CN103488973A - Method and system for recognizing vehicle brand based on image - Google Patents
Method and system for recognizing vehicle brand based on image Download PDFInfo
- Publication number
- CN103488973A CN103488973A CN201310416016.6A CN201310416016A CN103488973A CN 103488973 A CN103488973 A CN 103488973A CN 201310416016 A CN201310416016 A CN 201310416016A CN 103488973 A CN103488973 A CN 103488973A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- brand
- image
- car plate
- proper vector
- 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
Images
Abstract
The invention provides a method and system for recognizing a vehicle brand based on an image. The method and system can carry out multi-dimensional position detection in the image to fast recognize the vehicle brand, are high in detection rate and have little misinformation.
Description
Technical field
The present invention relates to vehicle identification, relate in particular to the vehicle brand recognition.
Background technology
In the intelligent transportation system in city, the vehicle brand recognition is an important ingredient.It can identify the brand message of vehicle automatically, such as certain car, is masses, Ford or liberation etc.The vehicle brand recognition all is widely used at traffic control system, public security system and business system.In traffic control system, can, according to distribution and the closeness of dissimilar vehicle in road network, carry out different signal lamp adjustings, the configuration of traffic police's police strength etc.; In public security system, the most directly application is the detection of deck vehicle.If the brand that certain car identifies and its car plate are when recording of public security system is inconsistent, this vehicle is likely just fake-licensed car; In business system, when understanding certain regional vehicle brand distribution situation, advertiser's advertisement putting meeting is more targeted, and effect is more obvious.
The vehicle brand recognition does not have ripe effective method in existing document.Similar work is mainly that car identifies not and vehicle identification:
The car sign is not classified and is obtained the vehicle brand message by the car mark on car body in traffic video or traffic image.There are two problems in the method: 1) it requires the sharpness of video or image high, and the car SD is clear visible, but traffic video/picture quality of present stage can not meet requirement; 2) prerequisite of car mark classification is that the car mark detects, and inspection vehicle is marked on the position in image.At present car mark detection technique is also immature, verification and measurement ratio is low report by mistake simultaneously more, so the car sign also can't not be applied in reality.Herein, wrong report refers to and thinks the non-car cursor position of car target by mistake.
The kind model of vehicle has been distinguished in vehicle identification, car for example, buggy, passenger vehicle and lorry etc.From function, vehicle identification is the subproblem of brand recognition.In the main method of vehicle recognition technology, inductive coil measures application the most widely.The inductive coil measurement is to utilize electromagnetic induction principle: when a car passes through, the inductance of coil changes, and produces certain waveform simultaneously.Obtain vehicle information by the classification to waveform.Although the method based on inductive coil has benefit with low cost, its problem also clearly: 1) install inconveniently, need to destroy road surface; 2) wave noise is large, and discrimination is low; 3) maintenance cost is high.
Therefore, need to a kind ofly can identify fast the vehicle brand based on carry out the multidimensional position probing in image, and the verification and measurement ratio height is reported less method and system by mistake simultaneously.
Summary of the invention
The invention provides a kind of vehicle brand recognition method based on image, the method comprises: detect the position of car plate in input picture; Proofread and correct detected car plate position; According to calibrated a plurality of vehicle parts of car plate position calculation position; Each extraction proper vector from the plurality of vehicle part position; And extracted proper vector is classified and exported the brand message of vehicle.
In an embodiment of the vehicle brand recognition method based on image of the present invention, the vehicle part position is to utilize the relation of vehicle part position and car plate position to calculate.
In an embodiment of the vehicle brand recognition method based on image of the present invention, the plurality of vehicle part position is the position of selecting headlight from this vehicle, fog lamp, air grid, rearview mirror, rain brush, car mark, bumper etc.
In an embodiment of the vehicle brand recognition method based on image of the present invention, this proper vector comprises resemblance and shape facility.
In an embodiment of the vehicle brand recognition method based on image of the present invention, this step that extracted proper vector is classified comprises: judge whether this shape facility is complementary with stored standard shape feature; If coupling, calculate the degree of confidence of this vehicle with respect to each brand based on this resemblance; By this degree of confidence, the highest brand is defined as the brand of this vehicle.
In an embodiment of the vehicle brand recognition method based on image of the present invention, this input picture can be the image of vehicle headstock, or the image of the vehicle tailstock.
The invention provides a kind of vehicle brand identity system based on image, this system comprises: car plate detection module, the position for detection of car plate in input picture; The car plate correction module, for proofreading and correct detected car plate position; Vehicle part position acquisition module, for a plurality of vehicle parts of the car plate position calculation position according to calibrated; The feature extraction module, for each the extraction proper vector from the plurality of vehicle part position; And the brand sort module, classified and exported the brand message of vehicle for the proper vector to extracted.
In an embodiment of the vehicle brand identity system based on image of the present invention, the plurality of vehicle part position is the position of selecting headlight from this vehicle, fog lamp, air grid, rearview mirror, rain brush, car mark, bumper etc.
In an embodiment of the vehicle brand identity system based on image of the present invention, this proper vector comprises resemblance and shape facility.
In an embodiment of the vehicle brand identity system based on image of the present invention, this brand sort module is further used for: judge whether this shape facility is complementary with stored standard shape feature; If coupling, calculate the degree of confidence of this vehicle with respect to each brand based on this resemblance; By this degree of confidence, the highest brand is defined as the brand of this vehicle.
In an embodiment of the vehicle brand identity system based on image of the present invention, this input picture can be the image of vehicle headstock, or the image of the vehicle tailstock.
Thus, the invention provides the effective car plate brand recognition of a set of maturation scheme.It both can process video and the image of general cleer and peaceful high definition, can process again traffic video and image under complex scene.This scheme does not require the travel direction of vehicle in video and image, can process front part of vehicle, can process vehicle tail yet.It is embodied as low, reliability is high, by common computer, video camera, just can realize, and recognition speed is fast, in video analysis, uses common computer just can reach Real time identification.
The accompanying drawing explanation
Fig. 1 illustrates the flowchart overview according to the vehicle brand recognition method based on image of the embodiment of the present invention;
Fig. 2 illustrates car plate and detects schematic diagram.
Fig. 3 illustrates car plate alignment model schematic diagram.
Fig. 4 illustrates car plate coupling schematic diagram.
Fig. 5 illustrates the vehicle part position and extracts schematic diagram.
Fig. 6 illustrates brand classification schematic diagram.
Fig. 7 illustrates the coupling classification results figure for vehicle headstock.
Fig. 8 illustrates the coupling classification results figure for the vehicle tailstock.
Fig. 9 illustrates the block diagram according to the vehicle brand identity system based on image of the embodiment of the present invention.
Embodiment
In the present invention, the vehicle brand recognition is based on image and carries out.Its input is certain frame of single image or video.
Fig. 1 shows the flowchart overview according to the vehicle brand recognition method based on image of the embodiment of the present invention.
Vehicle brand recognition method based on image of the present invention comprises the following steps:
(a) car plate detects: in step 101, detect the position of car plate in input picture.In this step, input picture to be made to car plate and detect, its output is the position of car plate in image.In one embodiment, position has comprised coordinate, car plate height and the car plate width of car plate in image.
Piece image can be exported a plurality of car plates position.As shown in the car plate detection schematic diagram of Fig. 2, this width image has been exported 3 car plate positions, represents the car plate position by rectangle frame respectively.The precision of the car plate position that vehicle detection obtains is not accurately simultaneously also unstable, there will be bigger than normal/less than normal/phenomenons such as left and right translation.
Car plate detects and has various schemes at present, and its relative merits are respectively arranged.In the present embodiment, this step has adopted the scheme of AdaBoost+Haar Feature.Its advantage is: (can process various complex scenes) applied widely, performance is high, and speed satisfies the demands simultaneously.
(b) car plate position correction: in step 102, proofread and correct detected car plate position.In this step, car plate is detected to the car plate position obtained and do correction.Its output is the exact position of car plate in image.Proofreaied and correct on the basis that car plate position correction step can detect at car plate, obtained the car plate exact position.Exact position is the assurance of car plate brand recognition performance.
In the present embodiment, this step has adopted the algorithm of binaryzation, by characters on license plate from the car plate background segment out, thereby obtains the exact position of car plate.This Binarization methods advantage is: speed is fast, applied widely.
In the prior art, the identification of the car plate of two dimension is known with localization method.And in the present invention, need to, based on image, the vehicle brand be identified fast.Now, only carrying out two-dimentional identification is inadequate with location; What need is identification and the location of carrying out multidimensional.
Therefore, in one embodiment of the invention, adopted the mode of Model Matching to carry out the car plate position correction of vehicle.Take headstock as example, and the model of headstock is by N vehicle part module composition, and each vehicle part module table is shown (xi, yi, fi), and wherein (xi, yi) means the position of vehicle part module, and fi is the proper vector of this vehicle part module.The SIFT descriptor due to its fast and the characteristic such as descriptive power is strong, be used as proper vector.The example of model is shown in Fig. 3.
In Fig. 3, each circle of left side means a vehicle part module on car body, and right side is the SIFT schematic diagram of single unit vehicle component models.
At this, use be the method for multilevel matching, find thus Optimum Matching on image.At first, the SIFT proper vector is extracted in each position (x, y) of image.Because car light or the car target area of different brands/vehicle are inconsistent, so the proper vector of different scale need to be extracted in each position.Then, find optimum coupling at image.After solving end, can obtain the position of each vehicle part module and whole similarity.Use identical method coupling tailstock model.Finally, the similarity of integral body by judgement headstock/tailstock, can judge that vehicle image is headstock or the tailstock.
In a word, by the car plate position correction, can obtain the result of each vehicle part module on the direction (headstock/tailstock) of vehicle and car body, concrete outcome is shown in Fig. 4.
(c) vehicle part position acquisition: in step 103, according to calibrated a plurality of vehicle parts of car plate position calculation position.In this step, according to the car plate position calculation vehicle part position of car plate alignment output, its output is the vehicle part position.This just need to utilize the relation of vehicle part position and car plate position to be calculated.
According to the position of each vehicle part module in car plate position correction step, image is carried out to normalized processing and obtain standard size.Obtain the position of each vehicle part module such as headlight, fog lamp, air grid on standard-sized image, with a rectangle frame, mean (x, y, w, h).Concrete outcome is shown in Fig. 5.
(d) feature extraction: in step 104, from each extraction proper vector of a plurality of vehicle parts position.In this step, extract proper vector in the vehicle part position, its output is proper vector.Proper vector is described the various characteristics of the vehicle part band of position, but can be processed by computerized algorithm simultaneously.
On standard-sized image, each vehicle part module extracts proper vector.Proper vector consists of two parts, and a part is resemblance; Another part is shape facility.The exemplary plot of proper vector is shown in Fig. 6.
Shape facility in the present embodiment adopts the proper vector of HoG (Histogram of Gradient).Main cause is: on shape, texture and the position of the vehicle key distinction ingredient of different brands, such as the shape of car light and position etc.HoG can describe this class feature preferably, has the fireballing advantage of extraction simultaneously.
And the resemblance in the present embodiment adopts the proper vector of LBP (Local Binary Pattern).
Then the proper vector of each vehicle part module is linked to be a total proper vector (f1, f2, f3 ...) (x, y, w, h).
(e) brand classification: in step 105, extracted proper vector is classified and exported the brand message of vehicle.
In this step, the brand classification comprises following sub-step: 1). judge whether described shape facility is complementary with stored standard shape feature; 2) if coupling is calculated the degree of confidence of described vehicle with respect to each brand based on described resemblance; 3) the highest brand of described degree of confidence is defined as to the brand of described vehicle.
In step 1), judge whether shape facility meets the requirements.For the vehicle of different brands, store in advance the standard shape feature of each vehicle part module, i.e. the position of this vehicle part module and size.For each brand, calculate the difference between shape facility and " standard shape feature ".If this difference is less than the threshold value of prior setting, judgement is likely the vehicle of this brand, and this shape facility is complementary with the standard shape feature of storing, and enters step 2), otherwise interrupt.
In step 2) in, each brand utilizes the svm classifier device as the sorter based on resemblance in advance.Utilize sorter can obtain the degree of confidence of this brand.
In step 3), for all brands that obtain degree of confidence, select brand that degree of confidence is the highest as final result.Net result is shown in Fig. 7 and Fig. 8.
Fig. 7 illustrates the coupling classification results for vehicle headstock.And Fig. 8 illustrates the coupling classification results for the vehicle tailstock.As can be seen from Fig. 7, for many vehicles on different tracks in same image, can the coupling based on for vehicle headstock classify, quickly and reliably obtain the vehicle brand.As can be seen from Fig. 8, for many vehicles on same track in same image, can the coupling based on for the vehicle tailstock classify, quickly and reliably obtain the vehicle brand.
It is the typical problem in machine learning that proper vector is classified, and has a large amount of ready-made algorithms to solve.The present embodiment adopts the method for multiclass linear SVM.Main cause is: speed is fast, performance is high.
Fig. 9 illustrates the block diagram according to the vehicle brand identity system based on image of the embodiment of the present invention.
Vehicle brand identity system based on image of the present invention comprises: car plate detection module, the position for detection of car plate in input picture; The car plate correction module, for proofreading and correct detected car plate position; Vehicle part position acquisition module, for a plurality of vehicle parts of the car plate position calculation position according to calibrated; The feature extraction module, for each the extraction proper vector from described a plurality of vehicle parts position; And the brand sort module, classified and exported the brand message of vehicle for the proper vector to extracted.
Thus, the invention provides and a kind ofly can identify fast the vehicle brand based on carry out the multidimensional position probing in image, and the verification and measurement ratio height is reported less method and system by mistake simultaneously.The method and system both can have been processed video and the image of general cleer and peaceful high definition, can process again traffic video and image under complex scene.This scheme does not require the travel direction of vehicle in video and image, can process front part of vehicle, can process vehicle tail yet.It is embodied as low, reliability is high, by common computer, video camera, just can realize, and recognition speed is fast, in video analysis, uses common computer just can reach Real time identification.
The vehicle part position is the position of all parts of vehicle, these parts such as headlight, fog lamp, air grid, rearview mirror, rain brush, car mark, bumper etc.
Example system described herein is only the example that is applicable to some realization, and the usable range or the function that are not intended to environment, architecture and framework to realizing process described herein, assembly and feature propose any restriction.Therefore, realization herein can be used for numerous environment or architecture, and realizes in can or having other equipment of processing power at universal or special computing system.Generally speaking, any function be described with reference to the drawings all can be used software, hardware (for example, fixed logic circuit) or the combination of these realizations to realize.The general expression of term as used herein " module " or " assembly " can be configured to realize the combination of software, hardware or the software and hardware of predetermined function.For example, in the situation that the software realization, term " module " or " assembly " can mean to carry out the program code of appointed task or operation when for example, in the upper execution of one or more treatment facilities (, CPU or processor) time.Program code can be stored in one or more computer readable memory devices or other computer memory devices.Thus, process described herein, assembly and module can be realized by computer program.
Although described the present invention according to several embodiment, the invention is not restricted to described embodiment but those skilled in the art will recognize, implement the present invention but can and change with the modification in the spirit and scope of claims, therefore instructions is considered as illustrative and not restrictive.
Claims (12)
1. the vehicle brand recognition method based on image, described method comprises:
Detect the position of car plate in input picture;
Proofread and correct detected car plate position;
According to calibrated a plurality of vehicle parts of car plate position calculation position;
Each extraction proper vector from described a plurality of vehicle parts position; And
Extracted proper vector is classified and exported the brand message of vehicle.
2. the vehicle brand recognition method based on image as claimed in claim 1, is characterized in that, described vehicle part position is to utilize the relation of described vehicle part position and described car plate position to calculate.
3. the vehicle brand recognition method based on image as claimed in claim 1, is characterized in that, described a plurality of vehicle parts position is the position of selecting headlight from described vehicle, fog lamp, air grid, rearview mirror, rain brush, car mark, bumper etc.
4. the vehicle brand recognition method based on image as claimed in claim 1, is characterized in that, described proper vector comprises resemblance and shape facility.
5. the vehicle brand recognition method based on image as claimed in claim 1, is characterized in that, the described step that extracted proper vector is classified comprises:
Judge whether described shape facility is complementary with stored standard shape feature;
If coupling, calculate the degree of confidence of described vehicle with respect to each brand based on described resemblance;
The highest brand of described degree of confidence is defined as to the brand of described vehicle.
6. the vehicle brand recognition method based on image as claimed in claim 1, is characterized in that, described input picture can be the image of vehicle headstock, or the image of the vehicle tailstock.
7. the vehicle brand identity system based on image, described system comprises:
The car plate detection module, the position for detection of car plate in input picture;
The car plate correction module, for proofreading and correct detected car plate position;
Vehicle part position acquisition module, for a plurality of vehicle parts of the car plate position calculation position according to calibrated;
The feature extraction module, for each the extraction proper vector from described a plurality of vehicle parts position; And
The brand sort module, classified and exported the brand message of vehicle for the proper vector to extracted.
8. the vehicle brand identity system based on image as claimed in claim 7, is characterized in that, described vehicle part position is to utilize the relation of described vehicle part position and described car plate position to calculate.
9. the vehicle brand identity system based on image as claimed in claim 7, is characterized in that, described a plurality of vehicle parts position is the position of selecting headlight from described vehicle, fog lamp, air grid, rearview mirror, rain brush, car mark, bumper etc.
10. the vehicle brand identity system based on image as claimed in claim 7, is characterized in that, described proper vector comprises resemblance and shape facility.
11. the vehicle brand identity system based on image as claimed in claim 7, is characterized in that, described brand sort module is further used for:
Judge whether described shape facility is complementary with stored standard shape feature;
If coupling, calculate the degree of confidence of described vehicle with respect to each brand based on described resemblance;
The highest brand of described degree of confidence is defined as to the brand of described vehicle.
12. the vehicle brand identity system based on image as claimed in claim 7 is characterized in that described input picture can be the image of vehicle headstock, or the image of the vehicle tailstock.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310416016.6A CN103488973B (en) | 2013-09-12 | 2013-09-12 | Vehicle brand recognition methods and system based on image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310416016.6A CN103488973B (en) | 2013-09-12 | 2013-09-12 | Vehicle brand recognition methods and system based on image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103488973A true CN103488973A (en) | 2014-01-01 |
| CN103488973B CN103488973B (en) | 2017-10-20 |
Family
ID=49829182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310416016.6A Active CN103488973B (en) | 2013-09-12 | 2013-09-12 | Vehicle brand recognition methods and system based on image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103488973B (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104239531A (en) * | 2014-09-19 | 2014-12-24 | 上海依图网络科技有限公司 | Accurate comparison method based on local visual features |
| CN104392611A (en) * | 2014-11-17 | 2015-03-04 | 英华达（南京）科技有限公司 | Method and system for identifying high-price cars |
| CN104408431A (en) * | 2014-11-28 | 2015-03-11 | 江苏物联网研究发展中心 | Vehicle model identification method under traffic monitoring |
| CN104778444A (en) * | 2015-03-10 | 2015-07-15 | 公安部交通管理科学研究所 | Method for analyzing apparent characteristic of vehicle image in road scene |
| CN105160340A (en) * | 2015-08-31 | 2015-12-16 | 桂林电子科技大学 | Vehicle brand identification system and method |
| CN105279475A (en) * | 2014-07-15 | 2016-01-27 | 贺江涛 | Fake-licensed vehicle identification method and apparatus based on vehicle identity recognition |
| CN105279476A (en) * | 2014-07-15 | 2016-01-27 | 贺江涛 | Vehicle face recognition method and device based on multiple features |
| CN105426899A (en) * | 2014-09-19 | 2016-03-23 | 腾讯科技（北京）有限公司 | Vehicle identification method and device and client side |
| 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 |
| CN105740855A (en) * | 2016-03-24 | 2016-07-06 | 博康智能信息技术有限公司 | Front and rear license plate detection and recognition method based on deep learning |
| CN105787437A (en) * | 2016-02-03 | 2016-07-20 | 东南大学 | Vehicle brand type identification method based on cascading integrated classifier |
| CN107016390A (en) * | 2017-04-11 | 2017-08-04 | 华中科技大学 | A kind of vehicle part detection method and system based on relative position |
| CN107092855A (en) * | 2016-02-18 | 2017-08-25 | 日本电气株式会社 | Vehicle part recognition methods and equipment, vehicle identification method and equipment |
| CN107133574A (en) * | 2017-04-12 | 2017-09-05 | 浙江大华技术股份有限公司 | A kind of vehicle feature recognition method and device |
| CN107506759A (en) * | 2016-06-14 | 2017-12-22 | 杭州海康威视数字技术股份有限公司 | A kind of motor vehicle brand identification method and device |
| CN107545216A (en) * | 2016-06-29 | 2018-01-05 | 深圳市格视智能科技有限公司 | A kind of vehicle identification method available for power-line patrolling |
| CN108171248A (en) * | 2017-12-29 | 2018-06-15 | 武汉璞华大数据技术有限公司 | A kind of method, apparatus and equipment for identifying train model |
| CN108519675A (en) * | 2018-03-25 | 2018-09-11 | 东莞市华睿电子科技有限公司 | A kind of scene display method worn display equipment and be combined with automatic driving vehicle |
| CN110491133A (en) * | 2019-08-08 | 2019-11-22 | 横琴善泊投资管理有限公司 | A kind of information of vehicles correction system and method based on confidence level |
| CN110895692A (en) * | 2018-09-13 | 2020-03-20 | 浙江宇视科技有限公司 | Vehicle brand identification method and device and readable storage medium |
| CN110991255A (en) * | 2019-11-11 | 2020-04-10 | 智慧互通科技有限公司 | Method for detecting fake-licensed vehicle based on deep learning algorithm |
| CN111242951A (en) * | 2020-01-08 | 2020-06-05 | 上海眼控科技股份有限公司 | Vehicle detection method, device, computer equipment and storage medium |
| CN111507342A (en) * | 2020-04-21 | 2020-08-07 | 浙江大华技术股份有限公司 | Image processing method, device and system and storage medium |
| CN111738228A (en) * | 2020-08-04 | 2020-10-02 | 杭州智诚惠通科技有限公司 | Multi-view vehicle feature matching method for hypermetrological evidence chain verification |
| CN112036421A (en) * | 2019-05-16 | 2020-12-04 | 搜狗（杭州）智能科技有限公司 | Image processing method and device and electronic equipment |
| CN112102408A (en) * | 2020-09-09 | 2020-12-18 | 东软睿驰汽车技术（沈阳）有限公司 | Monocular vision scale correction method and device and automatic driving automobile |
| US11386680B2 (en) | 2020-03-28 | 2022-07-12 | Wipro Limited | System and method of identifying vehicle brand and model |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090268946A1 (en) * | 2008-04-24 | 2009-10-29 | Gm Global Technology Operations, Inc. | Vehicle clear path detection |
| CN101630361A (en) * | 2008-12-30 | 2010-01-20 | 北京邮电大学 | Plate number, body color and mark identification-based equipment and plate number, body color and mark identification-based method for identifying fake plate vehicles |
| CN102708691A (en) * | 2011-12-26 | 2012-10-03 | 南京信息工程大学 | False license plate identification method based on matching between license plate and automobile type |
| CN103065143A (en) * | 2012-12-30 | 2013-04-24 | 信帧电子技术（北京）有限公司 | Automobile logo identification method and device |
-
2013
- 2013-09-12 CN CN201310416016.6A patent/CN103488973B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090268946A1 (en) * | 2008-04-24 | 2009-10-29 | Gm Global Technology Operations, Inc. | Vehicle clear path detection |
| CN101630361A (en) * | 2008-12-30 | 2010-01-20 | 北京邮电大学 | Plate number, body color and mark identification-based equipment and plate number, body color and mark identification-based method for identifying fake plate vehicles |
| CN102708691A (en) * | 2011-12-26 | 2012-10-03 | 南京信息工程大学 | False license plate identification method based on matching between license plate and automobile type |
| CN103065143A (en) * | 2012-12-30 | 2013-04-24 | 信帧电子技术（北京）有限公司 | Automobile logo identification method and device |
Non-Patent Citations (2)
| Title |
|---|
| 薛天以: "基于图像信息与模糊神经网络的特征识别技术及其应用", 《中国优秀硕士学位论文全文数据库》 * |
| 赵兵: "《基于混合特征的车牌识别技术研究》", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279475A (en) * | 2014-07-15 | 2016-01-27 | 贺江涛 | Fake-licensed vehicle identification method and apparatus based on vehicle identity recognition |
| CN105279476A (en) * | 2014-07-15 | 2016-01-27 | 贺江涛 | Vehicle face recognition method and device based on multiple features |
| CN104239531B (en) * | 2014-09-19 | 2017-09-26 | 上海依图网络科技有限公司 | A kind of precise alignment method based on local visual feature |
| CN105426899A (en) * | 2014-09-19 | 2016-03-23 | 腾讯科技（北京）有限公司 | Vehicle identification method and device and client side |
| CN105426899B (en) * | 2014-09-19 | 2019-11-08 | 腾讯科技（北京）有限公司 | Vehicle identification method, device and client |
| CN104239531A (en) * | 2014-09-19 | 2014-12-24 | 上海依图网络科技有限公司 | Accurate comparison method based on local visual features |
| CN104392611A (en) * | 2014-11-17 | 2015-03-04 | 英华达（南京）科技有限公司 | Method and system for identifying high-price cars |
| CN104408431A (en) * | 2014-11-28 | 2015-03-11 | 江苏物联网研究发展中心 | Vehicle model identification method under traffic monitoring |
| CN104408431B (en) * | 2014-11-28 | 2017-12-26 | 江苏物联网研究发展中心 | Car money recognition methods under traffic monitoring |
| CN104778444A (en) * | 2015-03-10 | 2015-07-15 | 公安部交通管理科学研究所 | Method for analyzing apparent characteristic of vehicle image in road scene |
| CN105160340A (en) * | 2015-08-31 | 2015-12-16 | 桂林电子科技大学 | Vehicle brand identification system and method |
| CN105787437A (en) * | 2016-02-03 | 2016-07-20 | 东南大学 | Vehicle brand type identification method based on cascading integrated classifier |
| CN107092855A (en) * | 2016-02-18 | 2017-08-25 | 日本电气株式会社 | Vehicle part recognition methods and equipment, vehicle identification method and equipment |
| 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 |
| CN105740855A (en) * | 2016-03-24 | 2016-07-06 | 博康智能信息技术有限公司 | Front and rear license plate detection and recognition method based on deep learning |
| CN107506759A (en) * | 2016-06-14 | 2017-12-22 | 杭州海康威视数字技术股份有限公司 | A kind of motor vehicle brand identification method and device |
| CN107545216A (en) * | 2016-06-29 | 2018-01-05 | 深圳市格视智能科技有限公司 | A kind of vehicle identification method available for power-line patrolling |
| CN107016390A (en) * | 2017-04-11 | 2017-08-04 | 华中科技大学 | A kind of vehicle part detection method and system based on relative position |
| CN107016390B (en) * | 2017-04-11 | 2019-11-12 | 华中科技大学 | A kind of vehicle part detection method and system based on relative position |
| CN107133574A (en) * | 2017-04-12 | 2017-09-05 | 浙江大华技术股份有限公司 | A kind of vehicle feature recognition method and device |
| CN107133574B (en) * | 2017-04-12 | 2022-06-17 | 浙江大华技术股份有限公司 | Vehicle feature identification method and device |
| CN108171248A (en) * | 2017-12-29 | 2018-06-15 | 武汉璞华大数据技术有限公司 | A kind of method, apparatus and equipment for identifying train model |
| CN108519675A (en) * | 2018-03-25 | 2018-09-11 | 东莞市华睿电子科技有限公司 | A kind of scene display method worn display equipment and be combined with automatic driving vehicle |
| CN110895692A (en) * | 2018-09-13 | 2020-03-20 | 浙江宇视科技有限公司 | Vehicle brand identification method and device and readable storage medium |
| CN110895692B (en) * | 2018-09-13 | 2023-04-07 | 浙江宇视科技有限公司 | Vehicle brand identification method and device and readable storage medium |
| CN112036421A (en) * | 2019-05-16 | 2020-12-04 | 搜狗（杭州）智能科技有限公司 | Image processing method and device and electronic equipment |
| CN110491133B (en) * | 2019-08-08 | 2020-10-16 | 善泊科技(珠海)有限公司 | Vehicle information correction system and method based on confidence |
| CN110491133A (en) * | 2019-08-08 | 2019-11-22 | 横琴善泊投资管理有限公司 | A kind of information of vehicles correction system and method based on confidence level |
| CN110991255A (en) * | 2019-11-11 | 2020-04-10 | 智慧互通科技有限公司 | Method for detecting fake-licensed vehicle based on deep learning algorithm |
| CN110991255B (en) * | 2019-11-11 | 2023-09-08 | 智慧互通科技股份有限公司 | Method for detecting fake-licensed car based on deep learning algorithm |
| CN111242951A (en) * | 2020-01-08 | 2020-06-05 | 上海眼控科技股份有限公司 | Vehicle detection method, device, computer equipment and storage medium |
| US11386680B2 (en) | 2020-03-28 | 2022-07-12 | Wipro Limited | System and method of identifying vehicle brand and model |
| CN111507342A (en) * | 2020-04-21 | 2020-08-07 | 浙江大华技术股份有限公司 | Image processing method, device and system and storage medium |
| CN111507342B (en) * | 2020-04-21 | 2023-10-10 | 浙江大华技术股份有限公司 | Image processing method, device, system and storage medium |
| CN111738228A (en) * | 2020-08-04 | 2020-10-02 | 杭州智诚惠通科技有限公司 | Multi-view vehicle feature matching method for hypermetrological evidence chain verification |
| CN112102408A (en) * | 2020-09-09 | 2020-12-18 | 东软睿驰汽车技术（沈阳）有限公司 | Monocular vision scale correction method and device and automatic driving automobile |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103488973B (en) | 2017-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103488973A (en) | Method and system for recognizing vehicle brand based on image | |
| Satzoda et al. | Multipart vehicle detection using symmetry-derived analysis and active learning | |
| KR101596299B1 (en) | Apparatus and Method for recognizing traffic sign board | |
| He et al. | Recognition of car makes and models from a single traffic-camera image | |
| CN101859382B (en) | License plate detection and identification method based on maximum stable extremal region | |
| Kheyrollahi et al. | Automatic real-time road marking recognition using a feature driven approach | |
| CN105335702B (en) | A kind of bayonet model recognizing method based on statistical learning | |
| Danti et al. | An image processing approach to detect lanes, pot holes and recognize road signs in Indian roads | |
| CN105335710A (en) | Fine vehicle model identification method based on multi-stage classifier | |
| Romdhane et al. | An improved traffic signs recognition and tracking method for driver assistance system | |
| Kuang et al. | Feature selection based on tensor decomposition and object proposal for night-time multiclass vehicle detection | |
| CN104200228A (en) | Recognizing method and system for safety belt | |
| CN105224945B (en) | A kind of automobile logo identification method based on joint-detection and identification algorithm | |
| Maldonado-Bascon et al. | Traffic sign recognition system for inventory purposes | |
| Ingole et al. | Characters feature based Indian vehicle license plate detection and recognition | |
| Supreeth et al. | An approach towards efficient detection and recognition of traffic signs in videos using neural networks | |
| Pradeep et al. | An improved technique for night-time vehicle detection | |
| Ju et al. | Vision-based moving objects detection for intelligent automobiles and a robustness enhancing method | |
| Bichkar et al. | Traffic sign classification and detection of Indian traffic signs using deep learning | |
| Boumediene et al. | Vehicle detection algorithm based on horizontal/vertical edges | |
| Hsu et al. | Developing an on-road obstacle detection system using monovision | |
| Vaddi et al. | Computer vision based vehicle recognition on indian roads | |
| Bota et al. | A framework for object detection, tracking and classification in urban traffic scenarios using stereovision | |
| Rao et al. | Object Sub-Categorization and Common Framework Method using Iterative AdaBoost for Rapid Detection of Multiple Objects | |
| Li et al. | A PCANet based method for vehicle make recognition |
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 |