CN110188749A - Designated vehicle Vehicle License Plate Recognition System and method under a kind of more vehicles - Google Patents
Designated vehicle Vehicle License Plate Recognition System and method under a kind of more vehicles Download PDFInfo
- Publication number
- CN110188749A CN110188749A CN201910382731.XA CN201910382731A CN110188749A CN 110188749 A CN110188749 A CN 110188749A CN 201910382731 A CN201910382731 A CN 201910382731A CN 110188749 A CN110188749 A CN 110188749A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- license plate
- target
- module
- image
- 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 35
- 238000001514 detection method Methods 0.000 claims abstract description 32
- 238000006243 chemical reaction Methods 0.000 claims abstract description 12
- 230000000007 visual effect Effects 0.000 claims description 13
- 230000001960 triggered effect Effects 0.000 claims description 4
- 238000013481 data capture Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000011895 specific detection Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 230000007812 deficiency Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 5
- 235000013399 edible fruits Nutrition 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to vehicle recongnition technique field, the designated vehicle Vehicle License Plate Recognition System under a kind of more vehicles is disclosed, including triggering captures equipment, obtains identification region module, vehicle detection module, vehicle identification module and vehicle tracking module;It also discloses recognition methods: target vehicle is captured, obtain target vehicle image;Position coordinates and candid photograph picture to acquired target vehicle in step (1) carry out image coordinate system conversion, obtain identification region;The identification region intercepted to acquired identification region module in step (2) carries out car plate detection;The license plate of final goal vehicle is identified;Target vehicle is tracked, aiming spot is constantly updated, until identifying target vehicle license plate.The present invention, the deficiency of distal end vehicle license plate can not be identified by overcoming existing car plate detection system, increase the designated vehicle Car license recognition under more vehicles, the flexibility of the Vehicle License Plate Recognition System of raising.
Description
Technical field
The present invention relates to vehicle recongnition technique field, designated vehicle Vehicle License Plate Recognition System under specifically a kind of more vehicles and
Method.
Background technique
In recent years, Vehicle License Plate Recognition System is rapidly developed, and is gradually changed into the technology to reach its maturity, and
Vehicle license plate identifies that the important foundation technology for belonging to comprehensive intelligent transportation and security administration platform construction, such technology are universal
Applied to many related fieldss.But the Vehicle License Plate Recognition System of prevalence can only identify distance system in current lane currently on the market
It unites nearest vehicle license plate, and the vehicle license plate of designated position cannot be identified, this method has certain limitation, no
The needs of user and developer can be met well.
A candid photograph region can be all specified when existing vehicle license plate system deployment, grabbed when vehicle drives into Vehicle License Plate Recognition System
When clapping region, Vehicle License Plate Recognition System can be triggered and capture the image of vehicle and automatically identify license plate.This capture region usually away from
One piece of region closer from camera visual field lower edge because existing Vehicle License Plate Recognition System can only to the vehicle of visual field nearby into
Row Car license recognition, for the vehicle license plate of distal end, the prior art can not make identification;Capture the length usually only one in region
Vehicle vehicle body length, i.e. certain moment capture region and only have a vehicle to pass through.
Though the prior art is able to satisfy the needs of bayonet, in certain specific occasions and it is not suitable for.If user's needs pair
The vehicle of designated position does Car license recognition, and current Vehicle License Plate Recognition System Car license recognition region is simply moved to designated position
It not can solve problem, the prior art can preferentially identify the vehicle license plate nearest apart from visual field lower edge, specified without identifying
The vehicle license plate of position.
In addition, this recognition point also exposes another deficiency of the prior art, if bayonet captures region distance view
Off field edge too far, i.e., candid photograph region distance visual field lower edge there are also a distance or capture region setting it is too long, when one
When vehicle enters the triggering candid photograph of candid photograph region, the license plate of previous vehicle is not yet driven out to visual field lower edge, and Vehicle License Plate Recognition System also can be excellent
First identify the vehicle license plate nearest apart from visual field lower edge, so that the wrong license plate previous vehicle treats as the license plate of latter vehicle,
Cause target vehicle and license plate matching error.
Summary of the invention
The purpose of the present invention is to provide the designated vehicle Vehicle License Plate Recognition Systems and method under a kind of more vehicles, for existing
Technology cannot carry out Car license recognition to the vehicle of designated position and solve follow the bus more recently condition vehicle and license plate matching error
The problem of, to solve the problems mentioned in the above background technology.
To achieve the above object, the invention provides the following technical scheme:
A kind of designated vehicle Vehicle License Plate Recognition System under more vehicles, including triggering capture equipment, obtain identification region module, vehicle
Detection module, vehicle identification module and vehicle tracking module, in which:
Equipment is captured in the triggering, is captured function for completing, is obtained position and the image of target vehicle;
The acquisition identification region module, for position coordinates and the candid photograph of capturing target vehicle received by equipment will to be triggered
Picture carries out image coordinate system conversion, obtains identification region;
The vehicle detection module, the identification region for being intercepted to acquisition identification region module carry out car plate detection;
The vehicle identification module is identified for the license plate to final goal vehicle;
The vehicle tracking module constantly updates aiming spot, until identifying target vehicle vehicle for tracking target vehicle
Board.
As a further solution of the present invention: the triggering captures equipment by detection module, host computer and captures equipment group
At, in which:
The detection module, for detect trigger signal and obtain signal triggering position coordinates, in the form of message will touching
It signals and coordinate is sent to host computer;
The host computer, for receiving message, parsing obtains triggering grab signal and trigger position coordinate, and sends capture immediately
Signal is completed to capture to equipment is captured;
The candid photograph equipment for receiving grab signal, and returns and captures image data to host computer.
A kind of designated vehicle licence plate recognition method under more vehicles, includes the following steps:
(1), target vehicle is captured, obtains target vehicle image;
(2), image coordinate system conversion is carried out to the position coordinates of acquired target vehicle in step (1) and candid photograph picture, obtained
Identification region;
(3), the identification region intercepted to acquired identification region module in step (2) carries out car plate detection;
(4), the license plate of final goal vehicle is identified;
(5), when in step (4) it is unidentified go out license plate or Car license recognition confidence level it is lower, and identification region central point is apart from visual field
Lower edge farther out when, then track target vehicle, constantly update aiming spot, until identifying target vehicle license plate.
As further scheme of the invention: in step (1), specifically capturing process are as follows: when external trigger captures condition
When establishment, detection module detects trigger signal and obtains the position coordinates of signal triggering, by trigger signal in the form of message
It is sent to host computer with coordinate, host computer receives message, and parsing obtains triggering grab signal and trigger position coordinate, and immediately
It sends grab signal and is captured to equipment completion is captured, capture equipment and receive grab signal, complete primary candid photograph, and return to candid photograph
Image data is to host computer.
As further scheme of the invention: in step (2), specific identification process are as follows: host computer has received detection
The position coordinates of module and the candid photograph picture for capturing equipment return, then host computer passes through according to the camera parameter for capturing equipment
A series of image coordinate system conversion, is converted to image coordinate (u, v), Change-over knot for the world coordinates (X, Y, Z) of target position
Fruit obtains a point on image, and marks the target point on the image;Then centered on the point, it is with twice of Vehicle length
Radius does circle, intercepts out identification region.
As further scheme of the invention: in step (2), image coordinate system conversion formula are as follows:
Wherein, f is camera focus, and R is spin matrix, and t is translation vector.
As further scheme of the invention: in step (3), specific detection process are as follows: car plate detection result returns to vehicle
The central point of board and the bounding rectangles of license plate;License plate central point and identification region central point are calculated then according to Euclidean distance formula
Euclidean distance, and therefrom find out that Euclidean distance is minimum and less than the license plate of vehicle commander's degree, which is target vehicle vehicle
Board.
As further scheme of the invention: Euclidean distance formula are as follows:
。
As further scheme of the invention: in step (4), specific identification process are as follows: according to the calculating knot of step (3)
The target license plate bounding rectangles that fruit returns intercept target license plate image;Then the target license plate screenshot is sent into Car license recognition mould
Block completes Car license recognition.
As further scheme of the invention: in step (5), specific identification process are as follows: with step (2) calculated mesh
Centered on punctuate, chooses side length and be equal to initialization tracing area of the square area of vehicle commander's degree as target following, open
Real time video data capture is opened, track algorithm is executed to each frame image of subsequent video stream, constantly updates aiming spot, when
Target point moves to visual field nearby or when the more visible position of license plate, stops tracking;Then it centered on the target point, obtains
Identification region repeats step (2), (3) and (4), identifies target vehicle license plate, and finally license plate is added to former candid photograph image
On, complete distal end Car license recognition.
Compared with prior art, the beneficial effects of the present invention are:
Designated vehicle Vehicle License Plate Recognition System under a kind of more vehicles, distal end can not be identified by overcoming existing car plate detection system
The deficiency of vehicle license plate, increases the designated vehicle Car license recognition under more vehicles, the flexibility of the Vehicle License Plate Recognition System of raising, this
Outside, this scheme will capture region and combine with board knowledge region, other than the location coordinate information of detection module feedback, user
Can also according to their own needs, customized board knows region, in identification license plate process, system only to board know the license plate in region into
Row identification, non-board know region nonrecognition license plate, and it is nearest apart from visual field lower edge to solve existing car plate detection System Priority identification
The defect of vehicle license plate.
Detailed description of the invention
Fig. 1 captures the flow diagram of equipment for triggering in the designated vehicle Vehicle License Plate Recognition System under a kind of more vehicles.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
In the embodiment of the present invention, a kind of designated vehicle Vehicle License Plate Recognition System under more vehicles, including triggering are captured equipment, are obtained
Taking identification region module, vehicle detection module, vehicle identification module and vehicle tracking module, in which: equipment is captured in the triggering,
For completing to capture function, position and the image of target vehicle are obtained;The acquisition identification region module, for candid photograph will to be triggered
The position coordinates and candid photograph picture of target vehicle received by equipment carry out image coordinate system conversion, obtain identification region;Institute
Vehicle detection module is stated, the identification region for being intercepted to acquisition identification region module carries out car plate detection;The vehicle is known
Other module, identifies for the license plate to final goal vehicle;The vehicle tracking module, for tracking target vehicle, no
It is disconnected to update aiming spot, until identifying target vehicle license plate.
It is made of referring to Fig. 1, equipment is captured in the triggering detection module, host computer and candid photograph equipment, in which: the inspection
Survey module, for detect trigger signal and obtain signal triggering position coordinates, by trigger signal and seat in the form of message
Mark is sent to host computer;The host computer, for receiving message, parsing obtains triggering grab signal and trigger position coordinate, and
Grab signal is sent immediately to be completed to capture to equipment is captured;The candid photograph equipment for receiving grab signal, and returns to candid photograph figure
Sheet data is to host computer.
A kind of designated vehicle licence plate recognition method under more vehicles, includes the following steps:
(1), target vehicle is captured, obtains target vehicle image;
(2), image coordinate system conversion is carried out to the position coordinates of acquired target vehicle in step (1) and candid photograph picture, obtained
Identification region;
(3), the identification region intercepted to acquired identification region module in step (2) carries out car plate detection;
(4), the license plate of final goal vehicle is identified;
(5), when in step (4) it is unidentified go out license plate or Car license recognition confidence level it is lower, and identification region central point is apart from visual field
Lower edge farther out when, then track target vehicle, constantly update aiming spot, until identifying target vehicle license plate.
In step (1), process is specifically captured are as follows: when external trigger, which captures condition, to be set up, detection module detects triggering
Signal and the position coordinates for obtaining signal triggering, are sent to host computer, host computer for trigger signal and coordinate in the form of message
Message is received, parsing obtains triggering grab signal and trigger position coordinate, and it is complete to equipment is captured to send grab signal immediately
It at candid photograph, captures equipment and receives grab signal, complete primary candid photograph, and return and capture image data to host computer.
In step (2), specific identification process are as follows: host computer have received detection module position coordinates (world coordinates) and
The candid photograph picture that equipment returns is captured, then host computer passes through a series of image coordinate according to the camera parameter for capturing equipment
System's conversion, is converted to image (pixel) coordinate (u, v) for the world coordinates (X, Y, Z) of target position, transformation result obtains image
On a point, and mark the target point on the image;It then, (can be according to resolution with twice of Vehicle length centered on the point
Rate size is adjusted or customized) circle is done for radius, intercept out identification region.
In step (2), image coordinate system conversion formula are as follows:
Wherein, f is camera focus, and R is spin matrix, and t is translation vector.
In step (3), specific detection process are as follows: car plate detection result returns to the central point of license plate and the shape based moment of license plate
Shape;The Euclidean distance of license plate central point and identification region central point is calculated then according to Euclidean distance formula, and therefrom finds out Europe
Formula distance is minimum and less than the license plate of vehicle commander's degree, which is target vehicle license plate.
Euclidean distance formula are as follows:
。
As further scheme of the invention: in step (4), specific identification process are as follows: according to the calculating knot of step (3)
The target license plate bounding rectangles that fruit returns intercept target license plate image;Then the target license plate screenshot is sent into Car license recognition mould
Block completes Car license recognition.
In step (5), specific identification process are as follows: centered on step (2) calculated target point, choose side length and be equal to one
Initialization tracing area of the square area of vehicle commander's degree as target following opens real time video data capture, to subsequent
Each frame image of video flowing executes track algorithm, constantly updates aiming spot, when target point move to visual field nearby or
When the more visible position of license plate, stop tracking;Then centered on the target point, identification region is obtained, repeats step (2), (3)
(4), it identifies target vehicle license plate, finally license plate is added on former candid photograph image, completes distal end Car license recognition.
The working principle of the invention is: according to image coordinate, carrying out Car license recognition to image specified location area;Tracking is remote
It holds target vehicle to nearby, extracts target vehicle license plate, complete distal end Car license recognition.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (10)
1. the designated vehicle Vehicle License Plate Recognition System under a kind of more vehicles, which is characterized in that capture equipment including triggering, obtain identification
Regions module, vehicle detection module, vehicle identification module and vehicle tracking module, in which:
Equipment is captured in the triggering, is captured function for completing, is obtained position and the image of target vehicle;
The acquisition identification region module, for position coordinates and the candid photograph of capturing target vehicle received by equipment will to be triggered
Picture carries out image coordinate system conversion, obtains identification region;
The vehicle detection module, the identification region for being intercepted to acquisition identification region module carry out car plate detection;
The vehicle identification module is identified for the license plate to final goal vehicle;
The vehicle tracking module constantly updates aiming spot, until identifying target vehicle vehicle for tracking target vehicle
Board.
2. the designated vehicle Vehicle License Plate Recognition System under a kind of more vehicles according to claim 1, which is characterized in that the touching
Hair is captured equipment and is made of detection module, host computer and candid photograph equipment, in which:
The detection module, for detect trigger signal and obtain signal triggering position coordinates, in the form of message will touching
It signals and coordinate is sent to host computer;
The host computer, for receiving message, parsing obtains triggering grab signal and trigger position coordinate, and sends capture immediately
Signal is completed to capture to equipment is captured;
The candid photograph equipment for receiving grab signal, and returns and captures image data to host computer.
3. the designated vehicle licence plate recognition method under a kind of more vehicles, which comprises the steps of:
(1), target vehicle is captured, obtains target vehicle image;
(2), image coordinate system conversion is carried out to the position coordinates of acquired target vehicle in step (1) and candid photograph picture, obtained
Identification region;
(3), car plate detection is carried out to the identification region that acquisition identification region module is intercepted in step (2);
(4), the license plate of final goal vehicle is identified;
(5), when in step (4) it is unidentified go out license plate or Car license recognition confidence level it is lower, and identification region central point is apart from visual field
Lower edge farther out when, then track target vehicle, constantly update aiming spot, until identifying target vehicle license plate.
4. the designated vehicle licence plate recognition method under a kind of more vehicles according to claim 3, which is characterized in that step
(1) in, process is specifically captured are as follows: when external trigger, which captures condition, to be set up, detection module detects trigger signal and obtains letter
Number triggering position coordinates, trigger signal and coordinate are sent to host computer in the form of message, host computer receives message, solution
Analysis obtains triggering grab signal and trigger position coordinate, and sends grab signal immediately and complete to capture to equipment is captured, and candid photograph is set
It is standby to receive grab signal, primary candid photograph is completed, and return and capture image data to host computer.
5. the designated vehicle licence plate recognition method under a kind of more vehicles according to claim 3, which is characterized in that step
(2) in, specific identification process are as follows: host computer has received the position coordinates of detection module and captures the candid photograph figure that equipment returns
Piece, then host computer is converted, by the generation of target position according to the camera parameter for capturing equipment by a series of image coordinate system
Boundary's coordinate (X, Y, Z) is converted to image coordinate (u, v), and transformation result obtains a point on image, and marks this on the image
Target point;Then centered on the point, circle is done using twice of Vehicle length as radius, intercepts out identification region.
6. the designated vehicle licence plate recognition method under a kind of more vehicles according to claim 5, which is characterized in that step
(2) in, image coordinate system conversion formula are as follows:
Wherein, f is camera focus, and R is spin matrix, and t is translation vector.
7. the designated vehicle licence plate recognition method under a kind of more vehicles according to claim 3, which is characterized in that step
(3) in, specific detection process are as follows: car plate detection result returns to the central point of license plate and the bounding rectangles of license plate;Then according to Europe
Formula range formula calculates the Euclidean distance of license plate central point and identification region central point, and it is minimum and small therefrom to find out Euclidean distance
In the license plate of vehicle commander's degree, which is target vehicle license plate.
8. the designated vehicle licence plate recognition method under a kind of more vehicles according to claim 7, which is characterized in that it is European away from
From formula are as follows:
。
9. the designated vehicle licence plate recognition method under a kind of more vehicles according to claim 3, which is characterized in that step
(4) in, specific identification process are as follows: according to the target license plate bounding rectangles that the calculated result of step (3) returns, intercept target license plate
Image;Then the target license plate screenshot is sent into Car license recognition module, completes Car license recognition.
10. the designated vehicle licence plate recognition method under a kind of more vehicles according to claim 3, which is characterized in that step
(5) in, specific identification process are as follows: centered on step (2) calculated target point, choose side length and be equal to vehicle commander's degree just
Initialization tracing area of the square region as target following opens real time video data capture, to each of subsequent video stream
Frame image executes track algorithm, constantly updates aiming spot, when target point moves to visual field nearby or license plate is more visible
When position, stop tracking;Then centered on the target point, identification region is obtained, step (2), (3) and (4) is repeated, identifies
License plate is finally added on former candid photograph image, completes distal end Car license recognition by target vehicle license plate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910382731.XA CN110188749A (en) | 2019-05-09 | 2019-05-09 | Designated vehicle Vehicle License Plate Recognition System and method under a kind of more vehicles |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910382731.XA CN110188749A (en) | 2019-05-09 | 2019-05-09 | Designated vehicle Vehicle License Plate Recognition System and method under a kind of more vehicles |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110188749A true CN110188749A (en) | 2019-08-30 |
Family
ID=67714221
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910382731.XA Pending CN110188749A (en) | 2019-05-09 | 2019-05-09 | Designated vehicle Vehicle License Plate Recognition System and method under a kind of more vehicles |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110188749A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111009131A (en) * | 2019-12-05 | 2020-04-14 | 成都思晗科技股份有限公司 | High-order video intelligence parking system based on image recognition |
CN111081027A (en) * | 2019-12-17 | 2020-04-28 | 浙江大华技术股份有限公司 | License plate recognition method and device, computer device and readable storage medium |
CN111210459A (en) * | 2020-01-08 | 2020-05-29 | 北京天睿空间科技股份有限公司 | Method for detecting moving target in large scene by using priori knowledge |
CN111241988A (en) * | 2020-01-08 | 2020-06-05 | 北京天睿空间科技股份有限公司 | Method for detecting and identifying moving target in large scene by combining positioning information |
CN111738185A (en) * | 2020-06-28 | 2020-10-02 | 杭州海康威视数字技术股份有限公司 | Target identification method, device and equipment |
CN111882917A (en) * | 2020-06-12 | 2020-11-03 | 深圳市捷顺科技实业股份有限公司 | Vehicle queue-jumping problem processing method and processing device |
CN112016474A (en) * | 2020-08-31 | 2020-12-01 | 重庆紫光华山智安科技有限公司 | Face recognition method, device and equipment and computer readable storage medium |
CN112396708A (en) * | 2020-11-02 | 2021-02-23 | 北京精英路通科技有限公司 | Parking management method and device, computer equipment and storage medium |
CN112802341A (en) * | 2020-12-30 | 2021-05-14 | 中山联合汽车技术有限公司 | Method for measuring position and attitude of front vehicle |
CN113255633A (en) * | 2021-07-16 | 2021-08-13 | 深圳市赛菲姆科技有限公司 | Camera adjustment control method, device, system and medium based on target tracking |
CN114241465A (en) * | 2021-12-14 | 2022-03-25 | 广西云高智慧城市科技有限公司 | Method for detecting and matching license plate of vehicle image and license plate identification method |
-
2019
- 2019-05-09 CN CN201910382731.XA patent/CN110188749A/en active Pending
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111009131A (en) * | 2019-12-05 | 2020-04-14 | 成都思晗科技股份有限公司 | High-order video intelligence parking system based on image recognition |
CN111081027A (en) * | 2019-12-17 | 2020-04-28 | 浙江大华技术股份有限公司 | License plate recognition method and device, computer device and readable storage medium |
CN111210459A (en) * | 2020-01-08 | 2020-05-29 | 北京天睿空间科技股份有限公司 | Method for detecting moving target in large scene by using priori knowledge |
CN111241988A (en) * | 2020-01-08 | 2020-06-05 | 北京天睿空间科技股份有限公司 | Method for detecting and identifying moving target in large scene by combining positioning information |
CN111241988B (en) * | 2020-01-08 | 2021-07-13 | 北京天睿空间科技股份有限公司 | Method for detecting and identifying moving target in large scene by combining positioning information |
CN111882917A (en) * | 2020-06-12 | 2020-11-03 | 深圳市捷顺科技实业股份有限公司 | Vehicle queue-jumping problem processing method and processing device |
CN111738185A (en) * | 2020-06-28 | 2020-10-02 | 杭州海康威视数字技术股份有限公司 | Target identification method, device and equipment |
CN111738185B (en) * | 2020-06-28 | 2023-09-05 | 杭州海康威视数字技术股份有限公司 | Target identification method, device and equipment |
CN112016474B (en) * | 2020-08-31 | 2021-11-09 | 重庆紫光华山智安科技有限公司 | Face recognition method, device and equipment and computer readable storage medium |
CN112016474A (en) * | 2020-08-31 | 2020-12-01 | 重庆紫光华山智安科技有限公司 | Face recognition method, device and equipment and computer readable storage medium |
CN112396708A (en) * | 2020-11-02 | 2021-02-23 | 北京精英路通科技有限公司 | Parking management method and device, computer equipment and storage medium |
CN112802341A (en) * | 2020-12-30 | 2021-05-14 | 中山联合汽车技术有限公司 | Method for measuring position and attitude of front vehicle |
CN113255633B (en) * | 2021-07-16 | 2023-04-14 | 深圳市赛菲姆科技有限公司 | Camera adjustment control method, device, system and medium based on target tracking |
CN113255633A (en) * | 2021-07-16 | 2021-08-13 | 深圳市赛菲姆科技有限公司 | Camera adjustment control method, device, system and medium based on target tracking |
CN114241465A (en) * | 2021-12-14 | 2022-03-25 | 广西云高智慧城市科技有限公司 | Method for detecting and matching license plate of vehicle image and license plate identification method |
CN114241465B (en) * | 2021-12-14 | 2024-08-02 | 广西云高智慧城市科技有限公司 | Method for detecting and matching license plate of vehicle image and license plate recognition method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110188749A (en) | Designated vehicle Vehicle License Plate Recognition System and method under a kind of more vehicles | |
CN110858295B (en) | Traffic police gesture recognition method and device, vehicle control unit and storage medium | |
CN106802113B (en) | Intelligent hit telling system and method based on many shell hole algorithm for pattern recognitions | |
CN105956586B (en) | A kind of intelligent tracking system based on TOF 3D video camera | |
JP6448223B2 (en) | Image recognition system, image recognition apparatus, image recognition method, and computer program | |
US20180048482A1 (en) | Control system and control processing method and apparatus | |
JP6453488B2 (en) | Statistical method and apparatus for passersby based on identification of human head top | |
CN112699839B (en) | Automatic video target locking and tracking method under dynamic background | |
CN109143241A (en) | The fusion method and system of radar data and image data | |
CN109325456B (en) | Target identification method, target identification device, target identification equipment and storage medium | |
CN108776974B (en) | A kind of real-time modeling method method suitable for public transport scene | |
CN102567703A (en) | Hand motion identification information processing method based on classification characteristic | |
CN111860352B (en) | Multi-lens vehicle track full tracking system and method | |
CN110672111A (en) | Vehicle driving path planning method, device, system, medium and equipment | |
CN110334625A (en) | A kind of parking stall visual identifying system and its recognition methods towards automatic parking | |
CN104090664B (en) | A kind of interactive projection method, apparatus and system | |
CN103997624A (en) | Overlapped domain dual-camera target tracking system and method | |
CN113158833B (en) | Unmanned vehicle control command method based on human body posture | |
CN106845410A (en) | A kind of flame identification method based on deep learning model | |
WO2022036478A1 (en) | Machine vision-based augmented reality blind area assembly guidance method | |
CN103593641A (en) | Object detecting method and device based on stereoscopic camera | |
CN107154051A (en) | Background wipes out method and device | |
CN108871409A (en) | A kind of fault detection method and system | |
CN110516548A (en) | A kind of iris center positioning method based on three-dimensional eyeball phantom and Snakuscule | |
EP4136570A1 (en) | Artificial intelligence and computer vision powered driving-performance assessment |
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: 20190830 |