CN108898840A - A kind of intelligent traffic lamp control method based on video monitoring - Google Patents

A kind of intelligent traffic lamp control method based on video monitoring Download PDF

Info

Publication number
CN108898840A
CN108898840A CN201810430898.4A CN201810430898A CN108898840A CN 108898840 A CN108898840 A CN 108898840A CN 201810430898 A CN201810430898 A CN 201810430898A CN 108898840 A CN108898840 A CN 108898840A
Authority
CN
China
Prior art keywords
phase
time
image
current
video monitoring
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201810430898.4A
Other languages
Chinese (zh)
Inventor
王永星
肖淑艳
许鹏程
陶为戈
张雷
刘舒祺
潘玲佼
朱佩之
王宜皓
黄静
丁翔宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu University of Technology
Original Assignee
Jiangsu University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu University of Technology filed Critical Jiangsu University of Technology
Priority to CN201810430898.4A priority Critical patent/CN108898840A/en
Publication of CN108898840A publication Critical patent/CN108898840A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/095—Traffic lights
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
    • G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/096—Arrangements for giving variable traffic instructions provided with indicators in which a mark progresses showing the time elapsed, e.g. of green phase
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Traffic Control Systems (AREA)

Abstract

The intelligent traffic lamp control method based on video monitoring that the invention discloses a kind of, belongs to field of locating technology, includes the following steps：Background image is chosen from video monitoring image；Foreground image is extracted using background subtraction；Estimate Vehicle length；Distribute the traffic light time in each lane.The present invention passes through the validity and feasibility of this paper system of the experiment show in DSP analogue system simulation traffic condition, time algorithm is distributed compared to traditional traffic lights, traffic lights vehicle pass-through efficiency is improved, traffic jam environment is effectively relieved, fully meets the requirement of true traffic condition.

