CN109377770A - The method and apparatus of statistical vehicle flowrate calculate equipment and storage medium - Google Patents
The method and apparatus of statistical vehicle flowrate calculate equipment and storage medium Download PDFInfo
- Publication number
- CN109377770A CN109377770A CN201811031635.2A CN201811031635A CN109377770A CN 109377770 A CN109377770 A CN 109377770A CN 201811031635 A CN201811031635 A CN 201811031635A CN 109377770 A CN109377770 A CN 109377770A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- video
- video frame
- reference line
- video flowing
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- 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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- 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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The application provides a kind of method and apparatus of statistical vehicle flowrate, calculates equipment.In the method, the video flowing that equipment obtains monitoring vehicle flowrate is calculated;The video flowing includes multiple video frames, and the calculating equipment is from the vehicle identified in each video frame in the video flowing;The calculating equipment calculates the vehicle flowrate that the video flowing monitors with wagon flow telegoniometer sequentially in time according to the vehicle in video frame each in the video flowing.In this way, the application can monitor the vehicle flowrate on road by way of video flowing.
Description
Technical field
This application involves the method and apparatus of video field more particularly to statistical vehicle flowrate, calculating equipment and computers can
Read storage medium.
Background technique
Vehicle has become the vehicles of common of people's trip.With universal, road (such as urban transportation) warp of vehicle
Chang Yongsai, so needing to be monitored vehicle flowrate.Current monitor mode is the vehicle that radar signal monitoring passes through, Huo Zhetong
It crosses gravity sensor and monitors the vehicle passed through.
Summary of the invention
In view of this, this application provides a kind of method and apparatus of statistical vehicle flowrate, calculating equipment, video can be passed through
Stream realizes the monitoring to vehicle flowrate.
In a first aspect, the application provides a kind of method of statistical vehicle flowrate.Calculate the video that equipment obtains monitoring vehicle flowrate
Stream;Such as video flowing can be the vehicle flowrate video flowing generated of capture apparatus monitoring road, the calculating equipment is from the shooting
Equipment obtains the video flowing.
The video flowing includes multiple video frames.The calculating equipment is from the vehicle identified in each video frame in the video flowing.
The calculating equipment according to the vehicle in video frame each in the video flowing, sequentially in time with wagon flow direction calculating
The vehicle flowrate that the video flowing monitors out.
As it can be seen that the application can monitor the vehicle flowrate on road by way of video flowing.
In a kind of possible design of first aspect, vehicle flowrate can be calculated in the following way by calculating equipment.
In this approach, it calculates same position of the equipment in the video flowing in each video frame and sets reference line, the ginseng
It is vertical with the wagon flow direction to examine line.In this way, the vehicle by the reference line can be counted by calculating equipment.
Specifically, equipment is calculated sequentially in time with wagon flow direction, and the reference is identified by from the video flowing
The number of the vehicle of line.Number by the vehicle of the reference line is the vehicle flowrate.
In a kind of possible design of first aspect, calculates equipment and can be identified from the video flowing in the following way and led to
Cross the number of the vehicle of the reference line.
In this approach, it calculates equipment and determines that the target vehicle in each video frame, the target vehicle are in the video frame
In the vehicle nearest with the reference line according to wagon flow direction distance.It calculates equipment and calculates the target vehicle in the video frame
At a distance from the reference line, and using calculated distance as the target range in the video frame.And so on, calculate equipment
The target range in the video flowing in each video frame can be calculated.
Calculate equipment sequentially in time, according to the target in strategy and the video flowing in each video frame away from
From being identified by each vehicle of the reference line.The strategy are as follows: the target range in the first video frame is less than the second view
The vehicle currently passed through is identified when target range in frequency frame, first video frame and second video frame are in the view
Adjacent two video frames in front and back sequentially in time in frequency stream.
This event as it can be seen that the application can be become larger by the target range of adjacent video frames in video flowing, has been identified
Vehicle is identified by the number of the vehicle of the reference line by the reference line.And so on, it can know from the video flowing
The vehicle of the reference line Chu not passed through every time;In this way, vehicle of all numbers by the reference line, i.e. vehicle flowrate can be calculated.
In a kind of possible design of first aspect, in each video frame in the video flowing, calculates equipment and calculate the view
For the headstock of target vehicle in frequency frame to the distance of reference line, calculated distance is the target range in the video frame.
In a kind of possible design of first aspect, in each video frame in the video flowing, calculates equipment and calculate the view
For the tailstock of target vehicle in frequency frame to the distance of reference line, calculated distance is the target range in the video frame.
In a kind of possible design of first aspect, in each video frame in the video flowing, calculates equipment and calculate the view
For datum mark on the vehicle body of target vehicle in frequency frame to the distance of reference line, calculated distance is the target in the video frame
Distance.
Second aspect, the application provide a kind of device of statistical vehicle flowrate, including multiple functional units.The device is by being somebody's turn to do
Multiple functional units execute in the method for the statistical vehicle flowrate that may arbitrarily design offer of first aspect or first aspect
Step.
The third aspect, the application provide a kind of calculating equipment, which includes processor and memory.The memory
Store computer instruction;The processor executes the computer instruction of memory storage, so that the calculating equipment executes first party
The step that may arbitrarily design in the method for the statistical vehicle flowrate provided of face or first aspect.
In a kind of possible design of the third aspect, the computer instruction stored in the memory mentions for realizing second aspect
Functional unit in the device of any statistical vehicle flowrate supplied.The calculating equipment executes statistics wagon flow by the functional unit
Step in the method for amount.
Fourth aspect provides a kind of computer readable storage medium, is stored with computer in computer readable storage medium
Instruction, when the processor for calculating equipment executes the computer instruction, which executes first aspect or first aspect
Arbitrarily may design provide statistical vehicle flowrate method in step.
In a kind of possible design of fourth aspect, the computer instruction stored in the computer readable storage medium is for real
Functional unit in the device for any statistical vehicle flowrate that existing second aspect provides.The calculating equipment by the functional unit come
Execute the step in the method for statistical vehicle flowrate.
5th aspect, provides a kind of computer program product, which includes computer instruction, the calculating
Machine instruction storage is in a computer-readable storage medium.The processor for calculating equipment can be read from computer readable storage medium
And the computer instruction is executed, so that the calculating equipment executes the arbitrarily possible design offer of first aspect or first aspect
Step in the method for statistical vehicle flowrate.
In a kind of possible design of 5th aspect, the computer instruction in the computer program product is for realizing second party
Functional unit in the device for any statistical vehicle flowrate that face provides.The calculating equipment executes statistics by the functional unit
Step in the method for vehicle flowrate.
6th aspect, provides a kind of system of statistical vehicle flowrate, which includes calculating equipment and first aspect or the
Capture apparatus in the arbitrarily possible design of one side.The calculating equipment executes any possibility of first aspect or first aspect
Step in the method for the statistical vehicle flowrate provided, such as the statistical vehicle flowrate that the calculating deployed with devices second aspect provides are provided
Device, which executes the step in this method by the functional unit in the device.
Detailed description of the invention
Fig. 1 is a kind of schematic diagram of wagon flow;
A kind of schematic diagram for the scene that Fig. 2 is applicable in by method provided by the present application;
Fig. 3 is a kind of flow diagram of the method for statistical vehicle flowrate provided by the present application;
Fig. 4 A and Fig. 4 B are respectively a kind of schematic diagram that identification vehicle provided by the present application passes through;
Fig. 5 is a kind of logical construction schematic diagram of the device 50 of statistical vehicle flowrate provided by the present application;
Fig. 6 is a kind of hardware structural diagram provided by the present application for calculating equipment 12.
Specific embodiment
Below in conjunction with the attached drawing in the application, technical solution provided by the present application is described.
Term brief introduction
Vehicle: refer to through wheel rotation and move the vehicles of vehicle body.Such as vehicle can be non-motor vehicle or
Motor vehicle.
Wagon flow direction: the moving direction in the same direction of multiple vehicles on road.By taking Fig. 1 as an example, three vehicles are travelled on lane
(A, B, C), this three vehicles are according to equidirectional traveling, and the direction is wagon flow direction.
Vehicle flowrate: refer to that equidirectional wagon flow passes through the vehicle of same reference line on road within the unit time.Fig. 1 is illustrated
The reference line, vehicle (A, B) do not reach the reference line, and a vehicle C is passing through the reference line.Optionally, which can be
Straight line, or the line being made of multiple spaced points.Optionally, which can be straight line or other types of line.
Optionally, the reference line is vertical with wagon flow direction.
A method of vehicle flowrate is calculated, is within a preset period of time M by the number of the vehicle of the reference line, then wagon flow
Amount is the ratio of M and the preset time period, and M is positive integer.
The embodiment of the present application provides a kind of system of statistical vehicle flowrate.Referring to fig. 2, in this embodiment, the system packet
It includes capture apparatus 21 and calculates equipment 22.It is understood that in a further embodiment, which can further include
Other processing equipments, such as network forwarding equipment, video processing equipment etc..
In embodiment shown in Fig. 2, which is used to obtain the vehicle flowrate monitored on road, and to passing through fixation
The vehicle of road segment segment is taken pictures.Capture apparatus 11 is based on resulting photo formation video flowing of continuously taking pictures, which includes
Multiple video frames, i.e. each frame in the video flowing are a video frame.The application forms video flowing to based on multiple pictures
Mode is without limitation;Such as can be a resulting photo of taking pictures every time is a video frame, will be taken pictures sequentially in time
Resulting multiple pictures synthetic video stream;For example, resulting multiple pictures of taking pictures can be formed with the processing of video flowing, one
Photo corresponds to a video frame, but retains the characteristic of the vehicle in the picture in the video frame.
Calculating equipment 12 of the capture apparatus 11 by the video stream of generation into the system.Calculating equipment 12 can be used
Method provided by the present application carrys out statistical vehicle flowrate.
This application provides the embodiments of a kind of method of statistical vehicle flowrate, can use institute in above-mentioned Fig. 2 in the method
Show 12 statistical vehicle flowrate of calculating equipment in embodiment.The method comprising the steps of S31, step S32 and step S33, such as Fig. 3 institute
Show.
Step S31 calculates equipment 12 from capture apparatus 11 and obtains video flowing.
As described above, the video flowing is the resulting video flowing of vehicle flowrate that the capture apparatus 11 monitors default road segment segment, it should
Video flowing includes multiple video frames.
Optionally, video flowing can be requested from capture apparatus 11 by calculating equipment 12, and capture apparatus 11 is by the video stream
To calculating equipment 12.
Optionally, capture apparatus 11 can be actively by the video stream to calculating equipment 12, such as periodically sets to calculating
Preparation gives the video flowing.Correspondingly, it calculates equipment 12 and receives the video flowing that capture apparatus 11 is sent, complete in this way to the video flowing
Acquisition.
Step S32 calculates equipment 12 from the vehicle identified in each video frame in the video flowing.
The video flowing includes multiple video frames, calculates equipment 12 for each video frame in the video flowing and makees vehicle respectively
Identification.
Optionally, convolutional neural networks (the convolution neural that equipment 12 disposes vehicle for identification is calculated
Network, CNN) algorithm.It calculates equipment 12 and vehicle is identified from video frame by the CNN algorithm, such as identify distance ginseng
The nearest vehicle of line is examined, or identifies all vehicles.
Optionally, candidate region (region proposal, RP) algorithm that equipment 12 disposes vehicle for identification is calculated.
It calculates equipment 12 and vehicle is identified from video frame by the RP algorithm, such as identify the vehicle nearest apart from above-mentioned reference line
, or identify all vehicles.
Step S33, calculate equipment 12 sequentially in time with wagon flow direction, according to each of being identified from the video flowing
Vehicle in the video frame calculates the vehicle flowrate monitored by the video flowing.
Since the video flowing is that the default road segment segment of the monitoring of capture apparatus 11 is resulting and identified in the video flowing
Vehicle in each video frame out, therefore calculating equipment 12 can count the default road sequentially in time with wagon flow direction
The vehicle flowrate in section.Citing offer below is several can be with statistical.
The first optional statistical, calculating equipment 12 can count sequentially in time with wagon flow direction and drive into this
The number of the vehicle of default road segment segment.Calculate equipment 12 can according to the period of the number that counts and the video flow monitoring,
Calculate the vehicle flowrate for the default road segment segment that the video flowing monitors.
For example, the scene domain (i.e. default road segment segment) that video flowing can monitor is limited.Determining the video
When direction of traffic in stream in each video frame, it can identify whether the vehicle for having new from the adjacent video frames two-by-two of the video flowing
Drive into the default road segment segment;If there is new vehicle drives into, then the number of the vehicle newly driven into is identified.And so on, it can be with
The vehicle newly driven into every time is identified from video flowing, and counts the summation of the number of the vehicle newly driven into every time.So as to
According to the period of the summation of statistics and the video flow monitoring, the wagon flow for the default road segment segment that the video flowing monitors is calculated
Amount.
Second of optional statistical, calculating equipment 12 can count sequentially in time with wagon flow direction and be driven out to this
The number of the vehicle of default road segment segment.Calculate equipment 12 can according to the period of the number that counts and the video flow monitoring,
Calculate the vehicle flowrate for the default road segment segment that the video flowing monitors.
For example, the scene domain (i.e. default road segment segment) that video flowing can monitor is limited.Determining the video
When direction of traffic in stream in each video frame, it can identify whether the vehicle for having new from the adjacent video frames two-by-two of the video flowing
It is driven out to the default road segment segment;If there is new vehicle is driven out to, then the number for the vehicle being newly driven out to is identified.And so on, it can be with
The vehicle being newly driven out to every time is identified from video flowing, and counts the summation of the number for the vehicle being newly driven out to every time.So as to
According to the period of the summation of statistics and the video flow monitoring, the wagon flow for the default road segment segment that the video flowing monitors is calculated
Amount.
The third optional statistical, calculating equipment 12 can be somebody's turn to do for each video frame in the video flowing each
Same position in video frame sets reference line, as shown in Figure 1, the reference line is vertical with the wagon flow direction.But the method is unlimited
Fixed specific location of the reference line in the video frame, for example, it can be set in the video frame wagon flow direction drive into place or
Person is driven out to place, the other any positions that can also be set in the video frame.
After setting the reference line, equipment 12 is calculated sequentially in time with wagon flow direction, is identified from the video flowing logical
Cross the vehicle of the reference line.Calculate number of the statistics of equipment 12 by the vehicle of the reference line, and can be according to passing through statistics
The period of number and the video flow monitoring calculates the vehicle flowrate for the default road segment segment that the video flowing monitors.
Optionally provide a kind of illustrate to realize the vehicle for being identified by the reference line from the video flowing.
Specifically, it calculates equipment 12 and determines target vehicle, the target carriage respectively in each video frame in the video flowing
For in the video frame according to the vehicle that wagon flow direction is nearest apart from the reference line.In the video frame, the video frame is calculated
Target vehicle at a distance from the reference line, calculated distance is as the target range in the video frame.
Then, equipment 12 is calculated sequentially in time, according to the target in the video frame each in strategy and the video flowing
Distance is identified by each vehicle of the reference line.The strategy are as follows: first video frame and second video frame is in the videos
Adjacent two video frames in front and back sequentially in time in stream;In the target range in the first video frame less than in the second video frame
Target range when be identified as currently thering is vehicle to pass through, and identify the number of vehicle currently passed through, by vehicle
Number can be one or more, if multiple vehicles pass through simultaneously, the number of identification while the vehicle passed through, if only one
A vehicle passes through, then be identified as by vehicle number be one.Since step S32 has had identified in each video frame
Vehicle, namely have identified the position of vehicle in the video frame, thus according to the strategy identified vehicle by reference to
The number for the vehicle that the vehicle currently passed through and identification currently pass through can be further identified when line.
Optionally provide a kind of illustrate to realize the vehicle for being identified by the reference line from the video flowing.
Specifically, equipment 12 is calculated in each video frame in the video flowing, calculates separately each vehicle in the video frame
At a distance from the reference line, the shortest distance is selected from a distance from calculated each vehicle with the reference line, by selection
The shortest distance is as the target range in the video frame, using the corresponding vehicle of the shortest distance as the target carriage in the video frame
?.In same video frame, if multiple vehicles all have the target range apart from the reference line, multiple vehicle is simultaneously
As multiple target vehicles, i.e., each vehicle in multiple vehicle is target vehicle;If only one vehicle have away from
The target range from the reference line, then this vehicle is as target vehicle.
Then, equipment 12 is calculated sequentially in time, according to the target in the video frame each in strategy and the video flowing
Distance is identified by each vehicle of the reference line.
And so on, all vehicles for passing through the reference line in the video flowing can be identified by the strategy by calculating equipment 12
?.According to the number of all vehicles by the reference line, the default road segment segment that the video flowing monitors can be calculated
Vehicle flowrate.
In a kind of optional embodiment, the strategy further include: the target range in the first video frame is greater than or equal to the
It is identified as none vehicle when target range in two video frames to pass through, first video frame and second video frame are at this
Adjacent two video frames in front and back sequentially in time in video flowing.In this way, calculating equipment 12 is by the strategy, it is suitable according to the time
Sequence, whether based on the target range in the video frame each in the video flowing, can be recognized accurately has vehicle to pass through the reference
Line.
And so on, all vehicles for passing through the reference line in the video flowing can be more accurately identified by the strategy
Number.
For example, as shown in Figure 4 A, I frame, J frame and k-th frame are to be arranged successively sequentially in time in video flowing
Three video frames.In I frame, according to wagon flow direction, compared to vehicle A and vehicle B, the headstock distance reference line of vehicle C
Recently, the headstock of vehicle C is 10 meters (meter, m) at a distance from reference line.In J frame, according to wagon flow direction, compared to vehicle
A and vehicle B, the headstock distance reference line of vehicle C is nearest, and the headstock of vehicle C is 5 meters at a distance from reference line.In k-th frame
In, according to wagon flow direction, the headstock of vehicle C by reference to line, therefore do not consider further that vehicle C at a distance from reference line, only
Compare vehicle A and vehicle B;At this moment, compared to vehicle A, the headstock distance reference line of vehicle B is nearest, the headstock of vehicle B and reference
The distance of line is 15 meters.Since vehicle B is greater than vehicle C and reference in J frame for (15 meters) at a distance from reference line in k-th frame
The distance (5 meters) of line, therefore the vehicle for being identified as vehicle and having passed through, and be identified by is vehicle C, that is, the number of the vehicle passed through
It is one.
For example, as shown in Figure 4 B, I frame, J frame and k-th frame are to be arranged successively sequentially in time in video flowing
Three video frames.In I frame, according to wagon flow direction, compared to the headstock distance reference line of vehicle A, vehicle B and vehicle C
Recently, the headstock of vehicle B is 10 meters at a distance from reference line, while the headstock of vehicle C is 10 meters at a distance from reference line.?
In J frame, according to wagon flow direction, compared to vehicle A, the headstock distance reference line of vehicle B and vehicle C are nearest, the headstock of vehicle B with
The distance of reference line is 5 meters, while the headstock of vehicle C is 5 meters at a distance from reference line.In k-th frame, according to wagon flow direction,
The headstock of the headstock of vehicle B and vehicle C simultaneously by reference to line, therefore do not consider further that vehicle B and vehicle C respectively with reference line
Distance;At this moment, the headstock distance reference line of vehicle A is nearest, and the headstock of vehicle A is 10 meters at a distance from reference line.Due in K
Vehicle A is greater than vehicle C (5 meters) at a distance from reference line in J frame for (10 meters) at a distance from reference line in frame, therefore is identified as
The vehicle for having vehicle to pass through, and being identified by is vehicle B and vehicle C, and the number of the vehicle as passed through is two.
Optionally, in each video frame in the video flowing, headstock and the reference line that equipment 12 calculates vehicle are calculated
Distance, resulting distance will be calculated as the distance of the vehicle distances reference line.For example, in each video frame
In, the headstock of the target vehicle is calculated to the distance of the reference line, and calculated distance is the target range in the video frame.
Optionally, in each video frame in the video flowing, the tailstock and the reference line that equipment 12 calculates vehicle are calculated
Distance, resulting distance will be calculated as the distance of the vehicle distances reference line.
Optionally, in each video frame in the video flowing, a datum mark is selected (to be located at from each vehicle
The middle position of the vehicle or other any positions), the datum mark of the calculating vehicle of equipment 12 is calculated at a distance from the reference line,
Resulting distance will be calculated as the distance of the vehicle distances reference line.
The application provides a kind of device of statistical vehicle flowrate, which is deployed in the calculating in above-mentioned embodiment illustrated in fig. 2
In equipment 12, the functional unit which includes is for realizing the step in the method for above-mentioned statistical vehicle flowrate;The application is implemented
Example is to how partition functionality unit without limitation, provides to following Examples a kind of division of functional unit, such as in the apparatus
Shown in Fig. 5.
The device 50 of statistical vehicle flowrate as shown in Figure 5, comprising:
Acquiring unit 51, for obtaining the video flowing of monitoring vehicle flowrate, the video flowing includes multiple video frames;;
Recognition unit 52, for from the vehicle identified in the video flowing in each video frame;
Computing unit 53, for sequentially in time with wagon flow direction, according to each of being identified from the video flowing
Vehicle in the video frame calculates the vehicle flowrate monitored by the video flowing.
Optionally, the computing unit 53, is used for:
Same position in each video frame sets reference line, and the reference line is vertical with the wagon flow direction;
Sequentially in time with wagon flow direction, the number of the vehicle of the reference line is identified by from the video flowing.
Optionally, the computing unit 53, is used for:
The target range in the video flowing in each video frame is calculated, the target range is the video frame
In target vehicle at a distance from the reference line, the target vehicle be in the video frame according to the wagon flow direction away from
From the vehicle nearest with the reference line;
Sequentially in time, according to the target range in strategy and the video flowing in each video frame, identification is logical
Cross each vehicle of the reference line, the strategy are as follows: in the target range in the first video frame less than in the second video frame
The vehicle currently passed through is identified when target range, first video frame and second video frame are to press in the video flowing
According to two video frames adjacent before and after time sequencing.
Optionally, the computing unit 53, in each video frame, the headstock for calculating the target vehicle to be arrived
The distance of the reference line, calculated distance are the target range in the video frame.
Each function in acquiring unit 51, recognition unit 52 and computing unit 53, there is corresponding step in the above-mentioned methods.Cause
This, the realization details of each function in acquiring unit 51, recognition unit 52 and computing unit 53 may refer to corresponding in the above method
The description of step.
A kind of possible basic hardware framework of the calculating equipment 12 is illustratively provided below, as shown in Figure 6.
Referring to Fig. 6, calculating equipment 12 includes processor 121, memory 122, communication interface 123 and bus 124.
It calculates in equipment 12, the quantity of processor 121 can be one or more, and Fig. 1 only illustrates one of processing
Device 121.Optionally, processor 121 can be at central processing unit (central processing unit, CPU) or ARM
Manage device.If calculating equipment 12 has multiple processors 121, the type of multiple processors 121 can be different, or can phase
Together.Optionally, the multiple processors 121 for calculating equipment 12 can also be integrated into multi-core processor.
Memory 122 stores computer instruction;For example, the computer instruction includes chain code;Such as the computer instruction
For realizing each step in method provided by the present application;Such as the computer instruction is for realizing dress provided by the present application
The 50 each functional units for including are set, or for realizing each step in method provided by the present application.
Memory 122 can be any or any combination of following storage medium: nonvolatile memory (non-
Volatile memory, NVM) (such as read-only memory (read only memory, ROM), solid state hard disk (Solid
State Drives, SSD), mechanical hard disk, disk, disk permutation), volatile memory (volatile memory).
Communication interface 123 can be any or any combination of following device: network interface (such as Ethernet connects
Mouthful), the device with network access facility such as wireless network card.
Communication interface 123 carries out data communication for calculating equipment 12 and other equipment (such as calculating equipment).
Fig. 6 indicates bus 124 with a thick line.Processor 121, memory 122 and communication interface 123 pass through bus 124
Connection.In this way, processor 121 can access memory 122 by bus 124, and communication interface is utilized by bus 124
123 carry out data interaction with other equipment (such as calculating equipment).
Optionally, the computer instruction in the execution memory 122 of equipment 12 is calculated, realizes the application on calculating equipment 12
The method of the statistical vehicle flowrate of offer, or device 50 provided by the present application is realized on calculating equipment 12.
Optionally, calculating equipment 12 is the server in public cloud or private clound or mixed cloud.Calculate equipment 12
After resource is virtualized, device is disposed in the resource of the virtualization.The device is for realizing statistics vehicle provided by the present application
The method of flow or the device are device 50 provided by the present application.
The application provides a kind of computer readable storage medium, is stored with computer in the computer readable storage medium and refers to
It enables, when the processor 121 for calculating equipment 12 executes the computer instruction, which executes statistics provided by the present application
Step in the method for vehicle flowrate.
The application provides a kind of computer readable storage medium, is stored with computer in the computer readable storage medium and refers to
It enables, the computer instruction is for realizing device 50.
The application provides a kind of computer program product, which includes computer instruction, the computer
Instruction storage is in a computer-readable storage medium.The processor for calculating equipment can be read simultaneously from computer readable storage medium
The computer instruction is executed, so that the step of calculating equipment executes the method for statistical vehicle flowrate provided by the present application.
The application provides a kind of computer program product, the computer instruction which includes for realizing
Device 50.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features;And these modification or
Replacement, the protection scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of method of statistical vehicle flowrate, which is characterized in that the described method includes:
The video flowing of monitoring vehicle flowrate is obtained, the video flowing includes multiple video frames;
From the vehicle identified in the video flowing in each video frame;
Sequentially in time with wagon flow direction, according to from the vehicle each of identified in the video flowing in the video frame,
Calculate the vehicle flowrate monitored by the video flowing.
2. the method according to claim 1, wherein described calculate the wagon flow monitored by the video flowing
Amount, comprising:
Same position in each video frame sets reference line, and the reference line is vertical with the wagon flow direction;
Sequentially in time with wagon flow direction, the number of the vehicle of the reference line is identified by from the video flowing.
3. according to the method described in claim 2, it is characterized in that, described sequentially in time with wagon flow direction from the video
The number that the vehicle of the reference line is identified by stream includes:
The target range in the video flowing in each video frame is calculated, the target range is in the video frame
Target vehicle at a distance from the reference line, the target vehicle be in the video frame according to wagon flow direction distance with
The nearest vehicle of the reference line;
Sequentially in time, according to the target range in strategy and the video flowing in each video frame, it is identified by institute
State each vehicle of reference line, the strategy are as follows: in the target range in the first video frame less than the target in the second video frame
Apart from when identify the vehicle that currently passes through, first video frame and second video frame be in the video flowing according to when
Between adjacent two video frames in sequence front and back.
4. according to the method described in claim 3, it is characterized in that, calculating each video frame in the video flowing
In target range, comprising:
In each video frame, the headstock of the target vehicle is calculated to the distance of the reference line, calculated distance
For the target range in the video frame.
5. a kind of device of statistical vehicle flowrate, which is characterized in that described device includes:
Acquiring unit, for obtaining the video flowing of monitoring vehicle flowrate, the video flowing includes multiple video frames;
Recognition unit, for from the vehicle identified in the video flowing in each video frame;
Computing unit, for sequentially in time with wagon flow direction, according to each of identifying the view from the video flowing
Vehicle in frequency frame calculates the vehicle flowrate monitored by the video flowing.
6. device according to claim 5, which is characterized in that the computing unit is used for:
Same position in each video frame sets reference line, and the reference line is vertical with the wagon flow direction;
Sequentially in time with wagon flow direction, the number of the vehicle of the reference line is identified by from the video flowing.
7. device according to claim 6, which is characterized in that the computing unit is used for:
The target range in the video flowing in each video frame is calculated, the target range is in the video frame
Target vehicle at a distance from the reference line, the target vehicle be in the video frame according to wagon flow direction distance with
The nearest vehicle of the reference line;
Sequentially in time, according to the target range in strategy and the video flowing in each video frame, it is identified by institute
State each vehicle of reference line, the strategy are as follows: in the target range in the first video frame less than the target in the second video frame
Apart from when identify the vehicle that currently passes through, first video frame and second video frame be in the video flowing according to when
Between adjacent two video frames in sequence front and back.
8. device according to claim 7, which is characterized in that
The computing unit calculates the headstock of the target vehicle to the reference line in each video frame
Distance, calculated distance are the target range in the video frame.
9. a kind of calculating equipment, which is characterized in that including processor and memory;
The memory, for storing computer instruction;
The processor, for executing the computer instruction of the memory storage, so that the calculating equipment perform claim is wanted
The method for seeking 1 to 4 described in any item statistical vehicle flowrates.
10. a kind of computer readable storage medium, the computer-readable recording medium storage computer instruction, the computer
Instruction instruction calculates the method that equipment perform claim requires 1 to 4 described in any item statistical vehicle flowrates.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811031635.2A CN109377770B (en) | 2018-09-05 | 2018-09-05 | Method and device for counting traffic flow, computing equipment and storage medium |
PCT/CN2019/087229 WO2020048156A1 (en) | 2018-09-05 | 2019-05-16 | Method and apparatus for counting vehicle flow, computing device, and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811031635.2A CN109377770B (en) | 2018-09-05 | 2018-09-05 | Method and device for counting traffic flow, computing equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109377770A true CN109377770A (en) | 2019-02-22 |
CN109377770B CN109377770B (en) | 2021-06-22 |
Family
ID=65404581
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811031635.2A Active CN109377770B (en) | 2018-09-05 | 2018-09-05 | Method and device for counting traffic flow, computing equipment and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109377770B (en) |
WO (1) | WO2020048156A1 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020048156A1 (en) * | 2018-09-05 | 2020-03-12 | 华为技术有限公司 | Method and apparatus for counting vehicle flow, computing device, and computer readable storage medium |
CN111046820A (en) * | 2019-12-17 | 2020-04-21 | 上海船舶研究设计院(中国船舶工业集团公司第六0四研究院) | Statistical method and device for vehicles in automobile roll-on-roll-off ship and intelligent terminal |
CN111369795A (en) * | 2020-03-09 | 2020-07-03 | 深圳大学 | Traffic flow statistical method, device, equipment and storage medium |
CN112950961A (en) * | 2021-01-27 | 2021-06-11 | 苏州智芯控联信息科技有限公司 | Traffic flow statistical method, device, equipment and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001283373A (en) * | 2000-03-30 | 2001-10-12 | Toshiba Corp | Traffic flow measuring system |
CN102708690A (en) * | 2012-06-20 | 2012-10-03 | 中国计量学院 | Method for measuring road noise on basis of road monitoring video |
JP5583067B2 (en) * | 2011-03-31 | 2014-09-03 | 中日本高速道路株式会社 | Vehicle detector |
CN104021679A (en) * | 2014-05-30 | 2014-09-03 | 宁波海视智能***有限公司 | Traffic flow statistic method based on video |
CN104599502A (en) * | 2015-02-13 | 2015-05-06 | 重庆邮电大学 | Method for traffic flow statistics based on video monitoring |
CN106097726A (en) * | 2016-08-23 | 2016-11-09 | 苏州科达科技股份有限公司 | The detection determination in region, traffic information detection method and device |
CN106710228A (en) * | 2016-12-21 | 2017-05-24 | 南京大学镇江高新技术研究院 | Implementation method of passenger and freight separated traffic parameter monitoring system |
CN108351219A (en) * | 2016-02-26 | 2018-07-31 | 华为技术有限公司 | Traffic control method and device |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101510358B (en) * | 2009-03-20 | 2010-08-25 | 吉林大学 | Method and apparatus for processing real time statistical vehicle flowrate using video image |
JP5297407B2 (en) * | 2010-03-19 | 2013-09-25 | 三菱電機株式会社 | Traffic flow measuring device |
EP2700054B1 (en) * | 2012-06-12 | 2015-04-22 | Institute of Electronics and Computer Science | System and method for video-based vehicle detection |
CN109377770B (en) * | 2018-09-05 | 2021-06-22 | 华为技术有限公司 | Method and device for counting traffic flow, computing equipment and storage medium |
-
2018
- 2018-09-05 CN CN201811031635.2A patent/CN109377770B/en active Active
-
2019
- 2019-05-16 WO PCT/CN2019/087229 patent/WO2020048156A1/en active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001283373A (en) * | 2000-03-30 | 2001-10-12 | Toshiba Corp | Traffic flow measuring system |
JP5583067B2 (en) * | 2011-03-31 | 2014-09-03 | 中日本高速道路株式会社 | Vehicle detector |
CN102708690A (en) * | 2012-06-20 | 2012-10-03 | 中国计量学院 | Method for measuring road noise on basis of road monitoring video |
CN104021679A (en) * | 2014-05-30 | 2014-09-03 | 宁波海视智能***有限公司 | Traffic flow statistic method based on video |
CN104599502A (en) * | 2015-02-13 | 2015-05-06 | 重庆邮电大学 | Method for traffic flow statistics based on video monitoring |
CN108351219A (en) * | 2016-02-26 | 2018-07-31 | 华为技术有限公司 | Traffic control method and device |
CN106097726A (en) * | 2016-08-23 | 2016-11-09 | 苏州科达科技股份有限公司 | The detection determination in region, traffic information detection method and device |
CN106710228A (en) * | 2016-12-21 | 2017-05-24 | 南京大学镇江高新技术研究院 | Implementation method of passenger and freight separated traffic parameter monitoring system |
Non-Patent Citations (1)
Title |
---|
毛欣: "基于车辆识别的流量监测方法研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020048156A1 (en) * | 2018-09-05 | 2020-03-12 | 华为技术有限公司 | Method and apparatus for counting vehicle flow, computing device, and computer readable storage medium |
CN111046820A (en) * | 2019-12-17 | 2020-04-21 | 上海船舶研究设计院(中国船舶工业集团公司第六0四研究院) | Statistical method and device for vehicles in automobile roll-on-roll-off ship and intelligent terminal |
CN111369795A (en) * | 2020-03-09 | 2020-07-03 | 深圳大学 | Traffic flow statistical method, device, equipment and storage medium |
CN112950961A (en) * | 2021-01-27 | 2021-06-11 | 苏州智芯控联信息科技有限公司 | Traffic flow statistical method, device, equipment and storage medium |
CN112950961B (en) * | 2021-01-27 | 2022-07-08 | 苏州智芯控联信息科技有限公司 | Traffic flow statistical method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2020048156A1 (en) | 2020-03-12 |
CN109377770B (en) | 2021-06-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109377770A (en) | The method and apparatus of statistical vehicle flowrate calculate equipment and storage medium | |
CN105139425B (en) | A kind of demographic method and device | |
CN110692083B (en) | Block-matched optical flow and stereoscopic vision for dynamic vision sensor | |
CN104732187B (en) | A kind of method and apparatus of image trace processing | |
US9679200B2 (en) | Image processing to derive movement characteristics for a plurality of queue objects | |
JP2020149704A (en) | System and method for activity monitoring using video data | |
WO2017035663A1 (en) | System and method for detecting and tracking objects | |
CN106031094A (en) | Accurate measurement of distributed counters | |
CN110264495A (en) | A kind of method for tracking target and device | |
CN109727458B (en) | Method for realizing interval parking charging through dynamic and static traffic linkage | |
CN107146409B (en) | The identification of equipment detection time exception and true time difference evaluation method in road network | |
Zhao et al. | Automated traffic surveillance system with aerial camera arrays imagery: Macroscopic data collection with vehicle tracking | |
CN109344746A (en) | Pedestrian counting method, system, computer equipment and storage medium | |
CN108847024A (en) | Traffic congestion recognition methods and system based on video | |
JP6792722B2 (en) | Vehicle number measurement system | |
WO2015132744A1 (en) | Distributed counters and meters in packet-switched system | |
A. Alsanabani et al. | Vehicle counting using detecting-tracking combinations: A comparative analysis | |
US10429200B1 (en) | Determining adjusted trip duration using route features | |
CN103810460B (en) | Object tracking method and object tracking device | |
CN110021161A (en) | A kind of prediction technique and system of traffic direction | |
Xu et al. | Coral-pie: A geo-distributed edge-compute solution for space-time vehicle tracking | |
US11727580B2 (en) | Method and system for gathering information of an object moving in an area of interest | |
CN109977796A (en) | Trail current detection method and device | |
CN113221791A (en) | Vehicle parking violation detection method and device, electronic equipment and storage medium | |
CN110099206A (en) | Photographic method, robot and computer readable storage medium based on robot |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |