CN102136194B - Road traffic condition detection device based on panorama computer vision - Google Patents

Road traffic condition detection device based on panorama computer vision Download PDF

Info

Publication number
CN102136194B
CN102136194B CN 201110069317 CN201110069317A CN102136194B CN 102136194 B CN102136194 B CN 102136194B CN 201110069317 CN201110069317 CN 201110069317 CN 201110069317 A CN201110069317 A CN 201110069317A CN 102136194 B CN102136194 B CN 102136194B
Authority
CN
China
Prior art keywords
road
sampled point
track
detection
point
Prior art date
Application number
CN 201110069317
Other languages
Chinese (zh)
Other versions
CN102136194A (en
Inventor
汤一平
孟炎
姜军
孙军
宗明理
奚亮亮
Original Assignee
浙江工业大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 浙江工业大学 filed Critical 浙江工业大学
Priority to CN 201110069317 priority Critical patent/CN102136194B/en
Publication of CN102136194A publication Critical patent/CN102136194A/en
Application granted granted Critical
Publication of CN102136194B publication Critical patent/CN102136194B/en

Links

Abstract

The invention discloses a road traffic condition detection device based on panorama computer vision, comprising a camera device of each measuring point and a microprocessor, wherein the camera device is installed on each road on a road network; the microprocessor is used for evaluating road traffic condition according to the panorama video data of the camera device; and the microprocessor comprises a panorama image acquisition unit, a sampling point, a lane, a lane driving direction customization module, a road congestion state detection module and a road service level judgement module. The invention provides a road traffic condition detection device based on panorama computer vision, which has the advantages of wide detection range, high detection precision, good detection instantaneity and intuitional and clear detection result, is convenient to implement and is convenient to realize on an embedded system; in addition, the road traffic condition detection device has subjective perceptibility index data and objective perceptibility congestion data, and is convenient for each level of road network of a city to comprehensively evaluate the road traffic condition on the aspect of time and space.

Description

Road traffic state detecting device based on panorama computer vision
Technical field
The invention belongs to panorama computer vision sensor technology, digital image processing techniques, embedded system, urban road digital coding and the network communications technology in the application of road traffic state context of detection, especially a kind of road traffic state detecting device based on panorama computer vision.
Background technology
Current traffic problems have become global " city common fault ", and traffic congestion is the main manifestations of city " traffic illness "." cause of disease " of urban traffic blocking comes from many factors, and traffic congestion directly affects people's trip quality, particularly utilizes the people of vehicular traffic.Road vehicle is crowded, and traffic hazard takes place frequently, and traffic environment worsens, energy shortage, environmental pollution constantly increases the weight of, the basic theory of these day by day serious traffic problems and modern transportation, i.e. and sensible, orderly, safe, comfortable, low energy consumption, to hang down the requirement such as pollution be fully contrary.
The evaluation criterion of modern transportation system is safe, unimpeded, energy-conservation.Therefore how hold in the urban highway traffic operation conditions service level, need to set up a kind of science, the objective appraisal method.But due to the system that road traffic service level is estimated that lacks at present a kind of relatively science and effective road traffic state detection means, thereby make citizen be difficult to understand accurately and hold in the change in time and space situation to urban highway traffic before travel; Relevant urban construction department drops into road infrastructure and the Expected Results of the traffic management measure taked is difficult to estimate accurately; The city manager is to the comparison of city self historical development and lack with other intercity lateral comparison the standard of passing judgment on; Roading department is to the urban highway traffic development trend and need Adopts measure to carry out the means that quantitatively scientific analysis lacks necessity.
The traffic information collection technology is considered to the gordian technique of a most important thing in intelligent transportation, and traffic information collection technology commonly used has ground induction coil, magneto-dependent sensor, ultrasonic sensor, microwave, GPS and vision sensor at present; Because the transport information detecting sensors such as ground induction coil, magnetosensitive, ultrasound wave, microwave need to be embedded in the underground face, must destroy original road surface during I﹠M, affected road traffic, simultaneously the pavement damage that causes due to the reasons such as overload of vehicle of the road of China must be often safeguarded the sensor that is embedded in below road; In addition these detection meanss can only perception go out on certain point on road or certain line the vehicle of process, therefore can only indirectly infer congestion in the speed of passing through vehicle of the set-up site of sensor; Therefore above-mentioned detection means exist that installation and maintenance inconvenience, cost of investment are high, poor anti jamming capability and the defective such as sensing range is limited.Vision sensor is a kind of contactless traffic flow detection means, its simulating human visual theory, fusion calculation machine technology and image processing techniques detect traffic flow by vision signal, are the new road traffic detection system that progressively grows up in recent years.Analyze detection and the statistical method of following the tracks of vehicle on road but at present the video of road traffic state is detected generally to adopt, this detection method computational resource that need to cost a lot of money makes general embedded system can't be competent at its detection computations work.In addition, the video camera that adopts at present is because visual range is limited, be difficult to obtain on road in a big way in the traffic behavior video image.
Chinese invention patent application number is 200810090474.4 to disclose traffic situation determination system, this system provides a kind of traffic situation determination system, utilize the congestion of road corresponding to the driving trace of the vehicle that GPS determines, in the correct judgement of carrying out congestion, number of communications and amount of communication data that the signal post between vehicle and information center relates to can be reduced, the low volume with communication cost of alleviating of communication process burden can be realized.This road traffic state detection means exists certain defect, infers that by Vehicular behavior road traffic state exists the problems such as one-sidedness, locality and subjectivity; Chinese invention patent application number is 200510026478.2 to disclose a kind of traffic method for measuring of surface road net and system of can be used for, this system adopts three layers of crossings, arterial street, urban main road network successively to measure to urban road, for the arterial street, " the equivalent traffic capacity " concept and definite method are proposed; Adopt " density ratio " index, the service level scale value of the service level scale value curve calculation arterial highway that provides according to the present invention is measured; Adopt " weighting density ratio " index that the mains service level is measured based on the arterial highway measurement result; Carrying out congested area, crowded arterial highway and crowded crossing according to measurement result successively identifies.This traffic method for measuring not yet relates to most crucial road traffic state data acquisition problem.Chinese invention patent application number is 200810132938.3 to disclose a kind of Intellective traffic information system and disposal route thereof, comprises the GPS module, is used for providing global positioning information; With the mobile terminal that the GPS module communicates, it is connected with cordless communication network; The ITS Information server, it is connected with cordless communication network and provides Real-time Traffic Information according to mobile terminal request.This Intellective traffic information system and disposal route thereof do not relate to most crucial road traffic state data acquisition problem yet.Chinese invention patent application number is 200810034716.8 to disclose road traffic state determination methods and system, this system with a plurality of traffic parameters as basis for estimation, simultaneously set up funtcional relationship for different sections of highway, given weight has improved the traffic behavior Accuracy of Judgement.The method comprises: (1) chooses a plurality of traffic parameters; (2) by the sampling analysis to this road section traffic volume parameter, set above-mentioned a plurality of traffic parameters and the funtcional relationship between its corresponding crowding coefficient in this highway section and set these a plurality of traffic parameters shared weighted value in this highway section degree of crowding judgement; (3) in each state judgement end of term in week, above-mentioned a plurality of traffic parameters in Real-time Collection this highway section and according to the function that sets calculate the corresponding crowding coefficient of each traffic parameter; (4) weighted value of each traffic parameter crowding coefficient corresponding with it done the weighted mean computing, obtain the mean crowding coefficient; (5) compare mean crowding coefficient and crowding coefficient threshold value, thus the judgement road traffic state.This judgment mode need to have a plurality of traffic parameter supports, and operand is large, and will obtain these traffic parameters simultaneously on all main roads of city is also an easy thing, needs very large input and maintenance.
This has been the fact that need not dispute on for the considerable economic benefit that intelligent transportation system can be brought and social benefit.Developing rapidly and combination of embedded calculating, radio communication and sensor technology makes people gather ubiquitously, transmit and store the road video/audio.If the video data to these magnanimity can obtain in time and accurately analyzing and understanding, just energy Real-time Obtaining traffic master data, predict traffic congestion and traffic hazard, plays a significant role at intelligent transportation field.Recent years, governments at all levels were very big to the input of the video monitoring on road, and still present video monitoring to various traffic events and abnormal conditions mainly still relies on artificial judgment, makes these data be difficult to be fully utilized.
In real time, telecommunication flow information collection accurately can make intelligent transportation system in time obtain traffic related information, traffic is effectively managed, and send induction information, thereby automatically regulate wagon flow, reduce the time that vehicle stops when road is smooth and easy, therefore arrange the newspaper etc. that relieves traffic congestion, causes trouble before red light.The volume of traffic of predict future and road traffic condition are for formulation traffic programme, road network planning provide foundation.Intelligent traffic administration system all will realize by qualitative analysis to quantitative examination in all many-sides such as traffic control, traffic administration decision-makings, and the transport information of this qualitative leap institute foundation has just comprised the multidate information of traffic flow collection.In addition, by the analysis to traffic data and traffic related information, can extensively carry out the theoretical research of urban transportation, carry out the front and back contrast of various job facilities, handling facility performance, the effect of judgement traffic measure etc.In a word, improve accuracy and the real-time of the traffic flow data that gathers, all very important to urban traffic control and urban road construction, there is very positive meaning in, harmonious society of energy-conservation that people-oriented to building.
A kind of design proposal of outstanding road traffic state detecting device must be followed 6 principles: 1) reliability; 2) credibility; 3) can quantize; 4) has comparability; 5) be convenient to identification; 6) be convenient to implementation and operation.A kind of outstanding evaluation system based on road traffic state detecting device, the concrete object of its evaluation need can be within the time of determining, in the space analysis and comparison urban highway traffic service level, the time zone of evaluation needs can be defined as in chronological order the different periods of year, season, the moon, week, day and every day; Need to be defined as rush day, flat peak day, working day, festivals or holidays etc. by the traffic flow distribution; Need to be defined as daily traffic slot, occasion period, inclement weather, accident period etc. by the traffic circulation characteristics.The area of space of estimating need to be defined as urban road road network, through street net, trunk road network, certain area road, certain road etc.
Realize that accuracy of detection is high, the detection real-time is good, key that testing result is simple and clear is directly to obtain certain road traffic and whether to be in following 6 kinds of status informations by direct, simple and clear, simple, the visual road traffic detection means of calculating, namely road traffic state is in service level A: unimpeded; Service level B: substantially unimpeded; Service level C: tentatively block up; Service level D: block up: service level E: seriously block up; Service level F: localized road and large tracts of land paralysis.
In evaluation path level of service appraisement system, most crucial problem is the detection of vehicle flowrate, congestion status and the average speed of road, and therefore optimal detection means is directly to measure in real time simultaneously vehicle flowrate, the average speed on road and the length of blocking up.
Obtaining of commercialization mainly contains following three kinds of modes on road traffic real time data means at present: 1) annular coil induction type checkout equipment, detect data such as road traffic flow, the flow direction, the speed of a motor vehicle, lane occupancy ratio and vehicle commander, queue lengths; This detection means need to be embedded in annular coil on the road surface, and need to destroy the road surface 1 year half left and right when maintenance and installation serviceable life, belongs to contact and measure; 2) long-range traffic microwave detector (RTMS) is collected the data such as vehicle flowrate, roadway occupancy and average velocity in each track; This pick-up unit cost is high; 3) based on car plate identification detector and queue length detecting device, extend car plate identification detector and the queue length detecting device at the stop line place in highway section by being arranged on the crossing, utilize the queue length detecting device to obtain queue length L; The vehicle number N of the moment t when utilizing the car plate identification detector to obtain vehicle through detecting device and process detecting device; The video detection system that possesses license plate identification, the identity by the identification vehicle detects hourage and the travel speed of motor vehicle on certain road, is thisly existing some problems aspect limitation and real-time as the road traffic state detection means.These detection meanss belong to objectivity and detect, and are significant aspect the road traffic investigation.But the common problem of this detection means is then to come by statistics indirectly to obtain vehicle flowrate and average speed by the ruuning situation of each vehicle on measurement road, exist some defective aspect implementation and operation, particularly existing deficiency for Assessment of Serviceability of Roads aspect the evaluation indexes such as real-time, putting maintenance into practice cost, calculating pressure and sensitivity index.
The urban transportation of China will be in the mixed traffic state within a very long time.The service level achievement data has following characteristics under the mixed traffic condition: the diversity of (1) data acquisition object: not only need to gather the road section traffic volume data but also need to gather crossing internal transportation data, often need to observe simultaneously simultaneously multiple behavior and the parameter thereof of traffic unit in once observing; (2) space-time of data leap property is strong: in order to obtain the achievement data of varying service level grade under different transportation conditions, detection need to be captured in the data on certain hour and spatial extent, and need to be online data.For above demand, above three kinds of mentioned commercialization traffic flow automatic checkout equipments can't realize this demand.
Realization enforcement key easily is to adopt friendly type, contactless, the large-area road traffic state detection means of a kind of road of not destroying the road surface or not relating to pavement construction, utilizes as far as possible existing equipment and investment simultaneously; The service state of road is the comprehensive embodiment of the many factors such as condition of road surface, operation conditions, means of transportation situation and traffic safety status, although wait by detecting these many status datas the service level status information that calculate to be to obtain road by statistics, preferably can be straightforward, simple and convenient, service status information that economy obtains road in real time.
Summary of the invention
for the limitation of the detection that overcomes existing road traffic state detecting device large, the diversity of data acquisition object is poor, a little less than data space-time leap property, implement investment and maintenance cost high, the detection means of contact is unfriendly to road and vehicle, be difficult to from macroscopic view, middle sight, three angles of microcosmic, the deficiencies such as subjective feeling Real-Time Evaluation road traffic service level state from the people, the invention provides that a kind of to have sensing range wide, accuracy of detection is high, the detection real-time is good, it is convenient to implement, testing result is simple and clear, namely there is the subjective feeling achievement data that the objective evaluation achievement data is arranged again, and be convenient to city road networks at different levels in the time, on the space, road traffic state is carried out the road traffic state detecting device based on panorama computer vision of comprehensive evaluation.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of road traffic state detecting device based on panorama computer vision, comprise the camera head that is arranged on each measurement point on each road on road network, the microprocessor that is used for carrying out according to the video data of camera head the evaluation path traffic behavior, described camera head is connected with described microprocessor by described video interface, and traffic behavior is detected delivery unit and result of calculation sends to signal lamp control module and traffic behavior release unit by described communication unit; Described microprocessor comprises:
The panoramic picture acquiring unit is used for obtaining initialization information and video image;
Sampled point, track and driveway travel directions customized module are used for defining the travel direction attribute, track direction change attribute, the locus attribute on the longitudinal direction of track of the sampled point on road and in a lateral direction the locus attribute in the track;
The congestion in road state detection module is for detection of the congestion status of some some travel directions of the moment on road;
The Assessment of Serviceability of Roads determination module, the service level for judging current road is divided into the Assessment of Serviceability of Roads grade 6 grades such as A, B, C, D, E, F, and the step of decision process is as follows:
At first obtain the total S of the sampled point in certain track in described sampled point, track and driveway travel directions customized module, obtain existing on certain track the total ES of sampled point in the described detection module that has a sampled point, can calculate the non-ratio value Rate (NS/S) of sampled point and sampled point, mobile ratio value Rate (YS/S) and the static ratio value Rate (SS/S) that has sampled point and sampled point that has sampled point and sampled point of existing by formula (12); Then according to each calculate ratio value table look-up the road shown in 1 the service level grade comprehensively the judgement table obtain the relevant service level grade in certain track;
Rate ( NS / S ) = ( S - ES ) S × 100 - - - ( 12 )
Rate ( YS / S ) = YS S × 100
Rate ( SS / S ) = SS S × 100
In formula, S is the sum of the sampled point in certain track, and ES is for existing the sum of sampled point on certain track, and NS is the non-sum that has sampled point on certain track, and YS is the static sum that has sampled point on certain track for the mobile sum that has sampled point on certain track, SS;
The service level grade of road judges that comprehensively table is as shown in table 1;
Table 1.
Further, described panoramic picture acquiring unit comprises system initialization module and image collection module;
System initialization module is used for data target information, track and sampled point customization data and check point spatial positional information are read into dynamic storage cell, calls in order in subsequent processes;
Image collection module passes the video image information of coming and video image information is kept at dynamic storage cell for reading from camera head.
Further again, in described Assessment of Serviceability of Roads determination module and in described congestion in road state detection module, realized by Assessment of Serviceability of Roads and the detection overall procedure that blocks up, at first be the customization step of sampled point, track and driveway travel directions, realized by described sampled point, track and driveway travel directions customized module; Be then to detect the detecting step that has sampled point from tn image constantly, realized by the described detection module of sampled point that exists; Next step processing be to detect the detecting step of mobile sampled point from tn front and back sequence image constantly, exist the detection module of sampled point to realize by described movement; Next step processing is the detecting step that exists sampled point and detected mobile sampled point to calculate the sampled point that blocks up in each track according to detected again, is realized by the described static detection module of sampled point that exists; Processing then is to go out the statistical computation step of the congestion regions in each track according to the static distribution statistical computation that has a sampled point that detects, and is realized by the described static detection module of piece that exists; Be further to calculate tn each track Assessment of Serviceability of Roads constantly and the calculation procedure of the length of blocking up according to the static distribution of piece on each track that exist that obtains, realized by described Assessment of Serviceability of Roads determination module; Completed above-mentioned block up detect and statistical computation after result of calculation is sent to delivery unit with control transport information lamp or the transmission testing result step of guidance information is provided; Return at last detected state and repeat cycle detection calculating.
described sampled point, track and driveway travel directions customized module, the naming method of sampled point adopts four-dimensional array S (i, j, k, l) represent a sampled point, wherein i is driveway travel directions property parameters value, j is track direction change property parameters value, k is the locus property parameters value on certain track longitudinal direction, from video camera begin nearby increase sequential system and be numbered, from the video camera distance more away from the k value larger, during with k≤N as closely, during N<k≤M as middle distance, during M<k as remote, 1 is in a lateral direction locus property parameters value in certain track, and data area is 0~4, for the travel direction property parameters value i of sampled point, regulation deviates from the travel direction property parameters value i=1 of road starting end, towards the travel direction property parameters value i=2 of road starting end, for track direction change property parameters value j, the track direction change property parameters value j=1 that regulation is turned left, track direction change property parameters value j=2 from the nearest Through Lane in the track of turning left, if also have just 3,4 code names codings in order of Through Lane, the track direction change property parameters value j=0 that regulation is turned right, then customization detects sampled point after having customized the track, and the space actual range between neighbouring sample point is 0.5 meter, considers that mainly vehicle is a rigid body, can adopt the sampled point of several continuous adjacent to characterize vehicle characteristics, specific practice is: sampled point generates automatically with the track direction, if the transverse width in track is 2.5 meters, evenly generate 5 sampled points at each track horizontal direction, automatically generate several sampled points from the road starting end on video image to end on longitudinal direction, if the distance from the road starting end on video image to end on the real road space is 200 meters, evenly generate 400 sampled points on the longitudinal direction of track, the four-dimensional array S (i of each generated sampled point, j, k, l) express, because the sampled point that the pass of vision ties up on image is dredged nearby, close at a distance, but the real space spacing distance of each sampled point is all identical, the travel direction attribute of the sampled point that customization is good, track direction change attribute, the locus attribute on the longitudinal direction of track and track locus attribute in a lateral direction etc. during information is kept at storage unit, by the customization to the pixel on imaging plane, realized that the mapping of the sampled point on the sampled point on the imaging plane and real road is related, namely set up the A (x on the plane of delineation, y) the sampled point S (i on pixel and road, j, k, l) corresponding relation.
Described congestion in road state detection module comprises the detection module that has sampled point, the mobile detection module of sampled point, static detection module, the Assessment of Serviceability of Roads detection module of the detection module of sampled point, the piece that blocks up and the length detection module of blocking up of existing of existing; The output format of congestion in road state detection module is made of following 6 parameter values, is respectively the moment parameter value of 14, the detection space location parameter value of 23, the travel direction property parameters value of 1, the track direction change property parameters value of 1, the Assessment of Serviceability of Roads parameter value of 1 and the length parameter value of blocking up of 3; Parameter is used for the temporal information that expression detects the moment constantly, parameter Time represents with 14 bit data forms constantly, be YYYYMMDDHHMMSS, wherein 1~4 YYYY represents that the year of the Gregorian calendar, 5~6 MM represent that the month of the Gregorian calendar, 7~8 DD represent that the day of the Gregorian calendar, 9~10 HH represent hour, 11~12 MM represent minute, 13~14 SS represent second; The detection space location parameter is used for the spatial positional information of expression check point, and detection space location parameter Location represents with 23 bit data forms; The driveway travel directions property parameters is used for the travel direction information in expression track, driveway travel directions property parameters Direction represents with 1 bit data form, regulation deviates from the travel direction property parameters value i=0 of road starting end, towards the travel direction property parameters value i=1 of road starting end; Track direction change property parameters is used for representing that this track allows the direction that moves ahead, track direction change property parameters Change represents with 1 bit data form, the track direction change property parameters value j=1 that regulation is turned left, track direction change property parameters value j=2 from the nearest Through Lane in the track of turning left, if also have just 3,4 code names codings in order of Through Lane, the track direction change property parameters value j=0 that regulation is turned right; The Assessment of Serviceability of Roads parameter is used for the congestion status of expression road, Assessment of Serviceability of Roads parameter S erviceLevel represents for alpha format with 1, the Assessment of Serviceability of Roads grade is divided into 6 grades such as A, B, C, D, E, F, wherein A represents that the Assessment of Serviceability of Roads grade is best, and F represents that the poorest grade of Assessment of Serviceability of Roads; The length parameter that blocks up is used for expression length of vehicle queue on the track when the track gets congestion situation, and for data layout represents, unit is meter the length parameter Length that blocks up with 3; A record of congestion in road state detection module output is to be made of six parameter values such as Time+Location+Direction+Change+ServiceLevel+Length like this, number of track-lines on the road of every record and detection becomes one-to-one relationship, 43 of the length of a record; If the road scope that panoramic vision sensor monitors has 8 tracks, 8 output records are so just arranged;
Described space position parameter Location comprises absolute position encoder, be used for expression from the logic mark code of the relative position of setting the coordinate central point, be used for natural number coding, branch road information coding from the origin-to-destination of road; Totally 23 codings as shown in Figure 10, wherein absolute position encoder is the most front 6, the 1st to the 3rd bit representation longitude, the 4th to the 6th bit representation latitude, such as the data that obtain are 120030,120 expression east longitude 120 degree, 030 expression north latitude 30 degree are the Hangzhous by leaving the city that can obtain correspondence in infosystem in; Logic mark code is the 7th to 17, with the central point in city, the zone is divided into A, B, C, D4 quadrant district, the quadrant district at the starting point place of the 7th bit representation road, the x, the y coordinate that represent the two ends, street with 4 bit digital, the 8th the x coordinate to the 9th bit representation street starting point, the 10th the y coordinate to the 11st bit representation street starting point, the quadrant district at the terminal point place of the 12nd bit representation road, the 13rd the x coordinate to the 14th bit representation street terminal point, the 15th the y coordinate to the 16th bit representation street terminal point; Be aided with lowercase for two parallel and two ends x, street that the y coordinate is identical and sequentially distinguish, represent with the 17th figure place; Natural number coding is the 18th to the 22nd, according to from south to north, ascending numbering from the east to the west, least unit is 1cm, and layout is carried out at left single right two ends that extend to, for only have one-sided street crossing if adopt the odd number layout at the left of road, in the right-hand employing even numbers layout of road; The branch road information coding is the 23rd, and branch road information coding N represents that the place ahead is obstructed, and L represents right turn ban, and R represents left turn ban;
Described logic mark code is 11, from the 7th to the 17th, be used for expression from intown relative position, its naming rule is: significant position is initial point take the city center, East and West direction is the x axle, the north-south is the y axle, the city is divided into 4 of A, B, C, D quadrant district, consider that the megalopolis is in district radius 100km, the x, the y coordinate that represent the two ends, street with 4 bit digital, parallel at a distance of in the 1km scope and two ends x, street that the y coordinate is identical can be aided with a, b, c....... sequentially distinguishes for two.
Technical conceive of the present invention is: therefore, develop a kind of novel traffic detecting device, take full advantage of the real time data of traffic detecting device, and based on these data, traffic behavior is estimated, induced and controls, for providing traffic information, traveler has important theory significance and actual application value.
Computer vision can be given the computer people of being similar to and observed and judgement.road condition pick-up unit based on computer vision, utilization is placed in the camera head (the above road of the cities of secondary grade has been installed a large amount of camera heads at present) on road, with more advanced computer video recognition technology, analysis by the road real time video image, directly obtain in real time road traffic state information, replace contact type measurement with non-contact measurement, can improve quality monitoring and data accuracy, can provide simultaneously subjective feeling information and objective detection data by corresponding algorithm, operation maintenance simultaneously is convenient, for other monitoring business provide video resource intuitively.
Analyze road traffic circulation situation should from macroscopic view, sight, three angles of microcosmic choose corresponding evaluation index and carry out.Macroscopic perspective is that whole urban road network traffic circulation index is carried out assay; Middle sight angle is according to aspects such as urban road grade, administrative region, passage, loop gateways, and assay is carried out in the road net traffic; Microcosmic angle is that the traffic circulation to certain road, certain crossing carries out assay.how from macroscopic view, middle sight, three angles of microcosmic are carried out the A+E of urban road traffic state, need to obtain simultaneously the point in urban road, line, face, spatial information and temporal information are waited in the zone, and this spatial information can be convenient to participate in directly computing in the road networks at different levels of city, namely can calculate by the traffic circulation state of putting on road the traffic circulation state that road is reached the standard grade, the traffic circulation state of reaching the standard grade from road can calculate the traffic circulation state on face, traffic circulation state from face can calculate the interior whole road grid traffic running status in certain zone.
Therefore, how to make road traffic state detecting device have that sensing range is wide, accuracy of detection is high, detect real-time good, implement convenient, testing result is simple and clear, and be convenient to city road networks at different levels on time, space road traffic state is carried out the characteristics such as comprehensive evaluation will be as the important evaluation index of road traffic state detecting device.
Realize the wide key of sensing range is how to utilize the road traffic state detection mode of computer vision; Realize road is monitored under this brand-new non-situation of discovering, obtain the function of real-time traffic parameter, can use up on the one hand and obtain greatly possibly large tracts of land road traffic condition information, also can alleviate on the other hand the cost of structure road monitoring system.Utilize panoramic vision sensor to monitor road, can obtain the not available omni-directional visual of human eye, thereby more fully gather the dynamic traffic stream information; Utilize the Dynamic Image Understanding technology to process road information, can Real-time Obtaining road traffic stream information, thus more automatically gather dynamic information.
Beneficial effect of the present invention is mainly manifested in: video information on a large scale that 1, can the whole road of real-time collecting, have sensing range wide, and can be to detecting with the interior road traffic state that carries out at 200 rice diameters; 2, installation and maintenance are noiseless, and because video detector is arranged on road often, therefore installing and safeguarding not to affect the current of road, does not need excavation yet, destroys the road surface; 3, namely there is the subjective feeling achievement data that the objective evaluation achievement data is arranged again; 4, low consumption easy to maintenance, traditional inductive coil detecting device needs excavated pavement to safeguard when damaging, and during video detecting device generation problem, can directly extract or repair facility, and has reduced maintenance cost; 5, detected parameters is abundant, and not only can detect this is that general inductive coil detecting device is incomparable; 6, be convenient to city road networks at different levels and on time, space, road traffic state carried out comprehensive evaluation; 7, detecting reliability, accuracy are high, have self study and intelligent function; 8, statistical computation is convenient, and algorithm is realized simple, can be connected with advanced person's the dynamic and intelligent traffic modules such as traffic control system by network, realizes more function.
Description of drawings
Fig. 1 is the schematic diagram based on the vehicle queue Detection ﹠ Controling signal lamp of the road traffic state detecting device of panorama computer vision;
Fig. 2 is the schematic diagram based on the detection congestion in road state of the road traffic state detecting device of panorama computer vision;
Fig. 3 is the optical schematic diagram of panorama computer vision sensor, wherein, (a) is front elevation, is (b) side view;
Fig. 4 is the schematic diagram of the captured road condition of panorama computer vision sensor;
Fig. 5 is the schematic diagram of another kind of panorama computer vision sensor;
Fig. 6 is the hardware structure diagram based on the road traffic state detecting device of panorama computer vision;
Fig. 7 is sampled point sort tree structure figure;
Fig. 8 processes block diagram based on the software of the detection congestion in road state of the road traffic state detecting device of panorama computer vision;
Fig. 9 is for being processed into temporal information, spatial positional information, road driving directional information, road track direction information, Assessment of Serviceability of Roads class information and the length information that blocks up the composition schematic diagram of 43 characters;
Figure 10 is the formation schematic diagram of path space positional information;
Figure 11 is for to represent schematic diagram with spatial positional information, temporal information and Assessment of Serviceability of Roads grade with three dimensional space coordinate;
Figure 12 for from the angle of Information Organization with the urban road state be divided into macroscopic aspect, the inforamtion tree structural drawing of sight aspect and microcosmic point.
Figure 13 is the detection computations process flow diagram that has the detection module of sampled point.
Embodiment
The invention will be further described below in conjunction with accompanying drawing.
Embodiment 1
with reference to Fig. 2~Figure 12, a kind of road traffic state detecting device based on panorama computer vision, comprise the camera head that is arranged on each measurement point on each road on road network, be used for carrying out according to the video data of camera head the microprocessor of evaluation path traffic behavior, described microprocessor comprises microprocessor system hardware and microprocessor software, it is characterized in that: described microprocessor hardware is by CPU, video memory, input block, display unit, storage unit, delivery unit, communication unit, video interface, RAM (Random AccessMemory) and ROM (Read-only Memory) consist of, as shown in Figure 6, described camera head is connected with described microprocessor by described video interface, and traffic behavior is detected described delivery unit and result of calculation sends to signal lamp control module and traffic behavior release unit by described communication unit, described microprocessor software comprises:
The panoramic picture acquiring unit is used for obtaining initialization information and video image, comprises system initialization module and image collection module;
System initialization module is used for data target information, track and sampled point customization data and check point spatial positional information are read into dynamic storage cell, calls in order in subsequent processes;
Image collection module passes the video image information of coming and video image information is kept at dynamic storage cell for reading from camera head;
The user's of intelligent transportation system demand exists very large difference, such as urban traffic control person is different from the demand of traveler, urban traffic control person needs the service state of dynamic grasp macroscopical urban road, and the service state of road between traveler often is concerned about from the starting point to the destination; Therefore, the Intercity Transportation state need to from microcosmic, sight and macroscopic view carry out respectively detection computations, tissue and expression on three different aspects, as shown in Figure 12; In general, need the road conditions around observation point are detected on microcosmic point, road conditions have on every side comprised the road conditions on each track on the direction of the direction of two Facing Movements of road and two Facing Movements; Need the testing result on microcosmic point is carried out worked structure on middle sight aspect, obtain traffic on a certain road and the traffic information of peripheral path; Process and organize at the traffic of certain road that needs on macroscopic aspect to obtain on centering sight aspect and the traffic information of peripheral path, to obtain the traffic information in certain zone in the city; The traffic state data of macroscopic aspect depends on the traffic state data of middle sight aspect, and the traffic state data of middle sight aspect depends on again the traffic state data of microcosmic point; Depend on again time and the spatial data of traffic state information bleeding point in the statistical computation process of these traffic state datas, and these times and spatial data are participated in statistical computation directly; Therefore, setting up a kind of naming system standard of describing the urban road space data is very necessary for express urban road traffic state on different aspects;
Assessment of Serviceability of Roads detects overall procedure as shown in Figure 8 with blocking up, and is at first the customization step S1 of sampled point, track and driveway travel directions, is realized by sampled point, track and driveway travel directions customized module; Be then to detect the detecting step S2 that has sampled point from tn image constantly, realized by the detection module that has sampled point; Next step processing be to detect the detecting step S3 of mobile sampled point from tn front and back sequence image constantly, exist the detection module of sampled point to realize by mobile; Next step processing is to have according to detected in S2 a detecting step S4 that in sampled point and S3, detected mobile sampled point calculates the sampled point that blocks up in each track again, is realized by the static detection module of sampled point that exists; Processing then is to go out the statistical computation step S5 of the congestion regions in each track according to the static distribution statistical computation that has a sampled point that detects in detecting step S4, is realized by the static detection module of piece that exists; Be further to calculate tn each track Assessment of Serviceability of Roads constantly and the calculation procedure S6 of the length of blocking up according to the static distribution of piece on each track that exist that obtains in S5, realized by the Assessment of Serviceability of Roads determination module; Completed above-mentioned block up detect and statistical computation after result of calculation is sent to delivery unit with control transport information lamp or the transmission testing result step S7 of guidance information is provided; Then turn back to step S2 and carry out cycle detection calculating;
sampled point, track and driveway travel directions customized module are used for defining the travel direction attribute, track direction change attribute, the locus attribute on the longitudinal direction of track of the sampled point on road and in a lateral direction the locus attribute in the track, the naming method of sampled point adopts four-dimensional array S (i, j, k, l) represent a sampled point, wherein i is driveway travel directions property parameters value, j is track direction change property parameters value, k is the locus property parameters value on certain track longitudinal direction, from video camera begin nearby increase sequential system and be numbered, from the video camera distance more away from the larger the present invention of k value during with k≤N as closely, during N<k≤M as middle distance, during M<k as remote, 1 is in a lateral direction locus property parameters value in certain track, and data area is 0~4, for the travel direction property parameters value i of sampled point, regulation deviates from the travel direction property parameters value i=1 of road starting end, towards the travel direction property parameters value i=2 of road starting end, for track direction change property parameters value j, the track direction change property parameters value j=1 that regulation is turned left, track direction change property parameters value j=2 from the nearest Through Lane in the track of turning left, if also have just 3,4 code names codings in order of Through Lane, the track direction change property parameters value j=0 that regulation is turned right, then customization detects sampled point after having customized the track, space actual range between neighbouring sample point is 0.5 meter, consider that mainly vehicle is a rigid body, can adopt the sampled point of several continuous adjacent to characterize vehicle characteristics, the detection method of Points replacing surfaces in the present invention so not only can also can filter out other interference on road by simplified operation simultaneously, specific practice is: sampled point generates automatically with the track direction, if the transverse width in track is 2.5 meters, evenly generate 5 sampled points at each track horizontal direction, automatically generate several sampled points from the road starting end on video image to end on longitudinal direction, if the distance from the road starting end on video image to end on the real road space is 200 meters, evenly generate 400 sampled points on the longitudinal direction of track, the four-dimensional array S (i of each generated sampled point, j, k, l) express, because the sampled point that the pass of vision ties up on image is dredged nearby, close at a distance, but the real space spacing distance of each sampled point is all identical, the travel direction attribute of the sampled point that customization is good, track direction change attribute, the locus attribute on the longitudinal direction of track and track locus attribute in a lateral direction etc. during information is kept at storage unit, by the customization to the pixel on imaging plane, realized that the mapping of the sampled point on the sampled point on the imaging plane and real road is related, namely set up the A (x on the plane of delineation, y) the sampled point S (i on pixel and road, j, k, l) corresponding relation, in fact the work such as the regulation of the attributes such as demarcation, driveway travel directions, travel direction change and lane width of panoramic vision sensor and name have been completed in described sampled point, track and driveway travel directions customized module,
Comprising a large amount of redundant informations in video image, show as the strong correlation between the consecutive frame of strong phase Sihe time domain of neighbor in space, these spatial redundancies and time redundancy make video image process will spend a large amount of computational resources and storage resources, especially more outstanding for the video context of detection performance of road conditions, Assessment of Serviceability of Roads; In order to reduce calculated load and the storage load that video image is processed, the detection mode of the sampled point that in the present invention, employing acquires a special sense detects the congestion status of road, there is two states in sampled point for track on road from the angle that has or not foreground object, there is sampled point, namely exists the sampled point of foreground object; The non-sampled point that exists does not namely exist the sampled point of foreground object; By having sampled point and non-ly existing the division of sampled point can greatly reduce spatial redundancy; For there being sampled point, divide from the seasonal effect in time series angle, be divided into static sampled point and the mobile sampled point that exists of existing; Can greatly reduce time redundancy by such division, as described in accompanying drawing 7; The detection core of congestion in road is to detect the static sampled point that exists, but will be from a two field picture direct-detection go out the static sampled point that exists and exist very large difficulty, detect and calculate the mobile sampled point that exists in the present invention from image sequence, then exist sampled point to calculate the static sampled point that exists according to having sampled point and moving, obtain the congestion in road state according to the static distribution situation of sampled point that exists at last; More the foreground object point on dense list bright road road is more sampled point, thereby the traffic density of indirectly inferring road is higher; The density of blocking up that reflects road also needs to deduct traffic density in movement from the traffic density of road, in the present invention, the traffic density in movement is adopted the mobile detection method that has sampled point; Only the sampled point on road is calculated when image is processed and to reduce calculated load and the storage load that video image is processed, make based on the road traffic state detecting device of panorama computer vision and can realize with embedded system;
The congestion in road state detection module, for detection of the congestion status of some some travel directions of the moment on road, comprise the detection module that has sampled point, the mobile detection module of sampled point, static detection module, the Assessment of Serviceability of Roads detection module of the detection module of sampled point, the piece that blocks up and the length detection module of blocking up of existing of existing; The output format of congestion in road state detection module is made of following 6 parameter values, as shown in Figure 9, be respectively the moment parameter value of 14, the detection space location parameter value of 23, the travel direction property parameters value of 1, the track direction change property parameters value of 1, the Assessment of Serviceability of Roads parameter value of 1 and the length parameter value of blocking up of 3; Parameter is used for the temporal information that expression detects the moment constantly, parameter Time represents with 14 bit data forms constantly, be YYYYMMDDHHMMSS, wherein 1~4 YYYY represents that the year of the Gregorian calendar, 5~6 MM represent that the month of the Gregorian calendar, 7~8 DD represent that the day of the Gregorian calendar, 9~10 HH represent hour, 11~12 MM represent minute, 13~14 SS represent second; The detection space location parameter is used for the spatial positional information of expression check point, and detection space location parameter Location represents with 23 bit data forms; The driveway travel directions property parameters is used for the travel direction information in expression track, driveway travel directions property parameters Direction represents with 1 bit data form, regulation deviates from the travel direction property parameters value i=0 of road starting end, towards the travel direction property parameters value i=1 of road starting end; Track direction change property parameters is used for representing that this track allows the direction that moves ahead, track direction change property parameters Change represents with 1 bit data form, the track direction change property parameters value j=1 that regulation is turned left, track direction change property parameters value j=2 from the nearest Through Lane in the track of turning left, if also have just 3,4 code names codings in order of Through Lane, the track direction change property parameters value j=0 that regulation is turned right; The Assessment of Serviceability of Roads parameter is used for the congestion status of expression road, Assessment of Serviceability of Roads parameter S erviceLevel represents for alpha format with 1, the Assessment of Serviceability of Roads grade is divided into 6 grades such as A, B, C, D, E, F, wherein A represents that the Assessment of Serviceability of Roads grade is best, and F represents that the poorest grade of Assessment of Serviceability of Roads; The length parameter that blocks up is used for expression length of vehicle queue on the track when the track gets congestion situation, and for data layout represents, unit is meter the length parameter Length that blocks up with 3; A record of congestion in road state detection module output is to be made of six parameter values such as Time+Location+Direction+Change+ServiceLevel+Length like this, number of track-lines on the road of every record and detection becomes one-to-one relationship, 43 of the length of a record; If the road scope that panoramic vision sensor monitors has 8 tracks, 8 output records are so just arranged;
Described space position parameter Location comprises absolute position encoder, be used for expression from the logic mark code of the relative position of setting the coordinate central point, be used for natural number coding, branch road information coding from the origin-to-destination of road; Totally 23 codings as shown in Figure 10, wherein absolute position encoder is the most front 6, the 1st to the 3rd bit representation longitude, the 4th to the 6th bit representation latitude, such as the data that obtain are 120030,120 expression east longitude 120 degree, 030 expression north latitude 30 degree are the Hangzhous by leaving the city that can obtain correspondence in infosystem in; Logic mark code is the 7th to 17, with the central point in city, the zone is divided into 4 of A, B, C, D quadrant district, the quadrant district at the starting point place of the 7th bit representation road, the x, the y coordinate that represent the two ends, street with 4 bit digital, the 8th the x coordinate to the 9th bit representation street starting point, the 10th the y coordinate to the 11st bit representation street starting point, the quadrant district at the terminal point place of the 12nd bit representation road, the 13rd the x coordinate to the 14th bit representation street terminal point, the 15th the y coordinate to the 16th bit representation street terminal point; Be aided with lowercase for two parallel and two ends x, street that the y coordinate is identical and sequentially distinguish, represent with the 17th figure place; Natural number coding is the 18th to the 22nd, according to from south to north, ascending numbering from the east to the west, least unit is 1cm, and layout is carried out at left single right two ends that extend to, for only have one-sided street crossing if adopt the odd number layout at the left of road, in the right-hand employing even numbers layout of road; The branch road information coding is the 23rd, and branch road information coding N represents that the place ahead is obstructed, and L represents right turn ban, and R represents left turn ban;
described logic mark code is 11, from the 7th to the 17th, be used for expression from intown relative position, its naming rule is: significant position is initial point take the city center, East and West direction is the x axle, the north-south is the y axle, the city is divided into A, B, C, 4 of D quadrant district, consider that the megalopolis is in district radius 100km, the x that represents the two ends, street with 4 bit digital, the y coordinate, parallel at a distance of in the 1km scope and the x of two ends for two, the street that the y coordinate is identical can be aided with a, b, c....... order difference, if for example Hangzhou Yan Anlu is made as the y axle, the belt North Road is made as the x axle, the logic of Wen Sanlu mark can be expressed as D0202D0702, can directly read Wen Sanlu in intown northwest from mark, the Wen Sanlu starting point is positioned at the city center westwards in 2km, to the 2km of NATO, the Wen Sanlu terminal point is in intown northwest, in the city center westwards approximately 7km to the 2km of NATO, if the spatial positional information Location of check point is 120030D0202D0702a006880, it is the Hangzhou that front 6 120030 coded representation east longitude 120 degree, north latitude 30 are spent the city corresponding with it, the position that ensuing 11 code D0202D0702a can directly read panoramic vision sensor from mark is on intown northwestern Wen Sanlu, from westwards approximately 68.8 meters of civilian three tunnel starting points,
The described detection module that has sampled point is for detection of the point of the foreground object on road; The detection computations flow process Sa~Sh of the described detection module that has a sampled point is as follows, as shown in Figure 13:
In the calculation procedure of Sa, according to from panoramic vision sensor in the position on road to the corresponding road of each sampled point the distance of physical location come setting threshold TH1, threshold value TH1 arranges as criterion in the back to the binary conversion treatment of sampled point the time;
In the calculation procedure of Sb, the panoramic picture that tn is obtained constantly is processed into the sampled point image by the corresponding pixel of sampled point, and the gray-scale value of corresponding each pixel of sampled point on the sampled point image represents with 8 bit data;
In the calculation procedure of Sc, calculate the difference between benchmark gray level image and described sampled point image, obtain the difference image of two width images;
In the calculation procedure of Sd, carry out the background modeling of benchmark gray level image, constantly update tn benchmark gray level image B constantly with formula (1) nObtain tn+1 benchmark gray level image B constantly n+1:
(1)
B n+1=B n+φ×(X n-B n)
In formula, X nBe the gray-scale value of each sampled point in tn sampled images constantly, B nBe the gray-scale value of each sampled point of tn benchmark gray level image constantly, B n+1Be the gray-scale value of each sampled point of t n+1 benchmark gray level image constantly, φ is the very little coefficient of a numerical value;
When calculating, at first calculate (the X of each sampled point on road n-B n) value, then getting the absolute value of its value | X n-B n|, if this absolute value | X n-B n| greater than the threshold value TH2 B of this sampled point simultaneously of regulation nNearest non-of value and this sampled point exists the absolute value of gray-scale value of sampled point less than the threshold value TH3 of regulation, just be judged to be foreground object and entered on this sampled point, the at this moment renewal of this sampled point just with the nearest non-gray-scale value of sampled point that exists of this sampled point as B n+1The background modeling of all the other sampled points all by formula (1) upgrades processing;
In Se and Sf calculation procedure, be used in each threshold value TH that sets in the Sa step and carry out binary conversion treatment, obtain existing sampled point binary image F nAt binary image F nIn all sampled points will be divided into " 0 " or " 1 " two states, have foreground object to exist on this sampled point of the expression of " 1 ", namely have sampled point; There is not foreground object on this sampled point of the expression of " 0 ", i.e. the non-sampled point that exists; According to the corresponding relation of the sampled point on image and the sampled point on road, be set to " 25CB " with being judged to be the non-value of the sampled point S (i, j, k, l) of sampled point that exists, its corresponding geometric graph pictograph is " zero ";
There is the detection module of sampled point in described movement, for detection of the foreground point of the mobile object thing on road track; The image of not taking in the same time under Same Scene is carried out the pixel that difference can obtain the changing unit in two width images, namely obtain difference image, computing method are as shown in formula (2);
Z1 n=X n-X ????????????????????????????????????????????(2)
In formula, X nBe t nThe gray-scale value of each sampled point in sampled images constantly, X N-αBe t N-αThe gray-scale value of each sampled point in sampled images constantly, Z1 nBe difference image, referred to herein as the first difference image, it has represented to experience each sampled point situation of change on the road of α after the time; Comprised the situation of change of the two states of sampled point at the first difference image, i.e. from " 1 " to " 0 " or the variation from " 0 " to " 1 " will be confirmed whether it is mobilely to have sampled point, also needs to observe t nAnd t N+ βThe situation of change of the gray scale of each sampled point in sampled images constantly namely obtains the second difference image, and computing method are as shown in formula (3);
Z2 n=X n-X n+β????????????????????????????????????????????????????(3)
In formula, X nBe t nThe gray-scale value of each sampled point in sampled images constantly, X N+ βBe t N+ βThe gray-scale value of each sampled point in sampled images constantly, Z2 nBe difference image, referred to herein as the second difference image, it has represented to experience each sampled point situation of change on the road of β after the time;
Then, use respectively threshold value TH1 to the first difference image Z1 nWith with threshold value TH2 to the second difference image Z2 nProcess, obtain respectively First Characteristic and extract image T1 nExtract image T2 with Second Characteristic nThe mobile sampled point that exists must be present in First Characteristic extraction image T1 nExtract image T2 with Second Characteristic nAmong, therefore First Characteristic is extracted image T1 nExtract image T2 with Second Characteristic nThere is sampled point in the movement of carrying out trying to achieve in image with computing, and computing formula is as shown in (4);
Y n=T1 n∧T2 n????????????????????????????????????????????(4)
In formula, T1 nFor First Characteristic extracts image, T2 nFor Second Characteristic extracts image, Y nFor including the bianry image of mobile sampled point;
Consider the relation of video camera and vehicle location, be positioned at video camera vehicle nearby from the speed of image reflection hurry up, otherwise speed more slowly; Therefore, need to be according to the impact of the distance of road and video camera to eliminate the impact of far and near vehicle on image when asking difference image; On image, road is divided into closely in the present embodiment, namely during k≤N, middle distance, i.e. N<k≤M and remote, i.e. M<k; Therefore can ask respectively the first difference image formula group (5) with asking the first difference image formula (2) to be rewritten as a minute nearly medium and long distance;
Z1’ nN=X’ n-X’ n-α1L(k≤N)
Z1’ nM=X” n-X” n-α2L(N<k≤M)????????????????????????????????(5)
Z1’ nL=X”’ n-X”’ n-α3L(M<k)
In formula, X ' nBe t nThe gray-scale value of closely each sampled point in sampled images constantly, X ' N-α 1Be t N-α 1The gray-scale value of closely each sampled point in sampled images constantly, Z1 ' nNBe the first difference image closely; X” nBe t nThe gray-scale value of each sampled point of middle distance in sampled images constantly, X " N-α 2Be t N-α 2The gray-scale value of each sampled point of middle distance in sampled images constantly, Z1 " nMBe middle distance the first difference image; X " ' nBe t nThe gray-scale value of remote each sampled point in sampled images constantly, X " ' N-α 3Be t N-α 3The gray-scale value of remote each sampled point in sampled images constantly, Z1 " ' nLBe remote the first difference image; α in formula (5) 1<α 2<α 3, and be all positive integer, the value size depends on the design rate of road and the acquisition rate of video image;
Further, use respectively threshold value TH1N to the first difference image Z1 ' closely nN, with threshold value TH1M to middle distance the first difference image Z1 ' nM, with threshold value TH1L to remote the first difference image Z1 ' nLProcess, obtaining closely, First Characteristic extracts image T1 ' nN, the middle distance First Characteristic extracts image T1 ' nMExtract image T1 ' with remote First Characteristic nLEach threshold value exists TH1L<TH1M<TH1N relation;
Further, with formula (6), First Characteristic is closely extracted image T1 ' nN, the middle distance First Characteristic extracts image T1 ' nMExtract image T1 ' with remote First Characteristic nLCarry out exclusive disjunction, obtain First Characteristic and extract image T1 ' n
T1’ n=T1’ nN∨T1’ nM∨T1’ nL???????????????????????????????????????(6)
In formula, T1 ' nFor First Characteristic extracts image, T1 ' nNFor First Characteristic closely extracts image, T1 ' nMFor the middle distance First Characteristic extracts image, T1 ' nLFor remote First Characteristic extracts image;
Extract the account form of image for Second Characteristic, adopt the identical account form of extracting image with First Characteristic, ask respectively the second difference image formula group with formula (a 7) minute nearly medium and long distance;
Z2’ nN=X’ n-X’ n+β1L(k≤N)
Z2’ nM=X” n-X” n+β2L(N<k≤M)????????????????????????????(7)
Z2’ nL=X”’ n-X”’ n+β3L(M<k)
In formula, X ' nBe t nThe gray-scale value of closely each sampled point in sampled images constantly, X ' N+ β 1Be t N+ β 1The gray-scale value of closely each sampled point in sampled images constantly, Z2 ' nNBe the first difference image closely; X” nBe t nThe gray-scale value of each sampled point of middle distance in sampled images constantly, X " N+ β 2Be t N+ β 2The gray-scale value of each sampled point of middle distance in sampled images constantly, Z2 " nMBe middle distance the first difference image; X " ' nBe t nThe gray-scale value of remote each sampled point in sampled images constantly, X " ' N+ β 3Be t N+ β 3The gray-scale value of remote each sampled point in sampled images constantly, Z2 " ' nLBe remote the first difference image; β in formula (7) 1<β 2<β 3,, and be all positive integer, the value size depends on the design rate of road and the acquisition rate of video image, in general can be set to β 11<β 22<β 33
Further, use respectively threshold value TH2N to the first difference image Z2 ' closely nN, with threshold value TH2M to middle distance the first difference image Z2 ' nM, with threshold value TH2L to remote the first difference image Z2 ' nLProcess, obtaining closely, First Characteristic extracts image T2 ' nN, the middle distance First Characteristic extracts image T2 ' nMExtract image T2 ' with remote First Characteristic nLEach threshold value exists TH2L<TH2M<TH2N relation;
Further, with formula (8), First Characteristic is closely extracted image T2 ' nN, the middle distance First Characteristic extracts image T2 ' nMExtract image T2 ' with remote First Characteristic nLCarry out exclusive disjunction, obtain First Characteristic and extract image T2 ' n
T2’ n=T2’ nN∨T2’ nM∨T2’ nL????????????????????????????????(8)
In formula, T2 ' nFor Second Characteristic extracts image, T2 ' nNFor Second Characteristic closely extracts image, T2 ' nMFor the middle distance Second Characteristic extracts image, T2 ' nLFor remote Second Characteristic extracts image;
First Characteristic is extracted image T1 ' nExtract image T2 ' with Second Characteristic nThere is sampled point in the movement of carrying out trying to achieve in image with computing, and computing formula is as shown in (9);
(9)
Y n=T1’ n∧T2’ n
In formula, T1 ' nFor First Characteristic extracts image, T2 ' nFor Second Characteristic extracts image, Y nFor including the bianry image of mobile sampled point; Be set to " 2642 " for being judged to be the mobile value of the sampled point S (i, j, k, l) of sampled point that exists, its corresponding geometric graph pictograph is " ♂ ";
The described static detection module that has sampled point is for detection of the information characteristics point of static foreground object on road; According to general knowledge, when getting congestion, road all has been crowded with vehicle on whole road, and these vehicles on road all are in relative static conditions, and the vehicle that at this moment is in relative static conditions will show in a plurality of static mode of sampled point that exists of relatively concentrating;
There is sampled point binary image F nIn comprising the mobile bianry image Yn that has sampled point WithThe static bianry image S that has sampled point n, therefore calculate the static bianry image S that has sampled point by formula (10) n
(10)
S n=F n-Y n
In formula, S nBe static sampled point bianry image, the F of existing nFor having sampled point bianry image, Y nBe mobile sampled point bianry image; Be set to " 25CF " for being judged to be the mobile value of the sampled point S (i, j, k, l) of sampled point that exists, its corresponding geometric graph pictograph is "●"; Block up the zone that occurs be exactly the static sampled point "●" that exists than the zone of comparatively dense, therefore, add up and calculate the static dense degree of sampled point and the range size of close quarters of existing and just can estimate more exactly the congestion status of road;
the described static detection module that has piece, be used for the length and filter out some interference on road of blocking up on estimation road travel line, such as bicycle, abandon on pedestrian and road, these interference can cause the non-sampled point that exists to be mistaken for the static sampled point that exists, because static vehicle is to be made of several adjacent static sampled points that exist, the static sampled point that exists that will isolate in the present invention is eliminated these interference by filter algorithm, specific algorithm is the static S (i that has sampled point that first reads horizontal direction on the track, j, k, l) array value, if be " 0 " with the static adjacent pixel value of sampled point that exists, should staticly exist sampled point to change into the non-sampled point that exists, the array value of two sampled point S that it is adjacent is (i, j, k, l-1) and (i, j, k, l+1), equally, be mistaken for the static situation that has sampled point for some non-sampled point that exists, adopt the erroneous judgement correction algorithm to eliminate erroneous judgement, specific algorithm is non-S (i, j, the k that has sampled point that first reads horizontal direction on the track, l) array value if be " 1 " with this non-adjacent pixel value of sampled point that exists, should non-ly exist sampled point to change into the static sampled point that exists, the array value of two sampled point S that it is adjacent is (i, j, k, l-1) and (i, j, k, l+1), can eliminate the prospect gray-scale value erroneous judgement that cause close to the road ground gray-scale value at some position of vehicle by above-mentioned erroneous judgement correction algorithm,
After having eliminated interference and having revised erroneous judgement, then carry out the static detection that has piece, the so-called static piece that exists is to be made of the static sampled point that exists of relatively concentrating, and considers the auto model on imaging plane, and static vehicle is to be showed by the static mode of piece that exists on road; It is " 25CB " that the present invention arranges the non-Unicode code that exists sampled point S (i, j, k, l) to be worth, and the geometric graph pictograph is " zero "; The mobile Unicode code that exists sampled point S (i, j, k, l) to be worth is " 2642 ", and the geometric graph pictograph is " ♂ "; The static Unicode code that exists sampled point S (i, j, k, l) to be worth is " 25CF ", and the geometric graph pictograph is "●";
adopt in the embodiment of the present invention the static detection mode that has piece is implemented respectively in each track, detect that static to have the mode of piece be that the starting end with every lane detects to the end end on imaging plane, in the static detection module that has a piece, adopt the general car size on road as the matching detection masterplate, the static piece that exists to be carried out matching detection in the present invention, if general car size is occupied 3 sampled points in a lateral direction vehicle, occupy 5 sampled points on the longitudinal direction of vehicle, so just with the masterplate of 3 * 5 sampled points from the starting end in all travel directions on road and all tracks to end to carrying out matching detection, namely from i=0, j=0 and k=0 begin to carry out matching detection, because the track has 5 sampled points in a lateral direction, namely the scope at the same horizontal direction l in a certain track is 0~4, from the scope 0~2 of l, then 1~3, follow 2~4, each carries out matching detection in a lateral direction three times, the method of matching detection is to have how many static situations of sampled point that exist to judge in masterplate by statistical computation 3 * 5 sampled points, if the static sampled point that exists more than 50% is arranged in matching stencil, namely having static more than 7 to exist sampled point just to be judged to be this zone in the masterplate of 3 * 5 sampled points is the static piece that exists, when the same horizontal direction l in a certain track detect finish after, if exist one and more than one when existing piece to satisfy matching detection masterplate situation in above-mentioned matching detection, k=k+5, otherwise k=k+1, then proceed matching detection until the terminal position to a certain track, then carry out the matching detection in next track, above-mentioned matching detection process circulates, then carry out the matching detection of next travel direction, above-mentioned matching detection process circulates again, after the static matching detection that has a piece that has traveled through all travel directions and all tracks, can obtain the static maximum k value that has the piece coupling of certain the track j on certain travel direction i, calculate by this Digital size the length that the track on this travel direction blocks up, because the actual range of two neighbouring sample points on road is 0.5 meter, if calculate k=150, the length of blocking up that so just can simply calculate upper certain the track j of certain travel direction i is 75 meters,
The Assessment of Serviceability of Roads determination module is for the service level of judging current road; The congestion in road degree is and static the how much proportional of sampled point that exist; In other words, if all sampled points on road are nearly all the static sampled points that exists, illustrate that the lane on road has occured seriously to block up; If all sampled points on road are nearly all the non-sampled points that exists, illustrating does not almost have vehicle on road; So, can be in which kind of service level by non-sampled point, mobile sampled point and the static ratio estimation road traffic state of sampled point that exists of existing of existing on certain runway; Assessment of Serviceability of Roads is divided into 6 each grade: service level A: unimpeded; Service level B: substantially unimpeded; Service level C: tentatively block up; Service level D: block up: service level E: seriously block up; Service level F: localized road and large tracts of land paralysis are judged Assessment of Serviceability of Roads according to the decision condition in table 1, the Assessment of Serviceability of Roads grade are divided into 6 grades such as A, B, C, D, E, F; The service level grade of road judges that comprehensively table is as shown in table 1;
Table 1
Several judgement size of data shown in table 1 and sampled point be custom made with direct relation, table 1 is one group of data of this enforcement; Need to suitably adjust according to the customization situation of sampled point during practical application; Obtain the total S of the sampled point in certain track in described sampled point, track and driveway travel directions customized module, obtain existing on certain track the total ES of sampled point in the described detection module that has a sampled point, can calculate the non-ratio value of sampled point and sampled point, mobile ratio value and the static ratio value that has sampled point and sampled point that has sampled point and sampled point of existing by formula (12);
Rate ( NS / S ) = ( S - ES ) S × 100
Rate ( YS / S ) = YS S × 100
Rate ( SS / S ) = SS S × 100
In formula, S is the sum of the sampled point in certain track, and ES is for existing the sum of sampled point on certain track, and NS is the non-sum that has sampled point on certain track, and YS is the static sum that has sampled point on certain track for the mobile sum that has sampled point on certain track, SS;
Described camera head adopts panoramic vision sensor, is used for obtaining large-area vedio data on road, and panoramic vision sensor becomes minute surface 2 and the camera lens of angle just to be consisted of towards the video camera 1 of minute surface by two; Angle between two minute surfaces 2 is 180 ° of-2 γ, and two minute surfaces 2 are W at the width value on front elevation, the height value on side view is R, and the width value W of two minute surfaces 2 and height value R are positioned at the areas imaging of video camera 1; On side view, the central shaft of described video camera 1 becomes the η angle with the central shaft of described vertical rod, and minute surface becomes the ε angle with the surface level direction of road side; On front elevation, the angle of minute surface and described vertical rod is 90 °-γ, the central shaft of video camera and the central axes of vertical rod, and the focal length of video camera is f;
The setting height(from bottom) of panoramic vision sensor is H, and the road surface is L along the visual range of road direction, 180 ° of-2 γ of angle between two minute surfaces, and formula (11) is the relation of H, L value and γ,
γ = ( tan - 1 ( L / H ) - ω ′ max × H ) / 2 - - - ( 11 )
In formula, γ represents the angle of minute surface and surface level, L be panoramic vision sensor along the visual length on surface level direction road, H is the setting height(from bottom) of panoramic vision sensor, Maximum visual angle for video camera.
Further, the maximum visual angle of described video camera It is 45 °, the setting height(from bottom) H of panoramic vision sensor is 5 meters, panoramic vision sensor along the visual length L on road direction greater than 200 meters, the angle γ that tries to achieve minute surface and surface level by formula (11) is 32 °, the length of minute surface is greater than W/2 * cos (γ), (ε-η), ε is the angle of the surface level direction of minute surface and road side to the width of every minute surface, and η is the angle between video camera central shaft and vertical rod central shaft greater than R/cos; In order to get rid of signal lamp to the detection of the density of blocking up impact, vertical rod be arranged in a signal lamp transformation period occupy the length of road by vehicle, operated by rotary motion is 60 meters in the distance from the stop line of signal light path; For from the distant local check point setting of signal lamp, in order to obtain congestion in road situation more accurately, preferably set up a check point every 200 meters on the road driving direction.
Embodiment 2
With reference to Fig. 1, Fig. 3~Figure 11, all the other and embodiment 1 are identical, difference is to detect simultaneously with an omnibearing vision sensor that is placed in the crossroad middle upper part state of the wait vehicle of the state of all crossroads outlets and all crossroad entrances, change over red light if the state of the some crossroads outlet signal lamp that just this direction is travelled that occurs blocking up detected, in order to avoid cause larger blocking up; If the state of some crossroads outlet does not have vehicle congestion, and a large amount of vehicle of comparing with other porch in this porch corresponding to outlet, crossroad gets congestion, suitably with the Green extension of this crossroad to relax the jam in this track, as shown in Figure 1, at this moment just need the green time in proper extension north-south, suitably reduce transmeridional green time.

Claims (5)

1. road traffic state detecting device based on panorama computer vision, it is characterized in that: comprise the camera head that is arranged on each measurement point on each road on road network, the microprocessor that is used for carrying out according to the video data of camera head the evaluation path traffic behavior, described camera head is connected with described microprocessor by video interface, and traffic behavior is detected delivery unit and result of calculation sends to signal lamp control module and traffic behavior release unit by communication unit; Described microprocessor comprises:
The panoramic picture acquiring unit is used for obtaining initialization information and video image;
Sampled point, track and driveway travel directions customized module are used for defining the travel direction attribute, track direction change attribute, the locus attribute on the longitudinal direction of track of the sampled point on road and in a lateral direction the locus attribute in the track;
The congestion in road state detection module is for detection of the congestion status of some some travel directions of the moment on road; Described congestion in road state detection module comprises the detection module that has sampled point, the mobile detection module of sampled point, static detection module, the Assessment of Serviceability of Roads detection module of the detection module of sampled point, the piece that blocks up and the length detection module of blocking up of existing of existing;
The Assessment of Serviceability of Roads determination module, the service level for judging current road is divided into A, B, C, D, E, a F6 grade with the Assessment of Serviceability of Roads grade, and the step of decision process is as follows:
At first obtain the total S of the sampled point in certain track in described sampled point, track and driveway travel directions customized module, obtain existing on certain track the total ES of sampled point in the described detection module that has a sampled point, calculate the non-ratio value Rate (NS/S) of sampled point and sampled point, mobile ratio value Rate (YS/S) and the static ratio value Rate (SS/S) that has sampled point and sampled point that has sampled point and sampled point of existing by formula (12); Then according to each calculate ratio value table look-up the road shown in 1 the service level grade comprehensively the judgement table obtain the relevant service level grade in certain track;
Rate ( NS / S ) = ( S - ES ) S × 100 - - - ( 12 )
Rate ( YS / S ) = YS S × 100
Rate ( SS / S ) = SS S × 100
In formula, S is the sum of the sampled point in certain track, and ES is for existing the sum of sampled point on certain track, and NS is the non-sum that has sampled point on certain track, and YS is the static sum that has sampled point on certain track for the mobile sum that has sampled point on certain track, SS;
The service level grade of road judges that comprehensively table is as shown in table 1;
Table 1.
2. the road traffic state detecting device based on panorama computer vision as claimed in claim 1, it is characterized in that: described panoramic picture acquiring unit comprises system initialization module and image collection module;
System initialization module is used for data target information, track and sampled point customization data and check point spatial positional information are read into dynamic storage cell, calls in order in subsequent processes;
Image collection module passes the video image information of coming and video image information is kept at dynamic storage cell for reading from camera head.
3. the road traffic state detecting device based on panorama computer vision as claimed in claim 1 or 2, it is characterized in that: in described Assessment of Serviceability of Roads determination module and in described congestion in road state detection module, realized by Assessment of Serviceability of Roads and the detection overall procedure that blocks up, at first be the customization step of sampled point, track and driveway travel directions, realized by described sampled point, track and driveway travel directions customized module; Be then to detect the detecting step that has sampled point from tn image constantly, realized by the described detection module of sampled point that exists; Next step processing be to detect the detecting step of mobile sampled point from tn front and back sequence image constantly, exist the detection module of sampled point to realize by described movement; Next step processing is the detecting step that exists sampled point and detected mobile sampled point to calculate the sampled point that blocks up in each track according to detected again, is realized by the described static detection module of sampled point that exists; Processing then is to go out the statistical computation step of the congestion regions in each track according to the static distribution statistical computation that has a sampled point that detects, and is realized by the detection module of the described piece that blocks up; Be further to calculate tn each track Assessment of Serviceability of Roads constantly and the calculation procedure of the length of blocking up according to the static distribution of piece on each track that exist that obtains, realized by described Assessment of Serviceability of Roads determination module; Completed above-mentioned block up detect and statistical computation after result of calculation is sent to delivery unit with control transport information lamp or the transmission testing result step of guidance information is provided; Return at last detected state and repeat cycle detection calculating.
4. the road traffic state detecting device based on panorama computer vision as claimed in claim 1, it is characterized in that: the output format of described congestion in road state detection module is made of following 6 parameter values, is respectively the moment parameter value of 14, the detection space location parameter value of 23, the travel direction property parameters value of 1, the track direction change property parameters value of 1, the Assessment of Serviceability of Roads parameter value of 1 and the length parameter value of blocking up of 3; Parameter is used for the temporal information that expression detects the moment constantly, parameter Time represents with 14 bit data forms constantly, be YYYYMMDDHHMMSS, wherein 1 ~ 4 YYYY represents that the year of the Gregorian calendar, 5 ~ 6 MM represent that the month of the Gregorian calendar, 7 ~ 8 DD represent that the day of the Gregorian calendar, 9 ~ 10 HH represent hour, 11 ~ 12 MM represent minute, 13 ~ 14 SS represent second; The detection space location parameter is used for the spatial positional information of expression check point, and detection space location parameter Location represents with 23 bit data forms; The driveway travel directions property parameters is used for the travel direction information in expression track, driveway travel directions property parameters Direction represents with 1 bit data form, regulation deviates from the travel direction property parameters value i=0 of road starting end, towards the travel direction property parameters value i=1 of road starting end; Track direction change property parameters is used for representing that this track allows the direction that moves ahead, track direction change property parameters Change represents with 1 bit data form, the track direction change property parameters value j=1 that regulation is turned left, track direction change property parameters value j=2 from the nearest Through Lane in the track of turning left, if also have just 3,4 code names codings in order of Through Lane, the track direction change property parameters value j=0 that regulation is turned right; The Assessment of Serviceability of Roads parameter is used for the congestion status of expression road, Assessment of Serviceability of Roads parameter S erviceLevel represents for alpha format with 1, the Assessment of Serviceability of Roads grade is divided into A, B, C, D, E, a F6 grade, wherein A represents that the Assessment of Serviceability of Roads grade is best, and F represents that the poorest grade of Assessment of Serviceability of Roads; The length parameter that blocks up is used for expression length of vehicle queue on the track when the track gets congestion situation, and for data layout represents, unit is meter the length parameter Length that blocks up with 3; A record of congestion in road state detection module output is to be made of six parameter values of Time+Location+Direction+Change+ServiceLevel+Length like this, number of track-lines on the road of every record and detection becomes one-to-one relationship, 43 of the length of a record; If the road scope that panoramic vision sensor monitors has 8 tracks, 8 output records are so just arranged;
Described space position parameter Location comprises absolute position encoder, be used for expression from the logic mark code of the relative position of setting the coordinate central point, be used for natural number coding, branch road information coding from the origin-to-destination of road; Totally 23 codings, wherein absolute position encoder is the most front 6, and the 1st to the 3rd bit representation longitude, and the 4th to the 6th bit representation latitude; Logic mark code is the 7th to 17, with the central point in city, the zone is divided into A, B, C, D4 quadrant district, the quadrant district at the starting point place of the 7th bit representation road, the x, the y coordinate that represent the two ends, street with 4 bit digital, the 8th the x coordinate to the 9th bit representation street starting point, the 10th the y coordinate to the 11st bit representation street starting point, the quadrant district at the terminal point place of the 12nd bit representation road, the 13rd the x coordinate to the 14th bit representation street terminal point, the 15th the y coordinate to the 16th bit representation street terminal point; Be aided with lowercase for two parallel and two ends x, street that the y coordinate is identical and sequentially distinguish, represent with the 17th figure place; Natural number coding is the 18th to the 22nd, according to from south to north, ascending numbering from the east to the west, least unit is 1cm, and layout is carried out at left single right two ends that extend to, for only have one-sided street crossing if adopt the odd number layout at the left of road, in the right-hand employing even numbers layout of road; The branch road information coding is the 23rd, and branch road information coding N represents that the place ahead is obstructed, and L represents right turn ban, and R represents left turn ban;
Described logic mark code is 11, from the 7th to the 17th, be used for expression from intown relative position, its naming rule is: significant position is initial point take the city center, East and West direction is the x axle, the north-south is the y axle, the city is divided into A, B, C, D4 quadrant district, consider that the megalopolis is in district radius 100km, the x, the y coordinate that represent the two ends, street with 4 bit digital, for two parallel at a distance of in the 1km scope and two ends x, street that the y coordinate is identical can be aided with lowercase and sequentially distinguish.
5. the road traffic state detecting device based on panorama computer vision as claimed in claim 1, it is characterized in that: described camera head adopts panoramic vision sensor, be used for obtaining large-area vedio data on road, panoramic vision sensor becomes minute surface and the camera lens of angle just to be consisted of towards the video camera of minute surface by two; Angle between two minute surfaces is 180 ° of-2 γ, and two minute surfaces are W at the width value on front elevation, the height value on side view is R, and the width value W of two minute surfaces and height value R are positioned at the areas imaging of video camera; On side view, the central shaft of described video camera becomes the η angle with the central shaft of vertical rod, and minute surface becomes the ε angle with the surface level direction of road side; On front elevation, the angle of minute surface and described vertical rod is 90 °-γ, the central shaft of video camera and the central axes of vertical rod, and the focal length of video camera is f;
The setting height(from bottom) of panoramic vision sensor is H, and the road surface is L along the visual range of road direction, 180 ° of-2 γ of angle between two minute surfaces, and formula (11) is the relation of H, L value and γ,
γ = ( tan - 1 ( L / H ) - ω ′ max × H ) / 2 - - - ( 11 )
In formula, γ represents the angle of minute surface and surface level, L be panoramic vision sensor along the visual length on surface level direction road, H is the setting height(from bottom) of panoramic vision sensor, Maximum visual angle for video camera;
The maximum visual angle of described video camera It is 45 °, the setting height(from bottom) H of panoramic vision sensor is 5 meters, panoramic vision sensor along the visual length L on road direction greater than 200 meters, the angle γ that tries to achieve minute surface and surface level by formula (11) is 32 °, the length of minute surface is greater than W/2 * cos (γ), (ε-η), ε is the angle of the surface level direction of minute surface and road side to the width of every minute surface, and η is the angle between video camera central shaft and vertical rod central shaft greater than R/cos; Vertical rod be arranged in a signal lamp transformation period occupy the length place of road by vehicle.
CN 201110069317 2011-03-22 2011-03-22 Road traffic condition detection device based on panorama computer vision CN102136194B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201110069317 CN102136194B (en) 2011-03-22 2011-03-22 Road traffic condition detection device based on panorama computer vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201110069317 CN102136194B (en) 2011-03-22 2011-03-22 Road traffic condition detection device based on panorama computer vision

Publications (2)

Publication Number Publication Date
CN102136194A CN102136194A (en) 2011-07-27
CN102136194B true CN102136194B (en) 2013-06-05

Family

ID=44295964

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201110069317 CN102136194B (en) 2011-03-22 2011-03-22 Road traffic condition detection device based on panorama computer vision

Country Status (1)

Country Link
CN (1) CN102136194B (en)

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102436739B (en) * 2011-09-27 2013-10-23 重庆大学 Method for distinguishing traffic jam of toll plaza of highway based on video detection technology
CN102496278B (en) * 2011-12-09 2014-05-07 北京世纪高通科技有限公司 Method and device for obtaining traffic states through images
CN102831261B (en) * 2012-07-31 2015-04-22 吉林大学 Modeling method of complex road
CN103310633A (en) * 2013-05-23 2013-09-18 北京交通发展研究中心 Traffic congestion evaluation method
CN104751627B (en) * 2013-12-31 2017-12-08 西门子公司 A kind of traffic determination method for parameter and device
CN103985250B (en) * 2014-04-04 2016-05-18 浙江工业大学 The holographic road traffic state vision inspection apparatus of lightweight
CN104933868B (en) * 2015-06-17 2017-07-07 苏州大学 A kind of real-time online Traffic State Detection Method based on Traffic Surveillance Video
CN105160324B (en) * 2015-09-08 2018-10-26 长安大学 A kind of vehicle checking method based on space of components relationship
CN106203694A (en) * 2016-07-07 2016-12-07 百度在线网络技术(北京)有限公司 Place crowding forecast model foundation, place crowding Forecasting Methodology and device
CN106297285B (en) * 2016-08-17 2018-09-21 重庆大学 Freeway traffic operating status fuzzy synthetic appraisement method based on changeable weight
CN107123296A (en) * 2017-06-09 2017-09-01 安徽富煌科技股份有限公司 A kind of global unobstructed degree voice announcer of circuit
CN108694833A (en) * 2018-07-17 2018-10-23 重庆交通大学 Traffic abnormal incident detecting system based on binary sensor
CN108922187A (en) * 2018-07-20 2018-11-30 肖哲睿 A kind of intelligent transportation system
CN109191830B (en) * 2018-08-09 2021-01-05 昆明理工大学 Road congestion detection method based on video image processing
CN110956800A (en) * 2018-09-27 2020-04-03 杭州海康威视系统技术有限公司 Road section traffic data preprocessing method and device and electronic equipment
CN109410582A (en) * 2018-11-27 2019-03-01 易念科技(深圳)有限公司 Traffic condition analysis method and terminal device
CN109448376A (en) * 2018-11-27 2019-03-08 科大国创软件股份有限公司 A kind of road condition analyzing method and system based on video
CN109686081A (en) * 2018-12-04 2019-04-26 大英县青少年学生校外活动中心 A kind of lane condition intelligent control system
CN110322704A (en) * 2019-06-14 2019-10-11 东南大学 A kind of queue length real-time estimation method based on number plate identification and GPS data
CN110992693A (en) * 2019-12-04 2020-04-10 浙江工业大学 Deep learning-based traffic congestion degree multi-dimensional analysis method
CN112013859B (en) * 2020-10-19 2021-01-26 四川京炜交通工程技术有限公司 Method for rapidly acquiring accurate position of road marking
CN112418192A (en) * 2021-01-21 2021-02-26 武汉中海庭数据技术有限公司 Multi-line direct connection method and device among multi-channel segments of crowdsourcing data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101030323A (en) * 2007-04-23 2007-09-05 凌子龙 Automatic evidence collecting device on crossroad for vehicle horning against traffic regulation
CN101183427A (en) * 2007-12-05 2008-05-21 浙江工业大学 Computer vision based peccancy parking detector
CN101710448A (en) * 2009-12-29 2010-05-19 浙江工业大学 Road traffic state detecting device based on omnibearing computer vision

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008107862A (en) * 2006-09-28 2008-05-08 Fujitsu Ltd Congestion effect determination program, congestion effect determination method and congestion effect determination apparatus
US8451140B2 (en) * 2007-12-20 2013-05-28 International Business Machines Corporation Monitoring road surface conditions

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101030323A (en) * 2007-04-23 2007-09-05 凌子龙 Automatic evidence collecting device on crossroad for vehicle horning against traffic regulation
CN101183427A (en) * 2007-12-05 2008-05-21 浙江工业大学 Computer vision based peccancy parking detector
CN101710448A (en) * 2009-12-29 2010-05-19 浙江工业大学 Road traffic state detecting device based on omnibearing computer vision

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
JP特开2008-107862A 2008.05.08

Also Published As

Publication number Publication date
CN102136194A (en) 2011-07-27

Similar Documents

Publication Publication Date Title
Gopalakrishnan et al. Is the shale energy boom a bust for nearby residents? Evidence from housing values in Pennsylvania
Frade et al. Bicycle sharing systems demand
CN103593976B (en) Based on the method and system of detecting device determination road traffic state
CN105185115B (en) A kind of traffic forecast method and forecasting system
CN103839409B (en) Based on the traffic flow modes method of discrimination of multibreak facial vision sensing cluster analysis
Kong et al. Efficient traffic state estimation for large-scale urban road networks
CN102332210B (en) Method for extracting real-time urban road traffic flow data based on mobile phone positioning data
Barrett et al. Developing a dynamic traffic management modeling framework for hurricane evacuation
CN103050005B (en) Method and system for space and time analysis of urban road traffic states
Lin et al. A review of travel-time prediction in transport and logistics
CN100580735C (en) Real-time dynamic traffic information processing method based on car detecting technique
CN104778834B (en) Urban road traffic jam judging method based on vehicle GPS data
CN102819955B (en) Road network operation evaluation method based on vehicle travel data
CN104157139B (en) A kind of traffic congestion Forecasting Methodology and method for visualizing
CN103794070B (en) A kind of based on bus or train route collaborative dynamic induction information broadcasting method and system
CN106971534B (en) Commuter characteristic analysis method based on number plate data
El Esawey et al. Development of daily adjustment factors for bicycle traffic
CN104732075B (en) A kind of Urban Road Traffic Accidents risk real-time predicting method
CN103903433B (en) The Real-time and Dynamic method of discrimination of a kind of road traffic state and device
KR20180116749A (en) Real Time Big Scale Traffic Data Collecting Method and Big Data Management System
CN102708680B (en) Commute travel mode identification method based on AGPS technology
Coric et al. Crowdsensing maps of on-street parking spaces
CN103886756B (en) Based on the freeway network method for detecting operation state of OBU
CN102110376B (en) Roadside parking space detection device based on computer vision
CN102087788B (en) Method for estimating traffic state parameter based on confidence of speed of float car

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant