CN110415532A - A kind of intelligence adjusts the traffic light device of lighting time - Google Patents
A kind of intelligence adjusts the traffic light device of lighting time Download PDFInfo
- Publication number
- CN110415532A CN110415532A CN201910798953.XA CN201910798953A CN110415532A CN 110415532 A CN110415532 A CN 110415532A CN 201910798953 A CN201910798953 A CN 201910798953A CN 110415532 A CN110415532 A CN 110415532A
- Authority
- CN
- China
- Prior art keywords
- image
- traffic lights
- value
- road
- pixel
- 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
Links
- 238000012545 processing Methods 0.000 claims abstract description 39
- 238000001514 detection method Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 230000002708 enhancing effect Effects 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 10
- 238000003709 image segmentation Methods 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 2
- 238000003708 edge detection Methods 0.000 claims description 2
- 241001269238 Data Species 0.000 claims 1
- 238000004891 communication Methods 0.000 abstract description 4
- 239000011159 matrix material Substances 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 230000003044 adaptive effect Effects 0.000 description 3
- AYFVYJQAPQTCCC-GBXIJSLDSA-N L-threonine Chemical compound C[C@@H](O)[C@H](N)C(O)=O AYFVYJQAPQTCCC-GBXIJSLDSA-N 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000005574 cross-species transmission Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000001627 detrimental effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Abstract
The present invention provides the traffic light device of intelligence adjusting lighting time a kind of, the traffic light device includes traffic lights ontology and the processing unit with the communication connection of traffic lights ontology, the processing unit includes image collection module, computing module and control module, the quantity of the traffic lights ontology is four, respectively the first traffic lights ontology, the second traffic lights ontology, third traffic lights ontology and the 4th traffic lights ontology, each traffic lights ontology include lamp stand, cross bar, camera, light compensating lamp, traffic lights, count-down device and infrared velometer.The present invention judges that the quantity of vehicle, high degree of automation carry out the setting of lighting time according to the size of all directions vehicle fleet size by way of image recognition, can improve the traffic efficiency of road, reduce the transit time of car owner.
Description
Technical field
The present invention relates to field of traffic control, and in particular to a kind of intelligence adjusts the traffic light device of lighting time.
Background technique
The red light of current traffic lights and the time of green light are substantially fixed, and this unreasonable setting often results in
The more lane of vehicle, vehicle congestion is impassable, the less lane P Passable of vehicle but passes through without vehicle, therefore,
We need a kind of traffic light device that lighting time can be automatically controlled according to vehicle flowrate, change automatically according to the size of vehicle flowrate
The time of bright light, to improve traffic efficiency.
Summary of the invention
In view of the above-mentioned problems, the present invention provides the traffic light devices that a kind of intelligence adjusts lighting time.
The purpose of the present invention is realized using following technical scheme:
A kind of intelligence adjusts the traffic light device of lighting time, and the traffic light device includes four of setting at the parting of the ways
A traffic lights ontology and the processing unit communicated to connect with traffic lights ontology, the processing unit include image collection module, meter
Calculate module and control module；
The traffic lights ontology includes lamp stand, is provided with cross bar at the top of the lamp stand, has been sequentially placed on the cross bar red
Outer velometer, count-down device, traffic lights, camera and light compensating lamp；
The camera obtains module with described image and connect, and the picture transfer of shooting to described image is obtained module,
Wherein, the camera on the first traffic lights ontology and the second traffic lights ontology obtains on a road two relative directions respectively
Road picture, the camera on third traffic lights ontology and the 4th traffic lights ontology obtain two phases on another article of road respectively
To the road picture in direction；
Described image obtains module and is used to receive the road picture of each thecamera head, and by the road picture transfer
To computing module；
The computing module is used for by identifying that the road picture obtains current time all directions road vehicle number
DNa is measured, the red light duration RL of all directions in the next round traffic lights period is calculatedaWith long green light time GLa, and by RLaAnd GLaIt passes
It is defeated to arrive control module, wherein a=1,2,3,4 respectively indicate road side corresponding with camera in four traffic lights ontologies
To；
The control module is attached with the traffic lights and count-down device respectively, red for next round based on the received
The red light duration RL in green light periodaWith long green light time GLaControl the display duration in each traffic lights next round traffic lights period；It is described
Control module is also used to control the count-down device and shows current red light or green light remaining display time.
The invention has the benefit that the present invention judges the quantity of vehicle by way of image recognition, journey is automated
Degree is high, and the setting of lighting time is carried out according to the size of all directions vehicle fleet size, can improve the traffic efficiency of road, reduces
The transit time of car owner.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 adjusts a kind of exemplary embodiment figure of the traffic light device of lighting time for a kind of intelligence of the present invention.
Fig. 2 is a kind of exemplary embodiment figure of processing unit of the present invention.
Fig. 3, a kind of exemplary embodiment figure being arranged at the parting of the ways for traffic lights ontology of the present invention.
Appended drawing reference:
Image collection module 1, computing module 2, control module 3, binary conversion treatment submodule 21, image segmentation submodule
22, edge determines submodule 23, detection sub-module 24, the first traffic lights ontology L1, the second traffic lights ontology L2, third traffic lights
Ontology L3, the 4th traffic lights ontology L4.
Specific embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of intelligence of the invention adjusts the traffic light device of lighting time, which is characterized in that described red green
Lamp device includes that four traffic lights ontologies at the parting of the ways and the processing unit with the communication connection of traffic lights ontology is arranged, described
Processing unit includes image collection module 1, computing module 2 and control module 3；
The traffic lights ontology includes lamp stand, is provided with cross bar at the top of the lamp stand, has been sequentially placed on the cross bar red
Outer velometer, count-down device, traffic lights, camera and light compensating lamp；
The camera obtains module 1 with described image and connect, and the picture transfer of shooting to described image is obtained module
1, wherein the camera on the first traffic lights ontology and the second traffic lights ontology obtains two relative directions on a road respectively
Road picture, the camera on third traffic lights ontology and the 4th traffic lights ontology obtains two on another article of road respectively
The road picture of relative direction；
Described image obtains the road picture that module 1 is used to receive each thecamera head, and the road picture is passed
It is defeated to arrive computing module 2；
The computing module 2 is used for by identifying that the road picture obtains current time all directions road vehicle number
DNa is measured, the red light duration RL of all directions in the next round traffic lights period is calculatedaWith long green light time GLa, and by RLaAnd GLaIt passes
It is defeated to arrive control module 3, wherein a=1,2,3,4 respectively indicate road side corresponding with camera in four traffic lights ontologies
To；
The control module 3 is attached with the traffic lights and count-down device respectively, for next round based on the received
The red light duration RL in traffic lights periodaWith long green light time GLaControl the display duration in each traffic lights next round traffic lights period；Institute
It states control module 3 and is also used to control the count-down device and show current red light or green light remaining display time.
The computing module 2 is calculated by the following formula the red light and green light of all directions in next round traffic light time
Show the time:
In formula, DN1 indicates the vehicle fleet size of corresponding first road direction of camera in the first traffic lights ontology, DN2 table
Show that the vehicle fleet size of corresponding second road direction of camera in the second traffic lights ontology, DN3 indicate in third traffic lights ontology
The vehicle fleet size of the corresponding third road direction of camera, DN4 indicate camera the corresponding 4th in the 4th traffic lights ontology
The vehicle fleet size in road direction, Ttal represent the total time in next round traffic lights period, GL1And GL2Respectively represent the first road direction
With the green light duration of the second road direction, RL3And RL4Respectively represent the red light of third road direction and the 4th road direction
Show time, GL3And GL4Respectively represent the green light duration RL of third road direction and the 4th road direction1And RL2Respectively
The red light for representing the first road direction and the second road direction shows the time, Max (DN1, DN2) indicate to take in DN1 and DN2 compared with
Big value, Max (DN3, DN4) indicate to take the larger value in DN3 and DN4.
The above embodiment of the present invention, judges the quantity of vehicle by way of image recognition, high degree of automation, according to
The size of all directions vehicle fleet size carries out the setting of lighting time, can improve the traffic efficiency of road, reduces the logical of car owner
The row time.
The computing module 2 includes:
Binary conversion treatment submodule 21, for carrying out self-adaption binaryzation processing to image；
Image segmentation submodule 22, for being split to the image by self-adaption binaryzation processing, by described image
It is divided into different blocks,
Edge determines submodule 23, for carrying out edge detection to the block and getting the number of edges of all blocks
According to,
Detection sub-module 24 carries out the detection of rectangle similarity for the edge data to each block, if the rectangle of block
Similarity detection is only greater than preset threshold, then determines that the block has vehicle, and count the number of vehicle in the image.
In one embodiment, described image segmentation submodule 22 uses watershed algorithm.In another embodiment
In, described image divides submodule 22 and uses GrabCut algorithm.
Preferably, the binary conversion treatment submodule 21 includes pretreatment unit and binary conversion treatment unit,
The pretreatment unit is used to carry out image details enhancing processing and obtains details to enhance image, and by described image
It is transferred to binary conversion treatment unit；
The binary conversion treatment unit carries out two for receiving the image that pretreatment unit sends over, and to described image
Value processing.
Preferably, pretreatment unit carries out details enhancing processing to image, comprising:
Using the gray value of calculated with weighted average method described image, gray level image A is converted by described image1, A1(x, y)
The horizontal pixel sum and image of the respectively image of gray value at expression (x, y), x ∈ [1, X], y ∈ [1, Y], X and Y
Longitudinal sum of all pixels；
To the gray level image A1In the gray value of pixel carry out customized normalized:
In formula, A2(x, y) is the gray scale value coefficient of treated pixel (x, y), and L is preset light intensity gray reference
Value, Φ and Γ are presetting adjusting parameter.
The above embodiment of the present invention is converted, the specular and dark effectively adjusted by carrying out customized normalization
The gray level ratio in area, suppresses specular, is promoted to dark region, and light in subsequent acquisition image is more advantageous to
The details in insufficient region.Often there is Luminance Distribution unevenness in the image that night shoots in image collection module 1, this
It is highly detrimental to obtain the profile of vehicle, and the above embodiment of the present invention solves the above problem just.
To the gray scale value coefficient A after normalized2(x, y) carries out customized transformation:
In formula, A3(x, y) is transformed gray scale value coefficient, and a is the transformation parameter of setting.
To image A1It is filtered operation:
Operation is filtered to pixel (x, y) using square filter window, sets gray scale maximum value in filter window
For W1max, minimum gray value W1min, the mean value of the gray value of all pixels point is W1ave in window, is then executed next
Step；
1): judging the gray value A of current pixel point (x, y)1Whether (x, y) meets condition W1min < A1(x, y) <
W1max, if so, not changing the gray value of pixel (x, y), window is moved to next pixel, if it is not, under then executing
One step；
2): judging whether the mean value W1ave of gray value meets condition W1min < W1ave < W1max, if so, will
Gray value of the W1ave as pixel (x, y), if it is not, then performing the next step；
3): judging whether the size of current filter window is less than preset threshold value, if it is not, then by the surplus ruler of filter window
Two pixels of very little each increase, then branch to step 1), if so, performing the next step；
4): by all pixels in current filter window, other than the pixel of gray scale maximum value and minimum gray value
Gray value of the average value of the gray value of point as pixel (x, y), and window is moved to next pixel.
Image A is denoted as by the image finished is filtered to all pixels point4。
The above embodiment of the present invention solves in traditional filtering algorithm, since noise quantity is excessive and filter effect weakens
The problem of, while noise reduction, the edge details of image are remained well.Above-described embodiment has well solved the present invention
In, due to the problem that night illumination deficiency causes the picture noise of the acquisition of image collection module 1 excessive, significantly reduce subsequent
Identification in noise influence.
To filtered image A4(x, y) carries out customized transformation:
In formula, A5(x, y) is the second gray scale value coefficient of transformed pixel, and b is the transformation parameter of setting.
To A3And A5It is calculated, is obtained third gray scale value coefficient comp (x, y):
Details enhancing image Det is sought according to third gray scale value coefficient comp (x, y):
In formula, α is customized gain coefficient, and Λ indicates preset adjusting parameter, is used for the gray value of pixel (x, y)
It is restored to [0,255] section.
Then the above embodiment of the present invention is carried out certainly again by first carrying out customized normalized to original image
Definition transformation, avoids the spillover on traditional algorithm.Customized transformation is carried out after being filtered to original image again, then
The comprehensive obtained image that converts customized twice carries out operation, has obtained details enhancing image, has enhanced edge details.
Preferably, the binary conversion treatment unit includes the first processing subelement, second processing subelement and integrated treatment
Subelement, the first processing subelement obtain the first image by objective contour enhancing, institute for handling image
It states second processing subelement to extract for adaptive targets, obtains the second image Jing Guo background process, integrated treatment
Unit is used to the first image and the second image carrying out operation, obtains final binary image.
Preferably, the first processing subelement is used to carry out contour extraction of objects to image, and obtaining includes passing through target
First image of edge enhancement, comprising:
The element generated in the processing array Mk, Mk of N2 × N2 is obtained by following formula:
In formula, N2>=3, and N2For odd number, (j, k) indicates that processing array center element coordinate, (m, n) indicate processing array
Element coordinate, g and h are preset regulation coefficient, and Thre is preset threshold parameter, Thre=Adj × sin (Ang),
Adj is adjusting parameter, and Ang is the detection angles of preset processing array.
The quantity Nadj of the angle of detection is set, then determines detection angles Angp, p ∈ [1, Nadj], p are integer,
According to different detection angles, different processing array Mk is generated for Nadj detection anglesp。
Enhance details the pixel (x in image Det by the sliding window of N2 × N22, y2) handled, x2∈ [1,
X], y2∈ [1, ymid), ymidIndicate the y that Det is up counted from bottom linemidCapable pixel, X and Y are respectively that details increases
The strong image Det horizontal and vertical total line number of pixel, by the gray value and processing array of the pixel in the window of N2 × N2
Mk carries out convolution algorithm, and obtains convolution algorithm result Corp(x2, y2)。
As preferred embodiment, ymidValue be
By the processing array of Nadj different detection angles to pixel (x2, y2) handled, choose Nadj convolution
Maximum value is used as pixel (x in operation result2, y；) gray value, thus obtain include objective contour the second image
finalA(x2, y2)。
The above embodiment of the present invention handles pixel by different detection angles, avoids conventional process side
In method, there is the problem of more non-targeted pixel.Detection speed when subsequent edges detection can be effectively reduced.
Preferably, the second processing subelement carries out adaptive targets extraction to image, obtains by background process
Second image, comprising:
Background process is carried out to the details enhancing image Det that pretreatment unit transmits:
B1(x1- u, y1- v)=Ω1Det(x1- u, y1-v)Mat1(u, v)
B2(x1- u, y1- v)=Ω2B1(x1- u, y1-v)Mat2(u, v)
In formula, Mat1And Mat2It is customized background process matrix, two matrixes are N2 × N2 matrix, wherein square
Battle array Mat1The first row, last line, first row and last element arranged are 1, remaining element is all 0, matrix Mat2First
Row, last line, first row and last element arranged are 0, remaining element is that 1, B1 is indicated by matrix Mat1Processing
Image, B2 indicate pass through matrix Mat2The image of processing, u ∈ [1, N2], v ∈ [1, N2], Ω1And Ω2It is preset adjustment
Parameter, y1∈[ymid, Y], ymidIndicate the y that Det is up counted from bottom linemidCapable pixel, x1∈ [1, X], X and Y
The respectively details enhancing image Det horizontal and vertical total line number of pixel.
In one embodiment, describedIt is described
Image B2 is filtered:
In formula, WMatiFor initial weight matrix, u1 ∈ [1, N2], v1 ∈ [1, N2], u and v are integer, filter window
Size is N2 × N2, i=Ψ+y1-1+x1X, Ψ are customized regulation coefficient, and X is image horizontal pixel point sum, and Wenh is
The enhancing initial weight matrix of N2 × N2, Wenh (r, s)=1-ewneh,r∈
[1, N2], s ∈ [1, N2], d are preset regulation coefficient °
Adaptive weighting matrix is updated using following manner:
WMati+1(u1, v1)=WMati(u1, v1)+ξiEiB2(x1- u1, y1-v1)
In formula, ξiFor the iteration step length of filtering, EiFor preset adjusting parameter.
The second image FinalB Jing Guo background process is obtained using following formula:
FinalB(x1, y1)=Det (x, y)-Filt (x1, y1)
The above embodiment of the present invention, since remotely located vehicle is often smaller on the image, traditional identification is calculated
Method is difficult to, thus first carries out the processing of background, its influence of non-vehicle target to vehicle identification is reduced, due to background process
When, primary processing is often difficult to thoroughly remove background, therefore has used two different background process matrixes, first matrix
First identify the region for being likely to be vehicle, second matrix reduces the noise of vehicle periphery, then again by certainly
The filter function of definition is filtered, and the generation of noise can also be suppressed while removing background, is subsequent further identification
It provides convenience.
In such a way that setting weight enhances matrix, so that the pixel of filter window middle section weight with higher
Value, strengthens the accuracy of background removal, solves and is easy background being mistakenly considered asking for target in traditional object detection method
Topic.
Preferably, the integrated treatment subelement is used to the first image and the second image carrying out operation, obtains most
Whole binary image, comprising:
First image and the second image group are spliced into as the complete image final (x, y) of a width, image final (x, y)
The 1st row of number is to y from beneathmidRow is image finalA (x2, y2), ymidThe above are image FinalB (x for row1,
y1)。
If finalA (x2, y2) it is greater than preset threshold value Threl or FinalB (x1, y1) it is greater than preset threshold value Thre2,
Then by (x2, y2) or (x1, y1) at the gray value of pixel be set as 255, otherwise, the gray value of the pixel is set as 0.
The above embodiment of the present invention screens pixel further progress, can reduce non-mesh by way of threshold value is arranged
Mark influence of the pixel to target identification.
The above embodiment of the present invention divides the image into two parts and is handled, so that the accuracy rate of identification is improved, and into
Out
Through the above description of the embodiments, those skilled in the art can be understood that it should be appreciated that can
To realize the embodiments described herein with hardware, software, firmware, middleware, code or its any appropriate combination.For hardware
It realizes, processor can be realized in one or more the following units: specific integrated circuit (ASIC), digital signal processor
(DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processing
Device, controller, microcontroller, microprocessor, other electronic units designed for realizing functions described herein or combinations thereof.
For software implementations, some or all of embodiment process can instruct relevant hardware to complete by computer program.
When realization, above procedure can be stored in computer-readable medium or as the one or more on computer-readable medium
Instruction or code are transmitted.Computer-readable medium includes computer storage media and communication media, wherein communication media packet
It includes convenient for from a place to any medium of another place transmission computer program.Storage medium can be computer can
Any usable medium of access.Computer-readable medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other
Optical disc storage, magnetic disk storage medium or other magnetic storage apparatus or can be used in carry or store have instruction or data
The desired program code of structure type simultaneously can be by any other medium of computer access.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (5)
1. the traffic light device that a kind of intelligence adjusts lighting time, which is characterized in that the traffic light device includes being arranged ten
Four traffic lights ontologies at word crossing and the processing unit communicated to connect with traffic lights ontology, the processing unit includes that image obtains
Modulus block, computing module and control module；
The traffic lights ontology includes lamp stand, is provided with cross bar at the top of the lamp stand, infrared survey has been sequentially placed on the cross bar
Fast device, count-down device, traffic lights, camera and light compensating lamp；
The camera obtains module with described image and connect, and the picture transfer of shooting to described image is obtained module, wherein
Camera on first traffic lights ontology and the second traffic lights ontology obtains the road of two relative directions on a road respectively
Picture, the camera on third traffic lights ontology and the 4th traffic lights ontology obtain two opposite sides on another article of road respectively
To road picture；
Described image obtains the road picture that module is used to receive each thecamera head, and the road picture is transferred to meter
Calculate module；
The computing module is used for by identifying that the road picture obtains current time all directions road vehicle quantity
DNa calculates the red light duration RL of all directions in the next round traffic lights periodaWith long green light time GLa, and by RLaAnd GLaTransmission
To control module, wherein a=1,2,3,4 respectively indicate road direction corresponding with camera in four traffic lights ontologies；
The control module is attached with the traffic lights and count-down device respectively, for next round traffic lights based on the received
The red light duration RL in periodaWith long green light time GLaControl the display duration in each traffic lights next round traffic lights period；The control
Module is also used to control the count-down device and shows current red light or green light remaining display time.
2. the traffic light device that a kind of intelligence according to claim 1 adjusts lighting time, which is characterized in that the calculating
Module is calculated by the following formula the display time of the red light and green light of all directions in next round traffic light time:
In formula, DN1 indicates that the vehicle fleet size of corresponding first road direction of camera in the first traffic lights ontology, DN2 indicate the
The vehicle fleet size of corresponding second road direction of camera in two traffic lights ontologies, DN3 indicate to image in third traffic lights ontology
The vehicle fleet size of corresponding third road direction, DN4 indicate the corresponding 4th road side of camera in the 4th traffic lights ontology
To vehicle fleet size, Ttal represents the total time in next round traffic lights period, GL1And GL2Respectively represent the first road direction and
The green light duration of two road directions, RL3And RL4The red light for respectively representing third road direction and the 4th road direction is shown
Time, GL3And GL4Respectively represent the green light duration RL of third road direction and the 4th road direction1And RL2It respectively represents
The red light of first road direction and the second road direction shows the time, and Max (DN1, DN2) expression takes larger in DN1 and DN2
Value, Max (DN3, DN4) indicate to take the larger value in DN3 and DN4.
3. the traffic light device that a kind of intelligence according to claim 1 adjusts lighting time, which is characterized in that
The computing module includes:
Binary conversion treatment submodule, for carrying out self-adaption binaryzation processing to image；
Described image is divided by image segmentation submodule for being split to the image by self-adaption binaryzation processing
Different blocks,
Edge determines submodule, for carrying out edge detection to the block and getting the edge datas of all blocks,
Detection sub-module carries out the detection of rectangle similarity for the edge data to each block, if the rectangle similarity of block
Detection is only greater than preset threshold, then determines that the block has vehicle, and count the number of vehicle in the image.
4. the traffic light device that a kind of intelligence according to claim 3 adjusts lighting time, which is characterized in that the two-value
Changing processing submodule includes pretreatment unit and binary conversion treatment unit,
The pretreatment unit, which is used to carry out image details enhancing processing acquisition details, enhances image, and described image is transmitted
To binary conversion treatment unit；
The binary conversion treatment unit carries out binaryzation for receiving the image that pretreatment unit sends over, and to described image
Processing.
5. the traffic light device that a kind of intelligence according to claim 4 adjusts lighting time, which is characterized in that the pre- place
It manages unit and details enhancing processing is carried out to image, comprising:
Using the gray value of calculated with weighted average method described image, gray level image A is converted by described image1, A1(x, y) is indicated
Gray value at (x, y), x ∈ [1, X], y ∈ [1, Y], X and Y's is respectively the horizontal pixel sum of image and indulging for image
To sum of all pixels；
To the gray level image A1In the gray value of pixel carry out customized normalized:
In formula, A2(x, y) is the gray scale value coefficient of treated pixel (x, y), and L is preset light intensity gray reference value, Φ and
Γ is presetting adjusting parameter；
To the gray scale value coefficient A after normalized2(x, y) carries out customized transformation:
In formula, A3(x, y) is transformed gray scale value coefficient, and a is the transformation parameter of setting；
To image A1It is filtered operation:
Operation is filtered to pixel (x, y) using square filter window, set in filter window gray scale maximum value as
W1max, minimum gray value W1min, the mean value of the gray value of all pixels point is W1ave in window, is then performed the next step；
1): judging the gray value A of current pixel point (x, y)1Whether (x, y) meets condition W1min < A1(x, y) < W1max, if
It is not change the gray value of pixel (x, y) then, window is moved to next pixel, if it is not, then performing the next step；
2): judging whether the mean value W1ave of gray value meets condition W1min < W1ave < W1max, if so, W1ave is made
For the gray value of pixel (x, y), if it is not, then performing the next step；
3): judging whether the size of current filter window is less than preset threshold value, if it is not, then that the surplus size of filter window is each
Increase by two pixels, then branch to step 1), if so, performing the next step；
4): by current filter window, all pixels point other than the pixel of gray scale maximum value and minimum gray value
Gray value of the average value of gray value as pixel (x, y), and window is moved to next pixel；
Image A is denoted as by the image finished is filtered to all pixels point4；
To filtered image A4(x, y) carries out customized transformation:
In formula, A5(x, y) is the second gray scale value coefficient of transformed pixel, and b is the transformation parameter of setting.
To A3And A5It is calculated, is obtained third gray scale value coefficient comp (x, y):
Details enhancing image Det is sought according to third gray scale value coefficient comp (x, y):
In formula, α is customized gain coefficient, and Λ indicates preset adjusting parameter, for restoring the gray value of pixel (x, y)
To [0,255] section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910798953.XA CN110415532A (en) | 2019-08-27 | 2019-08-27 | A kind of intelligence adjusts the traffic light device of lighting time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910798953.XA CN110415532A (en) | 2019-08-27 | 2019-08-27 | A kind of intelligence adjusts the traffic light device of lighting time |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110415532A true CN110415532A (en) | 2019-11-05 |
Family
ID=68369428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910798953.XA Pending CN110415532A (en) | 2019-08-27 | 2019-08-27 | A kind of intelligence adjusts the traffic light device of lighting time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110415532A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091723A (en) * | 2019-12-19 | 2020-05-01 | 中科芯集成电路有限公司 | Intelligent traffic light and system based on wireless communication |
| CN111753748A (en) * | 2020-06-28 | 2020-10-09 | 北京百度网讯科技有限公司 | Signal lamp adjusting method, device, equipment and storage medium |
| CN112349111A (en) * | 2020-09-30 | 2021-02-09 | 贵阳市大数据产业集团有限公司 | Traffic signal control system based on wisdom lamp pole |
| CN113470385A (en) * | 2021-06-17 | 2021-10-01 | 广东交通职业技术学院 | Traffic light control method, system and device based on machine vision and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101093539A (en) * | 2007-07-27 | 2007-12-26 | 哈尔滨工程大学 | Matching identification method by extracting characters of vein from finger |
| CN101329726A (en) * | 2008-07-30 | 2008-12-24 | 电子科技大学 | Method for reinforcing fingerprint image based on one-dimensional filtering |
| CN103247025A (en) * | 2012-02-06 | 2013-08-14 | 河北师范大学 | Circular self-adaptation template based image weighted mean filtering method |
| CN104574293A (en) * | 2014-11-28 | 2015-04-29 | 中国科学院长春光学精密机械与物理研究所 | Multiscale Retinex image sharpening algorithm based on bounded operation |
| CN104599512A (en) * | 2015-01-28 | 2015-05-06 | 深圳市汇川技术股份有限公司 | Traffic light automatic adjusting method and system and traffic light system |
| KR20150055652A (en) * | 2013-11-13 | 2015-05-22 | 한국건설기술연구원 | A Vehicle License Plate Recognition System and Method Thereof |
| CN105373781A (en) * | 2015-11-16 | 2016-03-02 | 成都四象联创科技有限公司 | Binary image processing method for identity authentication |
| CN109767406A (en) * | 2019-01-28 | 2019-05-17 | 中南林业科技大学 | A kind of adaptive median filter denoising method applied to image procossing |
-
2019
- 2019-08-27 CN CN201910798953.XA patent/CN110415532A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101093539A (en) * | 2007-07-27 | 2007-12-26 | 哈尔滨工程大学 | Matching identification method by extracting characters of vein from finger |
| CN101329726A (en) * | 2008-07-30 | 2008-12-24 | 电子科技大学 | Method for reinforcing fingerprint image based on one-dimensional filtering |
| CN103247025A (en) * | 2012-02-06 | 2013-08-14 | 河北师范大学 | Circular self-adaptation template based image weighted mean filtering method |
| KR20150055652A (en) * | 2013-11-13 | 2015-05-22 | 한국건설기술연구원 | A Vehicle License Plate Recognition System and Method Thereof |
| CN104574293A (en) * | 2014-11-28 | 2015-04-29 | 中国科学院长春光学精密机械与物理研究所 | Multiscale Retinex image sharpening algorithm based on bounded operation |
| CN104599512A (en) * | 2015-01-28 | 2015-05-06 | 深圳市汇川技术股份有限公司 | Traffic light automatic adjusting method and system and traffic light system |
| CN105373781A (en) * | 2015-11-16 | 2016-03-02 | 成都四象联创科技有限公司 | Binary image processing method for identity authentication |
| CN109767406A (en) * | 2019-01-28 | 2019-05-17 | 中南林业科技大学 | A kind of adaptive median filter denoising method applied to image procossing |
Non-Patent Citations (4)
| Title |
|---|
| 肖世德 等: "《高等机械CAD/CAM》", 31 January 2015 * |
| 谷曼曼: "运用光强相减和灰度值变换法改善数字全息图像质量研究", 《中国优秀硕士学位论文全文数据库》 * |
| 贾永红: "《数字图像处理》", 31 July 2015, 武汉大学出版社 * |
| 黄贤武: "基于方向滤波分散的指纹自动识别系统算法", 《中国图象图形学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091723A (en) * | 2019-12-19 | 2020-05-01 | 中科芯集成电路有限公司 | Intelligent traffic light and system based on wireless communication |
| CN111753748A (en) * | 2020-06-28 | 2020-10-09 | 北京百度网讯科技有限公司 | Signal lamp adjusting method, device, equipment and storage medium |
| CN111753748B (en) * | 2020-06-28 | 2023-12-08 | 阿波罗智联(北京)科技有限公司 | Signal lamp adjusting method, device, equipment and storage medium |
| CN112349111A (en) * | 2020-09-30 | 2021-02-09 | 贵阳市大数据产业集团有限公司 | Traffic signal control system based on wisdom lamp pole |
| CN113470385A (en) * | 2021-06-17 | 2021-10-01 | 广东交通职业技术学院 | Traffic light control method, system and device based on machine vision and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110415532A (en) | A kind of intelligence adjusts the traffic light device of lighting time | |
| CN104954664B (en) | Image processing apparatus and image processing method | |
| CN106815821B (en) | Denoising method and device for near-infrared image | |
| CN102314599A (en) | Identification and deviation-detection method for lane | |
| CN107705254B (en) | City environment assessment method based on street view | |
| CN107945523B (en) | Road vehicle detection method, traffic parameter detection method and device | |
| CN111401150B (en) | Multi-lane line detection method based on example segmentation and self-adaptive transformation algorithm | |
| TW201716266A (en) | Image inpainting system area and method using the same | |
| CN104112132A (en) | Automatic gun number identification method | |
| CN104778669A (en) | Fast image denoising method and device | |
| CN109934781B (en) | Image processing method, image processing device, terminal equipment and computer readable storage medium | |
| CN109147351A (en) | A kind of traffic light control system | |
| CN102306307B (en) | Positioning method of fixed point noise in color microscopic image sequence | |
| CN111145105B (en) | Image rapid defogging method and device, terminal and storage medium | |
| CN116630813B (en) | Highway road surface construction quality intelligent detection system | |
| CN113421215A (en) | Automatic tracking system of car based on artificial intelligence | |
| CN114881869A (en) | Inspection video image preprocessing method | |
| CN115205297A (en) | Abnormal state detection method for pneumatic winch | |
| CN110335322B (en) | Road recognition method and road recognition device based on image | |
| CN111652033A (en) | Lane line detection method based on OpenCV | |
| CN109800641A (en) | Method for detecting lane lines based on threshold adaptive binaryzation and connected domain analysis | |
| CN110633705A (en) | Low-illumination imaging license plate recognition method and device | |
| CN116823686B (en) | Night infrared and visible light image fusion method based on image enhancement | |
| CN105631425B (en) | License plate recognition method and system based on video stream and intelligent digital camera | |
| CN109903253B (en) | Road traffic video defogging algorithm based on depth-of-field prior |
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 |
Application publication date: 20191105 |
|
| RJ01 | Rejection of invention patent application after publication |