CN110991255B - Method for detecting fake-licensed car based on deep learning algorithm - Google Patents
Method for detecting fake-licensed car based on deep learning algorithm Download PDFInfo
- Publication number
- CN110991255B CN110991255B CN201911092643.2A CN201911092643A CN110991255B CN 110991255 B CN110991255 B CN 110991255B CN 201911092643 A CN201911092643 A CN 201911092643A CN 110991255 B CN110991255 B CN 110991255B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- license plate
- tail
- head
- 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.)
- Active
Links
Classifications
-
- 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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a method for detecting fake-licensed vehicles based on a deep learning algorithm, which comprises the steps of selecting any vehicle close-up diagram, and detecting and identifying all license plate information in the close-up diagram; detecting all the head and tail coordinate information in the close-up map, and associating and binding the head and tail information with license plate number information; detecting the vehicle model name of the head and tail area of each license plate; storing license plate information and bound vehicle type information into a database, judging whether the vehicle types are consistent or not if the vehicle information exists in the database, and considering the vehicle types as suspected fake-licensed vehicles if the vehicle types are inconsistent; and continuing to select the vehicle close-up map to repeat the above operation. The method selects the vehicle close-up image from the high-level video to carry out service processing, and captures the fake-licensed vehicle by combining with the deep learning algorithm, thereby ensuring the citizen rights and achieving specific practical significance for striking illegal criminal activities.
Description
Technical Field
The invention relates to the field of computer vision and machine learning, in particular to a method for detecting fake-licensed vehicles based on a deep learning algorithm.
Background
With the continuous development of social economy, the living standard of people is gradually improved, the keeping amount of motor vehicles in China is increased year by year, the illegal behavior of vehicle license plates is in multiple situations, and individual vehicle owners deliberately apply other license plate numbers to conduct the illegal behavior, so that good road traffic order is seriously disturbed, public security management and control by public security authorities is disturbed, normal market economic order is disturbed, and legal rights and interests of real vehicle owners are also damaged. The traffic law in China prescribes that the fake-licensed vehicles are not allowed to flow, but the fake-licensed vehicles are driven by benefits, the fake-licensed vehicles still exist, and the situation of the fake-licensed vehicles is remedied.
Although part of fake-licensed vehicles can be found by manual inspection, mass report and the like, the traditional method is time-consuming, labor-consuming and low in efficiency, the problem of fake-licensed vehicles is critical to be reduced by applying scientific technology, mass data are processed by an algorithm along with the development of deep learning in the field of image target detection and identification, and a new thought and solution is provided for fake-licensed behavior grabbing.
Disclosure of Invention
The invention aims to provide a method for detecting a fake-licensed car, which can improve the accuracy of fake-licensed car detection through various deep learning algorithms.
In order to achieve the above object, the present invention provides a method for detecting a fake-licensed car based on a deep learning algorithm, the method comprising:
selecting and identifying a vehicle close-up graph, and acquiring all license plate information in the vehicle close-up graph;
traversing all license plate information to obtain the head and tail information corresponding to all license plates;
binding license plate information and head and tail information, and identifying the vehicle types of all vehicles;
and judging whether all the vehicle information exists in the database, if so, comparing the vehicle types, and if not, judging that the vehicle is a suspected fake-licensed vehicle.
Further, if the vehicle information does not exist in the database, the license plate information and the head and tail information bound with the license plate are input into the database.
Further, selecting and identifying a vehicle close-up map, and obtaining all license plate information in the vehicle close-up map includes:
and selecting a vehicle close-up map, and acquiring vertex coordinates of all license plate positions in the vehicle close-up map, license plate colors, license plate numbers and license plate confidence by calling a license plate detection and recognition algorithm.
Further, if the license plate confidence is higher than a set threshold, corresponding license plate information is reserved;
if the license plate confidence is lower than the set threshold, discarding the corresponding license plate information.
Further, if the license plate confidence is higher than a set threshold, correcting the vehicle close-up graph to obtain corrected head and tail information.
Further, the correcting the vehicle close-up map specifically includes: rotating the vehicle close-up graph according to the four vertex coordinates of each license plate;
a vehicle head and tail detection algorithm is called, and confidence coefficients of all vehicle head and tail area rectangular frames and vehicle head and tail information in a vehicle close-up diagram are obtained;
if the confidence coefficient of the head and tail information is higher than a set threshold value, the head and tail information is reserved;
and if the confidence coefficient of the head and tail information is lower than the set threshold value, discarding the head and tail information.
Further, the method further comprises: comparing the head and tail information with the license plate information, determining whether the head and tail information and the license plate information are the same vehicle,
if the vehicle is the same vehicle, binding the license plate information and the vehicle head and tail information to form a group of vehicle information, wherein the vehicle information comprises license plate numbers, license plate colors and vehicle head and tail rectangular frame coordinates corresponding to the license plates.
Further, comparing the head and tail information with the license plate information, determining whether the head and tail information and the license plate information are the same vehicle or not, specifically comprising,
comparing the position relation between the rectangular frame of each vehicle head and vehicle tail and four vertexes of the license plate, if the four vertexes of the license plate are all positioned in the rectangular frame of the vehicle head and vehicle tail, selecting a center point of the license plate and a center point of the rectangular frame of the vehicle head and vehicle tail, and recognizing that the license plate and the vehicle head and vehicle tail belong to the same vehicle;
if all license plate vertices are positioned in a plurality of headstock or tailstock rectangular frames, a vehicle with the nearest license plate center point and the headstock tailstock center point is considered to be the same vehicle;
if the four vertexes of the license plate are not in the rectangular frame of any one of the front and rear of the vehicle, discarding the license plate information.
Further, if the same vehicle is confirmed, the vehicle information is confirmed to further comprise,
traversing the vehicle information, calling a vehicle type recognition algorithm, and recognizing names of vehicle types in the head and the tail of each license plate;
judging whether the vehicle exists in the database according to the license plate number and the license plate color,
if the vehicle type is present, the vehicle type comparison is carried out to judge the fake-licensed vehicle,
if the vehicle information does not exist, recording the vehicle information into a database, wherein the vehicle information comprises license plate numbers, vehicle colors and vehicle type names.
Further, the vehicle type comparison judging fake-licensed vehicle specifically comprises the steps of confirming whether the vehicle type is consistent with the historical vehicle type in the database if the historical vehicle record exists in the database, and confirming that the vehicle is the fake-licensed vehicle if the vehicle type is inconsistent with the historical vehicle type in the database.
The method for detecting the fake-licensed car based on the deep learning algorithm provided by the invention selects the close-up image of the car from the high-level video to carry out service processing, and identifies the information of all the cars in the close-up image of the car based on the deep learning algorithms such as license plate detection and identification algorithm, head-tail detection and car type identification, and the like, wherein the information comprises license plate positions, license plate numbers, license plate colors, head-tail positions and car type names, so that whether the belonged car is the fake-licensed car is further judged, the guarantee is provided for urban traffic management, and the concrete practical significance of citizen rights and illegal criminal activities is also guaranteed.
Drawings
FIG. 1 is a flow chart of a method for detecting a fake-licensed vehicle based on a deep learning algorithm of the present invention;
FIG. 2 is a flow chart of a method for detecting a fake-licensed vehicle based on a deep learning algorithm of the present invention;
FIG. 3 is a head-to-tail correction chart of a method for detecting a fake-licensed vehicle based on a deep learning algorithm of the present invention;
fig. 4 is a schematic diagram of a head and tail region of a vehicle according to a correction chart in the method for detecting a fake-licensed vehicle based on a deep learning algorithm.
Detailed Description
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
The invention discloses a method for detecting fake-licensed vehicles based on a deep learning algorithm,
specifically, as shown in fig. 1 and fig. 2, the invention discloses a method for detecting a fake-licensed car based on a deep learning algorithm, which specifically comprises the following steps:
101. selecting a vehicle close-up map, detecting and identifying the close-up map, and identifying all license plate information in the vehicle close-up map;
specifically, selecting any vehicle close-up image Pa, wherein license plate information of a plurality of vehicles possibly exists in the vehicle close-up image Pa, acquiring vertex coordinates of all license plate positions, colors of the license plates, license plate numbers and confidence degrees of the license plates in the vehicle close-up image through calling a license plate detection and recognition algorithm, forming a plurality of license plate records,
if the license plate confidence is lower than the set threshold, discarding the license plate information;
if the license plate confidence is higher than the set threshold, the license plate information is reserved.
102. Traversing all the identified license plate information, and identifying the information of the vehicle head and the vehicle tail corresponding to all the license plates;
after step 101, the license plate information with high confidence is reserved, the vehicle close-up diagram is corrected, and the corrected vehicle head and tail information is obtained, wherein the specific correction method is as follows:
as shown in fig. 3 and fig. 4, according to the obtained four vertex coordinates of each license plate, rotating the vehicle close-up map to enable the license plates to be in a horizontal angle, so that the head and tail regions of the vehicle can be conveniently identified, and then, calling a head and tail detection algorithm to obtain the rectangular frames of the head and tail regions of all vehicles in the vehicle close-up map and the confidence of the head and tail information;
if the confidence coefficient of the head and tail information is higher than a set threshold value, the head and tail information is reserved;
and if the confidence coefficient of the head and tail information is lower than the set threshold value, discarding the head and tail information.
103. Binding all license plates and the vehicle head and parking space information corresponding to the license plates, and identifying the vehicle types of all vehicles;
specifically, the method comprises the steps of judging according to four vertex coordinates of a license plate and coordinates of a rectangular frame of a front and a rear, and when the coordinates of the four vertices of the license plate are completely located in the rectangular frame of the front and the center of the license plate is closest to the center of the front and the rear of the vehicle, recognizing that the license plate and the front and the rear of the vehicle belong to the same vehicle, and storing the license plate number, the license plate color and the rectangular frame coordinates of the front and the rear of the vehicle to form a vehicle record.
And then, sequentially detecting the name and the confidence coefficient of the vehicle corresponding to each vehicle by calling a vehicle type detection algorithm, discarding the vehicle record if the confidence coefficient of the vehicle is lower, and reserving the vehicle record with high confidence coefficient of the vehicle.
104. And judging whether the vehicle information exists in the database, if so, comparing the vehicle types, and if not, judging that the vehicle is a suspected fake-licensed vehicle.
Specifically, traversing the vehicle information, inquiring whether a vehicle record exists in the database according to the license plate number and the license plate color, if the license plate number vehicle color records exist in the database, comparing the vehicle type corresponding to the license plate with the vehicle type existing in the database, and if the vehicle type comparison is inconsistent, considering the vehicle as a suspected fake license plate vehicle.
If the license plate number vehicle color record is not in the database, the vehicle record is fed into the database for the next vehicle type comparison of the vehicle, and meanwhile, the original database is enriched.
In the present invention, the pre-established database may include: a plurality of vehicle model databases, each vehicle model database comprising: a set of multiple sample images of the vehicle model; the sample image of the vehicle model comprises: vehicle images under different illumination conditions, vehicle images with different shooting angles and vehicle images with different scenes so as to ensure the integrity of vehicle type information.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (7)
1. A method for detecting a fake-licensed vehicle based on a deep learning algorithm, the method comprising:
calling a license plate detection and recognition algorithm to obtain vertex coordinates of all license plate positions in a vehicle close-up map, license plate colors, license plate numbers and license plate confidence, wherein the license plate colors and the license plate numbers form license plate information;
if the license plate confidence is higher than a set threshold, corresponding license plate information is reserved, the vehicle close-up diagram is corrected, and corrected vehicle head information or corrected vehicle tail information is obtained;
comparing the position relation between each head rectangular frame or each tail rectangular frame and four vertexes of the license plate according to the corrected head information or the corrected tail information and the vertex coordinates of the license plate position;
if the positions of the four vertexes of the license plate are all located in the head rectangular frame or the tail rectangular frame, the license plate and the head or the tail are considered to belong to the same vehicle;
if the positions of the four vertexes of the license plate are all located in a plurality of front rectangular frames or a plurality of rear rectangular frames, selecting a license plate center point and a front rectangular frame center point or a rear rectangular frame center point, and recognizing that one vehicle with the closest distance between the license plate center point and the front rectangular frame center point or the rear rectangular frame center point is the same vehicle;
if the vehicle is the same vehicle, binding the license plate information and the vehicle head information or the vehicle tail information to form vehicle information, and identifying the vehicle type of the vehicle;
and judging whether the vehicle information exists in the database, if so, comparing the vehicle types, and if not, judging that the vehicle is a suspected fake-licensed vehicle.
2. The method of detecting a fake-licensed car based on the deep learning algorithm of claim 1, further comprising:
if the vehicle information does not exist in the database, the license plate information and the head information or the tail information bound with the license plate information and the vehicle type are recorded into the database.
3. The method of detecting a fake-licensed car based on the deep learning algorithm of claim 2, further comprising:
and if the license plate confidence is lower than the set threshold, discarding the corresponding license plate information.
4. A method of detecting a fake-licensed vehicle based on a deep learning algorithm according to claim 3, characterized in that the correcting the vehicle close-up map comprises:
rotating the vehicle close-up image according to the four vertexes of the license plate to enable the license plate to be in a horizontal position;
a vehicle head and tail detection algorithm is called, and the confidence level of the vehicle head rectangular frames or the vehicle tail rectangular frames and the vehicle head information or the confidence level of the vehicle tail information of all vehicles in the vehicle close-up diagram are obtained;
if the confidence coefficient of the head information or the confidence coefficient of the tail information is higher than a head set threshold or a tail set threshold, reserving the head information or the tail information;
if the confidence coefficient of the head information or the confidence coefficient of the tail information is lower than the head set threshold or the tail set threshold, discarding the head information or the tail information.
5. The method of detecting a fake-licensed car based on the deep learning algorithm of claim 4, further comprising:
and if the four vertexes of the license plate are not in any one of the rectangular frame of the vehicle head or the rectangular frame of the vehicle tail, discarding the license plate information.
6. The method for detecting a fake-licensed car based on the deep learning algorithm according to claim 5, wherein after the license plate information and the head information or the tail information are bound to form car information if the same car, the method further comprises:
traversing the vehicle information, calling a vehicle type recognition algorithm, and recognizing the vehicle type name in the rectangular frame of the vehicle head or the rectangular frame of the vehicle tail corresponding to each license plate;
judging whether a vehicle exists in a database according to the license plate number and the license plate color;
if yes, comparing the vehicle types and judging the fake-licensed vehicle;
if the vehicle information does not exist, the vehicle information is input into a database, and the vehicle information comprises the license plate number, the vehicle color and the vehicle model name.
7. The method for detecting a fake-licensed car based on the deep learning algorithm of claim 6, wherein the performing the car type comparison and judgment fake-licensed car comprises:
if the historical vehicle records exist in the database, whether the vehicle type is consistent with the historical vehicle type in the database is confirmed, and if the vehicle type is inconsistent with the historical vehicle type, the vehicle is confirmed to be a fake-licensed vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911092643.2A CN110991255B (en) | 2019-11-11 | 2019-11-11 | Method for detecting fake-licensed car based on deep learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911092643.2A CN110991255B (en) | 2019-11-11 | 2019-11-11 | Method for detecting fake-licensed car based on deep learning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110991255A CN110991255A (en) | 2020-04-10 |
| CN110991255B true CN110991255B (en) | 2023-09-08 |
Family
ID=70083708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911092643.2A Active CN110991255B (en) | 2019-11-11 | 2019-11-11 | Method for detecting fake-licensed car based on deep learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110991255B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932903B (en) * | 2020-09-02 | 2022-04-19 | 智慧互通科技股份有限公司 | Parking lot entrance and exit management method and system based on multiple cameras |
| CN112885108B (en) * | 2020-12-23 | 2022-02-01 | 爱泊车美好科技有限公司 | Vehicle change detection method and system on parking space based on deep learning algorithm |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261771A (en) * | 2008-03-14 | 2008-09-10 | 康华武 | An automatic checking method for vehicle identity on the road |
| CN101540105A (en) * | 2009-04-15 | 2009-09-23 | 四川川大智胜软件股份有限公司 | Fake-licensed car detection method based on number-plate identification and gridding supervision |
| CN101635092A (en) * | 2009-05-22 | 2010-01-27 | 上海宝康电子控制工程有限公司 | Identification system and method of unlicensed motor vehicles |
| CN102521986A (en) * | 2011-12-05 | 2012-06-27 | 沈阳聚德视频技术有限公司 | Automatic detection system for fake plate vehicle and control method for automatic detection system |
| CN103246876A (en) * | 2013-05-10 | 2013-08-14 | 苏州祥益网络科技有限公司 | Image feature comparison based counterfeit vehicle registration plate identification method |
| CN103279739A (en) * | 2013-05-10 | 2013-09-04 | 浙江捷尚视觉科技有限公司 | Fake license plate detection method based on vehicle characteristic matching |
| CN103294775A (en) * | 2013-05-10 | 2013-09-11 | 苏州祥益网络科技有限公司 | Police service cloud image recognition vehicle management and control system based on geographic space-time constraint |
| CN103488973A (en) * | 2013-09-12 | 2014-01-01 | 上海依图网络科技有限公司 | Method and system for recognizing vehicle brand based on image |
| CN103617735A (en) * | 2013-12-20 | 2014-03-05 | 深圳市捷顺科技实业股份有限公司 | Vehicle identification method and system |
| CN106128113A (en) * | 2016-08-01 | 2016-11-16 | 深圳市永兴元科技有限公司 | The recognition methods of fake license plate vehicle and device |
| CN106599905A (en) * | 2016-11-25 | 2017-04-26 | 杭州中奥科技有限公司 | Fake-licensed vehicle analysis method based on deep learning |
| CN106650550A (en) * | 2015-10-28 | 2017-05-10 | 中通服公众信息产业股份有限公司 | Vehicle model identification method and vehicle model identification system through image characteristics of vehicle mark and vehicle head |
| CN106778648A (en) * | 2016-12-26 | 2017-05-31 | 江苏盛世华安智能科技股份有限公司 | Vehicle tracing and Vehicle License Plate Recognition System and recognition methods |
| CN107273792A (en) * | 2017-04-27 | 2017-10-20 | 北京果毅科技有限公司 | Model recognizing method and device |
| CN107346435A (en) * | 2017-06-15 | 2017-11-14 | 浙江捷尚视觉科技股份有限公司 | A kind of suspicion fake-licensed car catching method based on vehicle characteristics storehouse |
| CN108681707A (en) * | 2018-05-15 | 2018-10-19 | 桂林电子科技大学 | Wide-angle model recognizing method and system based on global and local Fusion Features |
| CN108694399A (en) * | 2017-04-07 | 2018-10-23 | 杭州海康威视数字技术股份有限公司 | Licence plate recognition method, apparatus and system |
-
2019
- 2019-11-11 CN CN201911092643.2A patent/CN110991255B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261771A (en) * | 2008-03-14 | 2008-09-10 | 康华武 | An automatic checking method for vehicle identity on the road |
| CN101540105A (en) * | 2009-04-15 | 2009-09-23 | 四川川大智胜软件股份有限公司 | Fake-licensed car detection method based on number-plate identification and gridding supervision |
| CN101635092A (en) * | 2009-05-22 | 2010-01-27 | 上海宝康电子控制工程有限公司 | Identification system and method of unlicensed motor vehicles |
| CN102521986A (en) * | 2011-12-05 | 2012-06-27 | 沈阳聚德视频技术有限公司 | Automatic detection system for fake plate vehicle and control method for automatic detection system |
| CN103246876A (en) * | 2013-05-10 | 2013-08-14 | 苏州祥益网络科技有限公司 | Image feature comparison based counterfeit vehicle registration plate identification method |
| CN103279739A (en) * | 2013-05-10 | 2013-09-04 | 浙江捷尚视觉科技有限公司 | Fake license plate detection method based on vehicle characteristic matching |
| CN103294775A (en) * | 2013-05-10 | 2013-09-11 | 苏州祥益网络科技有限公司 | Police service cloud image recognition vehicle management and control system based on geographic space-time constraint |
| CN103488973A (en) * | 2013-09-12 | 2014-01-01 | 上海依图网络科技有限公司 | Method and system for recognizing vehicle brand based on image |
| CN103617735A (en) * | 2013-12-20 | 2014-03-05 | 深圳市捷顺科技实业股份有限公司 | Vehicle identification method and system |
| CN106650550A (en) * | 2015-10-28 | 2017-05-10 | 中通服公众信息产业股份有限公司 | Vehicle model identification method and vehicle model identification system through image characteristics of vehicle mark and vehicle head |
| CN106128113A (en) * | 2016-08-01 | 2016-11-16 | 深圳市永兴元科技有限公司 | The recognition methods of fake license plate vehicle and device |
| CN106599905A (en) * | 2016-11-25 | 2017-04-26 | 杭州中奥科技有限公司 | Fake-licensed vehicle analysis method based on deep learning |
| CN106778648A (en) * | 2016-12-26 | 2017-05-31 | 江苏盛世华安智能科技股份有限公司 | Vehicle tracing and Vehicle License Plate Recognition System and recognition methods |
| CN108694399A (en) * | 2017-04-07 | 2018-10-23 | 杭州海康威视数字技术股份有限公司 | Licence plate recognition method, apparatus and system |
| CN107273792A (en) * | 2017-04-27 | 2017-10-20 | 北京果毅科技有限公司 | Model recognizing method and device |
| CN107346435A (en) * | 2017-06-15 | 2017-11-14 | 浙江捷尚视觉科技股份有限公司 | A kind of suspicion fake-licensed car catching method based on vehicle characteristics storehouse |
| CN108681707A (en) * | 2018-05-15 | 2018-10-19 | 桂林电子科技大学 | Wide-angle model recognizing method and system based on global and local Fusion Features |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110991255A (en) | 2020-04-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886896B (en) | Blue license plate segmentation and correction method | |
| CN102722704B (en) | Method and system for recognizing vehicle license plate by integrating video dynamic tracking | |
| CN105512660B (en) | License plate number identification method and device | |
| CN109190444B (en) | Method for realizing video-based toll lane vehicle feature recognition system | |
| CN105320923B (en) | Model recognizing method and device | |
| WO2017125063A1 (en) | Processing method and device for vehicle traffic violation | |
| CN106600977A (en) | Parking violation detection method and system based on multi-feature identification | |
| CN110991255B (en) | Method for detecting fake-licensed car based on deep learning algorithm | |
| CN104427310B (en) | Image storage method and its device | |
| CN108256445B (en) | Lane line detection method and system | |
| CN111597905B (en) | Highway tunnel parking detection method based on video technology | |
| CN101567041A (en) | Method for recognizing characters of number plate images of motor vehicles based on trimetric projection | |
| CN111369801B (en) | Vehicle identification method, device, equipment and storage medium | |
| CN112084900A (en) | Underground garage random parking detection method based on video analysis | |
| CN112651293B (en) | Video detection method for road illegal spreading event | |
| Pinthong et al. | License plate tracking based on template matching technique | |
| CN111488808A (en) | Lane line detection method based on traffic violation image data | |
| CN111209905A (en) | Defect shielding license plate recognition method based on combination of deep learning and OCR technology | |
| CN113221760A (en) | Expressway motorcycle detection method | |
| CN102280028B (en) | Vehicle monitoring method based on dynamic background analysis and monitoring tape scanning | |
| CN108985197B (en) | Automatic detection method for taxi driver smoking behavior based on multi-algorithm fusion | |
| CN110969135A (en) | Vehicle logo recognition method in natural scene | |
| JP4784932B2 (en) | Vehicle discrimination device and program thereof | |
| CN109977772A (en) | A kind of zebra stripes comity behavioral value method based on vehicle-mounted traveling recorder video | |
| CN104504702A (en) | Cement notch pavement crack recognition method based on square lattice searching method |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 075000 ten building, phase 1, airport economic and Technological Development Zone, Zhangjiakou, Hebei Applicant after: Smart intercommunication Technology Co.,Ltd. Address before: 075000 ten building, phase 1, airport economic and Technological Development Zone, Zhangjiakou, Hebei Applicant before: INTELLIGENT INTER CONNECTION TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |