CN104021676A - Vehicle positioning and speed measuring method based on dynamic video feature of vehicle - Google Patents
Vehicle positioning and speed measuring method based on dynamic video feature of vehicle Download PDFInfo
- Publication number
- CN104021676A CN104021676A CN201410293044.8A CN201410293044A CN104021676A CN 104021676 A CN104021676 A CN 104021676A CN 201410293044 A CN201410293044 A CN 201410293044A CN 104021676 A CN104021676 A CN 104021676A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image
- video
- measured
- characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a vehicle positioning and speed measuring method based on the dynamic video feature of a vehicle, belonging to the technical field of intelligent transportation and close-range photogrammetry. The vehicle positioning and speed measuring method comprises the following steps: judging the vehicle dynamic video feature size in a video image within any time quantum in one video monitoring system according to vehicle dynamic feature parameters extracted from the video image which calibrates a vehicle traveling process, and reconstructing and reducing a dynamic video feature model of a to-be-measured vehicle traveling process corresponding to each image frame; and calculating an actual position and a vehicle speed value sequence corresponding to each image frame in the to-be-measured vehicle traveling process according to a mapping relation between the dynamic variation characteristic of the image feature size of a vehicle to be measured and the actual vehicle movement parameters, and thus acquiring the actual position and traveling speed information of the vehicle. The vehicle positioning and speed measuring method is easy to realize and high in accuracy, and is applicable to the demands of various vehicles on speed measurement in a road traffic video monitoring system.
Description
Technical field
What the present invention relates to is a kind of method in intelligent transportation and close-shot photography measure technique field, specifically a kind of for existing road traffic video monitoring system, the vehicle location based on vehicle dynamic video features and vehicle speed measurement method.
Background technology
In traffic monitoring management, vehicle speed measurement is the important foundation of the road traffic management and control such as Traffic Accidents Reasons Analyzed analysis and confirmation of responsibility, vehicle flow monitoring and regulation and control intervention, plays vital effect for the foundation of intelligent transportation system.Aspect road traffic, traditional vehicle speed measuring method mainly comprises: detections of radar, inductive coil detection, laser/infrared detection, the detection of ultrasound wave/microwave etc., wherein: relatively more conventional is detections of radar and inductive coil detection method.In addition, along with the development of current close-shot photography measure technique and the raising of computing power, utilize technology that video frame image carries out vehicle location and vehicle speed measurement also at gradual perfection.
The principle of radar velocity measurement is: the other radar transmitter that is equipped with of road, and launch radar beam to road direction to the car, then accept the reflection echo of automobile, measure car speed by echo analysis, as the speed of a motor vehicle exceedes setting value, automatically trigger camera and complete shooting, record the identifying information of vehicles peccancy.The major defect of radar velocity measurement is low without duplicate measurements and resolution, in the time having more target vehicle on road surface, especially under complex accident operating mode, be difficult to carry out vehicle exactly and distinguish and vehicle speed measurement, and cost is higher.
It is the main method that current vehicle speed detection system is used that inductive coil detects, the party's ratio juris is: by electronic original part detect vehicle through time electric signal in inductive coil record vehicle by time status information, by gathering and calculating completes vehicle speed measurement.This method cost is lower, and accuracy of detection is higher, but coil easily damages, and installation and removal is all inconvenient, and the method can only be measured the average speed of vehicle in given area simultaneously, can not carry out continuous tracking measurement to the motion state of vehicle.
Main automobile video frequency speed-measuring method at present, conventionally simple velocity dependent definition in the time that the final speed of a motor vehicle is calculated, i.e. the mistiming t of the displacement d/ displacement of speed v=vehicle.Under the known prerequisite of the intrinsic sample frequency of video system, the calculating of vehicle movement relies on go forward side by side row-coordinate conversion of the unique point of choosing on vehicle to obtain completely, do not utilize the mutual restriction relation of characteristic dimension in picture frame or shape, therefore, the at present accuracy requirement of the quality of main video frequency speed-measuring method to video frame image and selected characteristic point is higher, has that false drop rate is high, measurement result is to matching algorithm error sensitivity and the problem such as robustness is low.In addition, some video frequency speed-measuring methods directly use three-dimensional coordinate relationship map to carry out plan range measuring and calculating, cause scaling method complexity and computing cost larger, not only cannot improve measuring accuracy and also reduce service efficiency.
Through the retrieval of prior art is found, Chinese patent literature CN102622895A open (bulletin) day 2012.08.01, a kind of vehicle speed detection method based on video is disclosed, first obtain traffic route video, and to its do pre-service obtain 720*288 pixel size only containing the image sequence of gray value information; Secondly in image, choose the vehicle tracking region of 2*8*90 size, from 9 continuous two field pictures, extract Image Projective Sequence; The poor method of reusable frame is extracted projection image sequence and chooses its eigenwert, uses the two-dimensional map relation (point is to the relation of distance) in mapping table to ask for these position of eigenwert point in real road; Finally set up the graph of relation of eigenwert point physical location and time, by the speed of least square fitting vehicle.Compared with prior art, the method for this technology can detect car speeds all in range of video, is not subject to environmental restraint, can judge real-time video, and detection time short, be easy to realize, accuracy is higher, have broad application prospects.But this Technology Need uses the two-dimensional map relation in mapping table, and these mapping relations all have different numerical expression relations for different camera systems or site layout project situation, and therefore, this existing method need to create different mapping tables according to different situations; Secondly, because mapping table is discrete data form, can not in table, all just have mapping relations for the arbitrfary point in video image, therefore, this technology is all restricted aspect measurability and measuring accuracy; In addition could analytical calculation after, this scheme need to be extracted Image Projective Sequence in 9 continuous two field pictures.
Through the retrieval of prior art is found, Chinese patent literature CN102592456A open (bulletin) day 2012.07.18, a kind of vehicle speed measuring method based on video is disclosed, comprise the steps: 1., demarcate on the spot: multiple continuous sections are selected at corresponding scene on the spot in video detection zone, and on the separatrix in adjacent section, calibrate actual detection line; 2., system drawing is set: scene actual detection line is on the spot converted into the virtual detection line in image, and the actual range between each virtual detection line is deposited in system; 3., the speed of a motor vehicle is calculated: scene is taken and obtained the image of successive frame on the spot and analyzes successively by frame number size, calculate the pixel value difference of vehicle target and current virtual detection line in each two field picture; Select minimum and two two field pictures based on different virtual detection line of pixel value difference absolute value, and according to its poor speed that calculates vehicle target of actual range and frame number between corresponding virtual detection line respectively.The present invention adopts Video Analysis Technology, greatly reduces system cost, and has improved the stability of system simultaneously.But defect and the deficiency of this technology are: need on the separatrix in adjacent section, to calibrate actual detection line on the spot at the scene, therefore, calibration process need to be suspended normal road traffic operation on the spot; Secondly, actual detection line and virtual detection line are discrete form, between detection line, have certain distance, touch on request the situation of detection line for vehicles failed, and this existing method cannot realize accurate Calculation; In addition, this existing method, in the time of the final calculating speed of a motor vehicle, in fact only utilizes two width two field pictures to calculate, and therefore, can only obtain the average velocity of vehicle between two two field pictures, if two two field picture interval times are longer, the method can produce larger measuring error.Finally, the method also cannot realize the real-time location to vehicle.
Summary of the invention
The present invention is directed to prior art above shortcomings, propose a kind of vehicle location and vehicle speed measurement method based on vehicle dynamic video features, can solve that traditional speed-measuring method equipment calibration is loaded down with trivial details, Measurement Algorithm is complicated, false drop rate is high, accuracy is low, real-time is poor and the problem such as hardware installation deployment cost height.
The present invention is achieved by the following technical solutions: the present invention is according to the dynamic video characteristic parameter of the vehicle extracting from demarcate vehicle driving process video image, vehicle dynamic characteristics of image size in random time section inner video image in same video monitoring system is judged to the dynamic video characteristic model of reconstruct the reduction to be measured Vehicle Driving Cycle process corresponding with each picture frame; Then by the dynamic variation characteristic of characteristics of image size and the mapping relations of actual vehicle kinematic parameter of vehicle to be measured, calculate physical location corresponding with each picture frame in Vehicle Driving Cycle process to be measured and vehicle speed value sequence, realize obtaining of vehicle physical location and travel speed information.
Described demarcation vehicle refers to: one has notable feature width, the motor vehicles that just pick-up lens drawn near in road traffic video monitoring system overlay area or from the close-by examples to those far off at the uniform velocity exercising.
The dynamic video characteristic parameter of the described vehicle extracting obtains in the following manner: utilize and demarcate the video image recording when vehicle is just drawing near to video monitoring system or from the close-by examples to those far off at the uniform velocity travelling, measure and record characteristics of image width and the actual motion state parameter sequence information of demarcating vehicle, and utilize the relation of vehicle dynamic video features parameter and characteristics of image size, obtain the dynamic video characteristic parameter of vehicle, characterize vehicle draw near or driving process from the close-by examples to those far off in sequence of image frames in, same characteristics of image width dimensions changes from small to big or the characteristic parameter of rule characteristic from large to small.
Described extraction is specially: record video image in whole driving process and the actual motion state parameter sequence with the demarcation vehicle that in video image, each picture frame is corresponding, be the physical location of vehicle and the information sequence of vehicle speed value, carry out resolving inversely by the characteristics of image size to demarcating vehicle in video frame image and actual motion state parameter sequence and obtained.
Described vehicle dynamic video features parameter and the relation of characteristics of image size refer to: L
u=(c
1+ c
2u) b, wherein: c
1and c
2for dynamic video characteristic parameter, L
ube respectively characteristics of image size and the physical size value of vehicle characteristics width with b, u is the horizontal ordinate average of vehicle characteristics width in image coordinate system, L
uwith u taking pixel as unit; Under right-handed coordinate system,
Wherein: P
w0=(X
w0, Y
w0, Z
w0) be the coordinate of a certain demarcation reference point in the coordinate system of road surface, its coordinate in camera coordinate system is P
c0=(X
c0, Y
c0, Z
c0), f is focal length of camera, and β is the video camera angle of pitch, and dX and dY are respectively level and the vertical resolution of video monitoring system, P
0=(u
0, v
0) be video system image coordinate system origin.
Described resolving inversely refers to: according to the vehicle image characteristic dimension in the physical size value b of the vehicle characteristics width of known demarcation vehicle and minimum two two field pictures and vehicle characteristics width images horizontal ordinate average composition sequence to (L
u1, u
1), (L
u2, u
2) ... (L
ui, u
i) ... (L
un, u
n), n>=2, and can obtain dynamic video characteristic parameter c in the relation of substitution vehicle dynamic video features parameter and characteristics of image size
1and c
2; In the time that uncalibrated image number of frames used is greater than 2, when n>2, preferably adopt least square method to obtain dynamic video characteristic parameter c
1and c
2.
Described vehicle characteristics width includes but not limited to: it is known and be not less than a certain characteristic width meeting the demands on the width of the carbody of 1.5 meters or car body that Width is parallel to camera system focal plane, size.
Described judgement refers to: the dynamic video characteristic parameter that utilizes vehicle, judge the dynamic image characteristic dimension of other vehicles in the interior picture frame of random time section in same video monitoring system, be specially: by the pixel value of whole landscape images characteristic widths of all picture frames in comparative analysis random time section video image and the departure degree of the dynamic video feature of vehicle whether within pre-set threshold value, if satisfied judge the dynamic image characteristic dimension that the pixel value of associated picture characteristic width is vehicle to be measured, and according to the corresponding vehicle to be measured of local area search algorithm identified, the vehicle dynamic characteristics of image dimension information sequence being simultaneously identified in document image frame sequence, be designated as
Described dynamic video characteristic model refers to:
wherein:
and b
xbe respectively characteristics of image size and the actual characteristic width dimensions value of vehicle to be measured in every frame video image, d
xfor a certain demarcation reference point P in the coordinate system of road surface
w0the air line distance of the physical location to the to be measured vehicle corresponding with picture frame in the coordinate system of road surface, and note away from camera direction for just.
Described reconstruct refers to:
A), according to the equal value sequence of vehicle characteristics width images horizontal ordinate to be measured, calculate and demarcate vehicle corresponding video frame images characteristic dimension reference sequences under the equal value sequence of same characteristic features width images horizontal ordinate by vehicle dynamic video features parameter and the relation of characteristics of image size;
B) by the linear ratio relation of movement images characteristic dimension reference sequences and vehicle image characteristic dimension sequence to be measured, calculate vehicle characteristics width physical size b to be measured
xwith demarcation vehicle characteristic width physical size b
0scale-up factor λ, thereby calculate vehicle characteristics width physical size b to be measured
x=λ b
0.
