CN1560756A - Intelligent traffic data processing method - Google Patents
Intelligent traffic data processing method Download PDFInfo
- Publication number
- CN1560756A CN1560756A CNA2004100034358A CN200410003435A CN1560756A CN 1560756 A CN1560756 A CN 1560756A CN A2004100034358 A CNA2004100034358 A CN A2004100034358A CN 200410003435 A CN200410003435 A CN 200410003435A CN 1560756 A CN1560756 A CN 1560756A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- data
- traffic data
- module
- traffic
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention is an intelligent traffic data processing method. The method includes: time correcting automatic interpolation, the noise eliminating filter of traffic data, space and time model of the traffic data, the noise eliminating compression and decompression to the traffic data based on two-dimension wavelet transform and two-dimension cosine transform. It at least includes time correcting automatic interpolation model, noise eliminating filter model, space and time model creating model, noise eliminating compression and decompression model, the dynamic displaying model. The intelligent traffic data processing method carries on two-dimension calculation and analysis to the traffic data acquired by the traffic sensor array, it can eliminate the noise and compress the data effectively, and thus it can detect and display the space and time information of the city traffic.
Description
Affiliated technical field
The present invention relates to a kind of intelligent transportation data processing method.
Background technology
Existing urban transportation data management system is to the single index raw data of distributed Road Detection section, do not add and handle ground directly demonstration and storage, here there are four problems, the one, the working sensor that detects traffic flow is unstable sometimes, and also there is the obliterated data problem in the sampling time drift; The 2nd, there is sensor noise in the traffic flow raw data, makes the data that show with storage really not reflect the truth of telecommunication flow information; The 3rd, the distribution situation when single index of existing Road Detection section can not directly reflect telecommunication flow information empty, the 4th, the traffic flow data amount is huge, needs effective method to carry out data compression and also requires the data of compression not comprise sensor noise simultaneously.
Summary of the invention
In order to overcome the prior art deficiency, the solution of first problem need be carried out interpolation to the data of sensor acquisition; The solution of second problem need be carried out filtering to the data of sensor acquisition; The data model when solution of the 3rd problem need be set up traffic flow empty adopts two-dimensional digital filtering that telecommunication flow information is handled, and adopts three-dimensional data display packing display process result simultaneously; The solution of the 4th problem need adopt denoising compressing method that traffic data is handled.The invention provides a kind of intelligent transportation data processing method.
The technical solution adopted for the present invention to solve the technical problems is:
At the problems referred to above, the traffic data disposal route that the present invention proposes comprises: time correcting automatic interpolation, the model when noise-removed filtering of traffic data, traffic data empty, based on the denoising compression of the traffic data of two-dimensional wavelet transformation and two-dimensional cosine transform with decompress.
Traffic data disposal route disclosed by the invention comprises following message processing module at least: MBM during the noise-removed filtering module of time correcting automatic interpolation module, traffic data, traffic data empty, based on denoising compression and decompression module, the two dimension of traffic data and the dynamic three-dimensional display module of the traffic data of two-dimensional wavelet transformation and two-dimensional cosine transform.
The sampling of step 1, traffic data, the three-dimensional traffic data modeling module cycle is to the sampling of traffic data, and the up-downgoing or the inner and outer ring of municipal highway is made as 6-8 track, and there are flow, average velocity, occupation rate, these four groups of data of long vehicle flow in each track,
Step 4, carry out traffic data denoising, compression:
1, carry out the one-dimensional wavelet transform of traffic data, k that is provided by three-dimensional traffic data modeling module is detected the measured three-dimensional traffic data stationary track variable m of section sensor
0With section variable k
0, the dimensionality reduction of realization three dimensional signal constitutes traditional one dimension traffic signals, and traffic signals f (t) forms difference signal D by the wave filter (Hi-pass filter, a low-pass filter) of two complementations of one-dimensional wavelet transform denoising compression module
J+1F (t) and approximate signal A
J+1F (t).One-dimensional wavelet transform denoising compression module is introduced down-sampling, from per two sampled points, get one as sampled value to keep data volume constant.Or:
2, carry out the two-dimensional wavelet transformation of traffic data, two-dimensional wavelet transformation denoising compression module detects in the measured three-dimensional traffic data of section sensor k, fixing track variable, and the dimensionality reduction of realization three dimensional signal constitutes two-dimentional traffic signals.Or:
3, carry out the two-dimensional cosine transform of traffic data, two-dimensional cosine transform denoising compression module is only to this minority low-frequency data coding.Two-dimensional cosine transform denoising compression module is provided with the low frequency coding region at frequency domain according to the sensor noise characteristic, and extra-regional data are not encoded.Traffic data obtains discrete cosine transform coefficient through two-dimensional cosine transform denoising compression module, adjusts high frequency DCT coefficient threshold value, dispels the sensor noise of ITS signal.Sensor noise shows as broadband component by a small margin in the cosine transform of two-dimensional cosine transform denoising compression module, get rational filtering threshold with its filtering.
The two dimension of step 5, traffic data and dynamic three-dimensional display:
1, the dynamic demonstration of the two dimension of processing or untreated traffic data is finished by the dynamic display module of two dimension, two dimension dynamically includes two-dimensional graphics program and X-Y scheme display routine in the display module, the dynamic display module of two dimension is with two variables constant in the three-dimensional traffic data model, as detect section number and the car Taoist monastic name is fixed, form one-dimensional data q
o(k
0, m
0, t), v
o(k
0, m
0, t), c
o(k
0, m
0, t), l
o(k
0, m
0, t), send two-dimensional graphics program and X-Y scheme display routine with these data, can realize that the two dimension of traffic data dynamically shows, or:
2, the dynamic three-dimensional display of processing or untreated traffic data is finished by the dynamic three-dimensional display module.Include three-dimensional drawing program and three-dimensional picture display routine in the dynamic three-dimensional display module, the dynamic three-dimensional display module is a variables constant in the three-dimensional traffic data model, and is number fixing as detecting section, forms 2-D data q
o(k
0, m, t), v
o(k
0, m, t), c
o(k
0, m, t), l
o(k
0, m t), send three-dimensional drawing program and three-dimensional picture display routine with these data, can realize the dynamic three-dimensional display of traffic data.
The invention has the beneficial effects as follows, intelligent transportation data processing method of the present invention is carried out two-dimentional computational analysis with the traffic flow data that the traffic flow sensor array of space distribution is obtained, data denoising and data compression can be carried out effectively, information when showing urban traffic flow empty can be dynamically detected.
Description of drawings
Fig. 1 is a functional block diagram of the present invention.
Fig. 2 is a process flow diagram of the present invention.
Fig. 3 is that the sensing station in the two-way highway section of embodiment distributes and the three-dimensional traffic stream data model.
Fig. 4 is 3001 data when detecting sections original empty that the dynamic three-dimensional display module shows.
Embodiment
Embodiment 1: as Fig. 1 is functional module connection layout of the present invention, data-interface connects numerical value interpolating module, data processing module, data disaply moudle and database, Data Control module: the numerical interpolation module is connected to form by null value interpolating module and predicted value interpolating module, data processing module is connected to form by small echo denoising module and cosine denoising module, and data disaply moudle is connected to form by 2-D data display module and three-dimensional data display module.(MBM during the noise-removed filtering module of time correcting automatic interpolation module, traffic data, traffic data empty, based on the denoising compression and the decompression module of the traffic data of two-dimensional wavelet transformation and two-dimensional cosine transform.) be process flow diagram of the present invention as Fig. 2,
The sampling of step 1, traffic data, typical urban transportation data comprise flow, average velocity, occupation rate, long vehicle flow, they are for detecting section, detecting the discrete function of section spacing from, time and car Taoist monastic name.The three-dimensional traffic data modeling module cycle is to the sampling of traffic data, cycle is 2 minutes, the up-downgoing or the inner and outer ring of municipal highway are made as 6 tracks, there is flow in each track, average velocity, occupation rate, these four groups of data of long vehicle flow, as Fig. 3 is the sensing station distribution and three-dimensional traffic stream data model in the two-way highway section of demonstration, in three-dimensional traffic data modeling module, the sensing station in two-way highway section, 6 tracks distributes as shown in Figure 3, each detects section 6 tracks, (m=1,2,3 is interior ring track, m=11,12,13 is the outer shroud track) traffic parameter.
