CN105448095B - Method and apparatus are surveyed in a kind of yellow mark car test - Google Patents
Method and apparatus are surveyed in a kind of yellow mark car test Download PDFInfo
- Publication number
- CN105448095B CN105448095B CN201410243705.6A CN201410243705A CN105448095B CN 105448095 B CN105448095 B CN 105448095B CN 201410243705 A CN201410243705 A CN 201410243705A CN 105448095 B CN105448095 B CN 105448095B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- vehicle window
- image
- window
- rectangle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of yellow mark car test to survey method and apparatus:For the positive candid photograph image of every width vehicle got, the area-of-interest for including vehicle window labeling is determined in image from the vehicle positive capture respectively;M subgraphs to be analyzed are detected from area-of-interest, including a rectangle vehicle window respectively in each subgraph to be analyzed labels, and M is positive integer;It is determined that it whether there is Yellow environment-friendly mark in each rectangle vehicle window labeling detected, if it is, the positive vehicle captured in image of the vehicle is defined as into yellow mark car.Using scheme of the present invention, can efficiently identify out whether the vehicle in image is yellow mark car.
Description
Technical field
The present invention relates to intelligent transportation field, method and apparatus are surveyed in more particularly to a kind of yellow mark car test.
Background technology
Huang mark car is the nickname of high pollution discharge vehicle, refers to the gasoline car of not up to state I discharge standards, or not up to state
The diesel vehicle of III discharge standards, what is pasted by it is Yellow environment-friendly mark, therefore is referred to as yellow mark car.
Because the pollution of Huang mark overall height, discharge be not up to standard, therefore environmental administration or traffic department would generally adopt to such vehicle
Particular provisions are taken to enter row constraint, it is such as limited and is travelled in some section/regions, correspondingly, then needed from monitoring figure
Detect the yellow mark car in these sections/region traveling in time as in.
But in the prior art, also without a kind of mode, it can effectively detect whether the vehicle in image is yellow mark
Car.
The content of the invention
In view of this, the invention provides a kind of yellow mark car test to survey method and apparatus, can efficiently identify out in image
Vehicle whether be yellow mark car.
In order to achieve the above object, the technical proposal of the invention is realized in this way:
A kind of yellow mark car detection method, including:
For the positive candid photograph image of every width vehicle got, following handle is carried out respectively:
The area-of-interest for including vehicle window labeling is determined in image from the vehicle positive capture;
M subgraphs to be analyzed are detected from the area-of-interest, include one respectively in each subgraph to be analyzed
Individual rectangle vehicle window labeling, M is positive integer;
It is determined that it whether there is Yellow environment-friendly mark in each rectangle vehicle window labeling detected, if it is, by the vehicle
The vehicle that forward direction is captured in image is defined as yellow mark car.
A kind of yellow mark car detector, including:
First processing module, it is positive from the vehicle respectively for the positive candid photograph image of every width vehicle for getting
The area-of-interest for determining to include vehicle window labeling in image is captured, and is notified to Second processing module;
The Second processing module, for detecting M subgraphs to be analyzed from the area-of-interest, each treat point
Analyse includes a rectangle vehicle window respectively in subgraph labels, and M is positive integer;It is determined that detect each rectangle vehicle window labeling in whether
Yellow environment-friendly mark be present, if it is, the positive vehicle captured in image of the vehicle is defined as into yellow mark car.
In view of the Yellow environment-friendly mark of yellow mark car generally use rectangle, therefore in scheme of the present invention, can first from
Vehicle positive capture detects that rectangle vehicle window labels in image, afterwards, can further analyze in the rectangle vehicle window labeling detected
With the presence or absence of Yellow environment-friendly mark, if it is, can determine that the positive vehicle captured in image of vehicle for yellow mark car;Namely
Say after scheme of the present invention, can efficiently identify out whether the vehicle in image is yellow mark car, so as to be Ministry of Communications
Door etc. carries out yellow mark car supervision etc. and provides effective supervision meanses.
Brief description of the drawings
Fig. 1 is the yellow flow chart marked car test and survey embodiment of the method for the present invention.
Fig. 2 is the schematic diagram of existing environmental mark.
Fig. 3 is the schematic diagram of existing compulsory insurance for traffic accident of motor-drivenvehicle mark.
Fig. 4 is the schematic diagram of existing vehicle annual test mark.
Fig. 5 is the yellow flow chart for marking car detection method preferred embodiment of the present invention.
Fig. 6 is the yellow composition structural representation for marking car detector embodiment of the present invention.
Embodiment
In order that technical scheme is clearer, clear, develop simultaneously embodiment referring to the drawings, to institute of the present invention
The scheme of stating is described in further detail.
Fig. 1 is the yellow flow chart marked car test and survey embodiment of the method for the present invention.As shown in figure 1, for the every width car got
It is positive to capture image (such as traffic block port forward direction vehicle image), can be respectively according to shown in following steps 11~13 at mode
Reason.
Step 11:The area-of-interest for including vehicle window labeling is determined in image from vehicle positive capture.
Above-mentioned area-of-interest typically refers to vehicle window region.
The mode of area-of-interest is determined from the positive candid photograph image of vehicle to be:
Car plate detection is carried out in the positive candid photograph image of vehicle;
It is first according to the position of car plate and size, and the relative position of vehicle window and car plate if being able to detect that car plate
Knowledge is tested, determines vehicle window region, and using vehicle window region as area-of-interest;
If car plate can not be detected, image of capturing positive to vehicle carries out vehicle window detection, navigates to vehicle window region, and
Using the vehicle window region detected as area-of-interest, it is impossible to which it is probably because vehicle does not hang car plate or car to detect car plate
Board is stained.
As can be seen that above detected using car plate position and vehicle window be combined by the way of determine area-of-interest, can be with
Avoid in the case where car plate can not be detected, it is impossible to the defects of carrying out algorithm operating.
Image is captured due to being that vehicle is positive, then vehicle window region just refers to the front windshield region of vehicle, car in fact
Window labeling is generally pasted onto the upper right corner in the front windshield region of vehicle.
Step 12:M subgraphs to be analyzed are detected from area-of-interest, are included respectively in each subgraph to be analyzed
One rectangle vehicle window labeling, M is positive integer.
Vehicle window labeling mainly includes following three class:Vehicle annual test mark, compulsory insurance for traffic accident of motor-drivenvehicle mark and environmental mark.Wherein, vehicle
Annual test mark and environmental mark are generally rectangular in shape, and the shape of compulsory insurance for traffic accident of motor-drivenvehicle mark is generally elliptical.
As shown in figs. 2 to 4, Fig. 2 is the schematic diagram of existing environmental mark, and Fig. 3 is the schematic diagram of existing compulsory insurance for traffic accident of motor-drivenvehicle mark, is schemed
4 be the schematic diagram of existing vehicle annual test mark.
In this step, M subgraphs to be analyzed can be detected from area-of-interest, are distinguished in each subgraph to be analyzed
Labelled including a rectangle vehicle window, M is positive integer, and depending on actual conditions, the rectangle vehicle window detected labels specific value
Vehicle annual test mark, environmental mark and other flase drop results etc. may be included.
Specifically, can be the sliding window of area-of-interest one predefined size of setting, when the sliding window is according to pre-
After fixed step size often slides once, the detection grader that can be generated respectively according to training in advance determine in the sliding window whether
Labelled including a rectangle vehicle window, if it is, can be using the image in the sliding window as a subgraph to be analyzed.
The predefined size and the specific value of the pre- fixed step size can be decided according to the actual requirements.
It is preferred that the detection grader can be cascade (Cascade) grader;Correspondingly, for each sliding window,
Local binary patterns (LBP, Local Binary Patterns) feature of the image in the sliding window can be obtained respectively, and
According to the LBP features and Cascade graders got, whether determine includes a rectangle vehicle window in the sliding window pastes
Mark.
In actual applications, a sufficient amount of rectangle vehicle window labeling positive sample (including rectangle vehicle window can be obtained in advance
The subgraph of labeling), and the LBP features of each positive sample are obtained respectively, generated according to each LBP features trainings got
Cascade graders, are implemented as prior art.
In machine vision, LBP is a kind of local binary patterns feature, can be good at describing the textural characteristics of image,
This feature computational methods are simple, and can effectively eliminate influence caused by ambient lighting, and in applied fields such as traffic block ports
Jing Zhong, the change of ambient lighting is extremely complex, labels the vehicle window caused in scheme of the present invention using LBP features and examines
Survey mode has more robustness.
It should be noted that when carrying out the labeling detection of rectangle vehicle window, ensure high recall rate as far as possible, avoid missing inspection, i.e.,
False drop rate can suitably be loosened, to avoid missing Yellow environment-friendly mark at this stage.
Step 13:It is determined that it whether there is Yellow environment-friendly mark in each rectangle vehicle window labeling detected, if it is, by car
The positive vehicle captured in image is defined as yellow mark car.
Because Huang mark car posts Yellow environment-friendly mark, therefore in this step, each square detected in step 12 can be directed to
Shape vehicle window labels, and determines whether Yellow environment-friendly mark be present, if it is, can be by the positive vehicle captured in image of vehicle
It is defined as yellow mark car.
As it was previously stated, the rectangle vehicle window labeling detected in step 12 may be vehicle annual test mark, it is also possible to for environmental protection
Mark, it is also possible to other flase drop results etc..Wherein, environmental mark may be yellow (Huang mark car) or green (non-yellow mark car)
May be blueness or yellow etc. Deng, vehicle annual test mark, but the vehicle annual test mark of yellow is usually yellow bottom surplus, and yellow ring
It is usually yellow bottom wrongly written or mispronounced character to protect mark, that is to say, that Yellow environment-friendly mark generally has following characteristics:Rectangle, yellow, yellow bottom are white
Word.
Therefore, in this step, each rectangle vehicle window labeling detected in step 12 can be directed to, obtains the rectangle car respectively
The predetermined characteristic of subgraph to be analyzed where window labeling, and the knowledge generated according to the predetermined characteristic and training in advance got
Other grader, determine whether rectangle vehicle window labeling is Yellow environment-friendly mark.The predetermined characteristic may include:Color histogram
Feature, local gray level histogram feature and Gradient Features.Yellow environment-friendly is identified by the way of various features are combined
Mark, so as to may be such that recognition result is more accurate, each feature is introduced respectively below.
1) color histogram feature
Described by color histogram is different color ratio shared in entire image, is not relevant for various colors and exists
Residing locus in image;Vehicle window is labelled due to reasons such as resolution ratio limitations, can not see specific grain details, but
It is that can be described well by color histogram feature.
In hsv color space, H components represent colourity, and S components represent saturation degree, and V component represents brightness, using H components
The color of target can be just told well.If H element quantizations to 0~360, then yellow may existing section be
[10,80], other colors can then fall in other positions.So, it is described by using the histogram feature of H components, you can
Yellow is labelled well and made a distinction with labeling such as other bluenesss, greens.
2) local gray level histogram feature
What local gray level histogram feature reflected is the frequency that certain gray scale occurs in image, as it was previously stated, the car of yellow
Annual test mark is usually yellow bottom surplus, and Yellow environment-friendly mark is usually yellow bottom wrongly written or mispronounced character, therefore uses local gray level histogram
Feature is described, you can makes a distinction both vehicle windows labeling.
3) Gradient Features
Gradient Features describe the textural characteristics of image on the whole, can be by the base of labeling by extracting Gradient Features
The information such as this form and inner vein all extracts.Based on this feature, environmental mark and other flase drop results can be entered
Row is distinguished, and flase drop result is probably because vehicle window is in the presence of caused by being stained or having pasted other unrelated articles etc..
How to obtain color histogram feature, local gray level histogram feature and Gradient Features is prior art.
Label for each rectangle vehicle window for being detected in step 12, treated point where rectangle vehicle window labeling is got
After color histogram feature, local gray level histogram feature and the Gradient Features of analysing subgraph, it can be given birth to according to training in advance
Into recognition classifier, determine the rectangle vehicle window labeling whether be Yellow environment-friendly mark, if it is, can determine that vehicle forward direction
Capture the vehicle in image and be defined as yellow mark car, otherwise, car is marked for non-Huang.
In actual applications, sufficient amount of rectangle vehicle window labeling positive sample can be obtained in advance, and is obtained each respectively just
Color histogram feature, local gray level histogram feature and the Gradient Features of sample, and according to each positive sample got
Features training generates recognition classifier, it is preferred that recognition classifier can be SVMs (SVM, Support Vector
Machine) grader, it is implemented as prior art.
Based on above-mentioned introduction, Fig. 5 is the yellow flow chart for marking car detection method preferred embodiment of the present invention.As shown in figure 5, bag
Include following steps 51~58.
Step 51:Car plate detection is carried out in the positive candid photograph image of vehicle, it is determined whether car plate is able to detect that, if
It is then to perform step 52, otherwise, performs step 53.
Step 52:According to the position of car plate and size, and the relative position priori of vehicle window and car plate, car is determined
Window region, and using vehicle window region as area-of-interest, step 54 is performed afterwards.
Step 53:Image of capturing positive to vehicle carries out vehicle window detection, and using the vehicle window region detected as interested
Region, step 54 is performed afterwards.
Step 54:M subgraphs to be analyzed are detected from area-of-interest, are included respectively in each subgraph to be analyzed
One rectangle vehicle window labeling, M is positive integer.
Step 55~56:Labelled for each rectangle vehicle window, obtain the son to be analyzed where rectangle vehicle window labeling respectively
Color histogram feature, local gray level histogram feature and the Gradient Features of image, and determine to be somebody's turn to do according to the feature got
Whether rectangle vehicle window labeling is Yellow environment-friendly mark, if it is, performing step 57, otherwise, performs step 58.
Step 57:Determine that the positive vehicle captured in image of vehicle for yellow mark car, terminates flow.
Step 58:Determine that the positive vehicle captured in image of vehicle for non-yellow mark car, terminates flow.
Once it is Yellow environment-friendly mark to have a rectangle vehicle window labeling, then the positive vehicle captured in image of vehicle is can determine that
Car is marked for Huang, is not Yellow environment-friendly mark if all of rectangle vehicle window labeling, then can determine that vehicle is positive and capture in image
Vehicle yellow mark car to be non-.
Fig. 6 is the yellow composition structural representation for marking car detector embodiment of the present invention.As shown in fig. 6, including:
First processing module, for the positive candid photograph image of every width vehicle for getting, captured respectively from vehicle is positive
The area-of-interest for including vehicle window labeling is determined in image, and is notified to Second processing module;
Second processing module, for detecting M subgraphs to be analyzed, each subgraph to be analyzed from area-of-interest
Middle to include a rectangle vehicle window labeling respectively, M is positive integer;It is determined that it whether there is yellow in each rectangle vehicle window labeling detected
Environmental mark, if it is, the positive vehicle captured in image of vehicle is defined as into yellow mark car.
Specifically,
First processing module carries out car plate detection in the positive candid photograph image of vehicle;If being able to detect that car plate, root
Position and size according to car plate, and the relative position priori of vehicle window and car plate, determine vehicle window region, and by vehicle window area
Domain is as area-of-interest;If car plate can not be detected, image of capturing positive to vehicle carries out vehicle window detection, and will detection
The vehicle window region arrived is as area-of-interest.
In addition,
Second processing module can be the sliding window that area-of-interest sets a predefined size, when sliding window is according to pre-
After fixed step size often slides once, the detection grader generated respectively according to training in advance determines whether wrapped in the sliding window
A rectangle vehicle window labeling is included, if it is, using the image in the sliding window as a subgraph to be analyzed.
It is preferred that
Detection grader is Cascade graders;
Second processing module is directed to each sliding window, obtains the LBP features of the image in the sliding window, and root respectively
According to the LBP features and Cascade graders got, whether determine includes a rectangle vehicle window in the sliding window pastes
Mark.
Further,
Second processing module can be directed to each rectangle vehicle window labeling detected, obtain rectangle vehicle window labeling place respectively
Subgraph to be analyzed predetermined characteristic, and the recognition classifier generated according to the predetermined characteristic and training in advance that get,
Determine whether rectangle vehicle window labeling is Yellow environment-friendly mark.
It is preferred that
Recognition classifier is SVM classifier;
Predetermined characteristic includes:Color histogram feature, local gray level histogram feature and Gradient Features.
The specific workflow of Fig. 6 shown device embodiments refer to the respective description in preceding method embodiment, herein
Repeat no more.
In summary, presently preferred embodiments of the present invention is these are only, is not intended to limit the scope of the present invention.
Within the spirit and principles of the invention, any modification, equivalent substitution and improvements made etc., it should be included in the present invention's
Within protection domain.
Claims (10)
- A kind of 1. yellow mark car detection method, it is characterised in that including:For the positive candid photograph image of every width vehicle got, following handle is carried out respectively:The area-of-interest for including vehicle window labeling is determined in image from the vehicle positive capture;M subgraphs to be analyzed are detected from the area-of-interest, include a square respectively in each subgraph to be analyzed Shape vehicle window labels, and M is positive integer;It is determined that it whether there is Yellow environment-friendly mark in each rectangle vehicle window labeling detected, if it is, the vehicle is positive Capture the vehicle in image and be defined as yellow mark car;Wherein, include in each rectangle vehicle window labeling for determining to detect with the presence or absence of Yellow environment-friendly mark:Labelled for each rectangle vehicle window for detecting, obtain the pre- of subgraph to be analyzed where rectangle vehicle window labeling respectively Determine feature;The predetermined characteristic includes:Color histogram feature, local gray level histogram feature and Gradient Features;The recognition classifier generated according to the predetermined characteristic and training in advance got, whether determine rectangle vehicle window labeling For Yellow environment-friendly mark.
- 2. according to the method for claim 1, it is characterised in thatIt is described to determine that the area-of-interest comprising vehicle window labeling includes in image from the vehicle positive capture:Car plate detection is carried out in the positive candid photograph image of the vehicle;If being able to detect that car plate, known according to the position of car plate and size, and the relative position priori of vehicle window and car plate Know, determine vehicle window region, and using vehicle window region as the area-of-interest;If car plate can not be detected, image of capturing positive to the vehicle carries out vehicle window detection, and the vehicle window that will be detected Region is as the area-of-interest.
- 3. according to the method for claim 1, it is characterised in thatIt is described to detect that M subgraphs to be analyzed include from the area-of-interest:The sliding window of one predefined size is set for the area-of-interest, when the sliding window is often slided according to pre- fixed step size After moving once, the detection grader generated respectively according to training in advance determines whether include a rectangle in the sliding window Vehicle window labels, if it is, using the image in the sliding window as a subgraph to be analyzed.
- 4. according to the method for claim 3, it is characterised in thatThe detection grader is cascade Cascade graders;The detection grader generated according to training in advance determines that whether including a rectangle vehicle window in the sliding window pastes Mark includes:Obtain the local binary patterns LBP features of the image in the sliding window;According to the LBP features and the Cascade graders got, determine whether include a square in the sliding window Shape vehicle window labels.
- 5. according to the method for claim 1, it is characterised in thatThe recognition classifier is support vector machines grader.
- A kind of 6. yellow mark car detector, it is characterised in that including:First processing module, for the positive candid photograph image of every width vehicle for getting, captured respectively from the vehicle is positive The area-of-interest for including vehicle window labeling is determined in image, and is notified to Second processing module;The Second processing module, for detecting M subgraphs to be analyzed, each son to be analyzed from the area-of-interest Include a rectangle vehicle window in image respectively to label, M is positive integer;It is determined that it whether there is in each rectangle vehicle window labeling detected Yellow environment-friendly mark, if it is, the positive vehicle captured in image of the vehicle is defined as into yellow mark car;Wherein, the Second processing module is directed to each rectangle vehicle window labeling detected, obtains rectangle vehicle window labeling respectively The predetermined characteristic of the subgraph to be analyzed at place, and the identification generated according to the predetermined characteristic and training in advance got is classified Device, determine whether rectangle vehicle window labeling is Yellow environment-friendly mark;The predetermined characteristic includes:Color histogram feature, office Portion's grey level histogram feature and Gradient Features.
- 7. device according to claim 6, it is characterised in thatThe first processing module carries out car plate detection in the positive candid photograph image of the vehicle;If being able to detect that car plate, Then according to the position of car plate and size, and the relative position priori of vehicle window and car plate, vehicle window region is determined, and by car Window region is as the area-of-interest;If car plate can not be detected, image of capturing positive to the vehicle carries out vehicle window Detection, and using the vehicle window region detected as the area-of-interest.
- 8. device according to claim 6, it is characterised in thatThe Second processing module is the sliding window that the area-of-interest sets a predefined size, when the sliding window After often being slided once according to pre- fixed step size, the detection grader generated respectively according to training in advance is determined in the sliding window Whether include a rectangle vehicle window to label, if it is, using the image in the sliding window as a subgraph to be analyzed.
- 9. device according to claim 8, it is characterised in thatThe detection grader is cascade Cascade graders;The Second processing module is directed to each sliding window, obtains the local binary patterns of the image in the sliding window respectively LBP features, and according to the LBP features and the Cascade graders got, determine whether include in the sliding window One rectangle vehicle window labeling.
- 10. device according to claim 6, it is characterised in thatThe recognition classifier is support vector machines grader.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410243705.6A CN105448095B (en) | 2014-06-03 | 2014-06-03 | Method and apparatus are surveyed in a kind of yellow mark car test |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410243705.6A CN105448095B (en) | 2014-06-03 | 2014-06-03 | Method and apparatus are surveyed in a kind of yellow mark car test |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105448095A CN105448095A (en) | 2016-03-30 |
CN105448095B true CN105448095B (en) | 2017-11-17 |
Family
ID=55558220
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410243705.6A Active CN105448095B (en) | 2014-06-03 | 2014-06-03 | Method and apparatus are surveyed in a kind of yellow mark car test |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105448095B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106446150B (en) * | 2016-09-21 | 2019-10-29 | 北京数字智通科技有限公司 | A kind of method and device of vehicle precise search |
CN108010326A (en) * | 2017-11-24 | 2018-05-08 | 南京依维柯汽车有限公司 | A kind of vehicle identification system and its method |
CN108389205B (en) * | 2018-03-19 | 2022-10-25 | 北京航空航天大学 | Rail foreign matter monitoring method and device based on air-based platform image |
CN113516104B (en) * | 2021-08-09 | 2023-08-29 | 上海高德威智能交通***有限公司 | Commercial passenger car identification method and device, electronic equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201009832Y (en) * | 2007-02-14 | 2008-01-23 | 张革军 | Environmental protection information identification device for vehicle |
CN102024148A (en) * | 2011-01-07 | 2011-04-20 | 四川川大智胜软件股份有限公司 | Method for identifying green mark of taxi |
CN202887219U (en) * | 2012-04-27 | 2013-04-17 | 乌朵·皮恩特克 | Dangerous cargo transportation identifying system |
CN103065142A (en) * | 2012-12-30 | 2013-04-24 | 信帧电子技术(北京)有限公司 | Automobile logo division method and device |
CN103077407A (en) * | 2013-01-21 | 2013-05-01 | 信帧电子技术(北京)有限公司 | Car logo positioning and recognition method and car logo positioning and recognition system |
CN103366579A (en) * | 2013-07-05 | 2013-10-23 | 江苏通慧智能科技有限公司 | Vehicle identification and positioning method |
CN203325216U (en) * | 2013-05-20 | 2013-12-04 | 安徽大学 | Yellow label car active signal monitoring system based on RFID and image license plate identification technologies |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006073647A2 (en) * | 2004-12-03 | 2006-07-13 | Sarnoff Corporation | Method and apparatus for unsupervised learning of discriminative edge measures for vehicle matching between non-overlapping cameras |
-
2014
- 2014-06-03 CN CN201410243705.6A patent/CN105448095B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201009832Y (en) * | 2007-02-14 | 2008-01-23 | 张革军 | Environmental protection information identification device for vehicle |
CN102024148A (en) * | 2011-01-07 | 2011-04-20 | 四川川大智胜软件股份有限公司 | Method for identifying green mark of taxi |
CN202887219U (en) * | 2012-04-27 | 2013-04-17 | 乌朵·皮恩特克 | Dangerous cargo transportation identifying system |
CN103065142A (en) * | 2012-12-30 | 2013-04-24 | 信帧电子技术(北京)有限公司 | Automobile logo division method and device |
CN103077407A (en) * | 2013-01-21 | 2013-05-01 | 信帧电子技术(北京)有限公司 | Car logo positioning and recognition method and car logo positioning and recognition system |
CN203325216U (en) * | 2013-05-20 | 2013-12-04 | 安徽大学 | Yellow label car active signal monitoring system based on RFID and image license plate identification technologies |
CN103366579A (en) * | 2013-07-05 | 2013-10-23 | 江苏通慧智能科技有限公司 | Vehicle identification and positioning method |
Also Published As
Publication number | Publication date |
---|---|
CN105448095A (en) | 2016-03-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Varadharajan et al. | Vision for road inspection | |
CN108898047B (en) | Pedestrian detection method and system based on blocking and shielding perception | |
KR102036127B1 (en) | Apparel production monitoring system using image recognition | |
Siriborvornratanakul | An automatic road distress visual inspection system using an onboard in‐car camera | |
De Charette et al. | Real time visual traffic lights recognition based on spot light detection and adaptive traffic lights templates | |
CN105913093B (en) | A kind of template matching method for Text region processing | |
WO2017190574A1 (en) | Fast pedestrian detection method based on aggregation channel features | |
CN104951784B (en) | A kind of vehicle is unlicensed and license plate shading real-time detection method | |
EP3806064A1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
US9092696B2 (en) | Image sign classifier | |
CN104751097B (en) | A kind of detection process method and device of vehicle identification code | |
CN109977877B (en) | Intelligent auxiliary image judging method, system and system control method for security inspection | |
CN102982313B (en) | The method of Smoke Detection | |
CN105448095B (en) | Method and apparatus are surveyed in a kind of yellow mark car test | |
CN111382704A (en) | Vehicle line-pressing violation judgment method and device based on deep learning and storage medium | |
CN106709530A (en) | License plate recognition method based on video | |
CN104050684B (en) | A kind of video frequency motion target sorting technique based on on-line training and system | |
CN111325769A (en) | Target object detection method and device | |
CN111191611A (en) | Deep learning-based traffic sign label identification method | |
CN104766344B (en) | Vehicle checking method based on movement edge extractor | |
DK2447884T3 (en) | A method for the detection and recognition of an object in an image and an apparatus and a computer program therefor | |
Azad et al. | A novel and robust method for automatic license plate recognition system based on pattern recognition | |
CN109409191A (en) | A kind of zebra stripes vehicle evacuation detection method and system based on machine learning | |
Bulugu | Algorithm for license plate localization and recognition for tanzania car plate numbers | |
CN108765456A (en) | Method for tracking target, system based on linear edge feature |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20190611 Address after: 201203 2nd Floor, No. 77-78, 887 Lane, Zuchong Road, Zhangjiang High-tech Park, Pudong New Area, Shanghai Patentee after: Gaodewei Intelligent Traffic System Co., Ltd., Shanghai Address before: 310053 Haikang Science and Technology Park, 555 Qianmo Road, Binjiang District, Hangzhou City, Zhejiang Province Patentee before: Hangzhou Hikvision Digital Technology Co., Ltd. |
|
TR01 | Transfer of patent right |