Described reduction refers to:
I) by vehicle, the mathematical model relation between the physical location in the coordinate system of road surface and corresponding video frame image characteristic dimension is deformed into:
wherein: c
3=Z
c0dY, c
4=-sin (β) dY;
Ii) characteristics of image size and the actual position information sequence of vehicle will be demarcated
substitution respectively
utilize least square method to solve parameter c
3and c
4, wherein:
refer to and demarcate the corresponding vehicle image characteristic dimension of vehicle i two field picture, d
0irefer to and in the coordinate system of road surface, demarcate the corresponding physical location of vehicle i two field picture;
Iii) right
carry out algebraic transformation and obtain relational expression:
by c
3and c
4again substitution above-mentioned relation formula, obtains in Vehicle Driving Cycle process to be measured characteristics of image size about the behavioral characteristics model of vehicle actual position information.
Described mapping relations refer to:
wherein: v
tfor the actual vehicle speed of vehicle to be measured,
for the characteristics of image size changing rate of vehicle to be measured.
Physical location and vehicle speed value sequence corresponding with each picture frame in described calculating Vehicle Driving Cycle process to be measured refer to: the note video system sampling period is T
e, frame of video speed is f
q,
the average speed of any two interframe is expressed as:
the average image feature size variations rate between any two frames is expressed as:
the average image characteristic dimension between any two frames is expressed as:
wherein: κ is the average image characteristic dimension weight coefficient, and κ ∈ (0,1) belongs to velocity-measuring system constant.According to relational expression
and relational expression
in Vehicle Driving Cycle process to be measured, be shown corresponding to physical location and the speedometer of any video frame image:
Successively that video frame image is corresponding
with
substitution above formula, can obtain to be measured vehicle physical location and the vehicle speed value sequence corresponding with video frame image.
According to actual needs, above-mentioned location and vehicle speed measurement method both can be demarcated in advance to road traffic video monitoring system, realize the online of video image processed in real time, also can demarcate video monitoring system afterwards, realize demarcating the off-line analysis of front video data, can meet by needs online or that offline mode is measured.
Technique effect
Compared with prior art, technique effect of the present invention comprises:
First, compared with traditional speed-measuring method, the invention belongs to a kind of noncontact Non-Destructive Testing and measuring method based on vehicle dynamic video features, the scope that tests the speed is wide, detect contain much information, accuracy and robustness is high, fast response time, metering system are easy, without additional firmware cost, support online and off-line is double mode.The present invention only needs to utilize the hardware of existing road traffic video monitoring system can realize easily online measurement in real time or off-line analysis calculating, reduce technology and possessed cost, be easy to apply, and, the method without pavement construction, can not affect traffic, be easy to Installation and Debugging and maintenance.
Secondly, compared with current existing video measuring method, the present invention has set up the mathematical model of vehicle image characteristic dimension in video image frame sequence and variation characteristic and vehicle physical location and speed by the dynamic video feature of research vehicle, take full advantage of the mutual restriction relation of same vehicle characteristics width Pixel Dimensions in multiple image, do not reducing under the prerequisite of measuring accuracy, strengthen the accuracy of vehicle identification, improved the efficiency of tracking measurement; Only need single camera to complete and test the speed, camera performance and picture quality are not had to particular/special requirement simultaneously yet; Vehicle characteristics width is chosen flexibly and easily, without the true three-dimension volume coordinate of estimating single unique point in video image, has reduced the system error factor of measuring; Directly adopt two-dimensional coordinate mapping calculation method, reduced algorithm complexity, alleviated calculated amount, improved response speed; In addition, the detailed movement process status parameter including vehicle movement track and speed that this method can be in larger road surface scope be obtained vehicle section continuous time, the quantity of information of measurement is abundant.
Brief description of the drawings
Fig. 1 the present invention relates to a kind of vehicle location based on vehicle dynamic video features and the overall flow figure of vehicle speed measurement method;
Fig. 2 is the process flow diagram that the present invention relates to measure in vehicle location and vehicle speed measurement method the preferred embodiment of calculating.
Embodiment
Below embodiments of the invention are elaborated, the present embodiment is implemented under taking technical solution of the present invention as prerequisite, provided detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following embodiment.
Embodiment 1
As shown in Figure 1, the present embodiment relates to a kind of vehicle location based on vehicle dynamic video features and vehicle speed measurement method comprise utilize demarcate vehicle obtain vehicle dynamic video features parameter, utilize video behavioral characteristics fast identification vehicle to be measured, reduce vehicle dynamic characteristic model to be measured and vehicle location and speed and calculate four steps, it is specifically respectively:
Vehicle driving process data acquisition vehicle dynamic video features parameter is demarcated in the first step, utilization: drive a demarcation vehicle and just the pick-up lens of road traffic video monitoring system is drawn near and at the uniform velocity exercised, the characteristics of image size of vehicle and vehicle actual motion state parameter sequence information in record video image frame, and utilize the relation of vehicle dynamic video features parameter and characteristics of image size, obtain vehicle dynamic video features parameter.
Preferably, selecting width of the carbody is 2.0 meters, and the significant motor vehicles of width characteristics are as demarcating vehicle.In the region, road surface apart within the scope of 1 meter, video camera, set and demarcate reference point.Demarcate on vehicle and be equipped with laser range finder, the actual range of measuring vehicle relative Calibration reference point in real time.On vehicle, be equipped with data transmission device, can pass in real time the distance of Vehicle Driving Cycle and vehicle speed data back measurement server.Drive and demarcate vehicle along a track to pick-up lens just, draw near and at the uniform velocity exercise with the speed of a motor vehicle of 30km/h, guarantee that, in road traffic video monitoring system overlay area, vehicle characteristics width video image is all clear and legible simultaneously.Record and demarcate the video frame image of vehicle in whole driving process and the vehicle physical location corresponding with every two field picture and the information sequence of vehicle speed value, be designated as { (d
0i, v
0i) | i>=3}.
According to vehicle, drawing near in sequence of image frames, the rule characteristic that same characteristics of image width dimensions changes from small to big is set up the relation of vehicle dynamic video features parameter and characteristics of image size: L
u=(c
1+ c
2u) b, wherein: c
1and c
2for vehicle dynamic video features parameter, L
ube respectively characteristics of image size and the physical size value of vehicle characteristics width with b, u is the horizontal ordinate average of vehicle characteristics width in image coordinate system, L
uwith u taking pixel as unit.Adopt right-handed coordinate system, bidding is determined the coordinate of reference point in the coordinate system of road surface and is: P
w0=(X
w0, Y
w0, Z
w0), its coordinate in camera coordinate system is P
c0=(X
c0, Y
c0, Z
c0), focal length of camera is f, and the level of video monitoring system and vertically resolution are respectively dX and dY, and video system image coordinate system origin is P
0=(u
0, v
0), the video camera angle of pitch is β, vehicle dynamic video features Parametric Representation is:
Wherein: X
c0, Z
c0, f, dX, dY, u
0, β is system constants.
According to known vehicle characteristics width physical size value b, and choose vehicle image characteristic dimension and the equal value sequence pair of vehicle characteristics width images horizontal ordinate in any five two field pictures: (L
u1, u
1), (L
u2, u
2) ... (L
ui, u
i) ... (L
un, u
n), n=5.Then, the relation by the parameter value sequence measuring to substitution vehicle dynamic video features parameter and characteristics of image size, adopts least square method to obtain vehicle dynamic video features parameter c
1and c
2.
Second step, utilize and demarcate vehicle dynamic video feature and identify vehicle to be measured: first, utilize gradient operator scan and obtain in section video sometime the pixel value of whole landscape images characteristic widths in all picture frames.Then, set up according to the pixel value of characteristics of image width and the ascending ordinal relation of characteristic width image horizontal ordinate average the sequence of pixel values pair that the some groups of pixel values by characteristics of image width and characteristic width image horizontal ordinate average form.Choose any group of sequence of pixel values pair, the demarcation vehicle dynamic video feature that vehicle characteristics width pixel value wherein and the equal value sequence of image horizontal ordinate are obtained the substitution first step successively, the characteristics of image size that calculates vehicle to be measured with respect to the pixel linear change rate deviation of the image horizontal ordinate average of vehicle image characteristic dimension whether 0.01 pixel than within.If satisfied judge the dynamic image characteristic dimension that the pixel value of associated picture characteristic width is vehicle to be measured, meanwhile, vehicle count device to be measured increases by 1; Choose next group sequence of pixel values if do not meet to carrying out operational analysis, judge until complete the analysis of all sequence of pixel values logarithm value groups.
Obtain after the dynamic image characteristic dimension of vehicle, centered by the mid point by characteristics of image width, in the regional area that 0.75 times of characteristics of image size is radius, adopt sobel operator to search for and identify corresponding vehicle to be measured, the vehicle dynamic characteristics of image dimension information sequence being simultaneously identified in recording of video frame sequence, is designated as
The 3rd step, the vehicle dynamic video features model to be measured that reduces: the mathematical model relation between the physical location according to vehicle in the coordinate system of road surface and corresponding video frame image characteristic dimension is set up vehicle dynamic video features model:
wherein:
and b
xbe respectively vehicle to be measured characteristics of image size and actual characteristic width dimensions value in every frame video image, d
xfor a certain demarcation reference point P in the coordinate system of road surface
w0the air line distance of the physical location to the to be measured vehicle corresponding with picture frame in the coordinate system of road surface, and note away from camera direction for just.Then, successively the dynamic image characteristic dimension information sequence of all vehicles to be measured of having identified in second step and vehicle dynamic video features are compared and computational analysis, reduce the behavioral characteristics model of all Vehicle Driving Cycle processes to be measured, concrete grammar is as follows:
A), according to the equal value sequence of vehicle characteristics width images horizontal ordinate to be measured, calculate and demarcate vehicle corresponding video frame images characteristic dimension reference sequences under the equal value sequence of same characteristic features width images horizontal ordinate by vehicle dynamic video features parameter and the relation of characteristics of image size;
B) by the linear ratio relation of movement images characteristic dimension reference sequences and vehicle image characteristic dimension sequence to be measured, calculate vehicle characteristics width physical size b to be measured
xwith demarcation vehicle characteristic width physical size b
0scale-up factor λ, thereby calculate vehicle characteristics width physical size b to be measured
x=λ b
0;
C) by vehicle, in the physical location in the coordinate system of road surface and corresponding diagram picture frame, the mathematical model relation between characteristics of image size is deformed into:
wherein: c
3=Z
c0dY, c
4=-sin (β) dY;
D) by all vehicle image characteristic dimensions and the actual position information sequence that record in the first step
substitution respectively
adopt least square method to obtain parameter c
3and c
4, wherein: d
0ifor demarcate the corresponding physical location of vehicle i two field picture in the coordinate system of road surface,
for demarcating the corresponding vehicle image characteristic dimension of vehicle i two field picture;
E) right
carry out algebraic transformation and obtain relational expression:
by c
3and c
4again substitution above-mentioned relation formula, obtains in Vehicle Driving Cycle process to be measured characteristics of image size about the behavioral characteristics model of vehicle actual position information.
The 4th step, calculating vehicle physical location and speed: utilize vehicle dynamic video features model and the frame of video speed of in the 3rd step, reducing, the mapping relations of characteristics of image size dynamic variation characteristic and actual vehicle kinematic parameter by vehicle to be measured, calculate physical location corresponding with each video frame image in Vehicle Driving Cycle process to be measured and vehicle speed value sequence.
The mapping relations of setting up characteristics of image size dynamic variation characteristic and actual vehicle kinematic parameter, are specifically expressed as:
wherein, v
tfor the actual vehicle speed of vehicle to be measured,
for the characteristics of image size changing rate of vehicle to be measured.The note video system sampling period is T
e, frame of video speed is f
q,
the average speed of any two interframe is expressed as:
the average image feature size variations rate between any two frames is expressed as:
the average image characteristic dimension between any two frames is expressed as:
wherein, be averaged characteristics of image size weight coefficient κ=0.5.According to co-relation, set up in Vehicle Driving Cycle process to be measured corresponding to the physical location of video frame image and the mathematical relation of the speed of a motor vehicle arbitrarily, be specifically expressed as:
Successively that video frame image is corresponding
with
substitution above formula, obtains to be measured vehicle physical location and the vehicle speed value sequence corresponding with video frame image.Finally, draw vehicle driving trace figure to be measured and speed of a motor vehicle change curve according to vehicle physical location and vehicle speed value sequence.
Like this, first the present embodiment preferred embodiment solves vehicle dynamic video features parameter by demarcating vehicle frame of video image and driving process data; Then, utilize vehicle dynamic video features to complete and treat the Tracking Recognition of surveying vehicle, finally restore vehicle dynamic video features model to be measured, and then calculate the physical location of motor vehicles relative Calibration reference point to be measured and exercise the speed of a motor vehicle.So the present embodiment is both without high, the baroque hardware device of setup cost as classic method, catch and the coordinate mapping calculation speed of a motor vehicle without simple dependence image characteristic point as existing video frequency speed-measuring method again, on the one hand greatly reduce system cost, improved on the other hand video measuring method accuracy, reduced computation complexity, improved the robustness of measuring system simultaneously.
As shown in Figure 2, particular flow sheet when it is implemented for preferred embodiment is actual, it merges above-mentioned preferred steps therein.
Claims (12)
1. vehicle location and the vehicle speed measurement method based on vehicle dynamic video features, it is characterized in that, according to the dynamic video characteristic parameter of the vehicle extracting from the driving process video image of demarcating vehicle, vehicle dynamic characteristics of image size in random time section inner video image in same video monitoring system is judged to the dynamic video characteristic model of reconstruct the reduction to be measured Vehicle Driving Cycle process corresponding with each picture frame; Then by the dynamic variation characteristic of characteristics of image size and the mapping relations of actual vehicle kinematic parameter of vehicle to be measured, calculate physical location corresponding with each picture frame in Vehicle Driving Cycle process to be measured and vehicle speed value sequence, realize obtaining of vehicle physical location and travel speed information;
Described demarcation vehicle refers to: one has notable feature width, the motor vehicles that just pick-up lens drawn near in road traffic video monitoring system overlay area or from the close-by examples to those far off at the uniform velocity exercising.
2. method according to claim 1, it is characterized in that, the dynamic video characteristic parameter of the described vehicle extracting obtains in the following manner: utilize and demarcate the video image recording when vehicle is just drawing near to video monitoring system or from the close-by examples to those far off at the uniform velocity travelling, measure and record characteristics of image width and the actual motion state parameter sequence information of demarcating vehicle, and utilize the relation of vehicle dynamic video features parameter and characteristics of image size, obtain the dynamic video characteristic parameter of vehicle, characterize vehicle draw near or driving process from the close-by examples to those far off in sequence of image frames in, same characteristics of image width dimensions changes from small to big or the characteristic parameter of rule characteristic from large to small.
3. method according to claim 1, it is characterized in that, described extraction is specially: record video image in whole driving process and the actual motion state parameter sequence with the demarcation vehicle that in video image, each picture frame is corresponding, be the physical location of vehicle and the information sequence of vehicle speed value, carry out resolving inversely by the characteristics of image size to demarcating vehicle in video frame image and actual motion state parameter sequence and obtained.
4. method according to claim 2, is characterized in that, described vehicle dynamic video features parameter and the relation of characteristics of image size refer to: L
u=(c
1+ c
2u) b, wherein: c
1and c
2for dynamic video characteristic parameter, L
ube respectively characteristics of image size and the physical size value of vehicle characteristics width with b, u is the horizontal ordinate average of vehicle characteristics width in image coordinate system, L
uwith u taking pixel as unit; Under right-handed coordinate system,
wherein: P
w0=(X
w0, Y
w0, Z
w0) be the coordinate of a certain demarcation reference point in the coordinate system of road surface, its coordinate in camera coordinate system is P
c0=(X
c0, Y
c0, Z
c0), f is focal length of camera, and β is the video camera angle of pitch, and dX and dY are respectively level and the vertical resolution of video monitoring system, P
0=(u
0, v
0) be video system image coordinate system origin.
5. method according to claim 3, it is characterized in that, described resolving inversely refers to: the sequence pair according to the vehicle image characteristic dimension in the physical size value b of the vehicle characteristics width of known demarcation vehicle and minimum two two field pictures and vehicle characteristics width images horizontal ordinate average composition: (L
u1, u
1), (L
u2, u
2) ... (L
ui, u
i) ... (L
un, u
n), n>=2, can obtain dynamic video characteristic parameter c in the relation of substitution vehicle dynamic video features parameter and characteristics of image size
1and c
2; In the time that uncalibrated image number of frames used is greater than 2, when n>2, preferably adopt least square method to obtain dynamic video characteristic parameter c
1and c
2.
6. according to the method described in claim 4 or 5, it is characterized in that, described vehicle characteristics width refers to: it is known and be not less than a certain characteristic width meeting the demands on the width of the carbody of 1.5 meters or car body that Width is parallel to camera system focal plane, size.
7. method according to claim 1, it is characterized in that, described judgement refers to: the dynamic video characteristic parameter that utilizes vehicle, judge the dynamic image characteristic dimension of other vehicles in the interior picture frame of random time section in same video monitoring system, be specially: by the pixel value of whole landscape images characteristic widths of all picture frames in comparative analysis random time section video image and the departure degree of the dynamic video feature of vehicle whether within pre-set threshold value, if satisfied judge the dynamic image characteristic dimension that the pixel value of associated picture characteristic width is vehicle to be measured, and according to the corresponding vehicle to be measured of local area search algorithm identified, the vehicle dynamic characteristics of image dimension information sequence being simultaneously identified in document image frame sequence, be designated as
8. method according to claim 1, is characterized in that, described dynamic video characteristic model refers to:
wherein:
and b
xbe respectively characteristics of image size and the actual characteristic width dimensions value of vehicle to be measured in every frame video image, d
xfor a certain demarcation reference point P in the coordinate system of road surface
w0the air line distance of the physical location to the to be measured vehicle corresponding with picture frame in the coordinate system of road surface, and note away from camera direction for just.
9. method according to claim 1, is characterized in that, described reconstruct refers to:
A), according to the equal value sequence of vehicle characteristics width images horizontal ordinate to be measured, calculate and demarcate vehicle corresponding video frame images characteristic dimension reference sequences under the equal value sequence of same characteristic features width images horizontal ordinate by vehicle dynamic video features parameter and the relation of characteristics of image size;
B) by the linear ratio relation of movement images characteristic dimension reference sequences and vehicle image characteristic dimension sequence to be measured, calculate vehicle characteristics width physical size b to be measured
xwith demarcation vehicle characteristic width physical size b
0scale-up factor λ, thereby calculate vehicle characteristics width physical size b to be measured
x=λ b
0.
10. method according to claim 1, is characterized in that, described reduction refers to:
I) by vehicle, the mathematical model relation between the physical location in the coordinate system of road surface and corresponding video frame image characteristic dimension is deformed into:
wherein: c
3=Z
c0dY, c
4=-sin (β) dY;
Ii) characteristics of image size and the actual position information sequence of vehicle will be demarcated
substitution respectively
utilize least square method to obtain parameter c
3and c
4, wherein:
refer to and demarcate the corresponding vehicle image characteristic dimension of vehicle i two field picture, d
0irefer to and in the coordinate system of road surface, demarcate the corresponding physical location of vehicle i two field picture;
Iii) right
carry out algebraic transformation and obtain relational expression:
by c
3and c
4again substitution above-mentioned relation formula, obtains in Vehicle Driving Cycle process to be measured characteristics of image size about the behavioral characteristics model of vehicle actual position information.
11. methods according to claim 1, is characterized in that, described mapping relations refer to:
wherein: v
tfor the actual vehicle speed of vehicle to be measured,
for the characteristics of image size changing rate of vehicle to be measured.
12. methods according to claim 1, is characterized in that, physical location and vehicle speed value sequence corresponding with each picture frame in described calculating Vehicle Driving Cycle process to be measured refer to: the note video system sampling period is T
e, frame of video speed is f
q,
the average speed of any two interframe is expressed as:
the average image feature size variations rate between any two frames is expressed as:
the average image characteristic dimension between any two frames is expressed as:
wherein: κ is the average image characteristic dimension weight coefficient, and κ ∈ (0,1) belongs to velocity-measuring system constant.According to relational expression
and relational expression
in Vehicle Driving Cycle process to be measured, be shown corresponding to physical location and the speedometer of any video frame image:
Successively that video frame image is corresponding
with
substitution above formula, can obtain to be measured vehicle physical location and the vehicle speed value sequence corresponding with video frame image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410293044.8A CN104021676B (en) | 2014-06-25 | 2014-06-25 | Vehicle location based on vehicle dynamic video features and vehicle speed measurement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410293044.8A CN104021676B (en) | 2014-06-25 | 2014-06-25 | Vehicle location based on vehicle dynamic video features and vehicle speed measurement method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104021676A true CN104021676A (en) | 2014-09-03 |
| CN104021676B CN104021676B (en) | 2016-08-03 |
Family
ID=51438406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410293044.8A Expired - Fee Related CN104021676B (en) | 2014-06-25 | 2014-06-25 | Vehicle location based on vehicle dynamic video features and vehicle speed measurement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104021676B (en) |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268901A (en) * | 2014-09-29 | 2015-01-07 | 深圳市热活力科技有限公司 | High-speed moving object detection processing method and system based on linear array image sensor |
| CN104318782A (en) * | 2014-10-31 | 2015-01-28 | 浙江力石科技股份有限公司 | Expressway video speed measuring method and system for zone overlapping |
| CN104331907A (en) * | 2014-11-10 | 2015-02-04 | 东南大学 | Method for measuring carrier speed based on ORB (Object Request Broker) character detection |
| CN104616559A (en) * | 2014-12-31 | 2015-05-13 | 北京新能源汽车股份有限公司 | System and method for simulating driving of real vehicle |
| CN105205550A (en) * | 2015-09-10 | 2015-12-30 | 浪潮电子信息产业股份有限公司 | Accident probability calculating method and device |
| CN105654060A (en) * | 2016-01-04 | 2016-06-08 | 中海网络科技股份有限公司 | Method for acquiring vehicle speed from road monitoring video |
| CN106204634A (en) * | 2016-06-22 | 2016-12-07 | 廖广军 | A kind of method measuring car speed by monitor video or vehicle-mounted camera |
| CN106503698A (en) * | 2016-12-07 | 2017-03-15 | 哈尔滨工业大学 | A kind of signalized intersections queuing vehicle static state spacing method for rapidly estimating |
| CN106991414A (en) * | 2017-05-17 | 2017-07-28 | 司法部司法鉴定科学技术研究所 | A kind of method that state of motion of vehicle is obtained based on video image |
| CN107292932A (en) * | 2016-04-07 | 2017-10-24 | 上海交通大学 | Head-on video frequency speed-measuring method based on image expansion rate |
| CN107533133A (en) * | 2015-04-22 | 2018-01-02 | 罗伯特·博世有限公司 | For the method and apparatus in the region for monitoring vehicle front |
| CN107845264A (en) * | 2017-12-06 | 2018-03-27 | 西安市交通信息中心 | A kind of volume of traffic acquisition system and method based on video monitoring |
| CN108510732A (en) * | 2018-05-28 | 2018-09-07 | 苏州创存数字科技有限公司 | A kind of walking reminding method and its system based on movement speed materialization |
| CN108877237A (en) * | 2018-07-27 | 2018-11-23 | 长安大学 | Vehicle Speed based on monitor video image integrates resolving system and method |
| CN109167956A (en) * | 2018-05-21 | 2019-01-08 | 同济大学 | The full-bridge face traveling load spatial distribution merged based on dynamic weighing and more video informations monitors system |
| CN109416884A (en) * | 2016-07-05 | 2019-03-01 | 三菱电机株式会社 | Identification region estimating device, identification region presumption method and identification region program for estimating |
| CN109478319A (en) * | 2016-07-11 | 2019-03-15 | 三菱电机株式会社 | Moving image processing apparatus, dynamic image processing method and dynamic image pro cess program |
| CN109686048A (en) * | 2019-01-02 | 2019-04-26 | 平安科技（深圳）有限公司 | Station platform gets over method for early warning, device, computer equipment and the storage medium of line |
| CN109979206A (en) * | 2017-12-28 | 2019-07-05 | 杭州海康威视系统技术有限公司 | Vehicle speed measuring method, device, system, electronic equipment and storage medium |
| CN110446106A (en) * | 2019-06-27 | 2019-11-12 | 驭势（上海）汽车科技有限公司 | A kind of recognition methods, electronic equipment and the storage medium of front camera file |
| CN110850109A (en) * | 2019-11-21 | 2020-02-28 | 中科智云科技有限公司 | Method for measuring vehicle speed based on fuzzy image |
| CN111177297A (en) * | 2019-12-31 | 2020-05-19 | 信阳师范学院 | Dynamic target speed calculation optimization method based on video and GIS |
| CN111276007A (en) * | 2020-01-20 | 2020-06-12 | 深圳市廿年科技有限公司 | Method for positioning and navigating automobile in parking lot through camera |
| CN111583669A (en) * | 2019-02-15 | 2020-08-25 | 杭州海康威视数字技术股份有限公司 | Overspeed detection method, overspeed detection device, control equipment and storage medium |
| CN112115739A (en) * | 2019-06-19 | 2020-12-22 | 北京地平线机器人技术研发有限公司 | Vehicle state quantity information acquisition method and device |
| CN112466121A (en) * | 2020-12-12 | 2021-03-09 | 江西洪都航空工业集团有限责任公司 | Speed measuring method based on video |
| CN112785855A (en) * | 2021-01-26 | 2021-05-11 | 张俊峰 | Method for acquiring vehicle speed from road monitoring video |
| CN113096407A (en) * | 2021-02-27 | 2021-07-09 | 惠州华阳通用电子有限公司 | Height-limiting channel vehicle anti-collision method and device |
| CN116884235A (en) * | 2023-08-09 | 2023-10-13 | 广东省交通运输规划研究中心 | Video vehicle speed detection method, device and equipment based on wire collision and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU197621U1 (en) * | 2019-10-17 | 2020-05-18 | Акционерное общество "ЭЛВИС-НеоТек" | Vehicle speed measuring device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003052457A2 (en) * | 2001-12-14 | 2003-06-26 | Kapsch Trafficcom Ag | Method and device for the geometric measurement and speed determination of vehicles |
| CN1963884A (en) * | 2006-12-13 | 2007-05-16 | 王海燕 | Method and system of video frequency velometer |
| CN102254318A (en) * | 2011-04-08 | 2011-11-23 | 上海交通大学 | Method for measuring speed through vehicle road traffic videos based on image perspective projection transformation |
| CN102867416A (en) * | 2012-09-13 | 2013-01-09 | 中国科学院自动化研究所 | Vehicle part feature-based vehicle detection and tracking method |
-
2014
- 2014-06-25 CN CN201410293044.8A patent/CN104021676B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003052457A2 (en) * | 2001-12-14 | 2003-06-26 | Kapsch Trafficcom Ag | Method and device for the geometric measurement and speed determination of vehicles |
| CN1963884A (en) * | 2006-12-13 | 2007-05-16 | 王海燕 | Method and system of video frequency velometer |
| CN102254318A (en) * | 2011-04-08 | 2011-11-23 | 上海交通大学 | Method for measuring speed through vehicle road traffic videos based on image perspective projection transformation |
| CN102867416A (en) * | 2012-09-13 | 2013-01-09 | 中国科学院自动化研究所 | Vehicle part feature-based vehicle detection and tracking method |
Non-Patent Citations (1)
| Title |
|---|
| 韩学源，金先龙，张晓云: "基于视频图像与直线线性变换理论的车辆运动信息重构", 《汽车工程》 * |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268901A (en) * | 2014-09-29 | 2015-01-07 | 深圳市热活力科技有限公司 | High-speed moving object detection processing method and system based on linear array image sensor |
| CN104268901B (en) * | 2014-09-29 | 2018-11-02 | 东莞市天蓝智能装备有限公司 | High-speed moving object detection process method and system based on line scan image sensor |
| CN104318782A (en) * | 2014-10-31 | 2015-01-28 | 浙江力石科技股份有限公司 | Expressway video speed measuring method and system for zone overlapping |
| CN104331907A (en) * | 2014-11-10 | 2015-02-04 | 东南大学 | Method for measuring carrier speed based on ORB (Object Request Broker) character detection |
| CN104331907B (en) * | 2014-11-10 | 2018-03-16 | 东南大学 | A kind of method based on ORB feature detections measurement bearer rate |
| CN104616559A (en) * | 2014-12-31 | 2015-05-13 | 北京新能源汽车股份有限公司 | System and method for simulating driving of real vehicle |
| CN107533133A (en) * | 2015-04-22 | 2018-01-02 | 罗伯特·博世有限公司 | For the method and apparatus in the region for monitoring vehicle front |
| CN107533133B (en) * | 2015-04-22 | 2021-09-07 | 罗伯特·博世有限公司 | Method and device for monitoring an area in front of a vehicle |
| CN105205550A (en) * | 2015-09-10 | 2015-12-30 | 浪潮电子信息产业股份有限公司 | Accident probability calculating method and device |
| CN105654060A (en) * | 2016-01-04 | 2016-06-08 | 中海网络科技股份有限公司 | Method for acquiring vehicle speed from road monitoring video |
| CN107292932A (en) * | 2016-04-07 | 2017-10-24 | 上海交通大学 | Head-on video frequency speed-measuring method based on image expansion rate |
| CN107292932B (en) * | 2016-04-07 | 2020-06-09 | 上海交通大学 | Head-on video speed measurement method based on image expansion rate |
| CN106204634A (en) * | 2016-06-22 | 2016-12-07 | 廖广军 | A kind of method measuring car speed by monitor video or vehicle-mounted camera |
| CN106204634B (en) * | 2016-06-22 | 2019-07-09 | 广东警官学院 | A method of car speed is measured by monitor video or vehicle-mounted camera |
| CN109416884B (en) * | 2016-07-05 | 2021-02-19 | 三菱电机株式会社 | Identification region estimation device, identification region estimation method, and identification region estimation program |
| CN109416884A (en) * | 2016-07-05 | 2019-03-01 | 三菱电机株式会社 | Identification region estimating device, identification region presumption method and identification region program for estimating |
| CN109478319A (en) * | 2016-07-11 | 2019-03-15 | 三菱电机株式会社 | Moving image processing apparatus, dynamic image processing method and dynamic image pro cess program |
| CN106503698A (en) * | 2016-12-07 | 2017-03-15 | 哈尔滨工业大学 | A kind of signalized intersections queuing vehicle static state spacing method for rapidly estimating |
| CN106503698B (en) * | 2016-12-07 | 2019-08-02 | 哈尔滨工业大学 | A kind of signalized intersections queuing vehicle static state spacing method for rapidly estimating |
| CN106991414A (en) * | 2017-05-17 | 2017-07-28 | 司法部司法鉴定科学技术研究所 | A kind of method that state of motion of vehicle is obtained based on video image |
| CN107845264A (en) * | 2017-12-06 | 2018-03-27 | 西安市交通信息中心 | A kind of volume of traffic acquisition system and method based on video monitoring |