A vehicle sensors (vertical dotted line place among the figure) is equipped with in each track.Each vehicle sensors can be gathered 4 groups of data: flow q (t), and average velocity v (t), occupation rate is c (t), the long vehicle flow is l (t).
The actual traffic stream that three-dimensional traffic data modeling module will detect section is expressed as three-dimensional function: flow be q (k, m, t), average velocity be v (k, m, t), occupation rate be c (k, m, t), the long vehicle flow is l (k, m, t), wherein m is the car Taoist monastic name, k is for detecting section number, and variable m and k constitute spatial parameter.
Data through three-dimensional traffic data modeling resume module are sent the dynamic three-dimensional display module, the situation of change that can show traffic flow, the situation that a certain index that data structure when showing that for the dynamic three-dimensional display module single index of traffic flow is empty as Fig. 4, each subgraph only reflect traffic flow changes with the track in time.
The dynamic three-dimensional display matrix comprises the vehicle flowrate speed of a motor vehicle v that detects each track of section (being 3001) here
o(3001, m, t), occupation rate c
o(k
0, m, t), long vehicle flow l
o(k
0, m t), has data structure
F (m, t)=[q
o(3001, m, t) v
o(3001, m, t) c
o(3001, m, t) l
o(3001, m, t)], then the dynamic space distribution situation of traffic flow is as shown in Figure 4.
Three-dimensional traffic data modeling module can be expressed as many achievement datas structure with section traffic data frame, and its data structure is
f(t，m
0)＝[q
o(t，1，k
0)v
o(t，1，k
0)c
o(t，1，k
0)l
o(t，1，k
0)q
o(t，2，k
0)v
o(t，2，k
0)c
o(t，2，k
0)l
o(t，2，k
0)...q
o(t，1，k
0)v
o(t，6，k
0)c
o(t，6，k
0)l
o(t，6，k
0)]。
In this data structure, the traffic data frame of k section is that (t), average velocity is that (t), occupation rate is that (t), the long vehicle flow is that (k, m t) arrange by the track l to c for k, m to v for k, m for k, m with flow q.
Step 4, carry out traffic data denoising, compression:
Carry out the one-dimensional wavelet transform of traffic data, one-dimensional wavelet transform denoising compression module adopts existing one-dimensional wavelet transform technology that one dimension traffic signals f is carried out wavelet decomposition and reconstruction.One-dimensional wavelet transform denoising compression module is realized two functions simultaneously: denoising and data compression.Traffic signals f (t) forms difference signal D by the wave filter (Hi-pass filter, a low-pass filter) of two complementations of one-dimensional wavelet transform denoising compression module
J+1F (t) and approximate signal A
J+1F (t).One-dimensional wavelet transform denoising compression module is introduced down-sampling, from per two sampled points, get one as sampled value to keep data volume constant.K that is provided by three-dimensional traffic data modeling module is detected the measured three-dimensional traffic data q of section sensor
o(k, m, t), v
o(k, m, t), c
o(k, m, t), l
o(k, m, t) in, fixing track variable m
0With section variable k
0, can realize the dimensionality reduction of three dimensional signal constituting traditional one dimension traffic signals:
q
o(k
0，m
0，t)＝q
o(t)，v
o(k
0，m
0，t)＝v
o(t)，
c
o(k
0，m
0，t)＝c
o(t)，l
o(k
0，m
0，t)＝l
o(t)。
One-dimensional wavelet transform denoising compression module makes respectively
f(t)＝q
o(t)，f(t)＝v
o(t)，f(t)＝c
o(t)，f(t)＝l
o(t)
Like this, one-dimensional wavelet transform denoising compression module adopts existing one-dimensional wavelet transform technology that one dimension traffic signals f is carried out wavelet decomposition and reconstruction.
One-dimensional wavelet transform denoising compression module is realized two functions simultaneously: denoising and data compression.
One-dimensional wavelet transform denoising compression module can be decomposed into traffic signals f its approximate information A
jF and differential information D
jF,
f＝A
1f+D
1f
Wherein, differential information D
jF mainly is made of sensor noise and branch road wagon flow variable quantity, does not disturb if do not wish to comprise in the data after compression this part, can abandon this part information in the process of wavelet reconstruction.
Traffic signals f (t) forms difference signal D by the wave filter (Hi-pass filter, a low-pass filter) of two complementations of one-dimensional wavelet transform denoising compression module
J+1F (t) and approximate signal A
J+1F (t).
In order to reduce data volume, one-dimensional wavelet transform denoising compression module is introduced down-sampling, from per two sampled points, get one as sampled value to keep data volume constant.
The two dimension of step 5, traffic data dynamically shows:
The two dimension of processing or untreated traffic data dynamically shows to be finished by the dynamic display module of two dimension, two dimension dynamically includes two-dimensional graphics program and X-Y scheme display routine in the display module, the dynamic display module of two dimension is with two variables constant in the three-dimensional traffic data model, as detect section number and the car Taoist monastic name is fixed, form one-dimensional data q
o(k
0, m
0, t), v
o(k
0, m
0, t), c
o(k
0, m
0, t), l
o(k
0, m
0, t), send two-dimensional graphics program and X-Y scheme display routine with these data, can realize that the two dimension of traffic data dynamically shows,
Embodiment 2: other step is with embodiment 1, and different is:
The sampling of step 1, traffic data, typical urban transportation data comprise flow, average velocity, occupation rate, long vehicle flow, they are for detecting section, detecting the discrete function of section spacing from, time and car Taoist monastic name.The three-dimensional traffic data modeling module cycle, the cycle was 2 minutes to the sampling of traffic data, and the up-downgoing or the inner and outer ring of municipal highway is made as 8 tracks, and there are flow, average velocity, occupation rate, these four groups of data of long vehicle flow in each track,
Embodiment 3: other step is with embodiment 1 or embodiment 2, and different is:
Step 4, carry out traffic data denoising, compression: carry out the two-dimensional wavelet transformation of traffic data, two-dimensional wavelet transformation denoising compression module detects the measured three-dimensional traffic data q of section sensor with k
o(k, m, t), v
o(k, m, t), c
o(k, m, t), l
o(k, m, t) in, fixing track variable m
0, can realize the dimensionality reduction of three dimensional signal constituting two-dimentional traffic signals:
q
o(k，m
0，t)＝q
o(k，t)，v
o(k，m
0，t)＝v
o(k，t)，
c
o(k，m
0，t)＝c
o(k，t)，l
o(k，m
0，t)＝l
o(k，t)。
At this moment, two-dimensional wavelet transformation denoising compression module makes respectively
f(k，t)＝q
o(k，t)，f(k，t)＝v
o(k，t)，f(k，t)＝c
o(k，t)，f(k，t)＝l
o(k，t)
Like this, two-dimensional wavelet transformation denoising compression module adopts the existing two-dimensional wavelet transformation technique that two-dimentional traffic signals f is carried out wavelet decomposition and reconstruction.Principle is the same, and two-dimensional wavelet transformation denoising compression module is realized two functions simultaneously: denoising and data compression.
The dynamic three-dimensional display of step 5, traffic data:
The dynamic three-dimensional display of processing or untreated traffic data is finished by the dynamic three-dimensional display module.Include three-dimensional drawing program and three-dimensional picture display routine in the dynamic three-dimensional display module, the dynamic three-dimensional display module is a variables constant in the three-dimensional traffic data model, and is number fixing as detecting section, forms 2-D data q
o(k
0, m, t), v
o(k
0, m, t), c
o(k
0, m, t), l
o(k
0, m t), send three-dimensional drawing program and three-dimensional picture display routine with these data, can realize the dynamic three-dimensional display of traffic data.
Embodiment 4: other step is with embodiment 1 or embodiment 2 or embodiment 3, and different is:
Step 4, carry out traffic data denoising, compression: carry out the two-dimensional cosine transform of traffic data, two-dimensional cosine transform denoising compression module is only to this minority low-frequency data coding, but filtering sensor noise, compressible data amount on the other hand on the one hand.Two-dimensional cosine transform denoising compression module traffic data adopts existing cosine transform fast algorithm.Two-dimensional cosine transform denoising compression module is provided with the low frequency coding region at frequency domain according to the sensor noise characteristic, and extra-regional data are not encoded.Traffic data obtains discrete cosine transform coefficient through two-dimensional cosine transform denoising compression module, adjusts high frequency DCT coefficient threshold value, dispels the sensor noise of ITS signal.Sensor noise shows as broadband component by a small margin in the cosine transform of two-dimensional cosine transform denoising compression module, get rational filtering threshold, can be with its filtering.In traffic signals transmission and storage, needn't transmit and storage sensor noise.
Embodiment 5: other step is with embodiment 1 or embodiment 2 or embodiment 3 or embodiment 4, and different is:
Each subgraph as Fig. 4 is respectively the raw data that detects section one day 3001 that the dynamic three-dimensional display module shows: flow q
o(3001, m, t), speed of a motor vehicle v
o(3001, m, t), occupation rate c
o(3001, m, t), v
o(3001, m, t), long vehicle flow l
o(3001, m, t).
Claims (5)
1, a kind of intelligent transportation data processing method is characterized in that:
The sampling of step 1, traffic data, the three-dimensional traffic data modeling module cycle is to the sampling of traffic data, and the up-downgoing or the inner and outer ring of municipal highway is made as 6-8 track, and there are flow, average velocity, occupation rate, these four groups of data of long vehicle flow in each track,
Step 2, carry out pretreatment: by the time correcting automatic interpolation module; Program in the time correcting automatic interpolation module with the data of gathering by every day at least 96 time sampling points standard time file nearby; Missing data is that the time point in the automatic data file after calibration is expressed as zero; Form zero interpolated data file; Or to the remainder certificate in the data file after time calibration; Some adjacent datas namely dope non-vanishing data value before and after utilizing; Form prediction interpolated data file
Step 3, the preprocessed data of finishing offer wavelet transform process module or cosine transform processing module,
Step 4, carry out traffic data denoising, compression:
(1) carry out the one-dimensional wavelet transform of traffic data, k that is provided by three-dimensional traffic data modeling module is detected the measured three-dimensional traffic data stationary track variable m of section sensor
0With section variable k
0, the dimensionality reduction of realization three dimensional signal constitutes traditional one dimension traffic signals, and traffic signals f (t) forms difference signal D by the wave filter (Hi-pass filter, a low-pass filter) of two complementations of one-dimensional wavelet transform denoising compression module
J+1F (t) and approximate signal A
J+1F (t), one-dimensional wavelet transform denoising compression module introduce down-sampling, from per two sampled points, get one as sampled value keeping data volume constant, or:
(2) carry out the two-dimensional wavelet transformation of traffic data, two-dimensional wavelet transformation denoising compression module detects in the measured three-dimensional traffic data of section sensor k, fixing track variable, and the dimensionality reduction of realization three dimensional signal constitutes two-dimentional traffic signals, or:
(3) carry out the two-dimensional cosine transform of traffic data, two-dimensional cosine transform denoising compression module is only to this minority low-frequency data coding, two-dimensional cosine transform denoising compression module is provided with the low frequency coding region at frequency domain according to the sensor noise characteristic, extra-regional data are not encoded, traffic data is through two-dimensional cosine transform denoising compression module, obtain discrete cosine transform coefficient, adjust high frequency DCT coefficient threshold value, dispel the sensor noise of ITS signal, sensor noise shows as broadband component by a small margin in the cosine transform of two-dimensional cosine transform denoising compression module, get rational filtering threshold with its filtering.
2, a kind of intelligent transportation data processing method according to claim 1 is characterized in that: the two dimension of step 5, traffic data and dynamic three-dimensional display
(1) the dynamic demonstration of the two dimension of processing or untreated traffic data is finished by the dynamic display module of two dimension, two dimension dynamically includes two-dimensional graphics program and X-Y scheme display routine in the display module, the dynamic display module of two dimension is with two variables constant in the three-dimensional traffic data model, as detect section number and the car Taoist monastic name is fixed, form one-dimensional data q
o(k
0, m
0, t), v
o(k
0, m
0, t), c
o(k
0, m
0, t), l
o(k
0, m
0, t), send two-dimensional graphics program and X-Y scheme display routine with these data, realize that the two dimension of traffic data dynamically shows, or:
(2) dynamic three-dimensional display of processing or untreated traffic data is finished by the dynamic three-dimensional display module, include three-dimensional drawing program and three-dimensional picture display routine in the dynamic three-dimensional display module, the dynamic three-dimensional display module is with a variables constant in the three-dimensional traffic data model, detect section number or car Taoist monastic name and fix, form 2-D data q
o(k
0, m, t), v
o(k
0, m, t), c
o(k
0, m, t), l
o(k
0, m, t), or q
o(k, m
0, t), v
o(k, m
0, t), c
o(k, m
0, t), l
o(k, m
0, t), send three-dimensional drawing program and three-dimensional picture display routine with these data, realize the dynamic three-dimensional display of traffic data.
3, a kind of intelligent transportation data processing method according to claim 1 and 2 is characterized in that the standard time by 720 time-sampling points every day.
4, a kind of intelligent transportation data processing method according to claim 1 and 2 is characterized in that the sampling of three-dimensional traffic data modeling module cycle to traffic data, and the cycle is 2 minutes.
5, a kind of intelligent transportation data processing method according to claim 3 is characterized in that the sampling of three-dimensional traffic data modeling module cycle to traffic data, and the cycle is 2 minutes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200410003435 CN1304987C (en) | 2004-03-09 | 2004-03-09 | Intelligent traffic data processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200410003435 CN1304987C (en) | 2004-03-09 | 2004-03-09 | Intelligent traffic data processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1560756A true CN1560756A (en) | 2005-01-05 |
| CN1304987C CN1304987C (en) | 2007-03-14 |
Family
ID=34439530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200410003435 Expired - Fee Related CN1304987C (en) | 2004-03-09 | 2004-03-09 | Intelligent traffic data processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1304987C (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100357987C (en) * | 2005-06-02 | 2007-12-26 | 上海交通大学 | Method for obtaining average speed of city rode traffic low region |
| CN101206801B (en) * | 2007-12-17 | 2011-04-13 | 青岛海信网络科技股份有限公司 | Self-adaption traffic control method |
| CN102184638A (en) * | 2011-04-28 | 2011-09-14 | 北京市劳动保护科学研究所 | Method for preprocessing pedestrian traffic data |
| CN102749084A (en) * | 2012-07-10 | 2012-10-24 | 南京邮电大学 | Path selecting method oriented to massive traffic information |
| CN102800197A (en) * | 2012-02-27 | 2012-11-28 | 东南大学 | Preprocessing method of road section dynamic traffic stream essential data of urban road |
| CN103914459A (en) * | 2012-12-31 | 2014-07-09 | 北京中交兴路信息科技有限公司 | Traffic information file compression and decompression method and device |
| CN104200684A (en) * | 2014-09-16 | 2014-12-10 | 安徽达尔智能控制***有限公司 | City main road green wave selection system based on wavelet transformation |
| CN105825670A (en) * | 2015-08-16 | 2016-08-03 | 姜涵 | Road oversaturation state judgment method and system based on data fusion |
| CN109979195A (en) * | 2019-03-22 | 2019-07-05 | 浙江大学城市学院 | A kind of short-term traffic flow forecast method of the fusion Spatio-temporal factors based on sparse regression |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739819A (en) * | 2009-11-19 | 2010-06-16 | 北京世纪高通科技有限公司 | Method and device for predicting traffic flow |
-
2004
- 2004-03-09 CN CN 200410003435 patent/CN1304987C/en not_active Expired - Fee Related
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100357987C (en) * | 2005-06-02 | 2007-12-26 | 上海交通大学 | Method for obtaining average speed of city rode traffic low region |
| CN101206801B (en) * | 2007-12-17 | 2011-04-13 | 青岛海信网络科技股份有限公司 | Self-adaption traffic control method |
| CN102184638A (en) * | 2011-04-28 | 2011-09-14 | 北京市劳动保护科学研究所 | Method for preprocessing pedestrian traffic data |
| CN102800197A (en) * | 2012-02-27 | 2012-11-28 | 东南大学 | Preprocessing method of road section dynamic traffic stream essential data of urban road |
| CN102800197B (en) * | 2012-02-27 | 2014-07-16 | 东南大学 | Preprocessing method of road section dynamic traffic stream essential data of urban road |
| CN102749084A (en) * | 2012-07-10 | 2012-10-24 | 南京邮电大学 | Path selecting method oriented to massive traffic information |
| CN103914459A (en) * | 2012-12-31 | 2014-07-09 | 北京中交兴路信息科技有限公司 | Traffic information file compression and decompression method and device |
| CN104200684A (en) * | 2014-09-16 | 2014-12-10 | 安徽达尔智能控制***有限公司 | City main road green wave selection system based on wavelet transformation |
| CN104200684B (en) * | 2014-09-16 | 2016-03-09 | 安徽达尔智能控制***有限公司 | A kind of major urban arterial highway filtering selective system based on wavelet transformation |
| CN105825670A (en) * | 2015-08-16 | 2016-08-03 | 姜涵 | Road oversaturation state judgment method and system based on data fusion |
| CN105825670B (en) * | 2015-08-16 | 2019-04-05 | 北京数行健科技有限公司 | Road hypersaturated state judgment method and system based on data fusion |
| CN109979195A (en) * | 2019-03-22 | 2019-07-05 | 浙江大学城市学院 | A kind of short-term traffic flow forecast method of the fusion Spatio-temporal factors based on sparse regression |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1304987C (en) | 2007-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1304987C (en) | Intelligent traffic data processing method | |
| CN1105993C (en) | One-dimensional signal adaptive filter for reducing blocking effect and filtering method | |
| CN1901620A (en) | Video image noise reducing method based on moving detection and self adaptive filter | |
| CN1822046A (en) | Infrared and visible light image fusion method based on regional property fuzzy | |
| CN1547725A (en) | Image matching | |
| CN103974071A (en) | Video coding method and equipment on basis of regions of interest | |
| CN1831893A (en) | Traffic information system | |
| CN1282131C (en) | Image merging method based on inseparable wavelet frame | |
| CN1804657A (en) | Small target super resolution reconstruction method for remote sensing image | |
| CN1251145C (en) | Pyramid image merging method being integrated with edge and texture information | |
| CN101059529A (en) | Method for measuring traffic flow average rate using video | |
| CN1901602A (en) | Quick double linear interpolating method in image amplification process | |
| CN113205018A (en) | High-resolution image building extraction method based on multi-scale residual error network model | |
| CN1431523A (en) | Optimization method of remote sensing image by use of syncretic bilinear interpolation and wavelet transformation | |
| CN1665299A (en) | Method for designing architecture of scalable video coder decoder | |
| CN103345747A (en) | Optimized picture shape feature extraction and structuring description device and method based on horizontal coordinate | |
| CN1924950A (en) | Vehicle characters recognition and measuring system and vehicle information recognition method | |
| CN1821755A (en) | Realtime detecting method for flocculate fractal artery image | |
| CN1917635A (en) | Method for transferring data of vector graphics | |
| CN116858751B (en) | Permeable concrete pavement porosity measuring and calculating method based on representative vehicle type sound processing | |
| CN1152341C (en) | Automatic generation method for digital house map | |
| Kakegawa et al. | Road surface segmentation based on vertically local disparity histogram for stereo camera | |
| CN1197026C (en) | Parallel reversely dispersed small wave change | |
| CN116434539B (en) | Expressway speed early warning method based on digital twinning under extreme rainwater weather | |
| CN1794312A (en) | Video frequency car position detector and its detecting method |
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 | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20070314 Termination date: 20110309 |