Description

A kind of intelligent traffic lamp control method based on video monitoring
Technical field
The present invention relates to a kind of method for controlling traffic signal lights, more particularly to a kind of intelligent transportation based on video monitoring Signalized control method, belongs to field of locating technology.
Background technique
Currently, China's car ownership is more than 1.9 hundred million, especially recent years, the swift and violent increase of automobile total value quantity is led Cause the generation of traffic faults and urban traffic blocking more and more frequent.Although road is increasingly improving, people, vehicle, road three are closed The harmony of system does not obtain being satisfied with solution, not only makes troubles to the trip of people, and deeper influence is to bring greatly The economic loss of amount, it is clear that traditional traffic light control system has been unable to meet in existing urban transportation situation, intelligent control Traffic signal lamp system comes into being in this context, and purport is intelligent control traffic lights to improve road utilization Rate improves traffic congestion situation, reduces environmental pollution by automobiles.
The developed countries such as America and Europe have started a large amount of research already and have practiced to solve the problems, such as this, the skill of different field Art is also all combined the research for being applied to intelligent transportation, for intelligent traffic light timing scheme, there is Probability, mould Paste controls, and the inherent immunity algorithm etc. in Digital Image Processing, even neural network and biology is applied to timing strategy In, China big city is deeper and deeper by traffic congestion effect, and study and practical level for developed country also Very big gap.Many small and medium cities still use the long timing scheme of the timing of most original.The maturation intelligence of European and American developed countries Traffic system details is not disclosed, therefore China related researcher develops the intelligent transportation algorithm meaning weight of autonomous property right Greatly.
Summary of the invention
The main object of the present invention is to provide for a kind of intelligent traffic lamp control method based on video monitoring, Under conditions of existing means of transportation, each phase is calculated in real time from video monitoring using image procossing and neural network correlation technique The upper information for waiting passing vehicle, realizes intelligent control traffic lights, improves road utilization rate, and reducing traffic congestion etc. has Great significance.
The purpose of the present invention can reach by using following technical solution：
A kind of intelligent traffic lamp control method based on video monitoring, includes the following steps：
Step S1：Background image is chosen from video monitoring image；
Step S2：Foreground image is extracted using background subtraction；
Step S3：Estimate Vehicle length；
Step S4：Distribute the traffic light time in each lane.
Further, in step S1, choosing background image from video monitoring image includes：
Assuming that season is indicated with Season, value is spring, summer, autumn, winter, the background image under fixed Season variable Take respectively daybreak, early morning, morning, a period of time from morning to afternoon, dusk and not the above period totally 7 back Scape image；
And there may be three kinds of situations of raining, mist and snow daily, are taking a Background in each case above Picture；
According to rainfall size, rains and be divided into light rain, moderate rain, heavy rain and heavy rain；
According to visibility size, mists and be divided into mist, mist, dense fog, thick fog and strong thick fog；
According to snowfall size, snows and be divided into slight snow, moderate snow and heavy snow.
Further, in the step S2, background subtraction is moved using the Differential Detection of present image and background image Region chooses a frame image as background image, the current image comprising background and prospect and background image is done difference operation, adopted It is carried out with following formula：
Wherein：Cn(i, j) indicates the pixel grey scale of the i-th row jth column of the n-th width image；
Bn(i, j) indicates the pixel grey scale of the i-th row jth column of the n-th width background image；
Fn(i, j) is the differential pixel gray scale of the i-th row jth column of the n-th width image；
T is threshold value.
Further, it in the step S3, estimates Vehicle length, includes the following steps：
Step S31：The calibration of monitoring camera
The length for waiting vehicle in vehicle pixel estimation true environment by waiting in image, ignores the radial direction of camera and cuts To distortion, ignore the vehicle error that face camera does not generate, founding mathematical models；
Step S32：Estimate Vehicle length
For M1And M2Between any line segment HG, the mapping point on A and B point line segment is respectively C and D, it is assumed that C and D point Being clipped to A and B point distance is d1And d2, it is assumed that d1< d2, it is assumed that A point coordinate is (xa,ya)；
