster piece, the cluster piece close mutual distance is merged into close quarters; And monitoring modular, be used for monitoring the close quarters of road network.
The flow process of this traffic congestion condition monitoring system as shown in Figure 2.At first, the road network MBM wherein becomes among the figure at the road networking of institute's modeling the road network modeling, limit in the corresponding diagram of highway section, node in the intersection corresponding diagram, the physical location of cluster piece is the physical location of border object, and motion vector is the slope of boundary straight line; Next, the cluster piece set up module according to the motion state of vehicle and the distance between them in road network, to form the cluster piece of vehicle, that is to say that mutual distance is close and object that motion state is similar constitutes cluster piece one by one; Prediction module is predicted the splitting time of each cluster piece and is produced division and merging incident; Event processing module is handled the division and the merging incident of cluster piece, and the cluster piece close mutual distance is merged into close quarters; At last, the close quarters in the monitoring module monitors road network.
Next, the prediction module in this system is described in detail.
Fig. 3 and Fig. 4 have provided process flow diagram and the exemplary plot of prediction module prediction cluster block splitting time respectively.At first import CB (being the cluster piece), judge the CB position, judge that promptly CB is in the middle of the end, highway section still is the highway section.Specifically, the cluster block splitting occurs in two kinds of situations.First kind of situation is when the cluster piece arrives the end, highway section (junction node in the spatial network just).When the mobile object in the cluster piece arrives the intersection, because they may be to different direction motions, so the cluster piece must divide.Obviously, splitting time is the time at first object arrival crossing of cluster piece.Second kind of situation is that the cluster piece is positioned in the middle of the highway section, and promptly the splitting time of cluster piece is that distance surpasses in the ε (between indicated object apart from threshold values) between the contiguous object of moving on same highway section.Yet, because contiguous object constantly variation in time, so be not easy to predict splitting time.Therefore, in this case, main task is the order of object on the Dynamic Maintenance highway section.We calculate two earliest times that object meets in the cluster piece, are designated as t
m, then the ultimate range of every pair of contiguous object is compared up to t with ε
mConstantly.If at some constantly, this distance surpasses ε, and process stops, and what surpass ε is recorded splitting time as the cluster piece the earliest constantly.Otherwise we are from t
mThe upgating object order goes through the same process again then constantly, surpasses ε up to some distances, and perhaps one of them object has arrived the end, highway section.When the speed of an object changed along with the variation in highway section, we need predict the division and the merging time of cluster piece again.
Fig. 5 has provided the more detailed block diagram that can realize the prediction module of Fig. 3 flow process.As shown in Figure 5, this prediction module comprises: load module is used to import CB (being the cluster piece); Judge module is used to judge the CB position, judges that promptly CB is in the middle of the end, highway section still is the highway section; Splitting time obtains module, is used for judging CB at judge module and obtains the time that splitting time is first object arrival crossing of cluster piece under the situation in the middle of the highway section; Computing module is used for judging CB under the situation at end, highway section at judge module, calculates two earliest time t that object meets in the cluster piece
mComparison module is used for the ultimate range of every pair of contiguous object is compared with ε with up to t
mConstantly; Update module does not all surpass ε if comparison module is judged the ultimate range of every pair of contiguous object, then from t
mObject-order after the upgating object order also will be upgraded is constantly sent into computing module; And the splitting time computing module, if sometime, the ultimate range that comparison module is judged every pair of contiguous object surpasses ε, the moment the earliest that then will surpass ε be recorded as the splitting time of cluster piece.
Fig. 6 and Fig. 7 provide process flow diagram and the exemplary plot that processing module is handled the division incident respectively.If the division incident occurs on the highway section, we can be divided into two to the cluster piece simply, and predict each division and merging incident.If the division incident occurs in the end, highway section, processing procedure will be complicated.A direct method is just to handle once division when having individual object to arrive the end, highway section at every turn.Obviously, the cost height of this method.In order to reduce the processing cost, propose component and split pattern.Specifically, calculate the time at each object arrival end, highway section in each cluster piece.After this, judge whether first object in the cluster piece arrives the end, highway section.When first object of a cluster piece arrives the end, highway section, the direction grouping of object in this cluster piece according to object.Then, according to distance threshold values ε every group objects is merged in the cluster piece in next highway section.
The merging of cluster piece occur on the highway section motion together in abutting connection with (just, their network distance is not more than ε) between the cluster piece.In order to predict the initial merging moment of cluster piece, the border object of our each cluster piece of Dynamic Maintenance and their effective time (being the time period that border object is kept in the cluster piece), in effective time, the minor increment of the border object of two cluster pieces and ε are compared then.Border object can be to safeguard by the service object order calculating splitting time.On the highway section, the processing procedure that merges incident is similar to the division incident.We obtain the merging incident from event queue and the time is merged into a cluster piece to a plurality of cluster pieces, and calculate the division and the merging time of the cluster piece after merging.Finally, the corresponding cluster piece that is affected in the update event formation.
Fig. 8 has provided the more detailed block diagram that can realize the processing module of Fig. 6 flow process.As shown in Figure 8, this processing module comprises: computing module is used for calculating the time that each object of each cluster piece arrives the end, highway section; Judge module is used for judging whether first object of cluster piece arrives the end, highway section; Grouping module is used for when first object of a cluster piece arrives the end, highway section, the direction grouping of object in this cluster piece according to object; Merge module, be used for every group objects being merged to the cluster piece in next highway section according to distance threshold values ε.
Except division and merging cluster piece, new object can enter network, and perhaps existing object can leave.For a new object, we locate all cluster pieces that the object on the same highway section enters, and judge whether that according to the definition of cluster piece a new object can join in the cluster piece.If object can add, the division of cluster piece and merging incident just are updated.If can not join certain cluster piece, be new cluster piece of this Object Creation just.
Fig. 9 provides the close quarters exemplary plot.Cluster piece according to safeguarding can make up the application layer cluster according to various criterion.We have considered three kinds of common cluster standards.Just, based on distance,, cut apart based on K-based on density.
What may be obvious that for the person of ordinary skill of the art draws other advantages and modification.Therefore, the present invention with wider aspect is not limited to shown and described specifying and exemplary embodiment here.Therefore, under situation about not breaking away from, can make various modifications to it by the spirit and scope of claim and the defined general inventive concept of equivalents thereof subsequently.
Claims (10)
1. one kind is come the system of monitoring and controlling traffic congestion based on cluster, comprising:
The road network MBM is used for the road network modeling;
The cluster piece is set up module, is used for according to motion of objects state and the distance between them, forms the cluster piece of vehicle in road network;
Prediction module is used to predict the splitting time of each cluster piece, and produces division and merging incident;
Event processing module is used to handle the division and the merging incident of cluster piece, and the cluster piece close mutual distance is merged into close quarters; And
Monitoring modular is used for monitoring the close quarters of road network.
According to claim 1 come the system of monitoring and controlling traffic congestion based on cluster, wherein the cluster piece is set up module mutual distance is close and object that motion state is similar and is constituted cluster piece one by one.
According to claim 1 come the system of monitoring and controlling traffic congestion based on cluster, wherein prediction module further comprises:
Load module is used to import the cluster piece;
Judge module is used to judge cluster piece position, judges that promptly the cluster piece is in the middle of end, highway section or highway section;
Splitting time obtains module, is used for judging the cluster piece at judge module and obtains the time that splitting time is first object arrival crossing of cluster piece under the situation in the middle of the highway section;
Computing module is used for judging the cluster piece under the situation at end, highway section at judge module, calculates two earliest time t that object meets in the cluster piece
m
Comparison module, be used for the ultimate range of every pair of contiguous object with compare apart from threshold values ε with up to t
mConstantly;
Update module does not all surpass apart from threshold values ε, then from t if comparison module is judged the ultimate range of every pair of contiguous object
mObject-order after the upgating object order also will be upgraded is constantly sent into computing module; And
The splitting time computing module, if sometime, the ultimate range that comparison module is judged every pair of contiguous object surpasses apart from threshold values ε, then will surpass the splitting time that be recorded as the cluster piece apart from the moment the earliest of threshold values ε.
According to claim 1 come the system of monitoring and controlling traffic congestion based on cluster, wherein processing module further comprises:
Computing module is used for calculating the time that each object of each cluster piece arrives the end, highway section;
Judge module is used for judging whether first object of cluster piece arrives the end, highway section;
Grouping module is used for when first object of a cluster piece arrives the end, highway section, the direction grouping of object in this cluster piece according to object; And
Merge module, be used for every group objects being merged to the cluster piece in next highway section according to distance threshold values ε.
According to claim 1 come the system of monitoring and controlling traffic congestion based on cluster, wherein in the one-tenth figure of road networking modeling, the limit in the corresponding diagram of highway section, the node in the intersection corresponding diagram.
6. one kind is come the method for monitoring and controlling traffic congestion based on cluster, comprising:
A, road network is carried out modeling;
B, according to motion of objects state and the distance between them, in road network, form the cluster piece of vehicle;
C, predict the splitting time of each cluster piece, and produce division and merging incident;
The division and the merging incident of D, processing cluster piece, the cluster piece close mutual distance is merged into close quarters; And
Close quarters in E, the monitoring road network.
According to claim 6 come the method for monitoring and controlling traffic congestion based on cluster, wherein mutual distance is close and object that motion state is similar constitutes cluster piece one by one in step B.
According to claim 6 come the method for monitoring and controlling traffic congestion based on cluster, wherein step C further comprises:
Input cluster piece;
Judge cluster piece position, judge that promptly the cluster piece is in the middle of end, highway section or highway section;
To obtain splitting time under the situation of cluster piece in the middle of the highway section be the time that first object of cluster piece arrives the crossing judging;
Judge the cluster piece under the situation at end, highway section, calculating two earliest time t that object meets in the cluster piece
m
The ultimate range of every pair of contiguous object with compare apart from threshold values ε with up to t
mConstantly;
If comparing the ultimate range of every pair of contiguous object does not all surpass apart from threshold values ε, then from t
mObject-order after the upgating object order also will be upgraded is constantly sent into computing module; And
If sometime, the ultimate range that compares every pair of contiguous object surpasses apart from threshold values ε, then will surpass the splitting time that be recorded as the cluster piece apart from the moment the earliest of threshold values ε.
According to claim 6 come the method for monitoring and controlling traffic congestion based on cluster, wherein step D further comprises:
Calculate the time at each object arrival end, highway section in each cluster piece;
Judge whether first object in the cluster piece arrives the end, highway section;
When first object of a cluster piece arrives the end, highway section, the direction grouping of object in this cluster piece according to object; And
According to distance threshold values ε every group objects is merged in the cluster piece in next highway section.
According to claim 6 come the method for monitoring and controlling traffic congestion based on cluster, wherein in the one-tenth figure of road networking modeling, the limit in the corresponding diagram of highway section, the node in the intersection corresponding diagram.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2008100560991A CN100570664C (en) | 2008-01-11 | 2008-01-11 | A kind of system and method thereof of coming the monitoring and controlling traffic congestion based on cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2008100560991A CN100570664C (en) | 2008-01-11 | 2008-01-11 | A kind of system and method thereof of coming the monitoring and controlling traffic congestion based on cluster |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101226688A true CN101226688A (en) | 2008-07-23 |
| CN100570664C CN100570664C (en) | 2009-12-16 |
Family
ID=39858659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2008100560991A Expired - Fee Related CN100570664C (en) | 2008-01-11 | 2008-01-11 | A kind of system and method thereof of coming the monitoring and controlling traffic congestion based on cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100570664C (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101814112B (en) * | 2010-01-11 | 2012-05-23 | 北京世纪高通科技有限公司 | Method and device for processing data |
| CN103065466A (en) * | 2012-11-19 | 2013-04-24 | 北京世纪高通科技有限公司 | Detection method of and detection device for abnormal traffic conditions |
| CN103853725A (en) * | 2012-11-29 | 2014-06-11 | 深圳先进技术研究院 | Traffic track data noise reduction method and system |
| CN104318773A (en) * | 2014-11-04 | 2015-01-28 | 杭州市综合交通研究中心 | Traffic jam determining method based on traffic jam space-time total amount |
| CN105023428A (en) * | 2014-04-15 | 2015-11-04 | 高德软件有限公司 | Road condition information assessment method and apparatus |
| CN106445957A (en) * | 2015-08-10 | 2017-02-22 | 华为技术有限公司 | Data visualization method and device |
| CN106504534A (en) * | 2016-11-28 | 2017-03-15 | 北京世纪高通科技有限公司 | A kind of method of predicted link road conditions, device and user equipment |
| CN107749164A (en) * | 2017-11-23 | 2018-03-02 | 浪潮软件集团有限公司 | Vehicle aggregation analysis method and device |
| CN109887279A (en) * | 2019-02-26 | 2019-06-14 | 北京隆普智能科技有限公司 | A kind of traffic congestion prediction technique and system |
| CN113344239A (en) * | 2021-04-25 | 2021-09-03 | 山东师范大学 | Traffic congestion condition prediction method and system based on two-stage spectral clustering |
| CN116819025A (en) * | 2023-07-03 | 2023-09-29 | 中国水利水电科学研究院 | Water quality monitoring system and method based on Internet of things |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11257362B2 (en) | 2018-04-18 | 2022-02-22 | International Business Machines Corporation | Determining traffic congestion patterns |
-
2008
- 2008-01-11 CN CNB2008100560991A patent/CN100570664C/en not_active Expired - Fee Related
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101814112B (en) * | 2010-01-11 | 2012-05-23 | 北京世纪高通科技有限公司 | Method and device for processing data |
| CN103065466A (en) * | 2012-11-19 | 2013-04-24 | 北京世纪高通科技有限公司 | Detection method of and detection device for abnormal traffic conditions |
| CN103065466B (en) * | 2012-11-19 | 2015-01-21 | 北京世纪高通科技有限公司 | Detection method of and detection device for abnormal traffic conditions |
| CN103853725B (en) * | 2012-11-29 | 2017-09-08 | 深圳先进技术研究院 | A kind of traffic track data noise-reduction method and system |
| CN103853725A (en) * | 2012-11-29 | 2014-06-11 | 深圳先进技术研究院 | Traffic track data noise reduction method and system |
| CN105023428A (en) * | 2014-04-15 | 2015-11-04 | 高德软件有限公司 | Road condition information assessment method and apparatus |
| CN104318773A (en) * | 2014-11-04 | 2015-01-28 | 杭州市综合交通研究中心 | Traffic jam determining method based on traffic jam space-time total amount |
| CN106445957A (en) * | 2015-08-10 | 2017-02-22 | 华为技术有限公司 | Data visualization method and device |
| CN106445957B (en) * | 2015-08-10 | 2019-11-12 | 华为技术有限公司 | The method for visualizing and device of data |
| CN106504534A (en) * | 2016-11-28 | 2017-03-15 | 北京世纪高通科技有限公司 | A kind of method of predicted link road conditions, device and user equipment |
| CN106504534B (en) * | 2016-11-28 | 2019-06-14 | 北京世纪高通科技有限公司 | A kind of method, apparatus and user equipment for predicting road conditions |
| CN107749164A (en) * | 2017-11-23 | 2018-03-02 | 浪潮软件集团有限公司 | Vehicle aggregation analysis method and device |
| CN109887279A (en) * | 2019-02-26 | 2019-06-14 | 北京隆普智能科技有限公司 | A kind of traffic congestion prediction technique and system |
| CN113344239A (en) * | 2021-04-25 | 2021-09-03 | 山东师范大学 | Traffic congestion condition prediction method and system based on two-stage spectral clustering |
| CN116819025A (en) * | 2023-07-03 | 2023-09-29 | 中国水利水电科学研究院 | Water quality monitoring system and method based on Internet of things |
| CN116819025B (en) * | 2023-07-03 | 2024-01-23 | 中国水利水电科学研究院 | Water quality monitoring system and method based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100570664C (en) | 2009-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100570664C (en) | A kind of system and method thereof of coming the monitoring and controlling traffic congestion based on cluster | |
| Ahmane et al. | Modeling and controlling an isolated urban intersection based on cooperative vehicles | |
| Florin et al. | A survey of vehicular communications for traffic signal optimization | |
| Jin et al. | Multi-agent intersection management for connected vehicles using an optimal scheduling approach | |
| CN106297291B (en) | Urban expressway traffic information acquisition system | |
| Chattaraj et al. | An intelligent traffic control system using RFID | |
| Wu et al. | Distributed mutual exclusion algorithms for intersection traffic control | |
| Ouallane et al. | Overview of road traffic management solutions based on IoT and AI | |
| Jin et al. | Platoon-based multi-agent intersection management for connected vehicle | |
| CN101819717B (en) | Road network performance judgment method based on traffic state space-time model | |
| Long et al. | Control strategies for dispersing incident-based traffic jams in two-way grid networks | |
| Ouallane et al. | Fusion of engineering insights and emerging trends: Intelligent urban traffic management system | |
| CN108762277A (en) | A kind of distribution AGV dispatching methods and scheduling system | |
| CN111311038A (en) | Evaluation method of traffic management and control service index | |
| Gomides et al. | Predictive congestion control based on collaborative information sharing for vehicular ad hoc networks | |
| Zhang et al. | Hybrid short-term traffic forecasting architecture and mechanisms for reservation-based Cooperative ITS | |
| CN112991723B (en) | Method, system and terminal for dividing task parallel granularity of intelligent networked computer based on geographic area | |
| Li et al. | Simulation analysis of robotic mobile fulfilment system based on cellular automata | |
| Umer et al. | Modeling vehicles mobility for connectivity analysis in VANET | |
| Horažďovský et al. | Data-driven management of dynamic public transport | |
| Hall | Incident dispatching, clearance and delay | |
| Sun et al. | Urban freight management with stochastic time-dependent travel times and application to large-scale transportation networks | |
| Merrad et al. | A survey on smart traffic network control and optimization | |
| CN112423383B (en) | Positioning method based on positioning base station and positioning label in multi-floor environment | |
| CN101232644A (en) | System and method for tracing mobile object based on grouping |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20091216 Termination date: 20130111 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |