CN103077391A - Automobile logo positioning method and device - Google Patents
Automobile logo positioning method and device Download PDFInfo
- Publication number
- CN103077391A CN103077391A CN2012105915493A CN201210591549A CN103077391A CN 103077391 A CN103077391 A CN 103077391A CN 2012105915493 A CN2012105915493 A CN 2012105915493A CN 201210591549 A CN201210591549 A CN 201210591549A CN 103077391 A CN103077391 A CN 103077391A
- Authority
- CN
- China
- Prior art keywords
- car
- information area
- described information
- circular
- circle
- 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
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an automobile logo positioning method and device. The method comprises the steps that automobile log positioning is conducted to an input image to obtain license plate positioning information; the information area of an automobile logo to be positioned is determined by adopting the obtained license plate positioning information; and circle detection is conducted to the information area by adopting characteristic parameters corresponding to a circle, and when the automobile logo to be positioned is determined to be a circular automobile logo, the position of the automobile logo to be positioned is determined in the information area. According to the technical scheme provided by the invention, the accurate positioning of the circular automobile logo above a license plate can be realized to complete effective recognition of vehicle types.
Description
Technical field
The present invention relates to the computer image processing field, particularly a kind of car target localization method and device.
Background technology
Increasing along with socioeconomic development and vehicle is by computer information, intelligently management vehicle becomes a kind of inexorable trend.
License plate recognition technology is widely used in traffic flow monitoring, and the charge of highway bayonet socket is in red light violation vehicle monitoring and the residential quarter automatic fare collection system.Present treatment technology can only be identified, but can not identify concrete vehicle car plate and large-scale, medium-sized, dilly.
Common car mark shape mainly is divided into circle, ellipse and rectangle at present.Yet in the correlation technique, accurately also lack relevant technical scheme in the location for circular car target, therefore, for the circular car mark of car plate upper area, need a kind of effective technical scheme to locate accurately.
Summary of the invention
The present invention proposes a kind of car target localization method and device, can't carry out pinpoint technical matters to the circular car mark of car plate top to solve at least in the correlation technique.
According to an aspect of the present invention, provide a kind of car target localization method.
Car target localization method according to the present invention comprises: carry out the car plate location for input picture, obtain the car plate locating information; The above-mentioned car plate locating information that employing is obtained is determined car target information area to be positioned; Adopt circular corresponding characteristic parameter that above-mentioned information area is carried out circle and detect, be designated as circular car timestamp at definite above-mentioned car to be positioned, in above-mentioned information area, determine above-mentioned car target to be positioned position.
According to an aspect of the present invention, provide a kind of car target locating device.
Car target locating device according to the present invention comprises: acquisition module, be used for carrying out the car plate location for input picture, and obtain the car plate locating information; Determination module is used for adopting the above-mentioned car plate locating information of obtaining to determine car target information area to be positioned; The detection and location module is used for adopting circular corresponding characteristic parameter that above-mentioned information area is carried out circle and detects, and is designated as circular car timestamp at definite above-mentioned car to be positioned, determines above-mentioned car target to be positioned position in above-mentioned information area.
By the present invention, go out car target general information zone according to car plate locating information stage discretion first, then in the fine positioning stage, adopting circular corresponding characteristic parameter that above-mentioned information area is carried out circle detects, be designated as circular car timestamp at definite above-mentioned car to be positioned, in above-mentioned information area, determine above-mentioned car target to be positioned position.Solved in the correlation technique and can't carry out pinpoint technical matters to the circular car mark of car plate top.Thereby can realize the circular car target of car plate top is accurately located, finish the effective identification to the vehicle vehicle.
Description of drawings
Accompanying drawing described herein is used to provide a further understanding of the present invention, consists of the application's a part, and illustrative examples of the present invention and explanation thereof are used for explaining the present invention, do not consist of improper restriction of the present invention.In the accompanying drawings:
Fig. 1 is the process flow diagram according to the car target localization method of the embodiment of the invention;
Fig. 2 is the process flow diagram of car target localization method according to the preferred embodiment of the invention;
Fig. 3 is the structured flowchart according to the car target locating device of the embodiment of the invention; And
Fig. 4 is the structured flowchart of car target locating device according to the preferred embodiment of the invention.
Embodiment
Fig. 1 is the process flow diagram according to the car target localization method of the embodiment of the invention.As shown in Figure 1, the car target localization method according to the embodiment of the invention may further comprise the steps (step S102-step S106):
Step S102: carry out the car plate location for input picture, obtain the car plate locating information;
Step S104: adopt the above-mentioned car plate locating information of obtaining to determine car target information area to be positioned;
Step S106: adopt circular corresponding characteristic parameter that above-mentioned information area is carried out circle and detect, be designated as circular car timestamp at definite above-mentioned car to be positioned, in above-mentioned information area, determine above-mentioned car target to be positioned position.
In Fig. 1, car target location mainly is divided into three phases.Phase one (being equivalent to step S102): at first car plate is positioned; Subordinate phase (being equivalent to step S104): the car plate locating information of obtaining according to the phase one determines car target general information zone, subordinate phase (being equivalent to step S104): the i.e. accurate positioning stage of car target, adopting circular corresponding characteristic parameter that above-mentioned information area is carried out circle detects, be designated as circular car timestamp at definite above-mentioned car to be positioned, in above-mentioned information area, determine above-mentioned car target to be positioned position.By effective combination of above-mentioned three steps, solved in the correlation technique and can't carry out pinpoint technical matters to the circular car mark of car plate top.Thereby can realize the circular car target of car plate top is accurately located, finish the effective identification to the vehicle vehicle.
Wherein, in step S102, the starting point that car plate is located is to utilize the feature of license plate area to judge licence plate, and license plate area is split from the view picture vehicle image.Car plate self has many inherent features, according to the different characteristic of car plate, can adopt different localization methods.At present the method for car plate location is a lot, and modal car plate location technology mainly contains method based on rim detection, based on the method for Color Segmentation, based on the method for wavelet transformation, the method analyzed based on the method for genetic algorithm, based on car plate location and the intensity-based image texture characteristic of mathematical morphology etc.
Wherein, for for the method for rim detection, so-called " edge " just refers to that its surrounding pixel gray scale has the set of those pixels of step variation.The both sides at " edge " belong to two zones, and each regional uniform gray level is consistent, and there is certain difference in the gray scale in these two zones in feature.The task of rim detection is accurately to locate the edge and suppress noise.The method that detects has multiple, for example Roberts boundary operator, Prewitt operator, Sobel operator and Lapalace edge detection.These methods utilize grey scale change violent these characteristics in object edge place to come the edge of detected image just.Each operator is different to the sensitivity of different edge types, and produce an effect is also different, and through the great many of experiments analysis as can be known, the Roberts boundary operator is a kind of operator that utilizes the local variance operator to seek the edge, locates more accurate; Prewitt operator and Sobel operator have certain inhibition ability to noise, but can not get rid of pseudo-edge fully; Laplace operator is Second Order Differential Operator, to the step change type marginal point accurate positioning in the image and have rotational invariance, but easily loses the directional information at a part of edge, and anti-noise ability is relatively poor simultaneously.For different environment and requirement, select suitable operator to come that image is carried out rim detection and just can reach good effect.More than be the simple description that the license plate locating method based on rim detection is carried out, other car plate location technologies can referring to the description in the correlation technique, repeat no more herein.
Wherein, in step S104, owing to car plate is located, therefore can the car target general information zone that be positioned at the car plate top be positioned according to the positional information of car plate.
In preferred implementation process, after execution in step S104, before the execution in step S106, can also comprise following processing: to above-mentioned car target information area executive level correction process.
Intelligent transportation system (Intelligent Traffic System is referred to as ITS)
In, the object of picked-up is the licence plate of moving vehicle normally, video camera generally can only be erected at the side top of highway, thereby the license plate image that collects has inclination and distortion in various degree, and the above inclination of 3 degree can cause the obvious sex change of character, most of optical character identification (Optical Character Recognition is referred to as OCR) method is difficult to adapt to, and this gives accurately cutting apart of character and identifies and bring very large difficulty.Therefore, for this problem, can be to above-mentioned car target information area executive level correction process.
In preferred implementation process, the above-mentioned rectification of above-mentioned execution is processed and be may further include following processing:
(1) adopts maximum between-cluster variance OTSU algorithm with license plate binary, obtain binary map;
(2) extract horizontal edge information in above-mentioned binary map, obtain horizontal edge figure;
(3) to above-mentioned horizontal edge figure in predetermined angular range at a predetermined angle the interval carry out angle rotation, for each rotation, add up before the above-mentioned horizontal edge figure horizontal projection value maximum in the four lines, choosing this horizontal projection, to be worth angle maximum in the corresponding angle be the car plate RA;
(4) adopt the bilinear interpolation algorithm that above-mentioned information area is corrected according to above-mentioned car plate RA.
By above-mentioned processing, in conjunction with the actual conditions of license plate image, the horizontal direction of car plate is rotated harmless the rectification, then adopt in vertical direction sciagraphy to carry out stretcher strain and correct, can effectively realize the horizontal tilt of car target information area is corrected.
In preferred implementation process, above-mentioned steps S106 may further include following processing:
(1) for above-mentioned information area, obtains edge image by edge detection algorithm;
(2) on the above-mentioned edge image that obtains, adopt the corresponding characteristic parameter of above-mentioned circle (for example, circular feature amount etc.) to obtain maximum point in the above-mentioned information area;
Wherein, circular feature C=μ
R/ δ
R, when regional R trends towards circle, circular feature amount C monotone increasing and trend towards infinitely, it is not subjected to the impact of regional translation, rotation and dimensional variation, and C is the characteristic quantity of all frontier points definition of a regional R of usefulness, wherein μ
RBe the mean distance from the regional center to the frontier point
(x in above-mentioned formula
k, y
K) be the coordinate of any point in the image; (x, y) is the regional barycenter coordinate; Definition δ
RFor from the regional barycenter to the frontier point apart from mean square deviation
(3) justify detection by the broad sense hough transform, determine that described car to be positioned is marked on the position of described information area;
(4) adopt the mathematical morphology filter algorithm, locate above-mentioned car target coordinate to be positioned and the above-mentioned car mark to be positioned of intercepting in above-mentioned information area.
In preferred implementation process, after step S104, before the step S106, can also comprise following processing: above-mentioned information area is carried out gray processing process, and adopt structural element that the gray level image that obtains is carried out opening operation.
Wherein, opening operation belongs to morphological images to be processed, and is to corrode first rear expansion, and its effect is: can make edge smoothing, eliminate tiny spine, disconnect narrow connection, the maintenance size is constant etc.Use same structural element that image is corroded first the computing of expanding again and be called opening operation.Particularly, the opening operation under structural element B is defined as follows:
This shows, opening operation can be used for eliminating the small object thing, when very thin some place separates the border of object, level and smooth larger object and its area of not obvious change.Therefore, after step S104, before the step S106, adopt opening operation, can effectively some irrelevant background images in the car target information area be removed.
In preferred implementation process, after the employing structural element is carried out opening operation to the gray level image that obtains, adopt the corresponding characteristic parameter of above-mentioned circle to before the detection of above-mentioned information area execution circle, can also comprise following processing: adopt the OTSU algorithm with above-mentioned Binary Sketch of Grey Scale Image, and obtain connected domain by morphological operation.
Wherein, so-called " binaryzation ", the gray-scale value of the pixel on the image is set to 0 or 255 exactly, namely whole image is presented obvious black and white effect.And obtain connected domain by morphological operation, and in correlation technique, there are a variety of methods, specifically can referring to the description in the correlation technique, repeat no more herein.
Below in conjunction with Fig. 2 above-mentioned preferred implementation is further specified.
Fig. 2 is the process flow diagram of car target localization method according to the preferred embodiment of the invention.As shown in Figure 2, this car target localization method can comprise following processing:
Step S202: utilize rim detection or machine learning scheduling algorithm that input picture is carried out the car plate location.
In preferred implementation process, can carry out the location to car plate in the following ways:
Y
1=Ymax-t*Hpai
Y
2=Ymin-t*Hpai
X
1=Xmin
X
2=Xmax
Wherein, t=0.5～4, Y
1And Y
2Respectively car mark zone up-and-down boundary coordinate, X
1And X
2Be respectively the coordinate on border, the regional left and right sides, Ymax and Ymin are respectively the coordinates of license plate area up-and-down boundary, and Xmin and Xmax are respectively the coordinates on border, the license plate area left and right sides, and Hpai is the height of car plate.
Step S204: according to car plate locating information coarse positioning car target information area.
The zone pre-service of step S206(car mark coarse positioning): the parameter of utilizing car plate to correct is carried out rectification to the zone (being above-mentioned car target information area) of car mark coarse positioning.
Particularly, can utilize the rotation angle information in the car plate rectification in conjunction with bilinear interpolation the horizontal tilt correction to be carried out in car mark zone.
(1) extracting the horizontal edge hum pattern of binaryzation car plate, namely by row search binary map, when running into saltus step, namely run at 0 → 1 or 1 → 0 o'clock, will be 1 with binary map white pixel corresponding point assignment on the outline map.
(2) with the horizontal edge figure that extracts with 1
0For step-length [20
0, 20
0] horizontally rotate in the scope, every rotation is once added up respectively every row projection value in the horizontal direction, gets wherein maximum front n capable, and then summation is as the horizontal projection value (n is threshold value, can get 4) of this anglec of rotation.
(3) the horizontal projection value Sum (α) that tries to achieve of more each anglec of rotation finds the maximum corresponding angle [alpha] of projection value to be the angle of car plate horizontal tilt.
(4) utilizing bilinear interpolation to carry out horizontal tilt to the coarse positioning zone with the α angle proofreaies and correct.
Step S208: gray processing is carried out in the car mark coarse positioning zone that will correct, utilizes structural element that gray level image is carried out opening operation one time, is used for removing some irrelevant background images at car target information area.
Step S210: utilize the OTSU Binarization methods to carry out binaryzation, carry out again morphological operation, obtain connected domain, the very little white point of area in the car target information area is removed.
Step S212: carry out circle detection by the how round fast algorithm of detecting of Generalized Hough Transform first, detect round approximate location, then less circular constraint factor is set (for example, the constraint function of initial segmentation gets 0 usually) adopt the numerical solution of partial differential equation through after the suitable iteration, can extract the approximate contours of all targets in the image, as the initial segmentation of target, adopt the level set function split image this moment, so that comprise a target object in each image.
For each target object, cut apart distance that level set function reinitializes as initial setting up take above-mentioned, larger circular constraint function is set (for example, can get 200) to detect circular object, then adopt partial differential equation that it is found the solution, if the solution of trying to achieve is 0, then target object is circular object, then all target images are stacked up, just obtain all circular targets in the original image.
If detect as circular, execution in step S214 then, otherwise, can arrange and carry out again one or many and detect, in case deviation appears in testing result, improve and detect correctness.Fig. 2 shows the technical scheme of carrying out again one-time detection, is not circular if namely detect, execution in step S218.
Step S214: detect connected region according to the axis, will be positioned at the circular connected region label for labelling of axis, process respectively, count the position of connected domain, thereby realization car target is accurately located.
Step S216: intercept final car mark at coarse positioning and in the car target information area after proofreading and correct.
Step S218: whether secondary detection car mark is circular; If so, execution in step S214.Otherwise flow process finishes.
Fig. 3 is the structured flowchart according to the car target locating device of the embodiment of the invention.As shown in Figure 3, this car target locating device includes but not limited to lower module:
Acquisition module 30 is used for carrying out the car plate location for input picture, obtains the car plate locating information;
Determination module 32 is connected with acquisition module 30, is used for adopting the above-mentioned car plate locating information of obtaining to determine car target information area to be positioned;
Detection and location module 34, be connected with determination module 32, be used for adopting circular corresponding characteristic parameter that above-mentioned information area is carried out circle and detect, be designated as circular car timestamp at definite above-mentioned car to be positioned, in above-mentioned information area, determine above-mentioned car target to be positioned position.
Demarcate effective combination of three modules of position device by car shown in Figure 3, solved in the correlation technique and can't carry out pinpoint technical matters to the circular car mark of car plate top.Thereby can realize the circular car target of car plate top is accurately located, finish the effective identification to the vehicle vehicle.
In preferred implementation process, as shown in Figure 4, said apparatus can also comprise: rectification module 36, be connected between determination module 32 and the detection and location module 34, and be used for above-mentioned information area executive level correction process.
In preferred implementation process, as shown in Figure 4, above-mentioned rectification module 36 may further include: the first acquiring unit 360, and be used for adopting maximum between-cluster variance OTSU algorithm with license plate binary, obtain binary map; Second acquisition unit 362 is used for extracting horizontal edge information in above-mentioned binary map, obtains horizontal edge figure; Statistic unit 364, be used for to above-mentioned horizontal edge figure in predetermined angular range at a predetermined angle the interval carry out the angle rotation, for each rotation, add up before the above-mentioned horizontal edge figure maximum horizontal projection value in the four lines; Choose unit 366, being used for choosing this horizontal projection, to be worth the maximum angle of corresponding angle be the car plate RA; Correcting unit 368 is used for adopting the bilinear interpolation algorithm that above-mentioned information area is corrected according to above-mentioned car plate RA.
In preferred implementation process, as shown in Figure 4, above-mentioned detection and location module 34 may further include: the 3rd acquiring unit 340, be used for for above-mentioned information area, and obtain edge image by edge detection algorithm; The 4th acquiring unit 342 is used at the above-mentioned edge image that obtains, and adopts the corresponding characteristic parameter of above-mentioned circle to obtain the interior maximum point of described information area; Determining unit 344 is used for justifying detection by the broad sense hough transform, determines that above-mentioned car to be positioned is marked on the position of described information area; Positioning unit 346 is used for adopting the mathematical morphology filter algorithm, locates above-mentioned car target coordinate to be positioned and the above-mentioned car mark to be positioned of intercepting in above-mentioned information area.
In preferred implementation process, said apparatus also comprises: the first processing module 38, can be connected between rectification module 36 and the detection and location module 34, be connected in for above-mentioned information area is carried out gray processing and process, and adopt structural element that the gray level image that obtains is carried out opening operation.
In preferred implementation process, said apparatus also comprises: the second processing module 40, can be connected between the first processing module 38 and the detection and location module 34, and be used for adopting the OTSU algorithm with above-mentioned Binary Sketch of Grey Scale Image, and obtain connected domain by morphological operation.
Need to prove, each module in the above-mentioned car target locating device, and the preferred working method that mutually combines of each unit can referring to the description among Fig. 1 to Fig. 2, repeat no more herein.
To sum up above-mentioned, by above-described embodiment provided by the invention, can realize the circular car target of car plate top is accurately located, finish the effective identification to the vehicle vehicle.And, by adopting some optimization process schemes, for example, to car target information area rectification, carry out the irrelevant background image of opening operation removal car target information area etc., more accurately the positioning car mark is identified vehicle.
Through the above description of the embodiments, those skilled in the art can be well understood to the present invention and can realize by the mode that software adds essential general hardware platform, can certainly pass through hardware, but the former is better embodiment in a lot of situation.Based on such understanding, the part that technical scheme of the present invention contributes to prior art in essence in other words can embody with the form of software product, this computer software product can be stored in the storage medium, such as ROM/RAM, magnetic disc, CD etc., comprise that some instructions are with so that a computer equipment (can be personal computer, server, the perhaps network equipment etc.) carry out the above-mentioned method of some part of each embodiment of the present invention or embodiment.
It below only is preferred implementation of the present invention; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the principle of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (10)
1. a car target localization method is characterized in that, comprising:
Carry out the car plate location for input picture, obtain the car plate locating information;
The described car plate locating information that employing is obtained is determined car target information area to be positioned;
Adopt circular corresponding characteristic parameter that described information area is carried out circle and detect, be designated as circular car timestamp at definite described car to be positioned, in described information area, determine described car target to be positioned position.
2. method according to claim 1 is characterized in that, before the circular corresponding characteristic parameter of employing is carried out the circle detection to described information area, also comprises: to described information area executive level correction process.
3. method according to claim 2 is characterized in that, carries out described rectification processing and comprises:
Adopt maximum between-cluster variance OTSU algorithm with license plate binary, obtain binary map;
Extract horizontal edge information in described binary map, obtain horizontal edge figure;
To described horizontal edge figure in predetermined angular range at a predetermined angle the interval carry out angle rotation, for each rotation, add up before the described horizontal edge figure horizontal projection value maximum in the four lines, choosing this horizontal projection, to be worth angle maximum in the corresponding angle be the car plate RA;
Adopt the bilinear interpolation algorithm that described information area is corrected according to described car plate RA.
4. method according to claim 1, it is characterized in that, adopt circular corresponding characteristic parameter that described information area is carried out circle and detect, be designated as circular car timestamp at definite described car to be positioned, determine that in described information area described car target to be positioned position comprises:
For described information area, obtain edge image by edge detection algorithm;
On the described edge image that obtains, adopt the corresponding characteristic parameter of described circle to obtain the interior maximum point of described information area;
Justify detection by the broad sense hough transform, determine that described car to be positioned is marked on the position of described information area;
Adopt the mathematical morphology filter algorithm, locate described car target coordinate to be positioned and the described car mark to be positioned of intercepting in described information area.
5. each described method in 4 according to claim 1 is characterized in that, is adopting the corresponding characteristic parameter of described circle described information area to be carried out before circle detects, and also comprises:
Described information area is carried out gray processing process, and adopt structural element that the gray level image that obtains is carried out opening operation;
Adopt the OTSU algorithm with described Binary Sketch of Grey Scale Image, and obtain connected domain by morphological operation.
6. a car target locating device is characterized in that, comprising:
Acquisition module is used for carrying out the car plate location for input picture, obtains the car plate locating information;
Determination module is used for adopting the described car plate locating information of obtaining to determine car target information area to be positioned;
The detection and location module is used for adopting circular corresponding characteristic parameter that described information area is carried out circle and detects, and is designated as circular car timestamp at definite described car to be positioned, determines described car target to be positioned position in described information area.
7. device according to claim 6 is characterized in that, also comprises: rectification module is used for described information area executive level correction process.
8. device according to claim 7 is characterized in that, described rectification module comprises:
The first acquiring unit is used for adopting maximum between-cluster variance OTSU algorithm with license plate binary, obtains binary map;
Second acquisition unit is used for extracting horizontal edge information in described binary map, obtains horizontal edge figure;
Statistic unit, be used for to described horizontal edge figure in predetermined angular range at a predetermined angle the interval carry out the angle rotation, for each rotation, add up before the described horizontal edge figure maximum horizontal projection value in the four lines;
Choose the unit, being used for choosing this horizontal projection, to be worth the maximum angle of corresponding angle be the car plate RA;
Correcting unit is used for adopting the bilinear interpolation algorithm that described information area is corrected according to described car plate RA.
9. device according to claim 6 is characterized in that, described detection and location module comprises:
The 3rd acquiring unit is used for for described information area, obtains edge image by edge detection algorithm;
The 4th acquiring unit is used at the described edge image that obtains, and adopts the corresponding characteristic parameter of described circle to obtain the interior maximum point of described information area;
Determining unit is used for justifying detection by the broad sense hough transform, determines that described car to be positioned is marked on the position of described information area;
Positioning unit is used for adopting the mathematical morphology filter algorithm, locates described car target coordinate to be positioned and the described car mark to be positioned of intercepting in described information area.
10. each described device in 9 according to claim 6 is characterized in that, also comprises:
The first processing module is used for that described information area is carried out gray processing and processes, and adopts structural element that the gray level image that obtains is carried out opening operation;
The second processing module is used for adopting the OTSU algorithm with described Binary Sketch of Grey Scale Image, and obtains connected domain by morphological operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210591549.3A CN103077391B (en) | 2012-12-30 | 2012-12-30 | Car target localization method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210591549.3A CN103077391B (en) | 2012-12-30 | 2012-12-30 | Car target localization method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103077391A true CN103077391A (en) | 2013-05-01 |
| CN103077391B CN103077391B (en) | 2016-01-20 |
Family
ID=48153915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210591549.3A Expired - Fee Related CN103077391B (en) | 2012-12-30 | 2012-12-30 | Car target localization method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103077391B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104391966A (en) * | 2014-12-03 | 2015-03-04 | 中国人民解放军国防科学技术大学 | Typical car logo searching method based on deep learning |
| CN105160300A (en) * | 2015-08-05 | 2015-12-16 | 山东科技大学 | Text extraction method based on level set segmentation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050027541A1 (en) * | 2003-07-31 | 2005-02-03 | Glen Hagood | System and Method for Fabricating Informational Placard |
| CN1928892A (en) * | 2006-09-20 | 2007-03-14 | 王枚 | Method and device for license plate location recognition, vehicle-logo location recognition and vehicle type |
| CN101196980A (en) * | 2006-12-25 | 2008-06-11 | 四川川大智胜软件股份有限公司 | Method for accurately recognizing high speed mobile vehicle mark based on video |
-
2012
- 2012-12-30 CN CN201210591549.3A patent/CN103077391B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050027541A1 (en) * | 2003-07-31 | 2005-02-03 | Glen Hagood | System and Method for Fabricating Informational Placard |
| CN1928892A (en) * | 2006-09-20 | 2007-03-14 | 王枚 | Method and device for license plate location recognition, vehicle-logo location recognition and vehicle type |
| CN101196980A (en) * | 2006-12-25 | 2008-06-11 | 四川川大智胜软件股份有限公司 | Method for accurately recognizing high speed mobile vehicle mark based on video |
Non-Patent Citations (3)
| Title |
|---|
| 李文举等: "质量退化的车牌字符分割方法", 《计算机辅助设计与图形学学报》 * |
| 李玲: "车标定位方法研究", 《中国优秀硕士论文全文数据库 信息科技辑》 * |
| 王玫等: "基于PCA和边缘不变矩的车标识别新方法", 《计算机工程与应用》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104391966A (en) * | 2014-12-03 | 2015-03-04 | 中国人民解放军国防科学技术大学 | Typical car logo searching method based on deep learning |
| CN104391966B (en) * | 2014-12-03 | 2017-09-29 | 中国人民解放军国防科学技术大学 | Typical logo searching method based on deep learning |
| CN105160300A (en) * | 2015-08-05 | 2015-12-16 | 山东科技大学 | Text extraction method based on level set segmentation |
| CN105160300B (en) * | 2015-08-05 | 2018-08-21 | 山东科技大学 | A kind of text abstracting method based on level-set segmentation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103077391B (en) | 2016-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tan et al. | A novel curve lane detection based on Improved River Flow and RANSA | |
| Yu et al. | A novel license plate location method based on wavelet transform and EMD analysis | |
| CN103324930B (en) | A kind of registration number character dividing method based on grey level histogram binaryzation | |
| EP1796043B1 (en) | Object detection | |
| Mahini et al. | An efficient features-based license plate localization method | |
| CN102930268B (en) | A kind of for polluting and the accurate positioning method of DataMatrix code in various visual angles situation | |
| Yan et al. | A method of lane edge detection based on Canny algorithm | |
| CN109583280A (en) | Lane detection method, apparatus, equipment and storage medium | |
| US8155381B2 (en) | Vehicle headlight detecting method and apparatus, and region-of-interest segmenting method and apparatus | |
| CN103065140A (en) | Location method and device for automobile logos | |
| CN109800752B (en) | Automobile license plate character segmentation and recognition algorithm based on machine vision | |
| US20070127777A1 (en) | Apparatus and method for detecting a road boundary | |
| Paunwala et al. | A novel multiple license plate extraction technique for complex background in Indian traffic conditions | |
| Wang et al. | A vision-based road edge detection algorithm | |
| CN102419820A (en) | Method for rapidly detecting car logo in videos and images | |
| CN105488501A (en) | Method for correcting license plate slant based on rotating projection | |
| CN103065144A (en) | Automobile logo identification method and device | |
| CN105303153A (en) | Vehicle license plate identification method and apparatus | |
| CN103324935A (en) | Method for vehicle positioning and region segmenting in image | |
| CN108256445A (en) | Method for detecting lane lines and system | |
| CN105023002A (en) | Vehicle logo positioning method based on active vision | |
| CN103093229A (en) | Positioning method and device of vehicle logo | |
| CN104732530A (en) | Image edge detection method | |
| CN103077391B (en) | Car target localization method and device | |
| CN103065139A (en) | Location method and device for automobile logos |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160120 Termination date: 20191230 |