It acquires：
Thereby determine that straight line SC and SD.
Further, in the step S31, the mathematical model of foundation is shown below：
It can determine line l after calibration1、l2And l3, and then the coordinate that can find out A and B point is：
Wherein：Variable b determines that the high height of the pixel of as camera collection image is asked according to the distance between A and B Solving expression formula is：
Wherein：Line l3As unit of pixel, line l1With line l2Between actual range unit be rice, M1、M2Between any line The online l of section3And l4On projection the line is busy section AB and line segment EF be in equal proportions.
Further, in the step S32, straight line SC and straight line SD, respectively：
Straight line SC：
Straight line SD：
The coordinate of solution point G and H is respectively：
The length for finding out GH is：
The length of GH is equal to Vehicle length.
Further, in the step S4, the traffic light time in each lane is distributed, is included the following steps：
Step S41：Assuming that the red green equal times of a cycle are T, time of the complete needs of the vehicle driving in a direction is allowed, Its phase is l respectively1、l2、l5、l6, the corresponding time of all having passed through is AT1、AT2、AT5、AT6, this four phases are all logical The capable time sorts from long to short, if the time is the same, according to AT1To AT8Sequence, the result after sequence are assumed to be t1、 t2、t3、t4, t1Not only transit time is long for corresponding phase, but also in AT1To AT8In it is forward, allow it first to pass through；
Step S42：t1、t2、t3、t4It is the complete current required time of corresponding phase, t1Corresponding phase is first passed through, and is led to simultaneously Capable can be t2Corresponding phase or t3Corresponding phase；
Work as t1During phase is current, t2And t3Any one passage is selected in corresponding phase, in t1Phase passage process In, the phase passed through simultaneously with it terminates；
When with t1After corresponding phase phase current simultaneously, t1Allow passage simultaneously when corresponding phase is current Another phase P Passable；
Work as t1After passage, t4Corresponding phase P Passable, works as t4Corresponding phase and current current phase all passages terminate Afterwards, this direction passage terminates；
Step S43：Assuming that unidirectional phase is sorted from long to short according to complete transit time, if there is same , according to from AT1To AT8Sequence, first is t1, t1Corresponding phase allows the complete transit time of current phase to be t when current2 And t3, remain next for t4, allow t1It first passes through, this side up, and time that vehicle passed through completely is TW；
If first allowing two phases current, then make another two phase current, complete transit time is TY；
TY >=TW is calculated, TW corresponded manner is selected, is i.e. a phase is once covered, its permitted phase is not influencing it Under his phase condition, P Passable.
Further, the time TW that vehicle has passed through completely is：
If first allowing two phases current, complete transit time TY is：
As (t2+t3-t1)≤t4, i.e. t2+t3≤t1+t4When, if t2≥t4, t1+t2≥t1+t4If t2< t4, t1+t4 =t1+t4, therefore, TY >=TW；
As (t2+t3-t1) > t4, i.e. t2+t3> t1+t4When, if t2≥t4, t1+t2≥t2+t3If t2< t4, t1+t4 ≥t2+t3, therefore, TY >=TW.
Further, in the step S43,
The complete transit time of vehicle for acquiring horizontal direction is TW1, the transit time of vertical direction is TW2, traffic lights it is total Time is T, can be distributed as follows the time：
Horizontal direction distribution the time be：
Vertical direction transit time is：
Work as TW1+TW2=0, without vehicle on present road, by default timing mode timing.
Advantageous effects of the invention：Intelligent traffic lamp controlling party according to the invention based on video monitoring Method, the intelligent traffic lamp control method provided by the invention based on video monitoring, by simulating traffic in DSP analogue system The experiment show of the situation validity and feasibility of this paper system is distributed time algorithm compared to traditional traffic lights, is improved Traffic lights vehicle pass-through efficiency, are effectively relieved traffic jam environment, fully meet the requirement of true traffic condition.
Detailed description of the invention
Fig. 1 is a preferred embodiment of the intelligent traffic lamp control method according to the invention based on video monitoring Flow chart；
Fig. 2 is a preferred embodiment of the intelligent traffic lamp control method according to the invention based on video monitoring Monitoring camera scaling method figure；
Fig. 3 is a preferred embodiment of the intelligent traffic lamp control method according to the invention based on video monitoring The vertical image surface chart at camera center；
Fig. 4 is a preferred embodiment of the intelligent traffic lamp control method according to the invention based on video monitoring Actual traffic crossing rough schematic view；
Fig. 5 is a preferred embodiment of the intelligent traffic lamp control method according to the invention based on video monitoring Assumed condition figure.
Specific embodiment
To make the more clear and clear technical solution of the present invention of those skilled in the art, below with reference to examples and drawings The present invention is described in further detail, and embodiments of the present invention are not limited thereto.
As shown in Figure 1, a kind of intelligent traffic lamp method based on video monitoring provided in this embodiment, including it is following Step：
Step S1, background image is chosen from video monitoring image；
Step S2, foreground image (also referred to as target or vehicle) is extracted using background subtraction；
Step S3, Vehicle length is estimated；
Step S4, the traffic light time in each lane is distributed；
In the present embodiment, in step S1, background image is chosen from video monitoring image, is selected from video monitoring image Take background image, because of the particularity of application environment, the position including monitoring camera be it is fixed, the range of shooting is also relatively solid Fixed.The variation of the background image of shooting is mainly illuminated by the light the influence of intensity, and Various Seasonal and in same season daily Intensity of illumination it is all hardly same, it is assumed that season indicates that value is spring, summer, autumn and winter, under fixed Season variable with Season Background image can take daybreak, early morning, morning, a period of time from morning to afternoon, dusk and not when above respectively Between section totally 7 background images；And daily there may be rainy (being divided into light rain, moderate rain, heavy rain and heavy rain), mist (according to can see Degree can be divided into mist, mist, dense fog, thick fog and strong thick fog again) and (slight snow, moderate snow and heavy snow) three kinds of situations of snowing, each case There are several other situations again and is taking a background image in each case above in protection scope；
In the present embodiment, in step S2, foreground image (also referred to as target or vehicle) is extracted using background subtraction, background Calculus of finite differences is the common method of moving object detection in vision system, it utilizes the Differential Detection of present image and background image A kind of technology of moving region, the basic thought of background subtraction are to choose a frame image as background image, i.e. step S1 is obtained Background image is taken, present image (including background and prospect) is done into difference operation with background image, if reference picture is selectively fitted When then capable of being accurately partitioned into prospect, i.e. target or vehicle, formula is：
Wherein：Cn(i, j) indicates the pixel grey scale of the i-th row jth column of the n-th width image；
Bn(i, j) indicates the pixel grey scale of the i-th row jth column of the n-th width background image；
Fn(i, j) is the differential pixel gray scale of the i-th row jth column of the n-th width image；
T is threshold value.
In the present embodiment, in step S3, Vehicle length is estimated, step is：
Step S31：The calibration of monitoring camera
The purpose of calibration camera is to wait vehicle by being waited in Vehicle length (pixel) estimation true environment in image Length, since camera faces road, so, waiting vehicle is all similar to vertical in the picture, ignores camera shooting The vehicle error that face camera does not generate, founding mathematical models, such as Fig. 2 and Fig. 3 institute are ignored in the radially and tangentially distortion of head Show, in Fig. 3, line l3As unit of pixel, line l1With line l2Between actual range unit be rice (m), easily demonstrate,prove, in point M1、 M2Between any line segment, with online l3And l4On projection be linear relationship, i.e. M1、M2Between any online l of line segment3And l4On Projection the line is busy section AB and line segment EF be in equal proportions, so line l3It is to be exaggerated l in fact as unit of pixel3Practical seat Mark, but wherein image account for total figure picture ratio it is still unchanged, corresponding real-world object size does not also become, so line l3It can be with As unit of pixel；
It can determine line l after calibration1、l2And l3, it is assumed that it is respectively：
And then the coordinate that can find out A and B point is：
Wherein：Variable b's can determine that as the pixel of camera collection image is high according to the distance between A and B height。
Solving expression formula is：
Quadratic equation with one unknown by solving above formula can solve known variables b and be：
With
Step S32：Estimate Vehicle length
For M1And M2Between any line segment HG, their mapping points on A and B point line segment are respectively C and D, it is assumed that C Arriving A and B point distance respectively with D is d1And d2(assuming that d1< d2), then the coordinate of C and D two o'clock can be by A point coordinate, line l3Table and d1And d2Calculating acquires, and first assumes that A point coordinate is (xa,ya), it is acquired according to geometrical relationship WithIt is possible thereby to determine straight line SC and SD, they are respectively：
Can the coordinate of solution point G and H be respectively：
The length of GH can be found out according to distance between two points formula：
The length of GH is namely equal to Vehicle length.
In the present embodiment, the traffic light time in each lane is distributed in the step S4, step is：
Fig. 4 is actual traffic crossing rough schematic view, it is assumed that the red green equal times of a cycle are T, it may be considered that allows one The time of the complete needs of the vehicle driving in a direction, such as horizontal direction, phase is l respectively1、l2、l5、l6, it is right all to have passed through The time answered is AT1、AT2、AT5、AT6.The time that this four phases are all passed through is sorted from long to short, if the time is the same, Then according to AT1To AT8Sequence, the result after sequence are assumed to be t1、t2、t3、t4。t1Corresponding phase not only transit time It is long, and in AT1To AT8In it is forward, allow it first to pass through.Assuming that last result is illustrated in fig. 5 shown below；
T on Fig. 51、t2、t3、t4It is the complete current required time of corresponding phase.t1Corresponding phase is first passed through, then together Shi Tonghang's can be t2Corresponding phase or t3Corresponding phase works as t1During phase is current, t2And t3It is selected in corresponding phase Any one passes through and (is easy to prove, this sequentially has no effect on last current total time), in t1During phase is current, with it Current phase necessarily terminates simultaneously, because of t1Transit time be it is longest, at least will not be shorter than other phases, when with t1It is right After answering phase while current phase, t1Allow another phase of passage simultaneously that can lead to when corresponding phase is current Row, works as t1After passage, t4Corresponding phase P Passable, works as t4After corresponding phase and current current phase are all passed through, this A direction passage terminates；
It is assumed that unidirectional phase is sorted from long to short according to complete transit time, if there is likewise, according to from AT1To AT8Sequence, first is t1, t1Corresponding phase allows the complete transit time of current phase to be t when current2And t3, it is left One is t4, allow t1First pass through, then, this side up, and time TW that vehicle passed through completely is：
If first allowing two phases current, then make two phases current, this mode is completely logical under hypothesis above The row time, TY was：
As (t2+t3-t1)≤t4That is t2+t3≤t1+t4When, if t2≥t4, t1+t2≥t1+t4If t2< t4, t1+t4= t1+t4, so TY >=TW；
As (t2+t3-t1) > t4That is t2+t3> t1+t4When, if t2≥t4, t1+t2≥t2+t3If t2< t4, t1+t4≥ t2+t3, so TY >=TW；
So TY >=TW, selects TW corresponded manner, i.e. a phase is once covered, its permitted phase is not influencing it Under his phase condition, P Passable；
The complete transit time of vehicle for acquiring horizontal direction in this way is TW1, the transit time of vertical direction is TW2, because red The total time of green light is T, can be distributed as follows the time：
Horizontal direction distribution the time be：
Vertical direction transit time is：
If TW in both the above formula1+TW2=0, illustrate without vehicle on present road, by default timing mode timing；
Time in one direction is assigned as (by taking horizontal direction as an example)：
In formula, m is 1 to 4, TSmFor assume in four phases reality can transit time, tmIt is taken by passage completely Between；
If without vehicle pass-through, t on this direction road1+t4=0 or t2+t3=0 there may be that is that is to say, bright TW1For 0, at this time, T1Inherently it is 0, does not distribute necessity of time.Vertical direction is similar with horizontal direction, T1With T2It can not all It is 0, because T is not 0, TW1+TW2≠0；
If TW1+TW2=0, such case is crossed by discussion, by default behavior timing.
Have amber light after arbitrary phase transit time, this be it is necessary, do not calculate in traffic lights total time T.
In conclusion in the present embodiment, being controlled according to the intelligent traffic lamp based on video monitoring of the present embodiment Method, the intelligent traffic lamp control method provided in this embodiment based on video monitoring, by being simulated in DSP analogue system The experiment show of the traffic condition validity and feasibility of this paper system distributes time algorithm compared to traditional traffic lights, Traffic lights vehicle pass-through efficiency is improved, traffic jam environment is effectively relieved, fully meets the requirement of true traffic condition.
The above, further embodiment only of the present invention, but scope of protection of the present invention is not limited thereto, and it is any Within the scope of the present disclosure, according to the technique and scheme of the present invention and its design adds those familiar with the art With equivalent substitution or change, protection scope of the present invention is belonged to.

Claims (9)

1. a kind of intelligent traffic lamp control method based on video monitoring, which is characterized in that include the following steps：
Step S1：Background image is chosen from video monitoring image；
Step S2：Foreground image is extracted using background subtraction；
Step S3：Estimate Vehicle length；
Step S4：Distribute the traffic light time in each lane.
2. a kind of intelligent traffic lamp control method based on video monitoring as described in claim 1, which is characterized in that step In rapid S1, choosing background image from video monitoring image includes：
Assuming that season is indicated with Season, value is spring, summer, autumn, winter, the background image difference under fixed Season variable Take daybreak, early morning, morning, a period of time from morning to afternoon, dusk and not in totally 7 Backgrounds of the above period Picture；
And there may be three kinds of situations of raining, mist and snow daily, are taking a background image in each case above；
According to rainfall size, rains and be divided into light rain, moderate rain, heavy rain and heavy rain；
According to visibility size, mists and be divided into mist, mist, dense fog, thick fog and strong thick fog；
According to snowfall size, snows and be divided into slight snow, moderate snow and heavy snow.
3. a kind of intelligent traffic lamp control method based on video monitoring as described in claim 1, which is characterized in that institute It states in step S2, background subtraction utilizes the Differential Detection moving region of present image and background image, chooses a frame image and makees For background image, the current image comprising background and prospect and background image are done into difference operation, carried out using following formula：
Wherein：Cn(i, j) indicates the pixel grey scale of the i-th row jth column of the n-th width image；
Bn(i, j) indicates the pixel grey scale of the i-th row jth column of the n-th width background image；
Fn(i, j) is the differential pixel gray scale of the i-th row jth column of the n-th width image；
T is threshold value.
4. a kind of intelligent traffic lamp control method based on video monitoring as described in claim 1, which is characterized in that institute It states in step S3, estimates Vehicle length, include the following steps：
Step S31：The calibration of monitoring camera
The length for waiting vehicle in vehicle pixel estimation true environment by waiting in image, ignores the radially and tangentially abnormal of camera Become, ignores the vehicle error that face camera does not generate, founding mathematical models；
Step S32：Estimate Vehicle length
For M1And M2Between any line segment HG, the mapping point on A and B point line segment is respectively C and D, it is assumed that C and D are arrived respectively A and B point distance is d1And d2, it is assumed that d1< d2, it is assumed that A point coordinate is (xa,ya)；
It acquires：
Thereby determine that straight line SC and SD.
5. a kind of intelligent traffic lamp control method based on video monitoring as claimed in claim 4, which is characterized in that institute It states in step S31, the mathematical model of foundation is shown below：
k3=tan α；
It can determine line l after calibration1、l2And l3, and then the coordinate that can find out A and B point is：
Wherein：Variable b determines that the high height of the pixel of as camera collection image solves table according to the distance between A and B It is up to formula：
Wherein：Line l3As unit of pixel, line l1With line l2Between actual range unit be rice, M1、M2Between any line segment exist Line l3And l4On projection the line is busy section AB and line segment EF be in equal proportions.
6. a kind of intelligent traffic lamp control method based on video monitoring as claimed in claim 4, which is characterized in that institute It states in step S32, straight line SC and straight line SD, respectively：
Straight line SC：
Straight line SD：
The coordinate of solution point G and H is respectively：
The length for finding out GH is：
The length of GH is equal to Vehicle length.
7. a kind of intelligent traffic lamp control method based on video monitoring as described in claim 1, which is characterized in that institute It states in step S4, distributes the traffic light time in each lane, include the following steps：
Step S41：Assuming that the red green equal times of a cycle are T, time of the complete needs of the vehicle driving in a direction is allowed, phase Position is l respectively1、l2、l5、l6, the corresponding time of all having passed through is AT1、AT2、AT5、AT6, this four phases are all passed through Time sorts from long to short, if the time is the same, according to AT1To AT8Sequence, the result after sequence are assumed to be t1、t2、 t3、t4, t1Not only transit time is long for corresponding phase, but also in AT1To AT8In it is forward, allow it first to pass through；
Step S42：t1、t2、t3、t4It is the complete current required time of corresponding phase, t1Corresponding phase is first passed through, while current It can be t2Corresponding phase or t3Corresponding phase；
Work as t1During phase is current, t2And t3Any one passage is selected in corresponding phase, in t1During phase is current, with it Current phase terminates simultaneously；
When with t1After corresponding phase phase current simultaneously, t1Allow the another of passage simultaneously when corresponding phase is current A phase P Passable；
Work as t1After passage, t4Corresponding phase P Passable, works as t4After corresponding phase and current current phase are all passed through, This direction passage terminates；
Step S43：Assuming that unidirectional phase is sorted from long to short according to complete transit time, if there is likewise, pressing According to from AT1To AT8Sequence, first is t1, t1Corresponding phase allows the complete transit time of current phase to be t when current2And t3, It remains next for t4, allow t1It first passes through, this side up, and time that vehicle passed through completely is TW；
If first allowing two phases current, then make another two phase current, complete transit time is TY；
TY >=TW is calculated, TW corresponded manner is selected, is i.e. a phase is once covered, its permitted phase is not influencing other phases In the case of position, P Passable.
8. a kind of intelligent traffic lamp control method based on video monitoring as claimed in claim 7, which is characterized in that vehicle The time TW to have passed through completely is：
If first allowing two phases current, complete transit time TY is：
As (t2+t3-t1)≤t4, i.e. t2+t3≤t1+t4When, if t2≥t4, t1+t2≥t1+t4If t2< t4, t1+t4=t1+ t4, therefore, TY >=TW；
As (t2+t3-t1) > t4, i.e. t2+t3> t1+t4When, if t2≥t4, t1+t2≥t2+t3If t2< t4, t1+t4≥t2+ t3, therefore, TY >=TW.
9. a kind of intelligent traffic lamp control method based on video monitoring as claimed in claim 7, which is characterized in that institute It states in step S43,
The complete transit time of vehicle for acquiring horizontal direction is TW1, the transit time of vertical direction is TW2, the total time of traffic lights For T, can distribute as follows the time：
Horizontal direction distribution the time be：
Vertical direction transit time is：
Work as TW1+TW2=0, without vehicle on present road, by default timing mode timing.
CN201810430898.4A 2018-05-08 2018-05-08 A kind of intelligent traffic lamp control method based on video monitoring Pending CN108898840A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810430898.4A CN108898840A (en) 2018-05-08 2018-05-08 A kind of intelligent traffic lamp control method based on video monitoring

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810430898.4A CN108898840A (en) 2018-05-08 2018-05-08 A kind of intelligent traffic lamp control method based on video monitoring

Publications (1)

Publication Number Publication Date
CN108898840A true CN108898840A (en) 2018-11-27

Family

ID=64342603

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810430898.4A Pending CN108898840A (en) 2018-05-08 2018-05-08 A kind of intelligent traffic lamp control method based on video monitoring

Country Status (1)

Country Link
CN (1) CN108898840A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021237750A1 (en) * 2020-05-29 2021-12-02 Siemens Ltd., China Method and apparatus for vehicle length estimation

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201066943Y (en) * 2007-07-24 2008-05-28 西安智达交通科技有限公司 Intelligent controller for intercrossed signal lamp without phase restraint
CN101325008A (en) * 2008-07-25 2008-12-17 浙江大学 Dynamic bidirectional green wave band intelligent coordination control method for urban traffic trunk line
US20090167561A1 (en) * 2007-12-26 2009-07-02 Aochengtongli S&T Development ( Beijing ) Co., Ltd Intelligent traffic light control system
CN101702263A (en) * 2009-11-17 2010-05-05 重庆大学 Pedestrian crosswalk signal lamp green wave self-adaption control system and method
CN102142197A (en) * 2011-03-31 2011-08-03 汤一平 Intelligent traffic signal lamp control device based on comprehensive computer vision
CN103247181A (en) * 2013-04-17 2013-08-14 同济大学 Intelligent traffic light controller based on video vehicle queue length detection and control method thereof
CN104064039A (en) * 2014-07-04 2014-09-24 武汉理工大学 Intelligent timing method of intersection traffic signal lamps
CN104575034A (en) * 2015-01-19 2015-04-29 浙江大学 Single-point intersection signal timing parameter optimization method based on bayonet data
CN106408957A (en) * 2016-11-21 2017-02-15 华南理工大学 Intersection phase time distribution method based on pass demand balance
EP3176768A1 (en) * 2015-12-02 2017-06-07 Siemens Aktiengesellschaft Method for the transformation of a switching order to a signal image of a set of signals
CN107919022A (en) * 2017-11-22 2018-04-17 浙江工业大学 A kind of intelligent traffic light signal control method of dynamic duration distribution

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201066943Y (en) * 2007-07-24 2008-05-28 西安智达交通科技有限公司 Intelligent controller for intercrossed signal lamp without phase restraint
US20090167561A1 (en) * 2007-12-26 2009-07-02 Aochengtongli S&T Development ( Beijing ) Co., Ltd Intelligent traffic light control system
CN101325008A (en) * 2008-07-25 2008-12-17 浙江大学 Dynamic bidirectional green wave band intelligent coordination control method for urban traffic trunk line
CN101702263A (en) * 2009-11-17 2010-05-05 重庆大学 Pedestrian crosswalk signal lamp green wave self-adaption control system and method
CN102142197A (en) * 2011-03-31 2011-08-03 汤一平 Intelligent traffic signal lamp control device based on comprehensive computer vision
CN103247181A (en) * 2013-04-17 2013-08-14 同济大学 Intelligent traffic light controller based on video vehicle queue length detection and control method thereof
CN104064039A (en) * 2014-07-04 2014-09-24 武汉理工大学 Intelligent timing method of intersection traffic signal lamps
CN104575034A (en) * 2015-01-19 2015-04-29 浙江大学 Single-point intersection signal timing parameter optimization method based on bayonet data
EP3176768A1 (en) * 2015-12-02 2017-06-07 Siemens Aktiengesellschaft Method for the transformation of a switching order to a signal image of a set of signals
CN106408957A (en) * 2016-11-21 2017-02-15 华南理工大学 Intersection phase time distribution method based on pass demand balance
CN107919022A (en) * 2017-11-22 2018-04-17 浙江工业大学 A kind of intelligent traffic light signal control method of dynamic duration distribution

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
杨永辉等: "基于视频分析的车辆排队长度检测", 《计算机应用研究》 *
王宁: "基于视频的车辆跟踪与交通事件检测", 《中国优秀博硕士学位论文全文数据库（硕士）•信息科技辑》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021237750A1 (en) * 2020-05-29 2021-12-02 Siemens Ltd., China Method and apparatus for vehicle length estimation

Similar Documents

Publication Publication Date Title
CN108831168B (en) Traffic signal lamp control method and system based on visual identification of associated intersection
CN109191830B (en) Road congestion detection method based on video image processing
CN201425781Y (en) Traffic signal lamps based on visitors flowrate
CN108470461B (en) Traffic signal controller control effect online evaluation method and system
EP3631616A1 (en) Road traffic control system, method, and electronic device
CN107862878B (en) Single Intersection self-adaptation control method based on phasing scheme decision
CN101702263B (en) Pedestrian crosswalk signal lamp green wave self-adaption control system and method
CN108629971B (en) Traffic light control method and optimal vehicle speed determination method
CN108510762B (en) Optimal control method for intelligent signal lamp in multi-line intersection area of expressway
CN110276267A (en) Method for detecting lane lines based on Spatial-LargeFOV deep learning network
CN108831183A (en) Managing system of car parking based on machine vision
CN105718923A (en) Method for vehicle detection and counting at night based on inverse projection drawings
CN109410608B (en) Picture self-learning traffic signal control method based on convolutional neural network
CN106934374A (en) The recognition methods of traffic signboard and system in a kind of haze scene
CN112329553B (en) Lane line marking method and device
CN107016362A (en) Vehicle based on vehicle front windshield sticking sign recognition methods and system again
CN117351702A (en) Intelligent traffic management method based on adjustment of traffic flow
Vani et al. Intelligent traffic control system with priority to emergency vehicles
CN109903574A (en) The acquisition methods and device of crossing traffic information
CN103680159A (en) Road intersection multiple virtual signal linear linkage control system and control method thereof
CN109493602A (en) A kind of evaluation method, the device and system of Urban arterial road coordinate control benefit
CN107622494A (en) Towards the vehicle detection at night and tracking of traffic video
Cheng et al. Semantic segmentation of road profiles for efficient sensing in autonomous driving
CN106846808B (en) A kind of vehicle parking based on license plate data time number calculating method
Hung et al. A traffic monitoring system for a mixed traffic flow via road estimation and analysis

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20181127