CN104732771A - Identification method for overtaking vehicle at traffic intersection - Google Patents
Identification method for overtaking vehicle at traffic intersection Download PDFInfo
- Publication number
- CN104732771A CN104732771A CN201510163552.9A CN201510163552A CN104732771A CN 104732771 A CN104732771 A CN 104732771A CN 201510163552 A CN201510163552 A CN 201510163552A CN 104732771 A CN104732771 A CN 104732771A
- Authority
- CN
- China
- Prior art keywords
- value
- vehicle
- image
- traffic intersection
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 32
- 230000006698 induction Effects 0.000 claims description 35
- 101100006584 Mus musculus Clnk gene Proteins 0.000 claims description 22
- 230000008030 elimination Effects 0.000 claims description 22
- 238000003379 elimination reaction Methods 0.000 claims description 22
- 239000003595 mist Substances 0.000 claims description 22
- 230000005540 biological transmission Effects 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 19
- 230000003534 oscillatory effect Effects 0.000 claims description 15
- 230000010355 oscillation Effects 0.000 claims description 12
- 230000001939 inductive effect Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 230000033228 biological regulation Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- 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
- G08G1/048—Detecting movement of traffic to be counted or controlled with provision for compensation of environmental or other condition, e.g. snow, vehicle stopped at detector
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to an identification method for an overtaking vehicle at a traffic intersection. The method comprises the steps that a vehicle position sensing system is utilized to sense whether a vehicle passes three positions of a straight lane cut-off line, the preset length away from the front of the straight lane cut-off line and the preset length away from the front of a left side lane cut-off line; an image detection system is utilized to shoot a traffic intersection image, perform haze removing processing on the traffic intersection image and identify the license number of the overtaking vehicle in the haze removed traffic intersection image; on the basis of the sensing result of the vehicle position sensing system, a Freescale single chip microcomputer MC9S12XS128 is utilized to determine whether the overtaking violation vehicle exists and control the image detection system to detect the license number of the violation vehicle. According to the identification method for the overtaking vehicle at the traffic intersection, overtaking violation behavior can be accurately and effectively detected, and corresponding violation vehicle information can be accurately identified in various hazy weather.
Description
Technical field
The present invention relates to detection of electrons field, particularly relate to a kind of traffic intersection and rob row vehicle identification method.
Background technology
Usually, at larger current crossing place, the track arranged comprises turn lane, left-hand lane, Through Lane and right-hand lane, Turning travel is carried out for the vehicle adjusting travel direction in tune track, left-hand lane is used for vehicle and turns left curved moving ahead, right-hand lane is used for vehicle and turns right curved moving ahead, and Through Lane is used for vehicle and keeps straight on to dead ahead.Correspondingly, can arrange the signal lamp indicating equipment comprising multiple signal lamp subelement at so current crossing, driver must pass through according to the instruction of signal lamp indicating equipment, and the behavior of the instruction of violation signal lamp indicating equipment is all decided to be act of violating regulations.
In prior art, the vehicle peccancy detection system of making a dash across the red light is more common, and seldom have detection Through Lane vehicle to rob the vehicle peccancy detection system of left-hand lane, more lack the embodiment that two kinds of system for detecting regulation violation combine, in fact, the vehicle peccancy behavior harm of making a dash across the red light is very large, the act of violating regulations that left-hand lane robbed by Through Lane vehicle also can bring larger safety problem, on the one hand, destroy normal road traffic order, cause the abnormal traveling behavior of vehicle, the illegal driving habits of driver; On the other hand, robbing every trade is easily cause the vehicle collision in two tracks, not only unfair to the normal vehicle of lamp that waits, and brings potential safety hazard to the vehicle of the lamp such as normal.Therefore need to detect this act of violating regulations of robbing row left-hand lane, the normal traveling of specification vehicle, ensure the security that crossing is current and fairness.
Vehicle peccancy detection system of the prior art is under haze weather, and because detected image lacks the treatment facility eliminating haze, testing result very easily affects by haze, causes the reliability of system and accuracy also to receive discount greatly.
Therefore, need a kind of traffic intersection to rob row vehicle identification method, the act of violating regulations taking the mode of detection of electrons automatically to detect vehicles peccancy to make a dash across the red light and rob left lateral, and can free from errors detect the information of vehicles comprising the number-plate number under various haze weather.
Summary of the invention
In order to solve the problems of the technologies described above, according to an aspect of the present invention, the invention provides a kind of traffic intersection and rob row vehicle identification method, it comprises: utilize vehicle location induction system respectively before Through Lane dead line, distance Through Lane dead line before preset length and distance left-hand lane dead line preset length three place location sensitive whether there is vehicle and pass through; Utilize image detecting system to take traffic intersection image, the process of mist elimination haze is carried out to traffic intersection image, and identify in mist elimination haze traffic intersection image the number-plate number of robbing driving; Based on the induction result of described vehicle location induction system, utilize Freescale single-chip microcomputer MC9S12XS128 to determine whether there is and rob capable vehicles peccancy, and control image detecting system to detect the number-plate number of vehicles peccancy.
Preferably, recognition methods of the present invention utilizes traffic intersection to rob a driving Identification platform and implements, therefore, according to another aspect of the present invention, the invention provides a kind of traffic intersection and rob a driving Identification platform, described Identification platform comprises vehicle location induction system, image detecting system and Freescale single-chip microcomputer MC9S12XS128, described vehicle location induction system is used for respectively at Through Lane dead line, whether there is vehicle apart from preset length three place location sensitive before preset length before Through Lane dead line and distance left-hand lane dead line to pass through, described Freescale single-chip microcomputer is connected respectively with described vehicle location induction system and described image detecting system, induction result based on described vehicle location induction system determines whether there is robs capable vehicles peccancy, and control image detecting system to detect the number-plate number of vehicles peccancy.
Particularly, described image detecting system comprises CMOS vision sensor, sharpening image processor and Car license recognition device, and wherein said CMOS vision sensor is for taking traffic intersection image; Described sharpening image processor is used for carrying out the process of mist elimination haze to export mist elimination haze traffic intersection image to traffic intersection image; Described Car license recognition device to be connected to identify in mist elimination haze traffic intersection image the number-plate number of vehicle in the near zone of preset length position before distance Through Lane dead line with described sharpening image processor, as the number-plate number rushing craspedodrome red light vehicle, identify the number-plate number of the vehicle of preset length position near zone before distance left-hand lane dead line in mist elimination haze traffic intersection image, as the number-plate number of robbing row left-hand lane vehicle.
Preferably, described Identification platform also comprises:
Power supply, comprise solar powered device, accumulator, change-over switch and electric pressure converter, described change-over switch is connected respectively with described solar powered device and described accumulator, determine whether be switched to described solar powered device to be powered by described solar powered device according to accumulator dump energy, described electric pressure converter is connected with described change-over switch, with the 5V voltage transitions will inputted by change-over switch for 3.3V voltage;
Signal lamp data collector, be connected respectively with multiple signal lamp unit, the quantity of signal lamp unit is identical with the track quantity at described current crossing, multiple signal lamp unit and multiple tracks one_to_one corresponding, whether described signal lamp data collector is current for green light exports the track sequence number in current track corresponding to the signal lamp unit of green light according to multiple signal lamp unit.
More specifically, described vehicle location induction system before Through Lane dead line, distance Through Lane dead line before preset length or distance left-hand lane dead line preset length three place location sensitive exist vehicle by time send the first induced signal, the second induced signal or the 3rd induced signal respectively.
More specifically, described sharpening image processor comprises:
Store sub-device, for prestoring sky upper limit gray threshold and sky lower limit gray threshold, described sky upper limit gray threshold and described sky lower limit gray threshold are for separating of the sky areas of publishing picture in picture, also for prestoring presetted pixel value threshold value, described presetted pixel value threshold value value is between 0 to 255;
The sub-device of haze Concentration Testing, is arranged in air, for detecting the haze concentration of traffic intersection position in real time, and removes intensity according to haze concentration determination haze, and described haze removes intensity value between 0 to 1;
The sub-device of Region dividing, connect described CMOS vision sensor to receive described traffic intersection image, gray processing process is carried out to obtain gray processing area image to described traffic intersection image, also be connected with the sub-device of storage, the pixel identification of gray-scale value in described gray processing area image between described sky upper limit gray threshold and described sky lower limit gray threshold is formed gray processing sky sub pattern, described gray processing sky sub pattern is partitioned into obtain the non-sky subimage of gray processing from described gray processing area image, the colour non-sky subimage corresponding with described gray processing non-sky subimage is obtained based on the correspondence position of described gray processing non-sky subimage in described beat image,
Black channel obtains sub-device, be connected with the sub-device of described Region dividing to obtain the non-sky subimage of described colour, for each pixel in the non-sky subimage of described colour, calculate its R, G, B tri-Color Channel pixel value, the R of all pixels in described colour non-sky subimage, G, B tri-extracts the Color Channel at the minimum Color Channel pixel value place of numerical value in Color Channel pixel value as black channel;
Overall air light value obtains sub-device, be connected to obtain presetted pixel value threshold value with the sub-device of described storage, obtain sub-device with the sub-device of described Region dividing and described black channel to be connected respectively to obtain described traffic intersection image and described black channel, multiple pixels that black channel pixel value in described traffic intersection image is more than or equal to presetted pixel value threshold value are formed set of pixels to be tested, the gray-scale value air light value as a whole of the pixel of maximum gradation value will be had in described set of pixels to be tested;
Atmospheric scattering light value obtains sub-device, be connected respectively with the sub-device of described Region dividing and the sub-device of described haze Concentration Testing, to each pixel of described traffic intersection image, extract its R, G, in B tri-Color Channel pixel value, minimum value is as target pixel value, use and keep the Gaussian filter EPGF (edge-preserving gaussian filter) at edge to carry out filtering process to obtain filtered target pixel value to described target pixel value, target pixel value is deducted filtered target pixel value to obtain object pixel difference, EPGF is used to carry out filtering process to obtain filtered target pixel value difference to object pixel difference, filtered target pixel value is deducted filtered target pixel value difference and remove reference value to obtain haze, haze is removed intensity and be multiplied by haze removal reference value to obtain haze removal threshold value, get haze and remove minimum value in threshold value and target pixel value as comparison reference, get the atmospheric scattering light value of the maximal value in comparison reference and 0 as each pixel,
Medium transmission rate obtains sub-device, obtain sub-device and described atmospheric scattering light value with described overall air light value to obtain sub-device and be connected respectively, the atmospheric scattering light value of each pixel is removed value divided by overall air light value to obtain, deducts 1 described except value is to obtain the medium transmission rate of each pixel;
The sub-device of sharpening Image Acquisition, device with described Region dividing, described overall air light value obtains sub-device and obtains sub-device with described medium transmission rate and be connected respectively, the medium transmission rate of each pixel is deducted to obtain the first difference by 1, described first difference is multiplied by overall air light value to obtain product value, the pixel value of each pixel in described traffic intersection image is deducted described product value to obtain the second difference, by described second difference divided by the medium transmission rate of each pixel to obtain the sharpening pixel value of each pixel, in described traffic intersection image, the pixel value of each pixel comprises the R of each pixel in described traffic intersection image, G, B tri-Color Channel pixel value, correspondingly, the sharpening pixel value of each pixel obtained comprises the R of each pixel, G, B tri-Color Channel sharpening pixel value, the sharpening pixel value composition mist elimination haze traffic intersection image of all pixels.
More specifically, described Freescale single-chip microcomputer is connected respectively with described signal lamp data collector, described vehicle location induction system and described image detecting system, when receiving track sequence number that described signal lamp data collector sends and being sequence number corresponding to left-hand lane and receiving described first induced signal, enter peccancy detection pattern; Described Freescale single-chip microcomputer is in described peccancy detection pattern, start described image detecting system, and when receiving described second induced signal, send Through Lane running red light for vehicle signal, receive the number-plate number rushing craspedodrome red light vehicle that described image detecting system exports, when receiving described 3rd induced signal, sending Through Lane vehicle and robbing row left-hand lane signal, receive the number-plate number of robbing row left-hand lane vehicle that described image detecting system exports.
More specifically, described Identification platform also comprises GPRS communication system, be connected with described Freescale single-chip microcomputer, for the number-plate number rushing craspedodrome red light vehicle or the number-plate number of robbing row left-hand lane vehicle are wirelessly sent to local traffic control Control Server, also for receiving the steering order that local traffic control Control Server issues.
More specifically, described vehicle location induction system comprises three induction subsystems being separately positioned on position, preset length three place before preset length before Through Lane dead line, distance Through Lane dead line or distance left-hand lane dead line, and each induction subsystem comprises an inductive coil, oscillatory circuit, a frequency detection circuit and a serial line interface.
More specifically, in each induction subsystem, when there being vehicle by inductive coil, inductive coil and carbody produce mutual inductance, cause oscillatory circuit oscillation frequency to change, and when passing through without vehicle, oscillatory circuit oscillation frequency remains unchanged, and frequency detection circuit is connected with oscillatory circuit, for detecting the oscillation frequency of oscillatory circuit, and when the oscillation frequency of change being detected, send corresponding induced signal by serial line interface.
More specifically, described Car license recognition device performs the identification of vehicle license plate number based on OCR recognizer.
Traffic intersection of the present invention robs row vehicle identification method, first in left-hand lane and the multiple detection sub-unit based on electromagnetic induction technology of Through Lane reasonable Arrangement making side, track, the testing result of the multiple detection sub-unit of comprehensive analysis, and judge whether to exist the act of violating regulations of robbing row left-hand lane with this, last according to atmospheric attenuation model determination haze to the influence factor of image, the process of mist elimination haze is carried out to the detected image gathered under foggy days, thus realizes in all weather to the accurate recognition of the license board information of vehicles peccancy.
Accompanying drawing explanation
Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:
Fig. 1 is the block diagram that the traffic intersection illustrated according to an embodiment of the present invention robs a driving Identification platform.
Embodiment
Be described in detail to implementing the embodiment that traffic intersection of the present invention robs the Identification platform of row vehicle identification method below with reference to accompanying drawings.
At present, every country is mainly concentrated the inspection of the act of violating regulations of current crossing vehicle and is aspects such as making a dash across the red light and bicycle lane travels, main cause is, makes a dash across the red light and vehicle that on bicycle lane, the vehicle that travels normally can travel to other and pedestrian bring huge accident potential.But, in fact, for the consideration of traffic efficiency, it is more late than the green light transit time of side Through Lane that the green light transit time of left-hand lane generally sets, thus in peak period, left-hand lane has often piled up a lot of vehicle waiting lamp, some drivers, in order to save transit time, are unwilling normally to wait lamp according to the rules, but select present Through Lane to travel, left side is turned to immediately, to occupy prior to the vehicle of lamp such as grade the track that keeps left when leaving Through Lane dead line.
Row left-hand lane robbed by the former vehicle at Through Lane act of violating regulations when signal lamp of turning left turns green also brings larger safety problem, on the one hand, destroy normal road traffic order, cause the abnormal traveling behavior of vehicle, the illegal driving habits of driver; On the other hand, robbing every trade is easily cause the vehicle collision in two tracks, not only unfair to the normal vehicle of lamp that waits, and brings potential safety hazard to the vehicle of the lamp such as normal.Therefore need to detect this act of violating regulations of robbing row left-hand lane, the normal traveling of specification vehicle, ensure the security that crossing is current and fairness.
In prior art, to rob the detection of the act of violating regulations of row left-hand lane very limited for the vehicle of Through Lane, even if having, the naked eyes being also only limited to traffic-police detect, such manual detection means not only inefficiency, and are difficult to evidence obtaining.
Meanwhile, vehicles peccancy infomation detection of the prior art is all based on image procossing substantially, if under the weather that haze is serious, detected image can be smudgy, easily causes the number-plate number to be difficult to identify, the even consequence of vehicles peccancy all None-identified.
For this reason, the invention provides a kind of traffic intersection and rob row vehicle identification method, take the mode of detection of electrons to detect the act of violating regulations of the vehicles peccancy making a dash across the red light and rob left-hand lane simultaneously, and introduce the reliable detection of haze Processing for removing equipment guarantee license board information.
Fig. 1 is the block diagram that the traffic intersection illustrated according to an embodiment of the present invention robs a driving Identification platform, described Identification platform comprises vehicle location induction system 1, image detecting system 2 and Freescale single-chip microcomputer 3, model is MC9S12XS128, described vehicle location induction system 1 is for respectively at Through Lane dead line, whether there is vehicle apart from preset length three place location sensitive before preset length before Through Lane dead line and distance left-hand lane dead line to pass through, described Freescale single-chip microcomputer 3 is connected respectively with described vehicle location induction system 1 and described image detecting system 2, induction result based on described vehicle location induction system 1 determines whether there is robs capable vehicles peccancy, and control image detecting system 2 to detect the number-plate number of vehicles peccancy.
Then, continue to be further detailed the concrete structure of Identification platform.
Described Identification platform also comprises: power supply, comprise solar powered device, accumulator, change-over switch and electric pressure converter, described change-over switch is connected respectively with described solar powered device and described accumulator, determine whether be switched to described solar powered device to be powered by described solar powered device according to accumulator dump energy, described electric pressure converter is connected with described change-over switch, with the 5V voltage transitions will inputted by change-over switch for 3.3V voltage.
Described Identification platform also comprises: signal lamp data collector, be connected respectively with multiple signal lamp unit, the quantity of signal lamp unit is identical with the track quantity at described current crossing, multiple signal lamp unit and multiple tracks one_to_one corresponding, whether described signal lamp data collector is current for green light exports the track sequence number in current track corresponding to the signal lamp unit of green light according to multiple signal lamp unit.
Described vehicle location induction system 1 before Through Lane dead line, distance Through Lane dead line before preset length or distance left-hand lane dead line preset length three place location sensitive exist vehicle by time send the first induced signal, the second induced signal or the 3rd induced signal respectively.
Described image detecting system 2 comprises CMOS vision sensor, sharpening image processor and Car license recognition device, described CMOS vision sensor is for taking traffic intersection image, described sharpening image processor is used for carrying out the process of mist elimination haze to export mist elimination haze traffic intersection image to traffic intersection image, described Car license recognition device to be connected to identify in mist elimination haze traffic intersection image the number-plate number of vehicle in the near zone of preset length position before distance Through Lane dead line with described sharpening image processor, as the number-plate number rushing craspedodrome red light vehicle, identify the number-plate number of the vehicle of preset length position near zone before distance left-hand lane dead line in mist elimination haze traffic intersection image, as the number-plate number of robbing row left-hand lane vehicle.
Described sharpening image processor comprises with lower component:
Store sub-device, for prestoring sky upper limit gray threshold and sky lower limit gray threshold, described sky upper limit gray threshold and described sky lower limit gray threshold are for separating of the sky areas of publishing picture in picture, also for prestoring presetted pixel value threshold value, described presetted pixel value threshold value value is between 0 to 255;
The sub-device of haze Concentration Testing, is arranged in air, for detecting the haze concentration of traffic intersection position in real time, and removes intensity according to haze concentration determination haze, and described haze removes intensity value between 0 to 1;
The sub-device of Region dividing, connect described CMOS vision sensor to receive described traffic intersection image, gray processing process is carried out to obtain gray processing area image to described traffic intersection image, also be connected with the sub-device of storage, the pixel identification of gray-scale value in described gray processing area image between described sky upper limit gray threshold and described sky lower limit gray threshold is formed gray processing sky sub pattern, described gray processing sky sub pattern is partitioned into obtain the non-sky subimage of gray processing from described gray processing area image, the colour non-sky subimage corresponding with described gray processing non-sky subimage is obtained based on the correspondence position of described gray processing non-sky subimage in described beat image,
Black channel obtains sub-device, be connected with the sub-device of described Region dividing to obtain the non-sky subimage of described colour, for each pixel in the non-sky subimage of described colour, calculate its R, G, B tri-Color Channel pixel value, the R of all pixels in described colour non-sky subimage, G, B tri-extracts the Color Channel at the minimum Color Channel pixel value place of numerical value in Color Channel pixel value as black channel;
Overall air light value obtains sub-device, be connected to obtain presetted pixel value threshold value with the sub-device of described storage, obtain sub-device with the sub-device of described Region dividing and described black channel to be connected respectively to obtain described traffic intersection image and described black channel, multiple pixels that black channel pixel value in described traffic intersection image is more than or equal to presetted pixel value threshold value are formed set of pixels to be tested, the gray-scale value air light value as a whole of the pixel of maximum gradation value will be had in described set of pixels to be tested;
Atmospheric scattering light value obtains sub-device, be connected respectively with the sub-device of described Region dividing and the sub-device of described haze Concentration Testing, to each pixel of described traffic intersection image, extract its R, G, in B tri-Color Channel pixel value, minimum value is as target pixel value, use and keep the Gaussian filter EPGF (edge-preserving gaussian filter) at edge to carry out filtering process to obtain filtered target pixel value to described target pixel value, target pixel value is deducted filtered target pixel value to obtain object pixel difference, EPGF is used to carry out filtering process to obtain filtered target pixel value difference to object pixel difference, filtered target pixel value is deducted filtered target pixel value difference and remove reference value to obtain haze, haze is removed intensity and be multiplied by haze removal reference value to obtain haze removal threshold value, get haze and remove minimum value in threshold value and target pixel value as comparison reference, get the atmospheric scattering light value of the maximal value in comparison reference and 0 as each pixel,
Medium transmission rate obtains sub-device, obtain sub-device and described atmospheric scattering light value with described overall air light value to obtain sub-device and be connected respectively, the atmospheric scattering light value of each pixel is removed value divided by overall air light value to obtain, deducts 1 described except value is to obtain the medium transmission rate of each pixel;
The sub-device of sharpening Image Acquisition, device with described Region dividing, described overall air light value obtains sub-device and obtains sub-device with described medium transmission rate and be connected respectively, the medium transmission rate of each pixel is deducted to obtain the first difference by 1, described first difference is multiplied by overall air light value to obtain product value, the pixel value of each pixel in described traffic intersection image is deducted described product value to obtain the second difference, by described second difference divided by the medium transmission rate of each pixel to obtain the sharpening pixel value of each pixel, in described traffic intersection image, the pixel value of each pixel comprises the R of each pixel in described traffic intersection image, G, B tri-Color Channel pixel value, correspondingly, the sharpening pixel value of each pixel obtained comprises the R of each pixel, G, B tri-Color Channel sharpening pixel value, the sharpening pixel value composition mist elimination haze traffic intersection image of all pixels.
Described Freescale single-chip microcomputer 3 is connected respectively with described signal lamp data collector, described vehicle location induction system 1 and described image detecting system 2, when receiving track sequence number that described signal lamp data collector sends and being sequence number corresponding to left-hand lane and receiving described first induced signal, enter peccancy detection pattern; Described Freescale single-chip microcomputer 3 is in described peccancy detection pattern, start described image detecting system 2, and when receiving described second induced signal, send Through Lane running red light for vehicle signal, receive the number-plate number rushing craspedodrome red light vehicle that described image detecting system 2 exports, when receiving described 3rd induced signal, sending Through Lane vehicle and robbing row left-hand lane signal, receive the number-plate number of robbing row left-hand lane vehicle that described image detecting system 2 exports.
Alternatively, described traffic intersection is robbed a driving Identification platform and is also comprised: GPRS communication system, be connected with described Freescale single-chip microcomputer 3, for the number-plate number rushing craspedodrome red light vehicle or the number-plate number of robbing row left-hand lane vehicle are wirelessly sent to local traffic control Control Server, also for receiving the steering order that local traffic control Control Server issues; Described vehicle location induction system 1 comprises three induction subsystems being separately positioned on position, preset length three place before preset length before Through Lane dead line, distance Through Lane dead line or distance left-hand lane dead line, and each induction subsystem comprises an inductive coil, oscillatory circuit, a frequency detection circuit and a serial line interface; In each induction subsystem, when there being vehicle by inductive coil, inductive coil and carbody produce mutual inductance, cause oscillatory circuit oscillation frequency to change, and when passing through without vehicle, oscillatory circuit oscillation frequency remain unchanged, frequency detection circuit is connected with oscillatory circuit, for detecting the oscillation frequency of oscillatory circuit, and when the oscillation frequency of change being detected, send corresponding induced signal by serial line interface; And described Car license recognition device performs the identification of vehicle license plate number based on OCR recognizer.
In addition, haze image can realize the mist elimination haze of image by a series of images treatment facility, to obtain the image of sharpening, improves the visibility of image.These image processing equipments perform different image processing functions respectively, based on the principle that haze is formed, reach the effect removing haze.The sharpening process of haze image all has great using value for dual-use field, and military domain comprises military and national defense, remote sensing navigation etc., and civil area comprises road monitoring, target following and automatic Pilot etc.
The process that haze image is formed can be described by atmospheric attenuation process, relation between haze image and real image and sharpening image can be stated by the medium transmission rate of overall air light value and each pixel, namely when known haze image, according to the medium transmission rate of overall air light value with each pixel, sharpening image can be solved.
There are some effective and through verifying means in the solving of medium transmission rate for overall air light value and each pixel, such as, for the medium transmission rate of each pixel, need the atmospheric scattering light value obtaining overall air light value and each pixel, and the atmospheric scattering light value of each pixel can obtain carrying out the Gaussian smoothing filter at twice maintenance edge to the pixel value of each pixel in haze image, therebetween, the intensity of haze removal is adjustable; And the acquisition pattern of overall air light value has two kinds, a kind of mode is, black channel by obtaining haze image (namely makes the black channel value of some pixels very low in haze image, black channel is R, G, one in B tri-Color Channel), in haze image, obtain by finding the maximum pixel of gray-scale value in multiple pixels that searching black channel pixel value is bigger than normal, be about to the gray-scale value air light value as a whole of that search out, that gray-scale value is maximum pixel, participate in the sharpening process of each pixel in haze image; In addition, overall air light value is also by obtaining with under type: the gray-scale value calculating each pixel in haze image, by the gray-scale value of pixel maximum for gray-scale value air light value as a whole.
Relation between concrete haze image and real image and sharpening image, and the relation between parameters can see above content.
By the discussion to haze image formation basic theory, build the relation between haze image and sharpening image, by this relation of multiple Parametric Representation, subsequently by the multiple parameter values that obtain and haze image and the higher image of reducible acquisition sharpness, some statistical means and empirical means have been used in acquisition due to parameter, therefore the image that described sharpness is higher can not be equal to real image completely, but there is the mist elimination haze effect of certain degree, for the every field operation under haze weather provides effective guarantee.
Traffic intersection of the present invention is adopted to rob row vehicle identification method, the detection mode of robbing row left-hand lane for existing detection too lays particular stress on manual detection, detection time and dynamics not and detect the technical matters being subject to haze weather impact, by the crossing Rational Arrangement checkout equipment that communicates at road, realize effective detection of robbing row left-hand lane vehicle, the image processing techniques of targeted, anti-fog haze improves the reliability of this Identification platform simultaneously.
Be understandable that, although the present invention with preferred embodiment disclose as above, but above-described embodiment and be not used to limit the present invention.For any those of ordinary skill in the art, do not departing under technical solution of the present invention ambit, the technology contents of above-mentioned announcement all can be utilized to make many possible variations and modification to technical solution of the present invention, or be revised as the Equivalent embodiments of equivalent variations.Therefore, every content not departing from technical solution of the present invention, according to technical spirit of the present invention to any simple modification made for any of the above embodiments, equivalent variations and modification, all still belongs in the scope of technical solution of the present invention protection.
Claims (9)
1. traffic intersection robs a row vehicle identification method, and it comprises: utilize vehicle location induction system respectively before Through Lane dead line, distance Through Lane dead line before preset length and distance left-hand lane dead line preset length three place location sensitive whether there is vehicle and pass through; Utilize image detecting system to take traffic intersection image, the process of mist elimination haze is carried out to traffic intersection image, and identify in mist elimination haze traffic intersection image the number-plate number of robbing driving; Based on the induction result of described vehicle location induction system, utilize Freescale single-chip microcomputer MC9S12XS128 to determine whether there is and rob capable vehicles peccancy, and control image detecting system to detect the number-plate number of vehicles peccancy.
2. the method for claim 1, it utilizes traffic intersection to rob a driving Identification platform and implements, described Identification platform comprises vehicle location induction system, image detecting system and Freescale single-chip microcomputer MC9S12XS128, wherein said image detecting system comprises CMOS vision sensor, sharpening image processor and Car license recognition device, and wherein said CMOS vision sensor is for taking traffic intersection image; Described sharpening image processor is used for carrying out the process of mist elimination haze to export mist elimination haze traffic intersection image to traffic intersection image; Described Car license recognition device to be connected to identify in mist elimination haze traffic intersection image the number-plate number of vehicle in the near zone of preset length position before distance Through Lane dead line with described sharpening image processor, as the number-plate number rushing craspedodrome red light vehicle, identify the number-plate number of the vehicle of preset length position near zone before distance left-hand lane dead line in mist elimination haze traffic intersection image, as the number-plate number of robbing row left-hand lane vehicle.
3. method as claimed in claim 2, wherein said Identification platform also comprises:
Power supply, comprise solar powered device, accumulator, change-over switch and electric pressure converter, described change-over switch is connected respectively with described solar powered device and described accumulator, determine whether be switched to described solar powered device to be powered by described solar powered device according to accumulator dump energy, described electric pressure converter is connected with described change-over switch, with the 5V voltage transitions will inputted by change-over switch for 3.3V voltage;
Signal lamp data collector, be connected respectively with multiple signal lamp unit, the quantity of signal lamp unit is identical with the track quantity at described current crossing, multiple signal lamp unit and multiple tracks one_to_one corresponding, whether described signal lamp data collector is current for green light exports the track sequence number in current track corresponding to the signal lamp unit of green light according to multiple signal lamp unit.
4. method as claimed in claim 2, wherein said sharpening image processor comprises:
Store sub-device, for prestoring sky upper limit gray threshold and sky lower limit gray threshold, described sky upper limit gray threshold and described sky lower limit gray threshold are for separating of the sky areas of publishing picture in picture, also for prestoring presetted pixel value threshold value, described presetted pixel value threshold value value is between 0 to 255;
The sub-device of haze Concentration Testing, is arranged in air, for detecting the haze concentration of traffic intersection position in real time, and removes intensity according to haze concentration determination haze, and described haze removes intensity value between 0 to 1;
The sub-device of Region dividing, connect described CMOS vision sensor to receive described traffic intersection image, gray processing process is carried out to obtain gray processing area image to described traffic intersection image, also be connected with the sub-device of storage, the pixel identification of gray-scale value in described gray processing area image between described sky upper limit gray threshold and described sky lower limit gray threshold is formed gray processing sky sub pattern, described gray processing sky sub pattern is partitioned into obtain the non-sky subimage of gray processing from described gray processing area image, the colour non-sky subimage corresponding with described gray processing non-sky subimage is obtained based on the correspondence position of described gray processing non-sky subimage in described beat image,
Black channel obtains sub-device, be connected with the sub-device of described Region dividing to obtain the non-sky subimage of described colour, for each pixel in the non-sky subimage of described colour, calculate its R, G, B tri-Color Channel pixel value, the R of all pixels in described colour non-sky subimage, G, B tri-extracts the Color Channel at the minimum Color Channel pixel value place of numerical value in Color Channel pixel value as black channel;
Overall air light value obtains sub-device, be connected to obtain presetted pixel value threshold value with the sub-device of described storage, obtain sub-device with the sub-device of described Region dividing and described black channel to be connected respectively to obtain described traffic intersection image and described black channel, multiple pixels that black channel pixel value in described traffic intersection image is more than or equal to presetted pixel value threshold value are formed set of pixels to be tested, the gray-scale value air light value as a whole of the pixel of maximum gradation value will be had in described set of pixels to be tested;
Atmospheric scattering light value obtains sub-device, be connected respectively with the sub-device of described Region dividing and the sub-device of described haze Concentration Testing, to each pixel of described traffic intersection image, extract its R, G, in B tri-Color Channel pixel value, minimum value is as target pixel value, use and keep the Gaussian filter EPGF at edge to carry out filtering process to obtain filtered target pixel value to described target pixel value, target pixel value is deducted filtered target pixel value to obtain object pixel difference, EPGF is used to carry out filtering process to obtain filtered target pixel value difference to object pixel difference, filtered target pixel value is deducted filtered target pixel value difference and remove reference value to obtain haze, haze is removed intensity and be multiplied by haze removal reference value to obtain haze removal threshold value, get haze and remove minimum value in threshold value and target pixel value as comparison reference, get the atmospheric scattering light value of the maximal value in comparison reference and 0 as each pixel,
Medium transmission rate obtains sub-device, obtain sub-device and described atmospheric scattering light value with described overall air light value to obtain sub-device and be connected respectively, the atmospheric scattering light value of each pixel is removed value divided by overall air light value to obtain, deducts 1 described except value is to obtain the medium transmission rate of each pixel;
The sub-device of sharpening Image Acquisition, device with described Region dividing, described overall air light value obtains sub-device and obtains sub-device with described medium transmission rate and be connected respectively, the medium transmission rate of each pixel is deducted to obtain the first difference by 1, described first difference is multiplied by overall air light value to obtain product value, the pixel value of each pixel in described traffic intersection image is deducted described product value to obtain the second difference, by described second difference divided by the medium transmission rate of each pixel to obtain the sharpening pixel value of each pixel, in described traffic intersection image, the pixel value of each pixel comprises the R of each pixel in described traffic intersection image, G, B tri-Color Channel pixel value, correspondingly, the sharpening pixel value of each pixel obtained comprises the R of each pixel, G, B tri-Color Channel sharpening pixel value, the sharpening pixel value composition mist elimination haze traffic intersection image of all pixels.
5. method as claimed in claim 3, wherein said vehicle location induction system before Through Lane dead line, distance Through Lane dead line before preset length or distance left-hand lane dead line preset length three place location sensitive exist vehicle by time send the first induced signal, the second induced signal or the 3rd induced signal respectively;
Described Freescale single-chip microcomputer is connected respectively with described signal lamp data collector, described vehicle location induction system and described image detecting system, when receiving track sequence number that described signal lamp data collector sends and being sequence number corresponding to left-hand lane and receiving described first induced signal, enter peccancy detection pattern; Described Freescale single-chip microcomputer is in described peccancy detection pattern, start described image detecting system, and when receiving described second induced signal, send Through Lane running red light for vehicle signal, receive the number-plate number rushing craspedodrome red light vehicle that described image detecting system exports, when receiving described 3rd induced signal, sending Through Lane vehicle and robbing row left-hand lane signal, receive the number-plate number of robbing row left-hand lane vehicle that described image detecting system exports.
6. method as claimed in claim 3, wherein said Identification platform also comprises:
GPRS communication system, be connected with described Freescale single-chip microcomputer, for the number-plate number rushing craspedodrome red light vehicle or the number-plate number of robbing row left-hand lane vehicle are wirelessly sent to local traffic control Control Server, also for receiving the steering order that local traffic control Control Server issues.
7. method as claimed in claim 3, wherein said vehicle location induction system comprises three induction subsystems being separately positioned on position, preset length three place before preset length before Through Lane dead line, distance Through Lane dead line or distance left-hand lane dead line, and each induction subsystem comprises an inductive coil, oscillatory circuit, a frequency detection circuit and a serial line interface.
8. method as claimed in claim 7, is characterized in that:
In each induction subsystem, when there being vehicle by inductive coil, inductive coil and carbody produce mutual inductance, cause oscillatory circuit oscillation frequency to change, and when passing through without vehicle, oscillatory circuit oscillation frequency remain unchanged, frequency detection circuit is connected with oscillatory circuit, for detecting the oscillation frequency of oscillatory circuit, and when the oscillation frequency of change being detected, send corresponding induced signal by serial line interface.
9. method as claimed in claim 2, wherein said Car license recognition device performs the identification of vehicle license plate number based on OCR recognizer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510163552.9A CN104732771B (en) | 2015-04-08 | 2015-04-08 | Traffic intersection robs row vehicle identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510163552.9A CN104732771B (en) | 2015-04-08 | 2015-04-08 | Traffic intersection robs row vehicle identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104732771A true CN104732771A (en) | 2015-06-24 |
| CN104732771B CN104732771B (en) | 2016-01-06 |
Family
ID=53456632
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510163552.9A Expired - Fee Related CN104732771B (en) | 2015-04-08 | 2015-04-08 | Traffic intersection robs row vehicle identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104732771B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325988A (en) * | 2020-03-10 | 2020-06-23 | 北京以萨技术股份有限公司 | Real-time red light running detection method, device and system based on video and storage medium |
| CN112084905A (en) * | 2020-08-27 | 2020-12-15 | 深圳市森国科科技股份有限公司 | Traffic light state identification method, system, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246644A (en) * | 2007-12-28 | 2008-08-20 | 北京航空航天大学 | Fixed intersection electric police grasp shoot device |
| EP2068291A1 (en) * | 2007-12-03 | 2009-06-10 | ROBOT Visual Systems GmbH | Method and device for sophisticated detecting of traffic violations in a restricted area controlled by traffic lights |
| CN101556737A (en) * | 2008-04-10 | 2009-10-14 | 上海宝康电子控制工程有限公司 | Left-turn violation detection system at vehicle intersection |
| CN103021177A (en) * | 2012-11-05 | 2013-04-03 | 北京理工大学 | Method and system for processing traffic monitoring video image in foggy day |
-
2015
- 2015-04-08 CN CN201510163552.9A patent/CN104732771B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2068291A1 (en) * | 2007-12-03 | 2009-06-10 | ROBOT Visual Systems GmbH | Method and device for sophisticated detecting of traffic violations in a restricted area controlled by traffic lights |
| CN101246644A (en) * | 2007-12-28 | 2008-08-20 | 北京航空航天大学 | Fixed intersection electric police grasp shoot device |
| CN101556737A (en) * | 2008-04-10 | 2009-10-14 | 上海宝康电子控制工程有限公司 | Left-turn violation detection system at vehicle intersection |
| CN103021177A (en) * | 2012-11-05 | 2013-04-03 | 北京理工大学 | Method and system for processing traffic monitoring video image in foggy day |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325988A (en) * | 2020-03-10 | 2020-06-23 | 北京以萨技术股份有限公司 | Real-time red light running detection method, device and system based on video and storage medium |
| CN112084905A (en) * | 2020-08-27 | 2020-12-15 | 深圳市森国科科技股份有限公司 | Traffic light state identification method, system, equipment and storage medium |
| CN112084905B (en) * | 2020-08-27 | 2024-03-12 | 深圳市森国科科技股份有限公司 | Traffic light state identification method, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104732771B (en) | 2016-01-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111212772B (en) | Method and device for determining a driving strategy of a vehicle | |
| CN111815959B (en) | Vehicle violation detection method and device and computer readable storage medium | |
| CN104732772B (en) | Traffic intersection robs a driving Identification platform | |
| CN108447305B (en) | Pre-warning method and pre-warning system for courier pedestrian | |
| CN103996053A (en) | Lane departure alarm method based on machine vision | |
| CN107316486A (en) | Pilotless automobile visual identifying system based on dual camera | |
| CN106327863A (en) | Method, device and system for detection and early warning of vehicle congestion | |
| CN106985819A (en) | The determination methods and device of vehicle driving intention | |
| CN104575043A (en) | Automatic prompt system and method during passing of motor vehicle through pedestrian crosswalk | |
| CN106020205A (en) | Unmanned vehicle system energy-saving control method and device | |
| CN104794906A (en) | Vehicle management platform of outdoor parking lot exit | |
| CN112102609A (en) | Intelligent detection system for highway vehicle violation behaviors | |
| CN104732771B (en) | Traffic intersection robs row vehicle identification method | |
| CN104407612A (en) | Miniature intelligent vehicle and test method applying miniature intelligent vehicle | |
| CN104732768B (en) | Pass through collecting method at crossing, signal lamp place | |
| CN104715615B (en) | Be positioned at the electronic recognition platform violating the regulations of traffic intersection | |
| CN111967384A (en) | Vehicle information processing method, device, equipment and computer readable storage medium | |
| CN109229012A (en) | A kind of automobile long-and-short distant light automatic switching method based on multiple road conditions intelligent recognition | |
| CN104715609B (en) | Pass through data acquisition system (DAS) in crossing, signal lamp place | |
| CN103076641B (en) | A kind of safety detecting system and detection method | |
| JP4912495B2 (en) | Image recognition apparatus and method, and navigation apparatus | |
| CN207380911U (en) | A kind of parking lot bayonet dual camera Vehicle License Plate Recognition System | |
| CN103935293A (en) | LDW system, lane recognition device and related method | |
| CN103991410A (en) | Method and system for preventing line pressing unlawful act of important transport vehicle | |
| CN104616503A (en) | System for detecting violation behavior of overtaking left lane of vehicle |
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 | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xu Shoukun Inventor after: Shi Lin Inventor before: Gao Ping |
|
| COR | Change of bibliographic data | ||
| GR01 | Patent grant | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20151215 Address after: The east town of Haian County in Jiangsu province 226600 Nantong Yingbin Road No. 8 Applicant after: HAIAN CHANGZHOU UNIVERSITY TECHNOLOGY TRANSFER CENTER Co.,Ltd. Address before: 221000, No. 5, east section, Xuzhou Road, Xuzhou Industrial Park, Jiawang District, Jiangsu, Xuzhou Applicant before: Gao Ping |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20221230 Address after: Room 610, Building 3, Science and Technology Mansion, Linyi Hi tech Industrial Development Zone, Shandong Province, 276000 Patentee after: Linyi Enke Development and Construction Co.,Ltd. Address before: 226600 No.8 Yingbin Avenue, Chengdong Town, Hai'an County, Nantong, Jiangsu Patentee before: HAIAN CHANGZHOU UNIVERSITY TECHNOLOGY TRANSFER CENTER Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160106 |