CN112053572A - Vehicle speed measuring method, device and system based on video and distance grid calibration - Google Patents
Vehicle speed measuring method, device and system based on video and distance grid calibration Download PDFInfo
- Publication number
- CN112053572A CN112053572A CN202010929214.2A CN202010929214A CN112053572A CN 112053572 A CN112053572 A CN 112053572A CN 202010929214 A CN202010929214 A CN 202010929214A CN 112053572 A CN112053572 A CN 112053572A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- video
- detected
- grid
- physical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012544 monitoring process Methods 0.000 claims abstract description 50
- 238000004891 communication Methods 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims description 2
- 238000009434 installation Methods 0.000 abstract description 5
- 238000012423 maintenance Methods 0.000 abstract description 5
- 238000005259 measurement Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 7
- 238000000691 measurement method Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000000827 velocimetry Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a vehicle speed measuring method, equipment and system based on video and distance grid calibration, which comprises the following steps: selecting any frame of road pavement image from the video captured by the road monitoring camera; automatically generating a grid calibration on the image; acquiring any frame of image containing a vehicle; restoring the position of the vehicle on the image to the position on the physical coordinate system by using grid calibration; detecting and tracking vehicles in video images monitored by the camera; restoring the position of the vehicle on each frame of image to the position on the physical coordinate system to obtain the motion track of the vehicle; and obtaining the average speed of the vehicle by adopting minimum mean square error operation. According to the vehicle speed measuring method based on the video and distance grid calibration, provided by the invention, the vehicle speed is measured by directly utilizing the monitoring video of the existing highway monitoring equipment without additionally arranging measuring equipment, and the method can be simultaneously suitable for measuring the speed of the vehicle when the number of vehicles is large, so that the equipment installation and maintenance cost is reduced, and the error is reduced.
Description
Technical Field
The invention relates to the technical field of vehicle speed measuring methods, in particular to a vehicle speed measuring method, device and system based on video and distance grid calibration.
Background
The expressway needs to measure the speed of the running vehicles so as to estimate the driving conditions (congestion degree) of the road, and investigate the violation of regulations such as vehicle overspeed, vehicle over-speed and the like. Common road vehicle speed measurement methods include:
(1) radar speed measurement: traffic police, administrative departments use fixed or mobile radar or laser guns to measure the speed of passing vehicles. The method is based on the Doppler effect, has the advantages of high speed precision and mature technology, but is high in price, a radar gun needs to be additionally installed and maintained on a road, and real-time and wide driving speed perception of each road section of the highway is difficult to form.
(2) An interval velocity measurement method comprises the following steps: and (3) arranging snapshot cameras with license plate recognition capability at a plurality of fixed places, then automatically measuring the time point when the vehicle passes through each place by using the computer system, and obtaining the average vehicle speed of each distance according to the distance divided by the time. The method needs to install a special camera for capturing the license plate number, and cannot utilize the existing highway monitoring equipment.
(3) A coil velocity measurement method: two groups of coils are embedded at certain intervals on a road, a vehicle is sensed when passing through the coils, a time point of passing the point is recorded, and the speed of the distance is obtained according to the distance divided by the time. When a large number of vehicles pass through, the coil does not have the vehicle recognition capability, and a large error may be caused by the sequential change of the passing of the vehicles (for example, the signals of car1 and car2 cannot be distinguished by the coil because the car1 and car2 pass through in sequence at a point a and then the car2 passes before the car1 at a point B, so that time measurement errors are caused, and an error is caused).
In the speed measurement method, whether radar speed measurement, interval speed measurement or coil speed measurement is needed to be added with measurement equipment widely at each section of the highway, which brings higher equipment installation and maintenance cost.
Radar, interval speed measurement and coil speed measurement cannot provide visual road condition perception for people (far less visual than pictures of a monitoring camera). Radar and coil velocity measurement can fail when the number of vehicles is large (relatively congested). For the radar, the radar cannot irradiate the shielded vehicle, so that the speed cannot be measured; for coil velocimetry, the measurement of the coil is disturbed when a plurality of vehicles are pressed continuously over the coil.
The existing highway monitoring equipment (widely arranged highway monitoring cameras) provides data basis and possibility for realizing continuous, wide and low-cost vehicle speed measurement and vehicle running condition monitoring on highway sections.
Disclosure of Invention
The invention provides a vehicle speed measuring method based on video and distance grid calibration, which is not required to be additionally provided with measuring equipment, directly utilizes the monitoring video of the existing highway monitoring equipment to measure the speed of a vehicle, can be simultaneously suitable for measuring the speed of the vehicle when more vehicles exist, reduces the equipment installation and maintenance cost and reduces errors.
The invention adopts the following technical scheme:
a vehicle speed measuring method based on video and distance grid calibration comprises the following steps:
the vehicle speed measuring method based on video and distance grid calibration is characterized by comprising the following steps:
step 2, automatically generating grid calibration on the road pavement image, wherein key reference points in the road pavement image form the top points of the grid, and the physical distance between each row and each column of the grid is measured;
step 3, acquiring any video image monitored by the road monitoring camera containing the vehicle to be detected, and judging whether the position of the vehicle to be detected is in grid calibration or not;
step 4, restoring the position of the vehicle to be detected on the image to the position on the physical coordinate system by utilizing grid calibration, and obtaining a timestamp of the vehicle to be detected at the position;
step 5, detecting and tracking the vehicle to be detected in the video images monitored by the road monitoring camera, and acquiring the video images monitored by the road monitoring camera containing the vehicle to be detected in each frame to obtain the motion track of the vehicle to be detected in the images;
step 6, restoring the position of the vehicle to be detected on each frame of image to the position on the physical coordinate system by utilizing grid calibration to obtain the motion track of the vehicle to be detected under the physical coordinate system;
and 7, obtaining the average speed of the vehicle to be measured by adopting minimum mean square error operation.
Further, the acquiring any frame of the video image monitored by the road monitoring camera including the vehicle to be detected in step 3, and determining whether the position of the vehicle to be detected is in the grid calibration, specifically includes: 3.1: recording the position of an image to be restored containing a vehicle to be detected as T, and recording the position on a corresponding physical coordinate system as T'; 3.2: checking whether T is in the grid calibration, if so, carrying out the next step; if not, the position of the image to be restored containing the vehicle to be detected is not in the range of the grid calibration, the position on the physical coordinate system is unknown, and the frame containing the video image monitored by the road monitoring camera of the vehicle to be detected is discarded.
Further, the step 4 of restoring the position of the vehicle to be measured on the image to the position on the physical coordinate system by using the grid calibration, and obtaining the timestamp of the vehicle to be measured at the position specifically includes: 4.1: acquiring a small quadrangle in the grid where the T is positioned, setting the vertex at the lower left corner as c1, calculating the corresponding physical position of c1 relative to the O point according to the physical distance calibrated by the grid, and recording the physical position as the corresponding physical position
4.2: solving the normalized relative position of T' in the physical square according to the relative position of the small quadrangle of T in the grid, wherein the abscissa of the position is x, and the ordinate is y; 4.3: the position of T 'on the physical coordinate system relative to point O is derived from the normalized relative position of T' on the physical square.
Further, the solving of the normalized relative position of T' in the physical square according to the relative position of T in the small quadrangle in the grid, where the abscissa of the position is x and the ordinate is y, specifically includes:
4.2.1: let the remaining three vertices of the trapezoid in the grid where T is located be c2, c3, and c4 in order
Wherein,
is a vector pointing from c1 to c2,
is a vector pointing from c1 to c 4;
4.2.2: denoting c1 to c3 as
And
linear combinations of (a) with c1 to T as
And
in linear combination, i.e.
The coefficient k is solved from equation 4.2.2-11、k2The coefficients a, b are solved from equation 4.2.2-2;
4.2.3: c1 to c2 are divided into x parts and 1-x parts, and the division point is P; c4 to c3 are divided into x and 1-x parts, and the division point is Q; dividing P to Q into y and 1-y parts, and the division point is T; namely:
from equations 4.2.3-3 and 4.2.2-2
Wherein, let m1＝k1-1,m2＝k2-1, converting equation 4.2.3-4 into
When both m1 and m2 are non-zero, the 1 formula xm in equations 4.2.3-52-2 formula xm1To obtain
ym1＝xm2-am2+bm1 4.2.3-6
Substituting equations 4.2.3-6 into equation 1 in equations 4.2.3-5 yields
m2x2+(bm1-am2+1)x-a＝0 4.2.3-7
The value of x can be solved by the equation 4.2.3-7, and the value of x is substituted into the equation 4.2.3-6 to obtain the value of y;
4.2.4: if the discriminant of equation 4.2.3-7 is less than 0, or the solved abscissa x and ordinate y are not in the range of [0,1], then there is no solution that meets the requirements, and the position on the physical coordinate system cannot be obtained; if there is a solution, the solution with x and y both in the range of [0,1] is retained.
Further, the normalized relative position of T 'in the physical square yields the position of T' in the physical coordinate system with respect to point O, which is formulated as:
the physical position of T' relative to the O point is as follows:
further, in the step 5, in detecting and tracking the vehicle to be detected in the video image monitored by the road monitoring camera, the detection method of the vehicle to be detected includes, but is not limited to, fast R-CNN, SSD, and Yolo, and the tracking algorithm of the vehicle to be detected includes, but is not limited to, a simple IOU tracking method, a tracking method based on a kalman filter, and a tracking method based on a deep learning feature and the kalman filter.
Further, the step 6 of restoring the position of the vehicle to be measured on each frame of image to the position of the vehicle to be measured on the physical coordinate system by using the grid calibration to obtain the motion trajectory of the vehicle to be measured under the physical coordinate system specifically includes: when the vehicle to be detected is located inside the grid calibration, the lower position of the physical coordinate system of the vehicle to be detected and a frame time stamp can be obtained in each frame, the lower position of the physical coordinate system of the vehicle to be detected is set to be S, the frame time stamp is set to be t, and a continuous video monitored by the road monitoring camera forms a motion track of the vehicle to be detected in the physical coordinate system.
Further, the step 7 of obtaining the average speed of the vehicle to be measured by using the minimum mean square error operation specifically includes: the average velocity formula is:
speed of rotation
The average speed of the vehicle to be measured is obtained.
The invention also provides a vehicle speed measuring device calibrated based on the video and distance grid, which comprises a processor, a memory and a communication bus, wherein the communication bus is used for realizing the communication connection between the processor and the memory, one or more computer readable programs are stored in the memory, and the processor reads the one or more computer readable programs stored in the memory to realize the steps of the vehicle speed measuring method calibrated based on the video and distance grid.
The invention also provides a vehicle speed measuring system based on the video and distance grid calibration, which is characterized by comprising a plurality of road monitoring cameras, vehicle speed measuring equipment based on the video and distance grid calibration and a traffic management platform, wherein the vehicle speed measuring equipment based on the video and distance grid calibration acquires video images containing vehicles to be measured from the road monitoring cameras and sends the speed information of the vehicles to be measured to the traffic management platform.
The invention has the beneficial effects that:
(1) calibrating the real-time picture captured by the road monitoring camera and the grid distance of key points on the image; the track of the vehicle in the video image is obtained by detecting and tracking the vehicle in the video image; then, restoring the position on the image to the position on the physical coordinate by utilizing grid calibration to obtain the track of the vehicle under a physical coordinate system; and finally, obtaining a speed estimation value of each vehicle under the minimum mean square error, and reducing the measurement error.
(2) The vehicle speed measurement is directly carried out by utilizing the monitoring video of the existing highway monitoring equipment, other speed measurement equipment does not need to be installed, and the installation and maintenance cost of the equipment is reduced.
(3) The method of the invention utilizes the video shot by the road monitoring camera to measure the speed of the vehicle, when a plurality of vehicles pass through the monitoring picture, the speed can still be measured according to the method of the invention, therefore, the method of the invention is also suitable for measuring the speed of the vehicle when the number of vehicles is large.
Drawings
Fig. 1 is a schematic step diagram of a vehicle speed measurement method based on video and distance grid calibration according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of calibration of a road pavement grid according to a first embodiment of the present invention.
Fig. 3 is a schematic diagram of T in a quadrilateral image coordinate system according to a first embodiment of the invention.
FIG. 4 is a diagram of T' in a square of a physical coordinate system according to a first embodiment of the present invention.
Fig. 5 is a schematic diagram of a curve fitted by a vehicle to be measured under a motion trajectory and a minimum mean square error in a physical coordinate system according to an embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a vehicle speed measuring device based on video and distance grid calibration according to a second embodiment of the present invention.
Fig. 7 is a schematic structural diagram of a vehicle speed measurement system based on video and distance grid calibration according to a second embodiment of the present invention.
In the figure, a processor 41, a memory 42, a communication bus 43, a road monitoring camera 51, a vehicle speed measuring device 52 calibrated based on video and distance grids, and a traffic management platform 53.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, the present invention provides a vehicle speed measurement method based on video and distance grid calibration, which comprises the following steps:
And 2, automatically generating mesh calibration on the road surface image to be monitored, wherein key reference points in the image form the vertexes of the mesh, and the physical distance between each row and each column of the mesh is measured in a known manner.
The system generates the grid calibrations at setup either manually or automatically by a computer program. As shown in fig. 2, there are some key reference points (such as the end points of the road markings and their extensions in the figure) in the image that constitute the vertices of a grid whose physical spacing per row and column is known in advance (e.g., 3.75m of highway width, 6m of solid length, 9m of solid spacing, as shown in fig. 2). The mesh plays a role: and solving the actual physical coordinate position of any point in the grid on the image.
Step 3, acquiring any video image monitored by the road monitoring camera containing the vehicle to be detected, and judging whether the position of the vehicle to be detected is in grid calibration, wherein the method specifically comprises the following steps:
3.1: marking grids as grid, and marking each small quadrangle in the grids as quadi,jWherein, i, j represents the grid of the ith row and the jth column;
3.2: recording the position of an image to be restored containing a vehicle to be detected as T, and recording the position on a corresponding physical coordinate system as T';
3.3: checking whether T is in grid, if yes, performing step 4; if not, the position of the image to be restored containing the vehicle to be detected is not in the range of the grid calibration, the position on the physical coordinate system is unknown, and the frame containing the video image monitored by the road monitoring camera of the vehicle to be detected is discarded.
And 4, restoring the position of the vehicle to be detected on the image to the position on the physical coordinate system by utilizing grid calibration, and obtaining the timestamp of the vehicle to be detected at the position, wherein the method specifically comprises the following steps:
4.1: obtaining a small quadrilateral quad where T is locatedi,jSetting the vertex at the lower left corner as c1, calculating the corresponding physical position of c1 relative to the O point according to the physical distance calibrated by the grid, and recording as
For example, the physical position of the lower left corner of the 3 rd row, 2 nd column grid in fig. 2 is (3.75m,9m +6m) — (3.75m,15 m).
4.2: as shown in FIG. 4, at quad according to Ti,jTo give a solution of T 'in the physical square c'1，c′2，c′3，c′4Wherein the abscissa of the position is x and the ordinate is y.
4.2.1: as shown in FIG. 3, let quadi,jThe other three vertexes are c2, c3 and c4 in sequence, and then the quad is obtainedi,jThe four vertexes of (1) are c1, c2, c3 and c4 in sequence
Wherein,
is a vector pointing from c1 to c2,
is a vector pointing from c1 to c 4;
4.2.2: due to the fact that
And
not collinear in a plane, a linear combination of which can be represented as any vector in that plane, and thus c1 through c3 are represented as
And
the linear combination of (a) and (b),denote c1 to T as
And
in linear combination, i.e.
The coefficient k is solved from equation (4.2.2-1)1、k2The coefficients a, b are solved from equation (4.2.2-2);
4.2.3: x and y represent coordinates of T, c1 to c2 are divided into x and 1-x parts, and the division point is P; c4 to c3 are divided into x and 1-x parts, and the division point is Q; dividing P to Q into y and 1-y parts, and the division point is T; namely:
from equation (4.2.3-1) and equation (4.2.1-1)
From equation (4.2.3-2), equation (4.2.1-2) and equation (4.2.2-1)
From equations (4.2.3-3), (4.2.3-4) and (4.2.3-5)
Compare equation (4.2.3-6) with respect to equation (4.2.2-2)
Is due to
Is a vector consisting of two adjacent sides of a quadrilateral, is linearly independent, and thus is derived from equations (4.2.3-6) and (4.2.2-2)
Wherein, let m1＝k1-1,m2＝k2-1, converting equation (4.2.3-7) to
When m1 and m2 have zero values, (4.2.3-8) can be easily solved; when both m1 and m2 are nonzero, (1) × m in equation (4.2.3-8)2-(2)×m1To obtain
ym1＝xm2-am2+bm1 (4.2.3-9)
Substituting equation (4.2.3-9) into equation (1) in equation (4.2.3-8) yields
m2x2+(bm1-am2+1)x-a＝0 (4.2.3-10)
Equation (4.2.3-10) is a one-dimensional quadratic equation, and the value of x is solved from equation (4.2.3-10) and is substituted into equation (4.2.3-9) to obtain the value of y.
4.2.4: if the discriminant of equation (4.2.3-10) is less than 0, or the solved (x, y) is not in the range of [0,1], it indicates that there is no satisfactory solution and the physical position cannot be obtained; if there is a solution, the solution with x and y both in the range of [0,1] is reserved.
In particular, in practical use, the above process can be implemented programmatically, so that always and only one set (x, y) of solutions lies in the range of [0,1 ].
4.3: according to T 'at physical square c'1，c′2，c′3，c′4The normalized relative position (x, y) of (a) yields the physical position of T' relative to point O.
The physical position of T' relative to the O point is as follows:
and 5, detecting and tracking the vehicle to be detected in the video images monitored by the road monitoring camera, acquiring the video images monitored by the road monitoring camera containing the vehicle to be detected in each frame, and obtaining the motion track of the vehicle to be detected in the images.
The detection method of the vehicle to be detected can be any one common target detection algorithm in the field of computer vision at present, including but not limited to Faster R-CNN, SSD, Yolo and the like; the tracking algorithm of the vehicle to be detected can be a simple IOU tracking method, a tracking method based on a Kalman filter, or a tracking method based on deep learning characteristics and the Kalman filter.
And 6, restoring the position of the vehicle to be detected on each frame of image to the position on the physical coordinate system by utilizing grid calibration to obtain the motion track of the vehicle to be detected under the physical coordinate system.
When the vehicle to be tested is positioned in the grid calibration, the physics of the vehicle to be tested can be obtained in each frameSetting the lower position of a physical coordinate system of a vehicle to be detected as S, setting the frame timestamp as t, and forming a motion track of the vehicle to be detected in the physical coordinate system by a continuous video monitored by a road monitoring camera (S)1，t1),(S2，t2),(S3，t3)…(Si，ti) Wherein i is the number of frames.
And 7, obtaining the average speed of the vehicle to be measured by adopting minimum mean square error operation.
The average velocity formula is:
speed of rotation
The average speed of the vehicle to be measured is obtained.
The beneficial effect of this embodiment does:
(1) calibrating the real-time picture captured by the road monitoring camera and the grid distance of key points on the image; the track of the vehicle in the video image is obtained by detecting and tracking the vehicle in the video image; then, restoring the position on the image to the position on the physical coordinate by utilizing grid calibration to obtain the track of the vehicle under a physical coordinate system; and finally, obtaining a speed estimation value of each vehicle under the minimum mean square error, and reducing the measurement error.
(2) The vehicle speed measurement is directly carried out by utilizing the monitoring video of the existing highway monitoring equipment, other speed measurement equipment does not need to be installed, and the installation and maintenance cost of the equipment is reduced.
(3) The method of the invention utilizes the video shot by the road monitoring camera to measure the speed of the vehicle, when a plurality of vehicles pass through the monitoring picture, the speed can still be measured according to the method of the invention, therefore, the method of the invention is also suitable for measuring the speed of the vehicle when the number of vehicles is large.
Example two
As shown in fig. 6, this embodiment provides a vehicle speed measuring device based on video and distance grid calibration on the basis of the first embodiment, for implementing the vehicle speed measuring method based on video and distance grid calibration of the first embodiment, the device includes a processor 41, a memory 42, and a communication bus 43, where the communication bus 43 is used for implementing a communication connection between the processor 41 and the memory 42, the memory 42 stores one or more computer readable programs, and the processor 41 implements the steps of the vehicle speed measuring method based on video and distance grid calibration as described in the first embodiment by reading the one or more computer readable programs stored in the memory 42. For details, please refer to the description in the first embodiment, which is not repeated herein.
EXAMPLE III
As shown in fig. 7, this embodiment provides a vehicle speed measurement system based on video and distance grid calibration on the basis of the first embodiment, for implementing the vehicle speed measurement method based on video and distance grid calibration in the first embodiment, where the system includes:
a plurality of road monitoring cameras 51 arranged beside the road for collecting traffic video images; the vehicle speed measuring device 52 based on video and distance grid calibration as described in the second embodiment is used for implementing the steps of the vehicle speed measuring method based on video and distance grid calibration in the first embodiment; a traffic management platform 53 is also included.
The vehicle speed measuring device 52 based on video and distance grid calibration obtains a video image containing a vehicle to be measured from the configured road monitoring camera 51 in real time, automatically detects the running speed of the vehicle to be measured in the image, and sends the vehicle speed information to the traffic management platform 53.
The vehicle speed measuring device 52 based on video and distance grid calibration obtains traffic video data collected by the road monitoring camera 51 from the network, analyzes the video data to obtain information about vehicle speed, and caches the vehicle speed result in the server or directly sends the vehicle speed result to the traffic management platform 53.
It will be apparent to those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented in program code executable by a computing device, such that they may be stored on a computer storage medium (ROM/RAM, magnetic disks, optical disks) and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; these modifications and substitutions do not cause the essence of the corresponding technical solution to depart from the scope of the technical solution of the embodiments of the present invention, and are intended to be covered by the claims and the specification of the present invention.
Claims (10)
1. The vehicle speed measuring method based on video and distance grid calibration is characterized by comprising the following steps:
step 1, selecting any frame of road pavement image from a real-time video captured by a road monitoring camera;
step 2, automatically generating grid calibration on the road pavement image, wherein key reference points in the road pavement image form the top points of the grid, and the physical distance between each row and each column of the grid is measured;
step 3, acquiring any video image monitored by the road monitoring camera containing the vehicle to be detected, and judging whether the position of the vehicle to be detected is in grid calibration or not;
step 4, restoring the position of the vehicle to be detected on the image to the position on the physical coordinate system by utilizing grid calibration, and obtaining a timestamp of the vehicle to be detected at the position;
step 5, detecting and tracking the vehicle to be detected in the video images monitored by the road monitoring camera, and acquiring the video images monitored by the road monitoring camera containing the vehicle to be detected in each frame to obtain the motion track of the vehicle to be detected in the images;
step 6, restoring the position of the vehicle to be detected on each frame of image to the position on the physical coordinate system by utilizing grid calibration to obtain the motion track of the vehicle to be detected under the physical coordinate system;
and 7, obtaining the average speed of the vehicle to be measured by adopting minimum mean square error operation.
2. The method for measuring vehicle speed based on video and distance grid calibration according to claim 1, wherein said obtaining any frame in step 3 includes a video image monitored by a road monitoring camera of a vehicle to be measured, and determining whether the position of the vehicle to be measured is in grid calibration, specifically comprises:
3.1: recording the position of an image to be restored containing a vehicle to be detected as T, and recording the position on a corresponding physical coordinate system as T';
3.2: checking whether T is in the grid calibration, if so, carrying out the next step; if not, the position of the image to be restored containing the vehicle to be detected is not in the range of the grid calibration, the position on the physical coordinate system is unknown, and the frame containing the video image monitored by the road monitoring camera of the vehicle to be detected is discarded.
3. The method for measuring vehicle speed based on video and distance grid calibration according to claim 2, wherein said step 4 of using grid calibration to restore the position of the vehicle to be measured on the image to the position on the physical coordinate system and obtain the timestamp of the vehicle to be measured at the position specifically comprises:
4.1: acquiring a small quadrangle in the grid where the T is positioned, setting the vertex at the lower left corner as c1, calculating the corresponding physical position of c1 relative to the O point according to the physical distance calibrated by the grid, and recording the physical position as the corresponding physical position
4.2: solving the normalized relative position of T' in the physical square according to the relative position of the small quadrangle of T in the grid, wherein the abscissa of the position is x, and the ordinate is y;
4.3: the position of T 'on the physical coordinate system relative to point O is derived from the normalized relative position of T' on the physical square.
4. The method for measuring vehicle speed based on video and distance grid calibration according to claim 3, wherein said solving the normalized relative position of T' in the physical square according to the relative position of the small quadrangle of T in the grid, the abscissa of the position being x, and the ordinate being y, specifically comprises:
4.2.1: let the remaining three vertices of the trapezoid in the grid where T is located be c2, c3, and c4 in order
Wherein,
is a vector pointing from c1 to c2,
is a vector pointing from c1 to c 4;
4.2.2: denoting c1 to c3 as
And
linear combinations of (a) with c1 to T as
And
in linear combination, i.e.
The coefficient k is solved from equation 4.2.2-11、k2The coefficients a, b are solved from equation 4.2.2-2;
4.2.3: c1 to c2 are divided into x parts and 1-x parts, and the division point is P; c4 to c3 are divided into x and 1-x parts, and the division point is Q; dividing P to Q into y and 1-y parts, and the division point is T; namely:
from equations 4.2.3-3 and 4.2.2-2
Wherein, let m1＝k1-1,m2＝k2-1, converting equation 4.2.3-4 into
When both m1 and m2 are non-zero, the 1 formula xm in equations 4.2.3-52-2 formula xm1To obtain
ym1＝xm2-am2+bm1 4.2.3-6
Substituting equations 4.2.3-6 into equation 1 in equations 4.2.3-5 yields
m2x2+(bm1-am2+1)x-a＝0 4.2.3-7
The value of x can be solved by the equation 4.2.3-7, and the value of x is substituted into the equation 4.2.3-6 to obtain the value of y;
4.2.4: if the discriminant of equation 4.2.3-7 is less than 0, or the solved abscissa x and ordinate y are not in the range of [0,1], then there is no solution that meets the requirements, and the position on the physical coordinate system cannot be obtained; if there is a solution, the solution with x and y both in the range of [0,1] is retained.
5. A method according to claim 3, wherein said normalized relative position of T 'in the physical square yields the position of T' in the physical coordinate system with respect to point O, according to the formula:
the physical position of T' relative to the O point is as follows:
6. the method for measuring vehicle speed based on video and distance grid calibration according to claim 1, wherein in the step 5, the vehicle to be measured in the video image monitored by the road monitoring camera is detected and tracked, the method for detecting the vehicle to be measured includes but is not limited to fast R-CNN, SSD, Yolo, and the algorithm for tracking the vehicle to be measured includes but is not limited to simple IOU tracking method, kalman filter-based tracking method, and deep learning feature and kalman filter-based tracking method.
7. The method for measuring vehicle speed based on video and distance grid calibration according to claim 5, wherein the step 6 of restoring the position of the vehicle to be measured on each frame image to the position on the physical coordinate system by using grid calibration to obtain the motion trajectory of the vehicle to be measured under the physical coordinate system specifically comprises:
when the vehicle to be detected is located inside the grid calibration, the lower position of the physical coordinate system of the vehicle to be detected and a frame time stamp can be obtained in each frame, the lower position of the physical coordinate system of the vehicle to be detected is set to be S, the frame time stamp is set to be t, and a continuous video monitored by the road monitoring camera forms a motion track of the vehicle to be detected in the physical coordinate system.
8. The method for measuring vehicle speed based on video and distance grid calibration according to claim 7, wherein the step 7 of obtaining the average speed of the vehicle to be measured by using minimum mean square error operation specifically comprises:
the average velocity formula is:
speed of rotation
The average speed of the vehicle to be measured is obtained.
9. Vehicle tachometer calibrated based on a video and distance grid, characterized in that it comprises a processor, a memory and a communication bus for implementing a communication connection between said processor and said memory, said memory having one or more computer readable programs stored therein, said processor implementing the steps of the method for measuring vehicle speed calibrated based on a video and distance grid according to any of the claims 1 to 8 by reading the one or more computer readable programs stored in said memory.
10. The vehicle speed measuring system based on video and distance grid calibration is characterized by comprising road monitoring cameras, the vehicle speed measuring equipment based on video and distance grid calibration according to claim 9 and a traffic management platform, wherein the vehicle speed measuring equipment based on video and distance grid calibration acquires video images containing vehicles to be measured from the road monitoring cameras and sends the speed information of the vehicles to be measured to the traffic management platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010929214.2A CN112053572A (en) | 2020-09-07 | 2020-09-07 | Vehicle speed measuring method, device and system based on video and distance grid calibration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010929214.2A CN112053572A (en) | 2020-09-07 | 2020-09-07 | Vehicle speed measuring method, device and system based on video and distance grid calibration |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112053572A true CN112053572A (en) | 2020-12-08 |
Family
ID=73610110
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010929214.2A Pending CN112053572A (en) | 2020-09-07 | 2020-09-07 | Vehicle speed measuring method, device and system based on video and distance grid calibration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112053572A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785855A (en) * | 2021-01-26 | 2021-05-11 | 张俊峰 | Method for acquiring vehicle speed from road monitoring video |
| CN112990128A (en) * | 2021-04-27 | 2021-06-18 | 电子科技大学 | Multi-vehicle speed measuring method based on video tracking |
| CN113160299A (en) * | 2021-01-28 | 2021-07-23 | 西安电子科技大学 | Vehicle video speed measurement method based on Kalman filtering and computer readable storage medium |
| CN113419075A (en) * | 2021-05-31 | 2021-09-21 | 广州忘平信息科技有限公司 | Ship speed measuring method, system, device and medium based on binocular vision |
| CN113553955A (en) * | 2021-07-23 | 2021-10-26 | 上海商汤科技开发有限公司 | Traffic detection method, traffic detection device, electronic equipment and storage medium |
| CN114018589A (en) * | 2021-10-25 | 2022-02-08 | 中汽研汽车检验中心（天津）有限公司 | Method and device for determining air bag ejection speed, electronic equipment and medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604448A (en) * | 2009-03-16 | 2009-12-16 | 北京中星微电子有限公司 | A kind of speed-measuring method of moving target and system |
| 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 |
| KR101633619B1 (en) * | 2016-03-23 | 2016-06-27 | 주식회사 토페스 | Method and apparatus for detecting velocity of vehicle using recognizing number of the vehicle of 2-dimensional image |
| CN106327880A (en) * | 2016-09-09 | 2017-01-11 | 成都通甲优博科技有限责任公司 | Vehicle speed identification method and system based on monitored video |
| CN106781476A (en) * | 2016-12-22 | 2017-05-31 | 中国人民解放军第三军医大学第三附属医院 | Vehicle dynamic position analysis method in traffic accident |
| US20180137356A1 (en) * | 2012-08-06 | 2018-05-17 | Cloudparc, Inc. | Tracking a vehicle using an unmanned aerial vehicle |
| CN109087510A (en) * | 2018-09-29 | 2018-12-25 | 讯飞智元信息科技有限公司 | traffic monitoring method and device |
| CN109949364A (en) * | 2019-04-01 | 2019-06-28 | 上海淞泓智能汽车科技有限公司 | A kind of vehicle attitude detection accuracy optimization method based on drive test monocular cam |
| 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 |
| CN110176036A (en) * | 2019-05-28 | 2019-08-27 | 中南林业科技大学 | A kind of interior method and system positioned of locomotive plane |
| CN110197588A (en) * | 2019-06-03 | 2019-09-03 | 长安大学 | A kind of truck driving behavior appraisal procedure and device based on GPS track data |
| CN110379168A (en) * | 2019-06-24 | 2019-10-25 | 东南大学 | A kind of vehicular traffic information acquisition method based on Mask R-CNN |
| CN111047879A (en) * | 2019-12-24 | 2020-04-21 | 苏州奥易克斯汽车电子有限公司 | Vehicle overspeed detection method |
| CN111383205A (en) * | 2020-03-11 | 2020-07-07 | 西安应用光学研究所 | Image fusion positioning method based on feature points and three-dimensional model |
-
2020
- 2020-09-07 CN CN202010929214.2A patent/CN112053572A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604448A (en) * | 2009-03-16 | 2009-12-16 | 北京中星微电子有限公司 | A kind of speed-measuring method of moving target and system |
| 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 |
| US20180137356A1 (en) * | 2012-08-06 | 2018-05-17 | Cloudparc, Inc. | Tracking a vehicle using an unmanned aerial vehicle |
| KR101633619B1 (en) * | 2016-03-23 | 2016-06-27 | 주식회사 토페스 | Method and apparatus for detecting velocity of vehicle using recognizing number of the vehicle of 2-dimensional image |
| CN106327880A (en) * | 2016-09-09 | 2017-01-11 | 成都通甲优博科技有限责任公司 | Vehicle speed identification method and system based on monitored video |
| CN106781476A (en) * | 2016-12-22 | 2017-05-31 | 中国人民解放军第三军医大学第三附属医院 | Vehicle dynamic position analysis method in traffic accident |
| 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 |
| CN109087510A (en) * | 2018-09-29 | 2018-12-25 | 讯飞智元信息科技有限公司 | traffic monitoring method and device |
| CN109949364A (en) * | 2019-04-01 | 2019-06-28 | 上海淞泓智能汽车科技有限公司 | A kind of vehicle attitude detection accuracy optimization method based on drive test monocular cam |
| CN110176036A (en) * | 2019-05-28 | 2019-08-27 | 中南林业科技大学 | A kind of interior method and system positioned of locomotive plane |
| CN110197588A (en) * | 2019-06-03 | 2019-09-03 | 长安大学 | A kind of truck driving behavior appraisal procedure and device based on GPS track data |
| CN110379168A (en) * | 2019-06-24 | 2019-10-25 | 东南大学 | A kind of vehicular traffic information acquisition method based on Mask R-CNN |
| CN111047879A (en) * | 2019-12-24 | 2020-04-21 | 苏州奥易克斯汽车电子有限公司 | Vehicle overspeed detection method |
| CN111383205A (en) * | 2020-03-11 | 2020-07-07 | 西安应用光学研究所 | Image fusion positioning method based on feature points and three-dimensional model |
Non-Patent Citations (7)
| Title |
|---|
| ZHONGQIANG WANG等: "High-Quality Real-Time Video Stabilization Using Trajectory Smoothing and Mesh-Based Warping", 《IEEE ACCESS》 * |
| 于艳玲: "视频检测系统中的车速检测技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 张桐: "基于视频的公路卡口车辆检测技术研究与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 徐晓娟: "基于视频的车辆跟踪算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 杜厚鹏: "基于监控视频的运动车辆检测与违章分析", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 臧晓蕾: "基于卡尔曼滤波器的船用雷达运动目标跟踪算法研究及性能分析", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 袁河洋: "基于视频的车辆速度检测方法研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785855A (en) * | 2021-01-26 | 2021-05-11 | 张俊峰 | Method for acquiring vehicle speed from road monitoring video |
| CN113160299A (en) * | 2021-01-28 | 2021-07-23 | 西安电子科技大学 | Vehicle video speed measurement method based on Kalman filtering and computer readable storage medium |
| CN113160299B (en) * | 2021-01-28 | 2023-04-18 | 西安电子科技大学 | Vehicle video speed measurement method based on Kalman filtering and computer readable storage medium |
| CN112990128A (en) * | 2021-04-27 | 2021-06-18 | 电子科技大学 | Multi-vehicle speed measuring method based on video tracking |
| CN113419075A (en) * | 2021-05-31 | 2021-09-21 | 广州忘平信息科技有限公司 | Ship speed measuring method, system, device and medium based on binocular vision |
| CN113419075B (en) * | 2021-05-31 | 2022-08-16 | 广州忘平信息科技有限公司 | Ship speed measuring method, system, device and medium based on binocular vision |
| CN113553955A (en) * | 2021-07-23 | 2021-10-26 | 上海商汤科技开发有限公司 | Traffic detection method, traffic detection device, electronic equipment and storage medium |
| CN114018589A (en) * | 2021-10-25 | 2022-02-08 | 中汽研汽车检验中心（天津）有限公司 | Method and device for determining air bag ejection speed, electronic equipment and medium |
| CN114018589B (en) * | 2021-10-25 | 2024-03-15 | 中汽研汽车检验中心（天津）有限公司 | Method and device for determining airbag ejection speed, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112053572A (en) | Vehicle speed measuring method, device and system based on video and distance grid calibration | |
| US9002068B2 (en) | Video speed detection system | |
| US8238610B2 (en) | Homography-based passive vehicle speed measuring | |
| CN109686088B (en) | Traffic video alarm method, equipment and system | |
| US11380105B2 (en) | Identification and classification of traffic conflicts | |
| CN107885795B (en) | Data verification method, system and device for card port data | |
| CN106991389A (en) | The apparatus and method for determining road edge | |
| CN113221682B (en) | Bridge vehicle load space-time distribution fine-grained identification method based on computer vision | |
| KR20200064873A (en) | Method for detecting a speed employing difference of distance between an object and a monitoring camera | |
| CN109727458B (en) | Method for realizing interval parking charging through dynamic and static traffic linkage | |
| CN113505638B (en) | Method and device for monitoring traffic flow and computer readable storage medium | |
| CN105869413A (en) | Method for measuring traffic flow and speed based on camera video | |
| CN112037536A (en) | Vehicle speed measuring method and device based on video feature recognition | |
| CN114782549B (en) | Camera calibration method and system based on fixed point identification | |
| CN115684637B (en) | Highway vehicle speed measuring method and device based on roadside monocular camera calibration | |
| CN108847035B (en) | Traffic flow evaluation method and device | |
| CN112907978A (en) | Traffic flow monitoring method based on monitoring video | |
| CN112415217A (en) | Vehicle speed measuring method based on video | |
| CN112485461A (en) | Power inspection robot speed detection system and method based on multi-vision markers | |
| CN113030506B (en) | Micro-area speed measurement method and system based on multi-license plate calibration library | |
| CN115862345A (en) | Method and device for determining vehicle speed, computer storage medium and terminal | |
| CN102622888B (en) | Self-learning identification method and device for licence plate based on video detection | |
| WO2024139285A1 (en) | Traffic intersection management method and apparatus, electronic device and storage medium | |
| CN116342676A (en) | Method, equipment and storage medium for measuring outline dimension of traffic holographic vehicle | |
| CN117877281A (en) | Traffic flow monitoring method, system, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201208 |