| CN109979206A (en) * | 2017-12-28 | 2019-07-05 | 杭州海康威视系统技术有限公司 | Vehicle speed measuring method, device, system, electronic equipment and storage medium |
| CN109167956A (en) * | 2018-05-21 | 2019-01-08 | 同济大学 | The full-bridge face traveling load spatial distribution merged based on dynamic weighing and more video informations monitors system |
| CN109167956B (en) * | 2018-05-21 | 2021-02-02 | 同济大学 | Full-bridge surface moving load spatial distribution monitoring system |
| CN108510732A (en) * | 2018-05-28 | 2018-09-07 | 苏州创存数字科技有限公司 | A kind of walking reminding method and its system based on movement speed materialization |
| CN108510732B (en) * | 2018-05-28 | 2021-07-02 | 合肥曌云科技有限公司 | Walking prompting method and system based on moving speed concretization |
| CN108877237A (en) * | 2018-07-27 | 2018-11-23 | 长安大学 | Vehicle Speed based on monitor video image integrates resolving system and method |
| CN108877237B (en) * | 2018-07-27 | 2020-07-14 | 长安大学 | Vehicle running speed integrated resolving system and method based on monitoring video image |
| CN109686048A (en) * | 2019-01-02 | 2019-04-26 | 平安科技（深圳）有限公司 | Station platform gets over method for early warning, device, computer equipment and the storage medium of line |
| CN111583669A (en) * | 2019-02-15 | 2020-08-25 | 杭州海康威视数字技术股份有限公司 | Overspeed detection method, overspeed detection device, control equipment and storage medium |
| CN111583669B (en) * | 2019-02-15 | 2022-01-07 | 杭州海康威视数字技术股份有限公司 | Overspeed detection method, overspeed detection device, control equipment and storage medium |
| CN112115739A (en) * | 2019-06-19 | 2020-12-22 | 北京地平线机器人技术研发有限公司 | Vehicle state quantity information acquisition method and device |
| CN110446106A (en) * | 2019-06-27 | 2019-11-12 | 驭势（上海）汽车科技有限公司 | A kind of recognition methods, electronic equipment and the storage medium of front camera file |
| CN110446106B (en) * | 2019-06-27 | 2022-01-14 | 驭势（上海）汽车科技有限公司 | Method for identifying front camera file, electronic equipment and storage medium |
| CN110850109A (en) * | 2019-11-21 | 2020-02-28 | 中科智云科技有限公司 | Method for measuring vehicle speed based on fuzzy image |
| CN111177297A (en) * | 2019-12-31 | 2020-05-19 | 信阳师范学院 | Dynamic target speed calculation optimization method based on video and GIS |
| CN111177297B (en) * | 2019-12-31 | 2022-09-02 | 信阳师范学院 | Dynamic target speed calculation optimization method based on video and GIS |
| CN111276007A (en) * | 2020-01-20 | 2020-06-12 | 深圳市廿年科技有限公司 | Method for positioning and navigating automobile in parking lot through camera |
| CN112466121A (en) * | 2020-12-12 | 2021-03-09 | 江西洪都航空工业集团有限责任公司 | Speed measuring method based on video |
| CN112785855A (en) * | 2021-01-26 | 2021-05-11 | 张俊峰 | Method for acquiring vehicle speed from road monitoring video |
| CN113096407A (en) * | 2021-02-27 | 2021-07-09 | 惠州华阳通用电子有限公司 | Height-limiting channel vehicle anti-collision method and device |
| CN116884235A (en) * | 2023-08-09 | 2023-10-13 | 广东省交通运输规划研究中心 | Video vehicle speed detection method, device and equipment based on wire collision and storage medium |
| CN116884235B (en) * | 2023-08-09 | 2024-01-30 | 广东省交通运输规划研究中心 | Video vehicle speed detection method, device and equipment based on wire collision and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104021676B (en) | 2016-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104021676A (en) | Vehicle positioning and speed measuring method based on dynamic video feature of vehicle | |
| CN102254318B (en) | Method for measuring speed through vehicle road traffic videos based on image perspective projection transformation | |
| CN102467821B (en) | Road distance detection method based on video image and apparatus thereof | |
| CN104567708B (en) | Full section of tunnel high speed dynamical health detection means and method based on active panoramic vision | |
| CN103424112B (en) | A kind of motion carrier vision navigation method auxiliary based on laser plane | |
| CN110738121A (en) | front vehicle detection method and detection system | |
| CN104575003B (en) | A kind of vehicle speed detection method based on traffic surveillance videos | |
| CN103686083B (en) | Real-time speed measurement method based on vehicle-mounted sensor video streaming matching | |
| CN103456172A (en) | Traffic parameter measuring method based on videos | |
| CN103176185A (en) | Method and system for detecting road barrier | |
| CN101604448A (en) | A kind of speed-measuring method of moving target and system | |
| CN104361752A (en) | Laser scanning based vehicle type recognition method for free flow charging | |
| CN106091951A (en) | A kind of municipal rail train wheel rim parameter on-line detecting system and method | |
| CN107632308A (en) | A kind of vehicle front barrier profile testing method based on recurrence superposition algorithm | |
| CN102914290A (en) | Metro gauge detecting system and detecting method thereof | |
| CN114170448A (en) | Evaluation method and device for visual perception algorithm | |
| CN103913600A (en) | Device and method for detecting speed measurement errors of speedometer of motor vehicle | |
| CN112455502B (en) | Train positioning method and device based on laser radar | |
| CN103177584B (en) | Vehicle speed detection method based on enumeration probe | |
| CN114758504B (en) | Online vehicle overspeed early warning method and system based on filtering correction | |
| CN104361751A (en) | Laser scanning based vehicle type recognition system for free flow charging | |
| CN103837087A (en) | Automatic pantograph detection method based on active shape model | |
| CN104112305A (en) | Passenger flow monitoring method and apparatus based on dual laser ranging | |
| CN204178554U (en) | A kind of laser scanning model recognition system freely flowing charge | |
| Pan et al. | A novel computer vision‐based monitoring methodology for vehicle‐induced aerodynamic load on noise barrier |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160803 Termination date: 20190625 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |