CN110020608A - A kind of vehicle identification method, equipment, system and parking charge system - Google Patents
A kind of vehicle identification method, equipment, system and parking charge system Download PDFInfo
- Publication number
- CN110020608A CN110020608A CN201910195940.3A CN201910195940A CN110020608A CN 110020608 A CN110020608 A CN 110020608A CN 201910195940 A CN201910195940 A CN 201910195940A CN 110020608 A CN110020608 A CN 110020608A
- Authority
- CN
- China
- Prior art keywords
- image
- vehicle
- convolutional neural
- parking
- neural networks
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
- G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Finance (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of vehicle identification method, equipment, system and parking charge systems.Method therein includes: the first image and the second image for obtaining image collecting device and acquiring to monitoring area；In response to having vehicle in the first image of confirmation and the second image, the first image and the second image are overlapped, third image is obtained；By the input of third image by convolutional neural networks model trained in advance, judge whether the vehicle in the first image and the second image is same vehicle, wherein convolutional neural networks model is to obtain based on the sample image training for including distracter.Whether the present invention is that same vehicle carries out identification judgement in superimposed image to the two cars for including by the convolutional neural networks model obtained based on the sample image training for including distracter, the accuracy of judgement can be improved in the image of the monitoring area of acquisition there are in the case where distracter.
Description
Technical field
The present invention relates to field of image recognition, in particular to a kind of vehicle identification method, equipment, system and parking charge system
System.
Background technique
Intelligent traffic monitoring system is an important development direction of current traffic monitoring industry, relies on computer vision
The picture shot with technologies such as deep learnings to monitoring camera automatically analyzes, and can be applied to act of violating regulations judgement, roadside
The many aspects such as parking stall management, Car license recognition, vehicle cab recognition.For example, needing in parking position management aspect by continuous
Identify whether the vehicle in monitored picture is same vehicle to carry out the calculating of down time.
In the case where monitoring environment, shooting angle, ambient lighting, the image resolution ratio of vehicle are often not fixed, and are often existed
More chaff interferent, existing vehicle identification algorithm are to require to carry out in the case where the various vehicle characteristics of each vehicle known pair
Than, above monitoring environment under identify monitored picture in vehicle whether be same vehicle accuracy rate it is lower.
Summary of the invention
In view of the above technical problems, the present invention provides a kind of vehicle identification method, equipment, system and parking charge system.
The technical scheme to solve the above technical problems is that
In a first aspect, the present invention provides a kind of vehicle identification method, comprising:
Obtain the first image and the second image that image collecting device acquires monitoring area；
In response to confirmation the first image and the second image in have vehicle, the first image and the second image are overlapped,
Obtain third image；
By the input of third image by convolutional neural networks model trained in advance, judge in the first image and the second image
Vehicle whether be same vehicle, wherein convolutional neural networks model be based on include distracter sample image it is trained
It arrives.
The beneficial effects of the present invention are: by the convolutional neural networks obtained based on the sample image training for including distracter
Whether model is that same vehicle carries out identification judgement in superimposed image to the two cars for including, can be in the monitored space of acquisition
There are the accuracys in the case where distracter, improving judgement in the image in domain.
Further, the opposite of monitoring area is arranged in image collecting device.
Further, before being overlapped the first image and the second image, further includes:
By comparing the position of vehicle in image and the position of preset parking stall, the first image and the second image are confirmed
In vehicle whether on parking stall；
In response to having vehicle, and the vehicle in the first image and the second image in the first image of confirmation and the second image
On parking stall, the first image and the second image are overlapped, obtain third image.
Beneficial effect using above-mentioned further scheme is: it is convenient that parking stall in monitoring area is managed, it prevents from missing
Identify the interim passing cars not on parking stall.
Further, the first image and the second image are overlapped, obtain third image, specifically includes:
3 channel RGB datas of the first image and the second image are overlapped, 6 channel RGB-RGB of third image are obtained
Data, will pass through 6 channel RGB-RGB data of third image judge whether the vehicle in the first image and the second image is same
One vehicle.
Further, the training method of convolutional neural networks model are as follows:
It will include that the same vehicle of distracter is overlapped in two images of same monitoring area as positive sample, it will
Include that the different vehicle of distracter is overlapped in two images of same monitoring area as negative sample, is based on multiple positive samples
Sheet and negative sample training convolutional neural networks model.
Further, by the input of third image by convolutional neural networks model trained in advance, judge the first image with
Whether the vehicle in the second image is same vehicle, is specifically included:
Based on the vehicle characteristics by two vehicles in convolutional neural networks model extraction third image trained in advance；
Calculate the vehicle characteristics similarity of two vehicles；
Judge whether the vehicle in the first image and the second image is same vehicle according to similarity.
Further, judge whether the vehicle in the first image and the second image is same vehicle according to similarity, specifically
Include:
When similarity is more than the upper limit of preset range, determine that the vehicle in the first image and the second image is same
Vehicle；
When similarity is lower than the lower limit of preset range, determining the vehicle in the first image and the second image not is same
Vehicle.
Second aspect, the present invention also provides a kind of computer readable storage medium, including instruction, when its on computers
When operation, so that computer is executed such as the method in any of the above-described embodiment.
The third aspect, the present invention also provides a kind of vehicle identification equipment, comprising:
Obtain module, the first image and the second image acquired for obtaining image collecting device to monitoring area；
Laminating module, in response to confirmation the first image and the second image in have vehicle, by the first image and second
Image is overlapped, and obtains third image；
Judgment module, for the input of third image by convolutional neural networks model trained in advance, to be judged the first figure
Whether the vehicle in picture and the second image is same vehicle, wherein convolutional neural networks model is based on including distracter
Sample image training obtains.
A kind of vehicle identification equipment provided by the invention, by the volume obtained based on the sample image training for including distracter
Whether product neural network model is that same vehicle carries out identification judgement in superimposed image to the two cars for including, and can adopted
There are the accuracys in the case where distracter, improving judgement in the image of the monitoring area of collection.
Further, the opposite of monitoring area is arranged in image collecting device.
Further, further includes:
Confirmation module, for by comparing the position of vehicle and the position of preset parking stall in image, confirmation first
Whether the vehicle in image and the second image is on parking stall；
Laminating module, in response to having a vehicle in the first image of confirmation and the second image, and the first image and the
First image and the second image are overlapped by the vehicle in two images on parking stall, obtain third image.
Beneficial effect using above-mentioned further scheme is: it is convenient that parking stall in monitoring area is managed, it prevents from missing
Identify the interim passing cars not on parking stall.
Further, laminating module, specifically for 3 channel RGB datas of the first image and the second image are overlapped,
6 channel RGB-RGB data of third image are obtained, so that judgment module is judged by 6 channel RGB-RGB data of third image
Whether the vehicle in the first image and the second image is same vehicle.
Further, further includes:
Training module, for will include that the same vehicle of distracter is overlapped in two images of same monitoring area
It will include that the different vehicle of distracter is overlapped in two images of same monitoring area as negative sample as positive sample
This, is based on multiple positive samples and negative sample training convolutional neural networks model.
Further, judgment module specifically includes:
Extraction unit, for based on by two vehicles in convolutional neural networks model extraction third image trained in advance
Vehicle characteristics；
Computing unit, for calculating the vehicle characteristics similarity of two vehicles；
Judging unit, for judging whether the vehicle in the first image and the second image is same vehicle according to similarity.
Further, judging unit is specifically used for:
When similarity is more than the upper limit of preset range, determine that the vehicle in the first image and the second image is same
Vehicle；
When similarity is lower than the lower limit of preset range, determining the vehicle in the first image and the second image not is same
Vehicle.
Further, equipment uses server or chip.
Fourth aspect, the present invention also provides a kind of vehicle identification systems, including above-mentioned vehicle identification equipment and Image Acquisition
Device.
A kind of vehicle identification system provided by the invention, vehicle identification equipment therein are by based on including distracter
Whether the convolutional neural networks model that sample image training obtains is same vehicle in superimposed image to the two cars for including
Identification judgement is carried out, the accuracy of judgement can be improved in the image of the monitoring area of acquisition there are in the case where distracter.
5th aspect, the present invention also provides a kind of parking charge system, including above-mentioned vehicle identification system and counting equipment,
If acquiring time of the time earlier than the second image of acquisition of the first image；
The counting equipment, for judging that the vehicle in the first image and the second image is not same vehicle when judgment module
When, using the time for acquiring the first image as the parking deadline of vehicle in the first image, the time of the second image will be acquired
As the parking initial time of vehicle in second image, and according to the parking initial time of same vehicle and parking end when
Between carry out parking charge.
Detailed description of the invention
Fig. 1 is a kind of flow chart of vehicle identification method provided in an embodiment of the present invention；
Fig. 2 is a kind of structural block diagram of vehicle identification equipment provided in an embodiment of the present invention；
Fig. 3 is a kind of structural block diagram of parking charge system provided in an embodiment of the present invention.
Specific embodiment
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the invention.
Fig. 1 is a kind of flow chart of vehicle identification method provided in an embodiment of the present invention, as shown in Figure 1, this method comprises:
S1, the first image and the second image that image collecting device acquires monitoring area are obtained；
Specifically, the opposite of monitoring area is arranged in image collecting device, for example, the camera that can be arranged by road side
The parking position on opposite is persistently monitored, separated in time interception image obtains two images therein as mapping to be checked
Picture, the interception time interval of two images are unsuitable too long.
S2, in response to confirmation the first image and the second image in have vehicle, the first image and the second image are folded
Add, obtains third image；
It realizes specifically, whether there is vehicle that a variety of prior arts can be used in confirmation image, including but not limited to, can pass through
Algorithm of target detection identifies the vehicle in the two images of interception, and the position of vehicle is confined with rectangle frame.
Then, 3 channel RGB datas of the first image and the second image are superimposed, obtain 6 channel RGB- of third image
RGB data, will pass through the difference that 6 channel RGB-RGB data of third image distinguish the first image and the second image.
Such as: the 3 channel RGB data of part of the first image are as follows:
[[204,204,204],
[204,204,204],
[204,204,204]],
……
The 3 channel RGB data of part of second image are as follows:
[[226,226,226],
[226,226,226],
[226,226,226]],
……
6 channel RGB-RGB data of the third image being then superimposed are as follows:
[[204,204,204,226,226,226],
[204,204,204,226,226,226],
[204,204,204,226,226,226]],
……
In addition, being managed for convenience to parking stall, prevents from misidentifying the interim passing cars not on parking stall, confirm
It, can also position by comparing vehicle in image and preset vehicle on the basis of having vehicle in first image and the second image
The position of position confirms the vehicle in the first image and the second image whether on parking stall, when confirming the first image and the second image
In have in the vehicle on parking stall, then the first image and the second image are overlapped.
S3, convolutional neural networks model trained in advance is passed through into the input of third image, judges the first image and the second figure
Whether the vehicle as in is same vehicle, wherein convolutional neural networks model is based on the sample image instruction for including distracter
It gets.
Specifically, in training convolutional neural networks model, need to one input data of convolutional neural networks model and
One corresponding label exports a result by convolutional neural networks, the result of output and label is compared, and reuses anti-
Data are modified to the direction propagated along comparison result, have so far learnt a wheel, by repeatedly learning, continuous corrective networks
Parameter improves the accuracy of convolutional neural networks model output result.After the training for completing convolutional neural networks model, it can incite somebody to action
In data to be tested input model, model can export corresponding judging result.If when prediction obtained input with instructed
The data practiced are similar, the obtained high of result certainty accuracy rate
In the step, can by camera obtain several scenes under include distracter image as sample, then lead to
Cross manually judge the vehicle in two images whether be same vehicle mode, provide the corresponding label of sample, wherein will wrap
Two images of the same vehicle containing distracter are overlapped as positive sample, will include the different vehicle of distracter
Two images are superimposed again as negative sample, are based on multiple positive samples and negative sample training convolutional neural networks model.Wherein, it can set
The label for setting positive sample is 1, and the label of negative sample is 0.
In the step, using include under several scenes distracter sample image as input data to convolutional Neural
Network has carried out a large amount of repetition trainings, with improve there are distracter to the two cars in superimposed image whether
The accuracy judged for same vehicle, wherein the quantity of sample image can according to actual needs accuracy of identification setting.
A kind of vehicle identification method provided in an embodiment of the present invention, by based on include distracter sample image it is trained
To convolutional neural networks model whether be that same vehicle carries out identification judgement, energy in superimposed image to the two cars for including
Enough the accuracy of judgement is improved there are in the case where distracter in the image of the monitoring area of acquisition.
Optionally, in this embodiment, step S3 is specifically included:
S3.1, the vehicle based on two vehicles in the convolutional neural networks model extraction third image by training in advance
Feature；
S3.2, the vehicle characteristics similarity for calculating two vehicles；
S3.3, judge whether the vehicle in the first image and the second image is same vehicle according to similarity.
It is mentioned specifically, doing feature for 6 channel RGB datas using VGG the or MOBLIE Net etc. in convolutional neural networks
It takes, whether the feature of extraction includes but is not limited to vehicle color, wheel hub, vehicle shape, has skylight etc. being capable of Division identification vehicle
Feature.
After having extracted feature, similarity is calculated using full articulamentum or one of Bayes's classification or SVM, and then sentence
Whether the vehicle in disconnected first image and the second image out is a vehicle, wherein the floating-point values that similarity is 0 to 1,0 represents
Completely dissimilar, 1 representative is completely similar.
Optionally, in this embodiment, step S3.3 is specifically included:
When similarity is more than the upper limit of preset range, determine that the vehicle in the first image and the second image is same
Vehicle；
When similarity is lower than the lower limit of preset range, determining the vehicle in the first image and the second image not is same
Vehicle.
The upper and lower bound of preset range can be chosen for same numerical value, can also choose different numerical value, for example, choosing default
The lower and upper limit of range are 0.5, at this point, similarity 0.5 can be used as it is uncertain as a result, i.e. fuzzy value；Choose default model
The lower and upper limit enclosed are respectively 0.4 and 0.6, at this point, the similarity between 0.4~0.6 can be used as uncertain result.
The embodiment of the invention also provides a kind of computer readable storage mediums, including instruction, when it is transported on computers
When row, so that computer is executed such as the method in any of the above-described embodiment.
Fig. 2 is a kind of structural block diagram of vehicle identification equipment provided in an embodiment of the present invention, modules in the equipment
The principle of work and power is expounded in foregoing teachings, is repeated no more below.
As shown in Fig. 2, the equipment includes:
Obtain module, the first image and the second image acquired for obtaining image collecting device to monitoring area；
Laminating module, in response to confirmation the first image and the second image in have vehicle, by the first image and second
Image is overlapped, and obtains third image；
Judgment module, for the input of third image by convolutional neural networks model trained in advance, to be judged the first figure
Whether the vehicle in picture and the second image is same vehicle, wherein convolutional neural networks model is based on including distracter
Sample image training obtains.
A kind of vehicle identification equipment provided in an embodiment of the present invention, by based on include distracter sample image it is trained
To convolutional neural networks model whether be that same vehicle carries out identification judgement, energy in superimposed image to the two cars for including
Enough the accuracy of judgement is improved there are in the case where distracter in the image of the monitoring area of acquisition.
Optionally, in this embodiment, the opposite of monitoring area is arranged in image collecting device.
Optionally, in this embodiment, which further includes confirmation module, for the position by comparing vehicle in image
With the position of preset parking stall, confirm the vehicle in the first image and the second image whether on parking stall；
Laminating module, in response to having a vehicle in the first image of confirmation and the second image, and the first image and the
First image and the second image are overlapped by the vehicle in two images on parking stall, obtain third image.
Optionally, in this embodiment, laminating module, specifically for by 3 channel RGB numbers of the first image and the second image
According to being overlapped, 6 channel RGB-RGB data of third image are obtained, so that judgment module passes through 6 channel RGB- of third image
RGB data judges whether the vehicle in the first image and the second image is same vehicle.
Optionally, in this embodiment, which further includes training module, for that will include the same vehicle of distracter
Two images be overlapped as positive sample, by include distracter different vehicle two images in superposition as negative
Sample is based on multiple positive samples and negative sample training convolutional neural networks model.
Optionally, in this embodiment, judgment module specifically includes:
Extraction unit, for based on by two vehicles in convolutional neural networks model extraction third image trained in advance
Vehicle characteristics；
Computing unit, for calculating the vehicle characteristics similarity of two vehicles；
Judging unit, for judging whether the vehicle in the first image and the second image is same vehicle according to similarity.
Optionally, in this embodiment, judging unit is specifically used for determining when similarity is more than the upper limit of preset range
Vehicle in first image and the second image is same vehicle, when similarity is lower than the lower limit of preset range, determines the first figure
Vehicle in picture and the second image is not same vehicle.
Optionally, in this embodiment, equipment uses server or chip.Wherein, server includes but is not limited to center
Server in machine room.
As shown in figure 3, the embodiment of the present invention also provides a kind of vehicle identification system, including above-mentioned vehicle identification equipment and figure
As acquisition device.
A kind of vehicle identification system provided by the invention, vehicle identification equipment therein are by based on including distracter
Whether the convolutional neural networks model that sample image training obtains is same vehicle in superimposed image to the two cars for including
Identification judgement is carried out, the accuracy of judgement can be improved in the image of the monitoring area of acquisition there are in the case where distracter.
As shown in figure 3, the embodiment of the present invention also provides a kind of parking charge system, including above-mentioned vehicle identification system and meter
Take equipment, if the time of the first image of acquisition is earlier than the time of the second image of acquisition；
Counting equipment, when the vehicle for being judged in the first image and the second image when judgment module is not same vehicle,
Time of the first image will be acquired as the parking deadline of vehicle in the first image, will acquire time of the second image as
The parking initial time of vehicle in second image, and stopped according to the parking initial time of same vehicle and parking deadline
Vehicle charging.
Specifically, vehicle identification equipment judges whether vehicle is same according to two images of image capture device continuous collecting
One vehicle then illustrates that the vehicle is parked in parking stall always if it is same vehicle, if not same vehicle, then schemes two
Parking deadline of the acquisition time of acquisition time image earlier as the vehicle as in, the later image of acquisition time
Parking initial time of the acquisition time as next vehicle, by continuously identifying judgement, available same vehicle
Initial time of stopping and parking deadline, to carry out parking charge accordingly.
Reader should be understood that in the description of this specification reference term " one embodiment ", " is shown " some embodiments "
The description of example ", " specific example " or " some examples " etc. mean specific features described in conjunction with this embodiment or example, structure,
Material or feature are included at least one embodiment or example of the invention.In the present specification, above-mentioned term is shown
The statement of meaning property need not be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
In addition, term " first ", " second ", " third " are used for description purposes only, it is not understood to indicate or imply phase
To importance.Unless specifically stated otherwise, the opposite step of the component and step that otherwise illustrate in these embodiments, digital table
It is not limit the scope of the invention up to formula and numerical value.
It is apparent to those skilled in the art that for convenience of description and succinctly, the dress of foregoing description
The specific work process with unit is set, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of unit, only
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.
Unit may or may not be physically separated as illustrated by the separation member, shown as a unit
Component may or may not be physical unit, it can and it is in one place, or may be distributed over multiple networks
On unit.It can select some or all of unit therein according to the actual needs to realize the mesh of the embodiment of the present invention
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
It, can if integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product
To be stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention substantially or
Say that all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Out, which is stored in a storage medium, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) executes all or part of each embodiment method of the present invention
Step.And storage medium above-mentioned include: USB flash disk, it is mobile hard disk, read-only memory (ROM, Read-Only Memory), random
Access various Jie that can store program code such as memory (RAM, Random Access Memory), magnetic or disk
Matter.
More than, only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto, and it is any to be familiar with
Those skilled in the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or substitutions,
These modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be wanted with right
Subject to the protection scope asked.
Claims (10)
1. a kind of vehicle identification method characterized by comprising
Obtain the first image and the second image that image collecting device acquires monitoring area；
In response to having vehicle in confirmation the first image and the second image, the first image and the second image are folded
Add, obtains third image；
By third image input by convolutional neural networks model trained in advance, the first image and the second figure are judged
Whether the vehicle as in is same vehicle, wherein the convolutional neural networks model is based on the sample graph for including distracter
As training obtains.
2. the method according to claim 1, wherein the monitoring area is arranged in described image acquisition device
Opposite.
3. the method according to claim 1, wherein the first image and the second image are overlapped it
Before, further includes:
By comparing the position of vehicle in image and the position of preset parking stall, the first image and the second image are confirmed
In vehicle whether on parking stall；
In response to having vehicle in confirmation the first image and the second image, and in the first image and the second image
The first image and the second image are overlapped by vehicle on parking stall, obtain third image.
4. the method according to claim 1, wherein described fold the first image and the second image
Add, obtain third image, specifically include:
3 channel RGB datas of the first image and the second image are overlapped, 6 channel RGB-RGB of third image are obtained
Data are judged in the first image and second image with will pass through 6 channel RGB-RGB data of the third image
Whether vehicle is same vehicle.
5. a kind of vehicle identification equipment characterized by comprising
Obtain module, the first image and the second image acquired for obtaining image collecting device to monitoring area；
Laminating module, in response to having vehicle in confirmation the first image and the second image, by the first image and
Second image is overlapped, and obtains third image；
Judgment module, for third image input by convolutional neural networks model trained in advance, to be judged to described the
Whether the vehicle in one image and the second image is same vehicle, wherein the convolutional neural networks model is based on including
What the sample image training of distracter obtained.
6. equipment according to claim 5, which is characterized in that the monitoring area is arranged in described image acquisition device
Opposite.
7. equipment according to claim 5, which is characterized in that further include:
Confirmation module, for by comparing the position of vehicle and the position of preset parking stall in image, confirmation described first
Whether the vehicle in image and the second image is on parking stall；
The laminating module, in response to having vehicle, and described first in confirmation the first image and the second image
The first image and the second image are overlapped by the vehicle in image and the second image on parking stall, obtain third figure
Picture.
8. according to the described in any item equipment of claim 5-7, which is characterized in that the equipment uses server or chip.
9. a kind of vehicle identification system, which is characterized in that including the described in any item vehicle identification equipment of such as claim 5-8 and
Image collecting device.
10. a kind of parking charge system, which is characterized in that set including vehicle identification system as claimed in claim 9 and charging
It is standby, if the time of acquisition the first image is earlier than the time for acquiring second image；
The counting equipment, for judging that the vehicle in the first image and the second image is not same when the judgment module
When vehicle, time of the first image will be acquired as the parking deadline of vehicle in the first image, by acquiring
Parking initial time of the time of the second image as vehicle in second image is stated, and is originated according to the parking of same vehicle
Time and parking deadline carry out charging.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910195940.3A CN110020608A (en) | 2019-03-15 | 2019-03-15 | A kind of vehicle identification method, equipment, system and parking charge system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910195940.3A CN110020608A (en) | 2019-03-15 | 2019-03-15 | A kind of vehicle identification method, equipment, system and parking charge system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110020608A true CN110020608A (en) | 2019-07-16 |
Family
ID=67189585
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910195940.3A Pending CN110020608A (en) | 2019-03-15 | 2019-03-15 | A kind of vehicle identification method, equipment, system and parking charge system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110020608A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814559A (en) * | 2020-06-10 | 2020-10-23 | 河南观潮智能科技有限公司 | Parking state identification method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009560A (en) * | 2016-11-02 | 2018-05-08 | 广州图普网络科技有限公司 | Commodity image similar categorization decision method and device |
| CN108182807A (en) * | 2017-12-27 | 2018-06-19 | 天津智芯视界科技有限公司 | A kind of generation method of car identifier |
| CN108389396A (en) * | 2018-02-28 | 2018-08-10 | 北京精英智通科技股份有限公司 | A kind of vehicle matching process, device and charge system based on video |
| CN109147341A (en) * | 2018-09-14 | 2019-01-04 | 杭州数梦工场科技有限公司 | Violation vehicle detection method and device |
-
2019
- 2019-03-15 CN CN201910195940.3A patent/CN110020608A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009560A (en) * | 2016-11-02 | 2018-05-08 | 广州图普网络科技有限公司 | Commodity image similar categorization decision method and device |
| CN108182807A (en) * | 2017-12-27 | 2018-06-19 | 天津智芯视界科技有限公司 | A kind of generation method of car identifier |
| CN108389396A (en) * | 2018-02-28 | 2018-08-10 | 北京精英智通科技股份有限公司 | A kind of vehicle matching process, device and charge system based on video |
| CN109147341A (en) * | 2018-09-14 | 2019-01-04 | 杭州数梦工场科技有限公司 | Violation vehicle detection method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814559A (en) * | 2020-06-10 | 2020-10-23 | 河南观潮智能科技有限公司 | Parking state identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460709B (en) | RTG visual barrier detection method based on RGB and D information fusion | |
| CN110096975A (en) | A kind of parking space state recognition methods, equipment and system | |
| CN109711264B (en) | Method and device for detecting occupation of bus lane | |
| CN110895662A (en) | Vehicle overload alarm method and device, electronic equipment and storage medium | |
| CN103258213B (en) | A kind of for the dynamic vehicle model recognizing method in intelligent transportation system | |
| CN106372666B (en) | A kind of target identification method and device | |
| CN107305627A (en) | A kind of automobile video frequency monitoring method, server and system | |
| CN107220603A (en) | Vehicle checking method and device based on deep learning | |
| CN110009929A (en) | A kind of Vehicle berth management method, equipment and system | |
| Jain et al. | Performance analysis of object detection and tracking algorithms for traffic surveillance applications using neural networks | |
| CN110516518A (en) | A kind of illegal manned detection method of non-motor vehicle, device and electronic equipment | |
| Kumtepe et al. | Driver aggressiveness detection via multisensory data fusion | |
| CN110766039B (en) | Muck truck transportation state identification method, medium, equipment and muck truck | |
| Hasegawa et al. | Type classification, color estimation, and specific target detection of moving targets on public streets | |
| CN104680795A (en) | Vehicle type recognition method and device based on partial area characteristic | |
| CN110516691A (en) | A kind of Vehicular exhaust detection method and device | |
| CN107944382A (en) | Method for tracking target, device and electronic equipment | |
| CN111523415A (en) | Image-based two-passenger one-dangerous vehicle detection method and device | |
| Soin et al. | Moving vehicle detection using deep neural network | |
| CN111666848A (en) | Method, device and equipment for detecting arrival of transport vehicle and storage medium | |
| Fraile et al. | Vehicle Trajectory Approximation and Classification. | |
| Wong et al. | Vehicle classification using convolutional neural network for electronic toll collection | |
| Snegireva et al. | Vehicle classification application on video using yolov5 architecture | |
| CN110020608A (en) | A kind of vehicle identification method, equipment, system and parking charge system | |
| Abbas | V-ITS: Video-based intelligent transportation system for monitoring vehicle illegal activities |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190716 |
|
| RJ01 | Rejection of invention patent application after publication |