CN104700620A - Traffic checkpoint-based method and device for recognizing fake-licensed vehicles - Google Patents
Traffic checkpoint-based method and device for recognizing fake-licensed vehicles Download PDFInfo
- Publication number
- CN104700620A CN104700620A CN201410124292.XA CN201410124292A CN104700620A CN 104700620 A CN104700620 A CN 104700620A CN 201410124292 A CN201410124292 A CN 201410124292A CN 104700620 A CN104700620 A CN 104700620A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- image
- licensed
- fake
- license plate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000004364 calculation method Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 229920000642 polymer Polymers 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Vehicle Waterproofing, Decoration, And Sanitation Devices (AREA)
Abstract
The invention discloses a traffic checkpoint-based method and device for recognizing fake-licensed vehicles. The method includes: determining images of vehicles, to be used as search objects, at a checkpoint; determining whether or not a vehicle reference image is provided; if yes, based on license plate number information, according to the vehicle reference image and the images of the vehicles at the checkpoint, generating paired images of suspected fake-licensed vehicles; if not, based on the license plate number information, generating paired images of suspected fake-licensed vehicles directly according to the images of the vehicles at the checkpoint; for each image pair of the suspected fake-licensed vehicles, acquiring texture feature codes of each image, and calculating similarity between the two texture feature codes acquired; if the similarity is less than a preset threshold, determining that the vehicles in the paired images of the suspected fake-licensed vehicles are mutually fake-licensed vehicles. The traffic checkpoint-based method and device has the advantages such that accuracy of recognition results can be improved.
Description
Technical Field
The invention relates to the field of intelligent analysis, in particular to a method and a device for identifying fake-licensed vehicles based on a traffic checkpoint.
Background
In the prior art, the fake-licensed vehicle is generally identified based on information such as license plate number, vehicle logo and vehicle body color, but the identification accuracy of the method is low. For example, due to the change of the ambient light in different time periods, the same vehicle is likely to be misjudged as a fake-licensed vehicle, and in addition, if the color of the fake-licensed vehicle is the same as that of the original vehicle and the vehicle logo is the same, the fake-licensed vehicle cannot be identified.
Disclosure of Invention
In view of the above, the invention provides a method and a device for identifying a fake-licensed vehicle based on a traffic gate, which can improve the accuracy of an identification result.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a fake-licensed vehicle identification method based on a traffic checkpoint comprises the following steps:
determining each gate vehicle image as a search object;
determining whether a vehicle reference image is set;
if yes, generating a suspected fake-licensed vehicle image pair according to the vehicle reference image and each gate vehicle image based on the license plate number information; if not, directly generating a suspected fake-licensed vehicle image pair according to each gate vehicle image based on the license plate number information;
and respectively acquiring the texture feature code of each image of each suspected fake-licensed vehicle image pair, calculating the similarity between the two acquired texture feature codes, and if the similarity is smaller than a preset threshold value, determining that the vehicles in the suspected fake-licensed vehicle image pair are fake-licensed vehicles.
A fake-licensed vehicle identification device based on a traffic gate, comprising:
the first processing module is used for determining each gate vehicle image as a search object; determining whether a vehicle reference image is set or not, if so, generating a suspected fake-licensed vehicle image pair according to the vehicle reference image and each gate vehicle image based on license plate number information, and if not, directly generating the suspected fake-licensed vehicle image pair according to each gate vehicle image based on the license plate number information; sending the generated suspected fake-licensed vehicle image pair to a second processing module;
the second processing module is used for respectively obtaining the texture feature code of each image of each suspected fake-licensed vehicle image pair, calculating the similarity between the two obtained texture feature codes, and if the similarity is smaller than a preset threshold value, determining that the vehicles in the suspected fake-licensed vehicle image pair are fake-licensed vehicles.
Therefore, by adopting the scheme of the invention, when the fake-licensed vehicle is identified, the license plate number information and the textural feature information of the vehicle can be considered, the textural feature information is not influenced by light change and the like, and the characteristics of the vehicle can be more objectively and accurately reflected compared with a vehicle logo, the color of a vehicle body and the like, so that the problems in the prior art are solved, and the accuracy of the identification result is improved.
Drawings
FIG. 1 is a flow chart of an embodiment of a method for identifying a fake-licensed vehicle based on a traffic gate according to the present invention.
Fig. 2 is a schematic view of a composition structure of an embodiment of the fake-licensed vehicle identification device based on a traffic gate.
Detailed Description
In order to make the technical solution of the present invention clearer and more obvious, the solution of the present invention is further described in detail below by referring to the drawings and examples.
FIG. 1 is a flow chart of an embodiment of a method for identifying a fake-licensed vehicle based on a traffic gate according to the present invention. As shown in FIG. 1, the method comprises the following steps 11-15.
Step 11: the respective gate vehicle images to be searched are determined.
In the prior art, in some important traffic gates, such as highway toll gates, public security checkpoints, etc., each passing vehicle is usually photographed by using a deployed camera device, and the photographed gate vehicle image is stored in a database for subsequent retrieval and viewing, etc., and the gate vehicle image is a vehicle front image.
In the scheme of the invention, the identification of the fake-licensed vehicle can be realized based on the vehicle image at the checkpoint; the specific determination of which gate vehicle images are the search objects can be determined according to actual needs, and the search range for searching the fake-licensed vehicle is formed by the gate vehicle images serving as the search objects.
Step 12: it is determined whether a vehicle reference image is provided and if so, step 13 is performed, otherwise, step 14 is performed.
The user may or may not provide one image as the vehicle reference image, and the subsequent processing modes may be different according to whether the user provides the vehicle reference image, as shown in step 13 and step 14.
The vehicle reference image provided by the user also needs to be a vehicle front image similar to the image of the vehicle at the gate, or the user can directly provide one image of the vehicle at the gate as the vehicle reference image.
Step 13: and based on the license plate number information, generating a suspected fake-licensed vehicle image pair according to the vehicle reference image and each bayonet vehicle image, and then executing the step 15.
The specific implementation manner in this step may be:
A. how to obtain the license plate number of the vehicle reference image, namely the license plate number of the vehicle in the vehicle reference image, is the prior art;
B. and aiming at each vehicle image of the gate, respectively obtaining the license plate number of the vehicle image of the gate, determining whether the license plate number of the vehicle image of the gate is the same as the license plate number of the vehicle reference image, and if so, forming a suspected fake-licensed vehicle image pair by the vehicle image of the gate and the vehicle reference image.
For example, the following steps are carried out:
assuming that the number of the bayonet vehicle images determined as the search object is 1000, and 5 license plates are the same as the license plate number of the vehicle reference image, 5 pairs of suspected fake-licensed vehicle images can be formed, wherein each pair of suspected fake-licensed vehicle images comprises two images, namely a vehicle reference image and a bayonet vehicle image with the same license plate number as the vehicle reference image.
Step 14: and (3) directly generating a suspected fake-licensed vehicle image pair according to each gate vehicle image based on the license plate number information, and then executing the step 15.
The specific implementation manner of this step may be:
A. respectively obtaining license plate numbers of the vehicle images of all the checkpoints;
B. dividing the images of the vehicles at the gates with the same license plate number into a group;
in practical application, the images of the vehicles in the gate with the same license plate number can be clustered by using a character string processing algorithm (such as a dictionary tree), and each clustering result corresponds to one group;
C. for each group, respectively determining whether the number of the included bayonet vehicle images is greater than 1, if so, respectively forming a suspected fake-licensed vehicle image pair by each two different bayonet vehicle images in the group, wherein the bayonet vehicle images included in any two suspected fake-licensed vehicle image pairs are different;
the number of the bayonet vehicle images included in each group may be one or multiple, and if the number of the bayonet vehicle images is multiple, two different pairs of suspected fake-licensed vehicle images can be generated according to the bayonet vehicle images in the group.
For example, the following steps are carried out:
assuming that the group a includes 2 mount vehicle images, which are mount vehicle image 1 and mount vehicle image 2; then, a suspected fake-licensed vehicle image pair can be formed by the bayonet vehicle image 1 and the bayonet vehicle image 2;
assuming that the group B comprises 3 mount vehicle images in total, namely a mount vehicle image 1, a mount vehicle image 2 and a mount vehicle image 3; then, a suspected fake-licensed vehicle image pair can be formed by the bayonet vehicle image 1 and the bayonet vehicle image 2, a suspected fake-licensed vehicle image pair can be formed by the bayonet vehicle image 1 and the bayonet vehicle image 3, and a suspected fake-licensed vehicle image pair can be formed by the bayonet vehicle image 2 and the bayonet vehicle image 3, so that 3 suspected fake-licensed vehicle image pairs are obtained.
Step 15: and respectively acquiring the texture feature code of each image of each suspected fake-licensed vehicle image pair, calculating the similarity between the two acquired texture feature codes, if the similarity is smaller than a preset threshold value, determining that the vehicles in the suspected fake-licensed vehicle image pair are fake-licensed vehicles, and finishing the processing.
After the suspected fake-licensed vehicles have been initially filtered through the processing shown in steps 13 and 14, the final fake-licensed vehicles may be further determined in the manner shown in step 15.
Specifically, before obtaining the texture feature code of each image, the following processing may be performed: determining whether the image needs to be corrected, if so, performing geometric alignment operation on the image, wherein the geometric alignment operation can be alignment according to a license plate or a vehicle logo, and the like, so as to facilitate subsequent texture feature code acquisition and how to correct the image.
In addition, the texture feature code of each image may be obtained by: respectively obtaining texture feature codes of P preset areas in the image, and combining the obtained P texture feature codes according to a preset mode to obtain the texture feature codes of the image, wherein P is a positive integer greater than 1, and the specific value can be determined according to actual needs.
The combining the obtained P texture feature codes according to the predetermined manner may be to cascade the obtained P texture feature codes according to a predetermined sequence.
The texture features generally refer to image texture features which are robust to light and color changes and efficient in calculation. Accordingly, the texture feature code includes, but is not limited to: haar (Haar), Local Binary Patterns (LBP), etc.
The specific areas of each predetermined area may be determined according to actual needs, and preferably, each predetermined area needs to be able to reflect differences between different vehicles, such as an annual inspection mark pasting area (pasting modes may be different on different vehicles), a rear view mirror area (different hanging decorations may be hung on rear view mirrors of different vehicles), and the like.
The size and position of each predetermined area can be preset, so that each predetermined area can be accurately found in each image according to the preset size and position, the texture feature code of each predetermined area is obtained, and how to obtain the texture feature code is the prior art.
For each suspected fake-licensed vehicle image pair, after texture feature codes of two images are obtained, the similarity between the two texture feature codes can be calculated, and the specific calculation mode is not limited, such as any mode which can be thought by those skilled in the art can be adopted; then, whether the calculated similarity is smaller than a preset threshold value or not is determined, if yes, the vehicles in the suspected fake-licensed vehicle image pair can be determined to be fake-licensed vehicles, and if not, the vehicles in the suspected fake-licensed vehicle image pair are determined to be the same vehicle; the specific value of the threshold can be determined according to actual needs.
For example, the following steps are carried out:
assuming that 5 suspected fake-licensed vehicle image pairs exist in total, the images are a suspected fake-licensed vehicle image pair 1, a suspected fake-licensed vehicle image pair 2, a suspected fake-licensed vehicle image pair 3, a suspected fake-licensed vehicle image pair 4 and a suspected fake-licensed vehicle image pair 5 respectively; the similarity between the texture feature codes of the two images in the suspected fake-licensed vehicle image pair 1 and the similarity between the texture feature codes of the two images in the suspected fake-licensed vehicle image pair 3 are both smaller than a predetermined threshold value, so that it can be determined that the two vehicles in the suspected fake-licensed vehicle image pair 1 are fake-licensed vehicles and the two vehicles in the suspected fake-licensed vehicle image pair 3 are fake-licensed vehicles.
In addition, when the scheme of the invention is realized, a plurality of threads can be started simultaneously, and all the threads work simultaneously so as to accelerate the processing speed.
For example, the following steps are carried out:
assuming that the total number of the gate vehicle images determined as the search object is 1000, 5 threads can be started simultaneously, each thread is responsible for processing 200 gate vehicle images respectively, including acquiring the license plate number and comparing the license plate number with the license plate number of the vehicle reference image to determine whether the images are the same, and if the images are the same, forming a suspected fake-licensed vehicle image and the like.
Furthermore, in the processing process, the current processing progress can be fed back to the user in real time, and the generated suspected fake-licensed vehicle image and the like can be displayed in real time.
Based on the above description, fig. 2 is a schematic structural diagram of a composition of an embodiment of the fake-licensed vehicle identification device based on a traffic gate according to the present invention. As shown in fig. 2, includes: the device comprises a first processing module and a second processing module.
The first processing module is used for determining each gate vehicle image as a search object; determining whether a vehicle reference image is set or not, if so, generating a suspected fake-licensed vehicle image pair according to the vehicle reference image and each gate vehicle image based on the license plate number information, and if not, directly generating the suspected fake-licensed vehicle image pair according to each gate vehicle image based on the license plate number information; sending the generated suspected fake-licensed vehicle image pair to a second processing module;
and the second processing module is used for respectively acquiring the texture feature code of each image of each suspected fake-licensed vehicle image pair, calculating the similarity between the two acquired texture feature codes, and if the similarity is smaller than a preset threshold value, determining that the vehicles in the suspected fake-licensed vehicle image pair are fake-licensed vehicles.
Wherein,
the first processing module may specifically include:
the first processing unit is used for determining each bayonet vehicle image as a search object and determining whether a vehicle reference image is set, if so, the second processing unit is informed to execute the self-function, otherwise, the third processing unit is informed to execute the self-function;
the second processing unit is used for acquiring the license plate number of the vehicle reference image; respectively acquiring the license plate number of each bayonet vehicle image, determining whether the license plate number of the bayonet vehicle image is the same as that of the vehicle reference image, and if so, forming a suspected fake-plate vehicle image pair by the bayonet vehicle image and the vehicle reference image; sending the obtained suspected fake-licensed vehicle image pair to a second processing module;
the third processing unit is used for respectively acquiring license plate numbers of the vehicle images of all the checkpoints; dividing the images of the vehicles at the gates with the same license plate number into a group; for each group, respectively determining whether the number of the included bayonet vehicle images is greater than 1, if so, respectively forming a suspected fake-licensed vehicle image pair by each two different bayonet vehicle images in the group, wherein the bayonet vehicle images included in any two suspected fake-licensed vehicle image pairs are different; and sending the obtained suspected fake-licensed vehicle image pair to a second processing module.
In addition, the first and second substrates are,
the second processing module may be further configured to determine whether a correction is required for each image before obtaining the texture feature code of the image, and if so, perform a geometric alignment operation on the image.
Preferably, the first and second liquid crystal films are made of a polymer,
the second processing module may respectively obtain texture feature codes of P predetermined regions in each image, and combine the obtained P texture feature codes according to a predetermined manner to obtain the texture feature codes of the image, where P is a positive integer greater than 1.
For a specific work flow of the embodiment of the apparatus shown in fig. 2, please refer to the corresponding description in the foregoing method embodiment, which is not repeated herein.
In summary, the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A fake-licensed vehicle identification method based on a traffic checkpoint is characterized by comprising the following steps:
determining each gate vehicle image as a search object;
determining whether a vehicle reference image is set;
if yes, generating a suspected fake-licensed vehicle image pair according to the vehicle reference image and each gate vehicle image based on the license plate number information; if not, directly generating a suspected fake-licensed vehicle image pair according to each gate vehicle image based on the license plate number information;
and respectively acquiring the texture feature code of each image of each suspected fake-licensed vehicle image pair, calculating the similarity between the two acquired texture feature codes, and if the similarity is smaller than a preset threshold value, determining that the vehicles in the suspected fake-licensed vehicle image pair are fake-licensed vehicles.
2. The method of claim 1,
the generating a suspected fake-licensed vehicle image pair according to the vehicle reference image and each gate vehicle image based on the license plate number information comprises:
acquiring a license plate number of the vehicle reference image;
and aiming at each vehicle image of the gate, respectively obtaining the license plate number of the vehicle image of the gate, determining whether the license plate number of the vehicle image of the gate is the same as the license plate number of the vehicle reference image, and if so, forming a suspected fake-card vehicle image pair by the vehicle image of the gate and the vehicle reference image.
3. The method of claim 1,
the step of directly generating a suspected fake-licensed vehicle image pair according to each gate vehicle image based on the license plate number information comprises the following steps:
respectively obtaining license plate numbers of the vehicle images of all the checkpoints;
dividing the images of the vehicles at the gates with the same license plate number into a group;
and respectively determining whether the number of the included bayonet vehicle images is greater than 1 or not for each group, if so, respectively forming a suspected fake-licensed vehicle image pair by each two different bayonet vehicle images in the group, wherein the bayonet vehicle images included in any two suspected fake-licensed vehicle image pairs are different.
4. The method of claim 1, 2 or 3,
before the obtaining the texture feature code of each image, the method further includes: it is determined whether a correction is required for the image and, if so, a geometric registration operation is performed on the image.
5. The method of claim 1, 2 or 3,
the acquiring the texture feature code of each image comprises:
respectively obtaining texture feature codes of P preset areas in the image, and combining the obtained P texture feature codes according to a preset mode to obtain the texture feature codes of the image, wherein P is a positive integer larger than 1.
6. The method of claim 5,
the texture feature code includes but is not limited to: haar, local binary pattern LBP.
7. The utility model provides a fake-licensed vehicle recognition device based on traffic bayonet, its characterized in that includes:
the first processing module is used for determining each gate vehicle image as a search object; determining whether a vehicle reference image is set or not, if so, generating a suspected fake-licensed vehicle image pair according to the vehicle reference image and each gate vehicle image based on license plate number information, and if not, directly generating the suspected fake-licensed vehicle image pair according to each gate vehicle image based on the license plate number information; sending the generated suspected fake-licensed vehicle image pair to a second processing module;
the second processing module is used for respectively obtaining the texture feature code of each image of each suspected fake-licensed vehicle image pair, calculating the similarity between the two obtained texture feature codes, and if the similarity is smaller than a preset threshold value, determining that the vehicles in the suspected fake-licensed vehicle image pair are fake-licensed vehicles.
8. The apparatus of claim 7,
the first processing module comprises:
the first processing unit is used for determining each bayonet vehicle image as a search object and determining whether a vehicle reference image is set, if so, the second processing unit is informed to execute the self-function, otherwise, the third processing unit is informed to execute the self-function;
the second processing unit is used for acquiring the license plate number of the vehicle reference image; respectively acquiring the license plate number of each bayonet vehicle image, determining whether the license plate number of the bayonet vehicle image is the same as that of the vehicle reference image, and if so, forming a suspected fake-licensed vehicle image pair by the bayonet vehicle image and the vehicle reference image; sending the obtained suspected fake-licensed vehicle image pair to the second processing module;
the third processing unit is used for respectively acquiring license plate numbers of the vehicle images of all the gates; dividing the images of the vehicles at the gates with the same license plate number into a group; for each group, respectively determining whether the number of the included bayonet vehicle images is greater than 1, if so, respectively forming a suspected fake-licensed vehicle image pair by each two different bayonet vehicle images in the group, wherein the bayonet vehicle images included in any two suspected fake-licensed vehicle image pairs are different; and sending the obtained suspected fake-licensed vehicle image pair to the second processing module.
9. The apparatus according to claim 7 or 8,
the second processing module is further configured to determine whether a correction is required for each image before obtaining the texture feature code of the image, and if so, perform a geometric alignment operation on the image.
10. The apparatus according to claim 7 or 8,
and the second processing module respectively acquires P texture feature codes of preset regions in each image, and combines the acquired P texture feature codes according to a preset mode to acquire the texture feature codes of the image, wherein P is a positive integer greater than 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410124292.XA CN104700620B (en) | 2014-03-28 | 2014-03-28 | A kind of fake license plate vehicle recognition method and device based on traffic block port |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410124292.XA CN104700620B (en) | 2014-03-28 | 2014-03-28 | A kind of fake license plate vehicle recognition method and device based on traffic block port |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104700620A true CN104700620A (en) | 2015-06-10 |
| CN104700620B CN104700620B (en) | 2018-06-22 |
Family
ID=53347692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410124292.XA Active CN104700620B (en) | 2014-03-28 | 2014-03-28 | A kind of fake license plate vehicle recognition method and device based on traffic block port |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104700620B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488479A (en) * | 2015-12-03 | 2016-04-13 | 浙江宇视科技有限公司 | Weighted local feature comparison based vehicle fake plate identification method and apparatus |
| CN105551261A (en) * | 2016-03-04 | 2016-05-04 | 博康智能网络科技股份有限公司 | False-license-plate vehicle detection method and system |
| CN105684059A (en) * | 2016-01-19 | 2016-06-15 | 冯旋宇 | Violation identification method and system for intelligent traffic |
| CN108388888A (en) * | 2018-03-23 | 2018-08-10 | 腾讯科技（深圳）有限公司 | A kind of vehicle identification method, device and storage medium |
| CN108898133A (en) * | 2018-06-06 | 2018-11-27 | 安徽大学 | A kind of fake-licensed car recognition methods based on image analysis |
| CN109101951A (en) * | 2018-09-03 | 2018-12-28 | 杨兴东 | A kind of method and system identifying fake license plate vehicle |
| CN110414459A (en) * | 2019-08-02 | 2019-11-05 | 中星智能系统技术有限公司 | Establish the associated method and device of people's vehicle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009131209A1 (en) * | 2008-04-24 | 2009-10-29 | 日本電気株式会社 | Image matching device, image matching method, and image matching program |
| CN102184413A (en) * | 2011-05-16 | 2011-09-14 | 浙江大华技术股份有限公司 | Automatic vehicle body color recognition method of intelligent vehicle monitoring system |
| 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 |
| CN102610102A (en) * | 2012-02-27 | 2012-07-25 | 安科智慧城市技术（中国）有限公司 | Suspect vehicle inspection and control method and 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 |
-
2014
- 2014-03-28 CN CN201410124292.XA patent/CN104700620B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009131209A1 (en) * | 2008-04-24 | 2009-10-29 | 日本電気株式会社 | Image matching device, image matching method, and image matching program |
| CN102184413A (en) * | 2011-05-16 | 2011-09-14 | 浙江大华技术股份有限公司 | Automatic vehicle body color recognition method of intelligent vehicle monitoring system |
| 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 |
| CN102610102A (en) * | 2012-02-27 | 2012-07-25 | 安科智慧城市技术（中国）有限公司 | Suspect vehicle inspection and control method and 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 |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488479A (en) * | 2015-12-03 | 2016-04-13 | 浙江宇视科技有限公司 | Weighted local feature comparison based vehicle fake plate identification method and apparatus |
| CN105488479B (en) * | 2015-12-03 | 2019-08-02 | 浙江宇视科技有限公司 | A kind of counterfeit vehicle registration plate identification method and device based on weighting local feature comparison |
| CN105684059A (en) * | 2016-01-19 | 2016-06-15 | 冯旋宇 | Violation identification method and system for intelligent traffic |
| WO2017124302A1 (en) * | 2016-01-19 | 2017-07-27 | 冯旋宇 | Violation recognition method and system for intelligent transportation |
| CN105551261A (en) * | 2016-03-04 | 2016-05-04 | 博康智能网络科技股份有限公司 | False-license-plate vehicle detection method and system |
| CN108388888A (en) * | 2018-03-23 | 2018-08-10 | 腾讯科技（深圳）有限公司 | A kind of vehicle identification method, device and storage medium |
| CN108388888B (en) * | 2018-03-23 | 2022-04-05 | 腾讯科技（深圳）有限公司 | Vehicle identification method and device and storage medium |
| CN108898133A (en) * | 2018-06-06 | 2018-11-27 | 安徽大学 | A kind of fake-licensed car recognition methods based on image analysis |
| CN109101951A (en) * | 2018-09-03 | 2018-12-28 | 杨兴东 | A kind of method and system identifying fake license plate vehicle |
| CN110414459A (en) * | 2019-08-02 | 2019-11-05 | 中星智能系统技术有限公司 | Establish the associated method and device of people's vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104700620B (en) | 2018-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104700620B (en) | A kind of fake license plate vehicle recognition method and device based on traffic block port | |
| WO2019169532A1 (en) | License plate recognition method and cloud system | |
| US9275311B2 (en) | Efficient image matching for large sets of images | |
| US10198657B2 (en) | All-weather thermal-image pedestrian detection method | |
| CN105404860B (en) | Method and apparatus for managing personal information of wandering away | |
| De Paula et al. | Automatic detection and classification of road lane markings using onboard vehicular cameras | |
| CN104778474B (en) | A kind of classifier construction method and object detection method for target detection | |
| CN105335722A (en) | Detection system and detection method based on depth image information | |
| JP4263737B2 (en) | Pedestrian detection device | |
| CN103077407B (en) | Car logo positioning and recognition method and car logo positioning and recognition system | |
| CN105447490B (en) | Vehicle critical point detection method and device based on gradient regression tree | |
| CN107194393B (en) | Method and device for detecting temporary license plate | |
| CN103093201B (en) | Vehicle-logo location recognition methods and system | |
| CN108319952B (en) | Vehicle feature extraction method and device | |
| Thalji et al. | Iris Recognition using robust algorithm for eyelid, eyelash and shadow avoiding | |
| CN104615986A (en) | Method for utilizing multiple detectors to conduct pedestrian detection on video images of scene change | |
| CN101996308A (en) | Human face identification method and system and human face model training method and system | |
| Juranek et al. | Real-time pose estimation piggybacked on object detection | |
| CN104699726A (en) | Vehicle image retrieval method and device for traffic block port | |
| Chen et al. | Automatic detection of traffic lights using support vector machine | |
| Yakimov et al. | Traffic signs detection and tracking using modified hough transform | |
| CN111444916A (en) | License plate positioning and identifying method and system under unconstrained condition | |
| Shao et al. | Faster R-CNN learning-based semantic filter for geometry estimation and its application in vSLAM systems | |
| Li et al. | Robust urban road image segmentation | |
| Wen et al. | A rear-vehicle detection system for static images based on monocular vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |