CN103853900A - Abnormal trajectory data correction method and device and traffic management system - Google Patents
Abnormal trajectory data correction method and device and traffic management system Download PDFInfo
- Publication number
- CN103853900A CN103853900A CN201210499093.8A CN201210499093A CN103853900A CN 103853900 A CN103853900 A CN 103853900A CN 201210499093 A CN201210499093 A CN 201210499093A CN 103853900 A CN103853900 A CN 103853900A
- Authority
- CN
- China
- Prior art keywords
- track
- dimensional space
- data
- abnormal
- vector representation
- 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
The invention is applicable to the technical field of information processing, and provides an abnormal trajectory data correction method, an abnormal trajectory data correction device and a traffic management system. The method comprises the steps of: performing a series of processing to original trajectory data, and then generating the vector representation of the trajectory; recognizing and correcting the abnormal trajectory data by using the vector representation of the trajectory and combining with a preset correction threshold. According to the abnormal trajectory data correction method, the vector representation of the trajectory is the regularized result of all original trajectory data, and the result still retains the trend characteristics of a traffic trajectory, so that the correction of the abnormal trajectory data noise is performed based on the regularized result, complex noise rules are not needed to set to recognize the noise, and the abnormal trajectory data correction method has the advantages of low algorithm complexity, high efficiency, rapid speed and easiness to expand. Furthermore, the correction of the abnormal trajectory data noise is based on the trend characteristics of the original trajectory data, so that the recognition rate of the noise in the abnormal trajectory data is high, and the robustness is high.
Description
Technical field
The invention belongs to technical field of information processing, relate in particular to a kind of modification method, device and traffic control system of abnormal track data.
Background technology
In recent years, the quantity rapid growth of urban automobile, has caused many such as traffic congestion, parking difficulty, the go on a journey problem of quality of common people that has a strong impact on such as difficult of calling a taxi.The transportation network in city is also increasingly sophisticated simultaneously, more and more higher to the requirement of a perfect traffic control system.Build in the blueprint of intelligent city in future, intelligent transportation is the most important thing.For the construction of intelligent transportation, will inevitably relate to the processing for extensive traffic track, and further, due to unpredictable reasons such as error, the delay of network service and the interference of abnormal signal of satellite navigation, in traffic track data, have a large amount of abnormal tracks, these abnormal tracks have a strong impact on the objectivity to traffic trajectory analysis.So, how the abnormal track in magnanimity track data is carried out to Transformatin and becomes a hot technology.
Abnormal track data in traffic track data mainly contains following characteristics: (1) needs data volume to be processed large, suppose that there are 50000 taxis in certain city, every taxi sends a record that comprises its current location, current time, manned situation, driver's telephone number etc. to cloud service center every 5 seconds, article one, record about 100 bytes, large appointment every month produces the data volume of 2.6TB; (2) abnormal track data is many and complicated, the integrality of track data and correctness are subject to the precision of satnav, the restriction of positioning equipment, the impact of the multiple objective and unpredictable factor such as network signal, causes existing in track data a large amount of unpredictable data; (3) high to processing speed requirement, a large amount of track datas require to handle within the sustainable time, so have specific (special) requirements for the time complexity of algorithm.
Existing technology is by filtering rule is set, track data to be filtered, but need the filtering rule of setting very complicated, and execution efficiency is low, if abnormal track data is too much in addition, may cause mass data to be filtered, this excessive filtration has a negative impact to data analysis equally.
Summary of the invention
The embodiment of the present invention provides a kind of modification method, device and traffic control system of abnormal track data, be intended to solve existing techniques in realizing complexity, and execution efficiency is low, if abnormal track data is too much in addition, may cause mass data to be filtered, the problem that this excessive filtration has a negative impact to data analysis equally.
On the one hand, provide a kind of modification method of abnormal track data, described method comprises:
Initial trace data definition, in the first two-dimensional space, and is generated to the first process data set based on described the first two-dimensional space coordinate axis;
The coordinate axis of described the first two-dimensional space, by the default default angle of direction rotation, is generated to the second two-dimensional space;
What the first deal with data was concentrated converts a little the point based on the second two-dimensional space coordinate axis S ' to, formation the second process data set;
Point concentrated described the second deal with data is converted into orderly line segment aggregate L;
At described the second two-dimensional space, described orderly line segment aggregate L is processed, generate the vector representation of a track;
Utilize the vector representation of described track, in conjunction with default correction threshold values, abnormal track is identified and revised.
On the other hand, provide a kind of correcting device of abnormal track data, described device comprises:
The first data set generation unit, for by initial trace data definition at the first two-dimensional space, and generate the first process data set based on described the first two-dimensional space coordinate axis;
Space converting unit, for the coordinate axis of described the first two-dimensional space is pressed to the default default angle of direction rotation, generates the second two-dimensional space;
The second data set generation unit, converts a little the point based on the second two-dimensional space coordinate axis S ' to for what the first deal with data was concentrated, formation the second process data set;
Line segment aggregate generation unit, for being converted into orderly line segment aggregate L by point concentrated described the second deal with data;
Track vector generation unit, at described the second two-dimensional space, processes described orderly line segment aggregate L, generates the vector representation of a track;
Track correct unit, for utilizing the vector representation of described track, in conjunction with default correction threshold values, identifies and revises abnormal track.
On the one hand, provide a kind of traffic control system again, described traffic control system comprises the correcting device of abnormal track data as above.
In the embodiment of the present invention, initial trace data are carried out to a series of processing, generate the vector representation of a track, recycle the vector representation of described track, in conjunction with default correction threshold values, to realize, abnormal track is identified and revised.Because the vector representation of described track is the regularization result of all initial trace data, this result still retains the feature of moving towards of traffic track, therefore carry out the correction of abnormal track data noise take this regularization result as foundation, complicated Noise rules need not be set and identify noise, algorithm complex is low, efficiency is high, and speed is fast, is easy to expansion.And the correction of abnormal track data noise is the feature of moving towards based on initial trace data, and therefore high to the noise discrimination in abnormal track data, robustness is high.In addition, while correction, can, by the amplitude of the noise correction of the abnormal track data of parameter correction threshold values control, can not produce the problem of over-correction.
Accompanying drawing explanation
Fig. 1 is the realization flow figure of the modification method of the abnormal track data that provides of the embodiment of the present invention one;
Fig. 2 is the structured flowchart of the correcting device of the abnormal track data that provides of the embodiment of the present invention two.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
In embodiments of the present invention, first by initial trace data definition in the first two-dimensional space; Again the coordinate axis of described the first two-dimensional space is pressed to the default default angle of direction rotation, generate the second two-dimensional space; The initial trace data-switching again the gps coordinate point set by oriented being combined into becomes orderly line segment aggregate S; Then at described the second two-dimensional space, described orderly line segment aggregate S is processed, generate the vector representation of a track; Finally utilize the vector representation of described track, in conjunction with default correction threshold values, abnormal track is identified and revised.
Below in conjunction with specific embodiment, realization of the present invention is described in detail:
Embodiment mono-
Fig. 1 shows the realization flow of the modification method of the abnormal track data that the embodiment of the present invention one provides, and details are as follows:
In step S101, initial trace data definition, in the first two-dimensional space, and is generated to the first process data set based on described the first two-dimensional space coordinate axis.
In the present embodiment, first by inquiry, obtain the gps coordinate point of initial trace data, the expression of gps coordinate point is defined in the first two-dimensional space, the coordinate axis of this first two-dimensional space comprises x axle and y axle, dimension corresponding x axle is called to longitude, dimension corresponding y axle is called to latitude, the coordinate of each gps coordinate point is made up of longitude and latitude.Again obtain through all tracks between any two gps coordinate points, such as the coordinate of these two gps coordinates o'clock in the first two-dimensional space is respectively (x
s, y
s) and (x
d, y
d), for starting point (x
s, y
s), arrange one apart from threshold values ε, for any gps coordinate (x '
s, y '
s), if x '
s∈ (x
s– ε, x
s+ ε) and y '
s∈ (y
s– ε, y
s+ ε), be all put in track alternate list through all tracks of this gps coordinate; For terminal (x
d, y
d), arrange one apart from threshold values ε ', for any gps coordinate (x '
d, y '
d), if x '
d∈ (x
d– ε, x
d+ ε) and y '
d∈ (y
d– ε, y
d+ ε), all processes in track alternate list (x '
d, y '
d) track put into the process data set of processing list and form initial trace data, i.e. the first process data set based on the first two-dimensional space coordinate axis.This first process data set is combined into by the oriented gps coordinate point set based on the first two-dimensional space coordinate axis.
In step S102, the coordinate axis of described the first two-dimensional space, by the default default angle of direction rotation, is generated to the second two-dimensional space.
In the present embodiment, by (x
s, y
s) and (x
d, y
d) between line, be designated as L, suppose that the angle between L and the x axle of the first two-dimensional space is α, by the coordinate axis of the first two-dimensional space rotation alpha+45 ° left, generate the second two-dimensional space, coordinate axis corresponding this second two-dimensional space is designated as to S '.It should be noted that, in the time of concrete execution, the sense of rotation of the first two-dimensional space and the angle of rotation can not limit.
In step S103, what the first deal with data was concentrated converts a little the point based on the second two-dimensional space coordinate axis S ' to, formation the second process data set.
In the present embodiment, what the first deal with data based on the first two-dimensional space coordinate axis was concentrated converts a little the point based on the second two-dimensional space coordinate axis to, forms new process data set, i.e. the second process data set.From here on, following is all based on S ' and this new process data set in steps.This second process data set is combined into by the oriented gps coordinate point set based on the second two-dimensional space coordinate axis.
In step S104, point concentrated described the second deal with data is converted into orderly line segment aggregate L.
In the present embodiment, the adjacent coordinate points that the second deal with data is concentrated connects, and converts a little an orderly line segment aggregate L to concentrated the second deal with data.
In step S105, at described the second two-dimensional space, described orderly line segment aggregate L is processed, generate the vector representation of a track.
In the present embodiment, generate the vector representation of a track by following steps.
Step 1, within the scope of the starting point and terminal of described orderly line segment aggregate L, sample respectively in two dimensions of described the second two-dimensional space, obtain two orderly sampling spot set.
In the present embodiment, based on S ' coordinate axis, the starting point coordinate after conversion is (x
s", y
s"), the terminal point coordinate after conversion is (x
d", y
d") is at [the x of the x of S ' axle
s", x
din "] scope, get successively n point, be designated as an orderly sampling spot set X={x
1..., x
n; Same method, at [the y of the y of S ' axle
s", y
don "], get m point, be designated as orderly sampling spot set Y={y
1, y
m, X and Y are two orderly sampling spot set that obtain
In the present embodiment, according to described orderly line segment aggregate L, calculate and sample in order the sampling spot x in point set X
i(x
i∈ X) mapping on y axle, be designated as orderly projection set Y '={ y
1' ..., y
n', wherein sample in order the x in point set X
iwith y in orderly projection set Y '
i' corresponding one by one.
According to described orderly line segment aggregate L, calculate the sampling spot y in orderly sampling spot set Y
i(y
i∈ Y) mapping on x axle, be designated as orderly projection set X '={ x
1' ..., x
m', the wherein y in orderly sampling spot set Y
iwith the x in orderly projection set X '
i' corresponding one by one.
Step 3, combine described two mapping sets, form the vector representation of a track.
In the present embodiment, combine orderly projection set Y ' and orderly projection set X ', form the vector representation Y '+X '={ y of a track
1' ..., y
n', x
1' ..., x
m', be put in result data collection R, until handle all tracks.
In step S106, utilize the vector representation of described track, in conjunction with default correction threshold values, abnormal track is identified and revised.
In the present embodiment, clustering processing is carried out in the vector representation of the track first step S105 being generated, then according to clustering processing result and default correction threshold values, abnormal track is identified and revised.
Exemplary, first the regularization result of all tracks in R is carried out to cluster, the result of cluster is k class, Lei center is (c
1, c
2..., c
k).
Arrange again one and revise threshold values
for the regularization result r of each track
i, r
ibelong to j class, calculate as follows:
Until the regularization result of all tracks in R of handling can complete the correction to abnormal track.
The present embodiment, carries out a series of processing to initial trace data, generates the vector representation of a track, recycles the vector representation of described track, in conjunction with default correction threshold values, to realize, abnormal track is identified and is revised.Because the vector representation of described track is the regularization result of all initial trace data, this result still retains the feature of moving towards of traffic track, therefore carry out the correction of abnormal track data noise take this regularization result as foundation, complicated Noise rules need not be set and identify noise, algorithm complex is low, efficiency is high, and speed is fast, is easy to expansion.And the correction of abnormal track data noise is the feature of moving towards based on initial trace data, and therefore high to the noise discrimination in abnormal track data, robustness is high.In addition, while correction, can, by the amplitude of the noise correction of the abnormal track data of parameter correction threshold values control, can not produce the problem of over-correction.
Embodiment bis-
Fig. 2 shows the concrete structure block diagram of the correcting device of the abnormal track data that the embodiment of the present invention two provides, and for convenience of explanation, only shows the part relevant to the embodiment of the present invention.The correcting device 2 of this abnormal track data can be the unit of software unit, hardware cell or a software and hardware combining in traffic control system.In the present embodiment, the correcting device 2 of this abnormal track data comprises: the first data set generation unit 21, space converting unit 22, the second data set generation unit 23, line segment aggregate generation unit 24, track vector generation unit 25 and track correct unit 26.
Wherein, the first data set generation unit 21, for by initial trace data definition at the first two-dimensional space, and generate the first process data set based on described the first two-dimensional space coordinate axis;
The second data set generation unit 23, converts a little the point based on the second two-dimensional space coordinate axis S ' to for what the first deal with data was concentrated, formation the second process data set;
Line segment aggregate generation unit 24, for being converted into orderly line segment aggregate L by point concentrated described the second deal with data;
Track vector generation unit 25, at described the second two-dimensional space, processes described orderly line segment aggregate L, generates the vector representation of a track;
Track correct unit 26, for utilizing the vector representation of described track, in conjunction with default correction threshold values, identifies and revises abnormal track.
Concrete, described track vector generation unit 25 comprises: sampling spot set generation module, mapping set generation module and track vector generation module.
Wherein, sampling spot set generation module, within the scope of starting point and terminal at described orderly line segment aggregate L, samples respectively in two dimensions of described the second two-dimensional space, obtains two orderly sampling spot set;
Mapping set generation module, for according to described orderly line segment aggregate L, the each sampling spot in described two the orderly sampling spot set that calculate, in the mapping of another one dimension, obtains two mapping sets;
Track vector generation module, for combining described two mapping sets, forms the vector representation of a track.
Concrete, described track correct unit 26 comprises: clustering processing module and track correct module.
Wherein, clustering processing module, for carrying out clustering processing to the vector representation of described track;
Track correct module, for according to clustering processing result and described default correction threshold values, identifies and revises abnormal track.。
The correcting device of the abnormal track data that the embodiment of the present invention provides can be applied in the embodiment of the method one of aforementioned correspondence, and details, referring to the description of above-described embodiment one, do not repeat them here.
It should be noted that in said system embodiment, included unit is just divided according to function logic, but is not limited to above-mentioned division, as long as can realize corresponding function; In addition, the concrete title of each functional unit also, just for the ease of mutual differentiation, is not limited to protection scope of the present invention.
In addition, one of ordinary skill in the art will appreciate that all or part of step realizing in the various embodiments described above method is can carry out the hardware that instruction is relevant by program to complete, corresponding program can be stored in a computer read/write memory medium, described storage medium, as ROM/RAM, disk or CD etc.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any modifications of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.
Claims (7)
1. a modification method for abnormal track data, is characterized in that, described method comprises:
Initial trace data definition, in the first two-dimensional space, and is generated to the first process data set based on described the first two-dimensional space coordinate axis;
The coordinate axis of described the first two-dimensional space, by the default default angle of direction rotation, is generated to the second two-dimensional space;
What the first deal with data was concentrated converts a little the point based on the second two-dimensional space coordinate axis S ' to, formation the second process data set;
Point concentrated described the second deal with data is converted into orderly line segment aggregate L;
At described the second two-dimensional space, described orderly line segment aggregate L is processed, generate the vector representation of a track;
Utilize the vector representation of described track, in conjunction with default correction threshold values, abnormal track is identified and revised.
2. the method for claim 1, is characterized in that, described at described the second two-dimensional space, and described orderly line segment aggregate L is processed, and the vector representation that generates a track specifically comprises:
Within the scope of the starting point and terminal of described orderly line segment aggregate L, sample respectively in two dimensions of described the second two-dimensional space, obtain two orderly sampling spot set;
According to described orderly line segment aggregate L, the each sampling spot in described two the orderly sampling spot set that calculate, in the mapping of another one dimension, obtains two mapping sets;
Combine described two mapping sets, form the vector representation of a track.
3. the method for claim 1, is characterized in that, the described vector representation that utilizes described track, in conjunction with default correction threshold values, is identified and revised specifically abnormal track and comprise:
The vector representation of described track is carried out to clustering processing;
According to clustering processing result and described default correction threshold values, abnormal track is identified and revised.
4. a correcting device for abnormal track data, is characterized in that, described device comprises:
The first data set generation unit, for by initial trace data definition at the first two-dimensional space, and generate the first process data set based on described the first two-dimensional space coordinate axis;
Space converting unit, for the coordinate axis of described the first two-dimensional space is pressed to the default default angle of direction rotation, generates the second two-dimensional space;
The second data set generation unit, converts a little the point based on the second two-dimensional space coordinate axis S ' to for what the first deal with data was concentrated, formation the second process data set;
Line segment aggregate generation unit, for being converted into orderly line segment aggregate L by point concentrated described the second deal with data;
Track vector generation unit, at described the second two-dimensional space, processes described orderly line segment aggregate L, generates the vector representation of a track;
Track correct unit, for utilizing the vector representation of described track, in conjunction with default correction threshold values, identifies and revises abnormal track.
5. device as claimed in claim 4, is characterized in that, described track vector generation unit comprises:
Sampling spot set generation module, within the scope of starting point and terminal at described orderly line segment aggregate L, samples respectively in two dimensions of described the second two-dimensional space, obtains two orderly sampling spot set;
Mapping set generation module, for according to described orderly line segment aggregate L, the each sampling spot in described two the orderly sampling spot set that calculate, in the mapping of another one dimension, obtains two mapping sets;
Track vector generation module, for combining described two mapping sets, forms the vector representation of a track.
6. device as claimed in claim 4, is characterized in that, described track correct unit comprises:
Clustering processing module, for carrying out clustering processing to the vector representation of described track;
Track correct module, for according to clustering processing result and described default correction threshold values, identifies and revises abnormal track.
7. a traffic control system, is characterized in that, described system comprises the correcting device of the abnormal track data as described in claim 4 to 6 any one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210499093.8A CN103853900B (en) | 2012-11-29 | 2012-11-29 | Modification method, device and the traffic control system of a kind of abnormal track data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210499093.8A CN103853900B (en) | 2012-11-29 | 2012-11-29 | Modification method, device and the traffic control system of a kind of abnormal track data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103853900A true CN103853900A (en) | 2014-06-11 |
CN103853900B CN103853900B (en) | 2016-12-21 |
Family
ID=50861551
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210499093.8A Active CN103853900B (en) | 2012-11-29 | 2012-11-29 | Modification method, device and the traffic control system of a kind of abnormal track data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103853900B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104778355A (en) * | 2015-04-03 | 2015-07-15 | 东南大学 | Trajectory outlier detection method based on wide-area distributed traffic system |
CN108955728A (en) * | 2018-08-30 | 2018-12-07 | 乐跑体育互联网(武汉)有限公司 | A kind of motion profile method for correcting error |
CN109671262A (en) * | 2019-01-16 | 2019-04-23 | 广州思创科技发展有限公司 | Based on accident black-spot to drivers ' behavior pre-warning system and method |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101334845B (en) * | 2007-06-27 | 2010-12-22 | 中国科学院自动化研究所 | Video frequency behaviors recognition method based on track sequence analysis and rule induction |
CN101719220A (en) * | 2009-12-02 | 2010-06-02 | 北京航空航天大学 | Method of trajectory clustering based on directional trimmed mean distance |
-
2012
- 2012-11-29 CN CN201210499093.8A patent/CN103853900B/en active Active
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104778355A (en) * | 2015-04-03 | 2015-07-15 | 东南大学 | Trajectory outlier detection method based on wide-area distributed traffic system |
CN104778355B (en) * | 2015-04-03 | 2017-06-13 | 东南大学 | The abnormal track-detecting method of traffic system is distributed based on wide area |
CN108955728A (en) * | 2018-08-30 | 2018-12-07 | 乐跑体育互联网(武汉)有限公司 | A kind of motion profile method for correcting error |
CN108955728B (en) * | 2018-08-30 | 2022-06-17 | 乐跑体育互联网(武汉)有限公司 | Motion trajectory deviation rectifying method |
CN109671262A (en) * | 2019-01-16 | 2019-04-23 | 广州思创科技发展有限公司 | Based on accident black-spot to drivers ' behavior pre-warning system and method |
Also Published As
Publication number | Publication date |
---|---|
CN103853900B (en) | 2016-12-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103106280B (en) | A kind of range query method of uncertain space-time trajectory data under road network environment | |
CN108253975B (en) | Method and equipment for establishing map information and positioning vehicle | |
CN105528359B (en) | For storing the method and system of travel track | |
CN104462190B (en) | A kind of online position predicting method excavated based on magnanimity space tracking | |
CN106875744B (en) | Nearby vehicle recognition system and method | |
CN103035123B (en) | Abnormal data acquisition methods and system in a kind of traffic track data | |
CN103853725B (en) | A kind of traffic track data noise-reduction method and system | |
CN104331422A (en) | Road section type presumption method | |
CN103500516A (en) | High-efficiency trace replay method and system based on electronic map | |
US11255678B2 (en) | Classifying entities in digital maps using discrete non-trace positioning data | |
CN103593856A (en) | Method and system for tracking single target | |
CN103853900A (en) | Abnormal trajectory data correction method and device and traffic management system | |
CN113587944A (en) | Quasi-real-time vehicle driving route generation method, system and equipment | |
CN110598917A (en) | Destination prediction method, system and storage medium based on path track | |
Singh et al. | Multi-scale graph-transformer network for trajectory prediction of the autonomous vehicles | |
CN111666359A (en) | POI candidate arrival point mining method, device and equipment | |
CN109974690A (en) | Vehicle positioning method, equipment and system | |
CN109918468A (en) | Internet of things equipment position data region screening technique based on Mercator projection | |
CN103853901A (en) | Traffic track data preprocessing method and system | |
CN104598574A (en) | Method and device for storing massive GPS (global positioning system) data | |
CN111581306B (en) | Driving track simulation method and device | |
CN116561240A (en) | Electronic map processing method, related device and medium | |
CN114999162A (en) | Road traffic flow obtaining method and device | |
CN103854480B (en) | Traffic monitoring data matrix complementing method | |
CN115388878A (en) | Map construction method and device and terminal equipment |
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 |