CN108564814A - A kind of parking position detection method and device based on image - Google Patents
A kind of parking position detection method and device based on image Download PDFInfo
- Publication number
- CN108564814A CN108564814A CN201810573699.9A CN201810573699A CN108564814A CN 108564814 A CN108564814 A CN 108564814A CN 201810573699 A CN201810573699 A CN 201810573699A CN 108564814 A CN108564814 A CN 108564814A
- Authority
- CN
- China
- Prior art keywords
- parking stall
- parking
- feature
- image
- point
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06V10/507—Summing image-intensity values; Histogram projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The parking position detection method based on image that the invention discloses a kind of, including:The location information for obtaining monitoring parking stall, the location information of each parking stall is indicated by the coordinate of multiple angle points;The marginal information for obtaining monitoring image carries out preliminary screening to parking space state;Image is handled, the angle point of parking stall is extracted;The coordinate for obtaining the angle point of each parking stall calculates each angular coordinate to the distance of parking stall central point, builds position feature in conjunction with the location information of parking stall, the grey level histogram feature for combining parking stall obtains the composite character of parking stall;Training parking stall grader, the parking stall grader completed using training judge whether current parking stall has vehicle.The detection method can handle multiple parking stalls simultaneously, can reduce equipment cost, improve the parking stall management efficiency in parking lot.
Description
Technical field
The present invention relates to a kind of parking position detection method, analyzed based on monitoring image more particularly to a kind of
Parking position detection method and device.
Background technology
With increasing rapidly for automobile demand amount, the automobile production quantity in China has occupied first place in the world.Public Parking
Quantity cannot increasingly meet the increasingly increased parking demand of people, the problem of " parking difficulty ", becomes increasingly conspicuous.With parking lot
The more build the more big, the disadvantage that the labor intensity of labor management is big, efficiency is low is more prominent, cannot be satisfied today's society efficiently, fast section
The demand played.Intelligent parking lot system comes into being, and plays an important role in medium-and-large-sized parking lot.And parking position
Detection, is a most important part for Intelligent parking lot system.
Parking position detection technique is broadly divided into four classes:Traditional manpower management system needs to put into a large amount of manpower,
It is time-consuming and laborious, it is easy that parking lot is made to block up;Ground induction coil needs road pavement to construct when installing, and influences the operation in parking lot,
When machine breakdown, maintenance needs the surface construction that satisfies the need, and causes to increase equipment cost and maintenance cost, and be not suitable for outdoor large size
The parking stall measure in parking lot;Ultrasound examination needs to be positioned manually in vehicle location;Intelligent parking based on video analysis
Field system can guide car owner to find empty parking space in time, when reverse car seeking, can be as accurate as each parking stall, accuracy is high, subtracts
Few car owner blindly finds the time of parking stall in parking lot.The normalization in parking lot is promoted to build.
Point many modules in Intelligent parking lot management system, parking stall measure module occupies important in the entire system
Status.Since video image to be detected is dynamic, such as Changes in weather, intensity of illumination, shade and pedestrian's sundries factor
It influences, the accuracy of testing result can be reduced to a certain extent.
The problem of parking lot detection method based on video analysis aims to solve the problem that has:
(1) different vehicle color, difference in size, car owner's factors such as block lack of standardization on parking stall line of stopping influence detection
Accuracy;
(2) weather, illumination influence of the variation to testing result;
(3) influence to testing result such as the shade on parking stall, pedestrian, sundries.
Invention content
In order to solve above-mentioned technical problem, the present invention provides a kind of parking position detection side based on image
Method, the detection method combination texture and gray feature, carry out judgement parking space state, and discrimination is high, can exclude weather, illumination,
The influence to testing result such as pedestrian, sundries, shade on parking stall, and the detection method can handle multiple parking stalls, energy simultaneously
Equipment cost is enough reduced, the parking stall management efficiency in parking lot is improved.
The technical scheme is that:
A kind of parking position detection method based on image, includes the following steps:
S01:The location information for obtaining monitoring parking stall carries out the location information of each parking stall by the coordinate of multiple angle points
It indicates;
S02:The marginal information for obtaining monitoring image carries out preliminary screening to parking space state;
S03:Image is handled, the angle point of parking stall is extracted;
S04:The coordinate for obtaining the angle point of each parking stall, calculate each angular coordinate to parking stall central point distance, in conjunction with
The location information of parking stall builds position feature, and the grey level histogram feature for combining parking stall obtains the composite character of parking stall;
S05:Training parking stall grader, the parking stall grader completed using training judge whether current parking stall has vehicle.
In preferred technical solution, before the step S02, image is pre-processed by gaussian filtering.
In preferred technical solution, the step S02 is specifically included:
S21:The edge direction of all pixels point and local gradient magnitude in image are calculated, the amplitude on gradient direction is obtained
Larger point;
S22:The amplitude of acquisition is subjected to non-maxima suppression, local maximum is found out, obtains marginal point.
In preferred technical solution, the angle point in the step S03 is Harris angle points, and window function E (u, v) is:
Wherein (u, v) is the offset of dimensional Gaussian window function, and w (x, y) is the pixel of window function, I (x, y) table
The gray scale of diagram picture.
In preferred technical solution, position feature is built in the step S04, the grey level histogram feature for combining parking stall obtains
To the composite character of parking stall, following steps are specifically included:
S41:The feature vector Dist for building dimension A, traverse all angle points to central point distance D (x), according to following public affairs
Formula calculates Dist features:
Obtain the position feature of angle point distribution;
S42:The intensity value ranges of pixel are 0-255, the feature Hist of structure dimension B, are traversed each in parking area
Pixel obtains corresponding gray value Gray, then Hist [Gray] ++, build grey level histogram feature;
S43:Co-location feature and gray feature, the composite character that structure dimension is A+B.
In preferred technical solution, two graders are constructed by SVM in the step S05, training parking stall grader includes
Following steps:
S51:Acquire training set T={ (x1,y1),…,(xl,yl)}∈(X×Y)l;
Wherein, xi∈ X=Rn,yi∈ Y={ -1,1 } (i=1,2 ..., l);xiFor feature vector, yiRepresent label;
S52:Choose kernel function K (xi, xj) and parameter, ai、ajThe value of optimal solution is represented, between C is two in object function
Weight, l represents the dimension of feature vector;
Obtain optimal solution:
S53:Choose α*One-componentAnd threshold value is calculated, wherein K (xi-xj) represent the value of kernel function:
S54:Construct decision function:
When function value is " 1 ", indicate that current parking stall is parked vehicle and indicates no vehicle when value is " -1 ".
The parking position detection device based on image that the invention also discloses a kind of, including:
One parking stall position acquisition module obtains the location information of monitoring parking stall, the location information of each parking stall is passed through more
The coordinate of a angle point is indicated;
One parking space state preliminary screening module, obtains the marginal information of monitoring image, and preliminary screening is carried out to parking space state;
One parking stall angle point grid module, handles image, extracts the angle point of parking stall;
One composite character builds module, obtains the coordinate of the angle point of each parking stall, calculates in each angular coordinate to parking stall
The distance of heart point builds position feature in conjunction with the location information of parking stall, and the grey level histogram feature for combining parking stall obtains parking stall
Composite character;
One parking stall classifier training judgment module, training parking stall grader are judged using the parking stall grader that training is completed
Whether current parking stall has vehicle.
In preferred technical solution, the specific processing of the step parking space state preliminary screening module includes:
S21:The edge direction of all pixels point and local gradient magnitude in image are calculated, the amplitude on gradient direction is obtained
Larger point;
S22:The amplitude of acquisition is subjected to non-maxima suppression, local maximum is found out, obtains marginal point.
In preferred technical solution, position feature is built in the composite character structure module, the gray scale for combining parking stall is straight
Square figure feature obtains the composite character of parking stall, specifically includes following steps:
S41:The feature vector Dist for building dimension A, traverse all angle points to central point distance D (x), according to following public affairs
Formula calculates Dist features:
Obtain the position feature of angle point distribution;
S42:The intensity value ranges of pixel are 0-255, the feature Hist of structure dimension B, are traversed each in parking area
Pixel obtains corresponding gray value Gray, then Hist [Gray] ++, build grey level histogram feature;
S43:Co-location feature and gray feature, the composite character that structure dimension is A+B.
In preferred technical solution, two graders, training are constructed by SVM in the parking stall classifier training judgment module
Parking stall grader includes the following steps:
S51:Acquire training set T={ (x1,y1),…,(xl,yl)}∈(X×Y)l;
Wherein, xi∈ X=Rn,yi∈ Y={ -1,1 } (i=1,2 ..., l);xiFor feature vector, yiRepresent label;
S52:Choose kernel function K (xi, xj) and parameter, ai、ajThe value of optimal solution is represented, between C is two in object function
Weight, l represents the dimension of feature vector;
Obtain optimal solution:
S53:Choose α*One-componentAnd threshold value is calculated, wherein K (xi-xj) represent the value of kernel function:
S54:Construct decision function:
When function value is " 1 ", indicate that current parking stall is parked vehicle and indicates no vehicle when value is " -1 ".
Compared with prior art, it is an advantage of the invention that:
1, the present invention, in conjunction with parking stall coordinate, extracts Harris corner features, and obtain vehicle on the basis of gaussian filtering
The Harris features of position, are predicted by svm classifier, to determine the state of parking stall.Compared with prior art, verification and measurement ratio of the present invention
Height can judge parking stall under the parking lot environment of various complexity, can be very good to exclude weather, illumination, on parking stall
The influence to parking stall measure such as pedestrian, sundries, shade, and shown by a large amount of test, the parking stall measure accuracy of this method
It is 98.15%, disclosure satisfy that requirement of the large-scale outdoor parking space to parking stall measure.
2, the detection method can handle multiple parking stalls simultaneously, can reduce equipment cost, improve the parking stall pipe in parking lot
Manage efficiency.
Description of the drawings
The invention will be further described with reference to the accompanying drawings and embodiments:
Fig. 1 is that the present invention is based on the flow charts of the parking position detection method of image.
Specific implementation mode
In order to make the objectives, technical solutions and advantages of the present invention clearer, With reference to embodiment and join
According to attached drawing, the present invention is described in more detail.It should be understood that these descriptions are merely illustrative, and it is not intended to limit this hair
Bright range.In addition, in the following description, descriptions of well-known structures and technologies are omitted, to avoid this is unnecessarily obscured
The concept of invention.
Embodiment:
Below in conjunction with the accompanying drawings, presently preferred embodiments of the present invention is described further.
As shown in Figure 1, the present invention is based on the parking position detection method of image, include the following steps:
Step 1:From monitoring image obtain needed for monitoring parking stall location information, by the location information of each parking stall with
The coordinate representations of four points (upper left, lower-left, upper right, bottom right) and preservation prepare for follow-up parking position monitoring.
Step 2:Image is obtained from monitoring camera video, with gaussian filtering to image preprocessing;
x2And y2What is indicated respectively is that for other pixels at a distance from center pixel in neighborhood, what σ was represented is standard in neighborhood
Difference.H (x, y) indicates two-dimensional Gaussian filter, is a kind of convolution masterplate calculated using normal distribution, utilizes Gaussian filter
Convolution algorithm is carried out with image, Fuzzy Processing can be carried out to image.
Step 3:Parking space state preliminary screening obtains the marginal information of parking stall using Canny algorithms, and parking stall has vehicle to park
State, marginal information is abundant, and marginal information is sparse when without car state, is tentatively judged using the characteristic.
(1) pass through previous step gaussian filtering denoising;
(2) edge direction of all pixels point and local gradient magnitude in image are calculated, Sobel is used
It is exactly marginal point that operator, which obtains the point of amplitude maximum on gradient direction,;
Three matrix of above formula is respectively the x of the operator to convolution mask, y to convolution mask and pending neighborhood of a point point mark
Remember matrix, the gradient magnitude that can express each of which point with mathematical formulae accordingly is:
sx=(a2+2a3+a4)-(a0+2a7+a6)
sy=(a0+2a1+a2)-(a6+2a5+a4)
Then gradient direction can be calculated with following formula:
If angle Θ is equal to zero, i.e. representative image possesses longitudinal edge at this, and left is dark compared with right.
(3) non-maxima suppression is carried out by the amplitude that above step obtains, in the magnitude image found out, it is understood that there may be
The case where multiple higher magnitude are closed on, but really there are one marginal points, for such situation, we carry out non-very big
Value inhibits, and local maximum is found out, so as to reject most of non-edge point.
Step 4:To the Harris angle points of treated image zooming-out parking stall;
Wherein, E (u, v) indicates window function, and (u, v) is the offset of dimensional Gaussian window function, and w (x, y) is window
The pixel of function, I (x, y) indicate the gray scale of image.
Step 5:The coordinate for obtaining the angle point of each parking stall calculates each angular coordinate to the distance of parking stall central point, knot
The location information for closing parking stall builds position feature:Using parking stall central point as origin, calculate
Euclidean distance D (x) of each angular coordinate to central point:
Wherein h (x), h (y) represent the x of angle point, y-coordinate, and c (x), c (y) represent central point x, y-coordinate;
Build dimension be 27 feature vector Dist, traverse all angle points to central point distance D (x), according to following public affairs
Formula calculates Dist features:
Obtain the position feature of angle point distribution.Build grey level histogram feature:The intensity value ranges of pixel are 0-255,
The feature Hist that dimension is 256 is built, each pixel in parking area is traversed, obtains corresponding gray value Gray, then Hist
[Gray] ++, co-location feature and gray feature, the composite character that structure dimension is 256+27 are trained in conjunction with SVM classifier
Parking stall grader simultaneously carries out classification prediction;
Different kernel functions is selected using SVM, and error correction is carried out to related data.The type of kernel function K mainly has:
(1) linear kernel function:K(x,xi)=xTxi;
(2) Polynomial kernel function:K(x,xi)=(γ xTxi+r)P, γ > 0;
(3) Radial basis kernel function:K(x,xi)=exp (- γ | | x-xi||2), γ > 0;
(4) two layers of perception kernel function:K(x,xi)=tanh (γ xTxi+r)。
SVM algorithm, if practical problem belongs to more classification, can be constructed by SVM to solve the problems, such as two classification
Multi-categorizer.Further, it is also possible to by the way that multiple two graders are reconfigured, to handle more classification problems.Judge on parking stall
Whether there are vehicle, actually a kind of two classification problems, therefore using two classification SVM models, judges whether vehicle is parked on parking stall
, form is as follows:
(1) training set is acquired:
T={ (x1,y1),…,(xl,yl)}∈(X×Y)l
Wherein, xi∈ X=Rn,yi∈ Y={ -1,1 } (i=1,2 ..., l);xiFor feature vector, T is training dataset, yi
Represent label.
(2) suitable kernel function K (x, x are chosenr) and parameter, ai、ajThe value of optimal solution is represented, C is
Weight in object function between two, l represent the dimension of feature vector:
Obtain optimal solution:
(3) α is chosen*One-componentWherein K (xi-xj) value of kernel function is represented, and calculate threshold value:
(4) decision function is constructed:
When function value is " 1 ", indicate that current parking stall is parked vehicle and indicates no vehicle when value is " -1 ".
After the completion of training, XML template files are preserved, XML file is loaded directly into when subsequently using, is judged using anticipation function
Whether current parking stall has vehicle, and exports as a result, completing to judge.
It should be understood that the above-mentioned specific implementation mode of the present invention is used only for exemplary illustration or explains the present invention's
Principle, but not to limit the present invention.Therefore, that is done without departing from the spirit and scope of the present invention is any
Modification, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.In addition, appended claims purport of the present invention
Covering the whole variations fallen into attached claim scope and boundary or this range and the equivalent form on boundary and is repairing
Change example.
Claims (10)
1. a kind of parking position detection method based on image, which is characterized in that include the following steps:
S01:The location information of each parking stall is carried out table by the location information for obtaining monitoring parking stall by the coordinate of multiple angle points
Show;
S02:The marginal information for obtaining monitoring image carries out preliminary screening to parking space state;
S03:Image is handled, the angle point of parking stall is extracted;
S04:The coordinate for obtaining the angle point of each parking stall, calculate each angular coordinate to parking stall central point distance, in conjunction with parking stall
Location information build position feature, the grey level histogram feature for combining parking stall obtains the composite character of parking stall;
S05:Training parking stall grader, the parking stall grader completed using training judge whether current parking stall has vehicle.
2. the parking position detection method according to claim 1 based on image, which is characterized in that the step S02
Before, image is pre-processed by gaussian filtering.
3. the parking position detection method according to claim 1 or 2 based on image, which is characterized in that the step
S02 is specifically included:
S21:The edge direction of all pixels point and local gradient magnitude in image are calculated, it is larger to obtain the amplitude on gradient direction
Point;
S22:The amplitude of acquisition is subjected to non-maxima suppression, local maximum is found out, obtains marginal point.
4. the parking position detection method according to claim 1 based on image, which is characterized in that the step S03
In angle point be Harris angle points, window function E (u, v) is:
Wherein (u, v) is the offset of dimensional Gaussian window function, and w (x, y) is the pixel of window function, and I (x, y) indicates figure
The gray scale of picture.
5. the parking position detection method according to claim 1 based on image, which is characterized in that the step S04
Middle structure position feature, the grey level histogram feature for combining parking stall obtain the composite character of parking stall, specifically include following steps:
S41:The feature vector Dist for building dimension A, traverse all angle points to central point distance D (x), according to following formula meter
Calculate Dist features:
Obtain the position feature of angle point distribution;
S42:The intensity value ranges of pixel are 0-255, and the feature Hist of structure dimension B traverses each pixel in parking area
Point obtains corresponding gray value Gray, then Hist [Gray] ++, build grey level histogram feature;
S43:Co-location feature and gray feature, the composite character that structure dimension is A+B.
6. the parking position detection method according to claim 1 based on image, which is characterized in that the step S05
In by SVM construct two graders, training parking stall grader include the following steps:
S51:Acquire training set T={ (x1,y1),…,(xl,yl)}∈(X×Y)l;
Wherein, xi∈ X=Rn,yi∈ Y={ -1,1 } (i=1,2 ..., l);xiFor feature vector, yiRepresent label;
S52:Choose kernel function K (xi, xj) and parameter, ai、ajThe value of optimal solution is represented, C is the power between two in object function
Weight, l represent the dimension of feature vector;
Obtain optimal solution:
S53:Choose α*One-componentAnd threshold value is calculated, wherein K (xi-xj) represent the value of kernel function:
S54:Construct decision function:
When function value is " 1 ", indicate that current parking stall is parked vehicle and indicates no vehicle when value is " -1 ".
7. a kind of parking position detection device based on image, which is characterized in that including:
One parking stall position acquisition module obtains the location information of monitoring parking stall, the location information of each parking stall is passed through multiple angles
The coordinate of point is indicated;
One parking space state preliminary screening module, obtains the marginal information of monitoring image, and preliminary screening is carried out to parking space state;
One parking stall angle point grid module, handles image, extracts the angle point of parking stall;
One composite character builds module, obtains the coordinate of the angle point of each parking stall, calculates each angular coordinate to parking stall central point
Distance, build position feature in conjunction with the location information of parking stall, the grey level histogram feature for combining parking stall obtains the mixing of parking stall
Feature;
One parking stall classifier training judgment module, training parking stall grader are judged current using the parking stall grader that training is completed
Whether parking stall has vehicle.
8. the parking position detection device according to claim 7 based on image, which is characterized in that step parking stall shape
State preliminary screening module it is specific processing include:
S21:The edge direction of all pixels point and local gradient magnitude in image are calculated, it is larger to obtain the amplitude on gradient direction
Point;
S22:The amplitude of acquisition is subjected to non-maxima suppression, local maximum is found out, obtains marginal point.
9. the parking position detection device according to claim 7 based on image, which is characterized in that the composite character
Structure module in build position feature, the grey level histogram feature for combining parking stall obtains the composite character of parking stall, specifically include with
Lower step:
S41:The feature vector Dist for building dimension A, traverse all angle points to central point distance D (x), according to following formula meter
Calculate Dist features:
Obtain the position feature of angle point distribution;
S42:The intensity value ranges of pixel are 0-255, and the feature Hist of structure dimension B traverses each pixel in parking area
Point obtains corresponding gray value Gray, then Hist [Gray] ++, build grey level histogram feature;
S43:Co-location feature and gray feature, the composite character that structure dimension is A+B.
10. the parking position detection device according to claim 7 based on image, which is characterized in that the parking stall point
Class device trains in judgment module and constructs two graders by SVM, and training parking stall grader includes the following steps:
S51:Acquire training set T={ (x1,y1),…,(xl,yl)}∈(X×Y)l;
Wherein, xi∈ X=Rn,yi∈ Y={ -1,1 } (i=1,2 ..., l);xiFor feature vector, yiRepresent label;
S52:Choose kernel function K (xi, xj) and parameter, ai、ajThe value of optimal solution is represented, C is the power between two in object function
Weight, l represent the dimension of feature vector;
Obtain optimal solution:
S53:Choose α*One-componentAnd threshold value is calculated, wherein K (xi-xj) represent the value of kernel function:
S54:Construct decision function:
When function value is " 1 ", indicate that current parking stall is parked vehicle and indicates no vehicle when value is " -1 ".
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810573699.9A CN108564814B (en) | 2018-06-06 | 2018-06-06 | Image-based parking lot parking space detection method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810573699.9A CN108564814B (en) | 2018-06-06 | 2018-06-06 | Image-based parking lot parking space detection method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108564814A true CN108564814A (en) | 2018-09-21 |
CN108564814B CN108564814B (en) | 2020-11-17 |
Family
ID=63553024
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810573699.9A Active CN108564814B (en) | 2018-06-06 | 2018-06-06 | Image-based parking lot parking space detection method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108564814B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110132278A (en) * | 2019-05-14 | 2019-08-16 | 驭势科技(北京)有限公司 | A kind of instant method and device for positioning and building figure |
CN110348297A (en) * | 2019-05-31 | 2019-10-18 | 纵目科技(上海)股份有限公司 | A kind of detection method, system, terminal and the storage medium of parking systems for identification |
CN110490079A (en) * | 2019-07-19 | 2019-11-22 | 万翼科技有限公司 | Inspection data processing method, device, computer equipment and storage medium |
CN110796063A (en) * | 2019-10-24 | 2020-02-14 | 百度在线网络技术(北京)有限公司 | Method, device, equipment, storage medium and vehicle for detecting parking space |
CN110969655A (en) * | 2019-10-24 | 2020-04-07 | 百度在线网络技术(北京)有限公司 | Method, device, equipment, storage medium and vehicle for detecting parking space |
CN111428616A (en) * | 2020-03-20 | 2020-07-17 | 东软睿驰汽车技术(沈阳)有限公司 | Parking space detection method, device, equipment and storage medium |
CN111539278A (en) * | 2020-04-14 | 2020-08-14 | 浙江吉利汽车研究院有限公司 | Detection method and system for target vehicle |
CN112115741A (en) * | 2019-06-20 | 2020-12-22 | 上海汽车集团股份有限公司 | Parking garage position detection method and device |
CN112598922A (en) * | 2020-12-07 | 2021-04-02 | 安徽江淮汽车集团股份有限公司 | Parking space detection method, device, equipment and storage medium |
CN112634650A (en) * | 2020-12-18 | 2021-04-09 | 中标慧安信息技术股份有限公司 | Parking lot management method and system based on audio and video monitoring |
CN113658272A (en) * | 2021-08-19 | 2021-11-16 | 湖北亿咖通科技有限公司 | Vehicle-mounted camera calibration method, device, equipment and storage medium |
CN114782928A (en) * | 2022-06-22 | 2022-07-22 | 苏州魔视智能科技有限公司 | Parking space detection method and device, electronic equipment and storage medium |
CN115791791A (en) * | 2022-11-14 | 2023-03-14 | 中国科学院沈阳自动化研究所 | Visual detection method for liquid crystal panel packing scrap |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101196996A (en) * | 2007-12-29 | 2008-06-11 | 北京中星微电子有限公司 | Image detection method and device |
CN101807352A (en) * | 2010-03-12 | 2010-08-18 | 北京工业大学 | Method for detecting parking stalls on basis of fuzzy pattern recognition |
DE102010019464A1 (en) * | 2010-05-05 | 2011-11-10 | Gisela Toussaint | Data center for receiving, processing, and transmission of special signals, is provided for detecting all public park spaces occupied, by which precise geographical coordinates of their four corner points are detected |
WO2013076365A1 (en) * | 2011-11-22 | 2013-05-30 | Nokia Corporation | Method for image processing and an apparatus |
CN104916163A (en) * | 2015-06-29 | 2015-09-16 | 惠州华阳通用电子有限公司 | Parking space detection method |
CN105913685A (en) * | 2016-06-25 | 2016-08-31 | 上海大学 | Video surveillance-based carport recognition and intelligent guide method |
CN106373426A (en) * | 2016-09-29 | 2017-02-01 | 成都通甲优博科技有限责任公司 | Computer vision-based parking space and illegal lane occupying parking monitoring method |
CN106599921A (en) * | 2016-12-14 | 2017-04-26 | 深圳市捷顺科技实业股份有限公司 | Parking stall guiding method and device |
KR101755980B1 (en) * | 2016-01-29 | 2017-07-10 | 세종대학교산학협력단 | Copy-Move Forgery Detection method and apparatus based on scale space representation |
CN107610506A (en) * | 2017-09-04 | 2018-01-19 | 浙江工商大学 | The detection method and system of parking position state |
CN107886080A (en) * | 2017-11-23 | 2018-04-06 | 同济大学 | One kind is parked position detecting method |
-
2018
- 2018-06-06 CN CN201810573699.9A patent/CN108564814B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101196996A (en) * | 2007-12-29 | 2008-06-11 | 北京中星微电子有限公司 | Image detection method and device |
CN101807352A (en) * | 2010-03-12 | 2010-08-18 | 北京工业大学 | Method for detecting parking stalls on basis of fuzzy pattern recognition |
DE102010019464A1 (en) * | 2010-05-05 | 2011-11-10 | Gisela Toussaint | Data center for receiving, processing, and transmission of special signals, is provided for detecting all public park spaces occupied, by which precise geographical coordinates of their four corner points are detected |
WO2013076365A1 (en) * | 2011-11-22 | 2013-05-30 | Nokia Corporation | Method for image processing and an apparatus |
CN104916163A (en) * | 2015-06-29 | 2015-09-16 | 惠州华阳通用电子有限公司 | Parking space detection method |
KR101755980B1 (en) * | 2016-01-29 | 2017-07-10 | 세종대학교산학협력단 | Copy-Move Forgery Detection method and apparatus based on scale space representation |
CN105913685A (en) * | 2016-06-25 | 2016-08-31 | 上海大学 | Video surveillance-based carport recognition and intelligent guide method |
CN106373426A (en) * | 2016-09-29 | 2017-02-01 | 成都通甲优博科技有限责任公司 | Computer vision-based parking space and illegal lane occupying parking monitoring method |
CN106599921A (en) * | 2016-12-14 | 2017-04-26 | 深圳市捷顺科技实业股份有限公司 | Parking stall guiding method and device |
CN107610506A (en) * | 2017-09-04 | 2018-01-19 | 浙江工商大学 | The detection method and system of parking position state |
CN107886080A (en) * | 2017-11-23 | 2018-04-06 | 同济大学 | One kind is parked position detecting method |
Non-Patent Citations (4)
Title |
---|
AJAY,A; SOWMYA, V;SOMAN, KP: "Vehicle Detection in Aerial Imagery using Eigen Features", 《2017 INTERNATIONAL CONFERENCE ON COMMUNICATION AND SIGNAL PROCESSING (ICCSP)》 * |
冯翔: "数据挖掘在入侵检测中的应用", 《中国优秀硕士学位论文全文数据库(信息科技辑)》 * |
杨英杰,胡义轩,张文龙: "基于Harris与SVM角点判断的车位状态检测方法", 《计算机光盘软件与应用》 * |
贺强,晏立: "基于LOG和Canny算子的边缘检测算法", 《计算机工程》 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110132278A (en) * | 2019-05-14 | 2019-08-16 | 驭势科技(北京)有限公司 | A kind of instant method and device for positioning and building figure |
CN110348297A (en) * | 2019-05-31 | 2019-10-18 | 纵目科技(上海)股份有限公司 | A kind of detection method, system, terminal and the storage medium of parking systems for identification |
CN110348297B (en) * | 2019-05-31 | 2023-12-26 | 纵目科技(上海)股份有限公司 | Detection method, system, terminal and storage medium for identifying stereo garage |
CN112115741B (en) * | 2019-06-20 | 2024-02-20 | 上海汽车集团股份有限公司 | Parking garage position detection method and device |
CN112115741A (en) * | 2019-06-20 | 2020-12-22 | 上海汽车集团股份有限公司 | Parking garage position detection method and device |
CN110490079B (en) * | 2019-07-19 | 2022-06-03 | 万翼科技有限公司 | Patrol data processing method and device, computer equipment and storage medium |
CN110490079A (en) * | 2019-07-19 | 2019-11-22 | 万翼科技有限公司 | Inspection data processing method, device, computer equipment and storage medium |
CN110796063A (en) * | 2019-10-24 | 2020-02-14 | 百度在线网络技术(北京)有限公司 | Method, device, equipment, storage medium and vehicle for detecting parking space |
CN110969655A (en) * | 2019-10-24 | 2020-04-07 | 百度在线网络技术(北京)有限公司 | Method, device, equipment, storage medium and vehicle for detecting parking space |
CN110969655B (en) * | 2019-10-24 | 2023-08-18 | 百度在线网络技术(北京)有限公司 | Method, device, equipment, storage medium and vehicle for detecting parking space |
CN111428616A (en) * | 2020-03-20 | 2020-07-17 | 东软睿驰汽车技术(沈阳)有限公司 | Parking space detection method, device, equipment and storage medium |
CN111428616B (en) * | 2020-03-20 | 2023-05-23 | 东软睿驰汽车技术(沈阳)有限公司 | Parking space detection method, device, equipment and storage medium |
CN111539278A (en) * | 2020-04-14 | 2020-08-14 | 浙江吉利汽车研究院有限公司 | Detection method and system for target vehicle |
CN112598922A (en) * | 2020-12-07 | 2021-04-02 | 安徽江淮汽车集团股份有限公司 | Parking space detection method, device, equipment and storage medium |
CN112634650A (en) * | 2020-12-18 | 2021-04-09 | 中标慧安信息技术股份有限公司 | Parking lot management method and system based on audio and video monitoring |
CN113658272A (en) * | 2021-08-19 | 2021-11-16 | 湖北亿咖通科技有限公司 | Vehicle-mounted camera calibration method, device, equipment and storage medium |
CN113658272B (en) * | 2021-08-19 | 2023-11-17 | 亿咖通(湖北)技术有限公司 | Vehicle-mounted camera calibration method, device, equipment and storage medium |
CN114782928A (en) * | 2022-06-22 | 2022-07-22 | 苏州魔视智能科技有限公司 | Parking space detection method and device, electronic equipment and storage medium |
CN115791791A (en) * | 2022-11-14 | 2023-03-14 | 中国科学院沈阳自动化研究所 | Visual detection method for liquid crystal panel packing scrap |
CN115791791B (en) * | 2022-11-14 | 2024-06-18 | 中国科学院沈阳自动化研究所 | Visual detection method for liquid crystal display panel boxing scrap |
Also Published As
Publication number | Publication date |
---|---|
CN108564814B (en) | 2020-11-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108564814A (en) | A kind of parking position detection method and device based on image | |
WO2018107939A1 (en) | Edge completeness-based optimal identification method for image segmentation | |
CN112819094B (en) | Target detection and identification method based on structural similarity measurement | |
CN102999753B (en) | License plate locating method | |
CN110309781B (en) | House damage remote sensing identification method based on multi-scale spectrum texture self-adaptive fusion | |
CN105184779B (en) | One kind is based on the pyramidal vehicle multiscale tracing method of swift nature | |
CN102663357A (en) | Color characteristic-based detection algorithm for stall at parking lot | |
CN104036262B (en) | A kind of method and system of LPR car plates screening identification | |
CN110414355A (en) | The right bit sky parking stall of view-based access control model and parking stall line detecting method during parking | |
CN109376740A (en) | A kind of water gauge reading detection method based on video | |
CN105976383A (en) | Power transmission equipment fault diagnosis method based on limit learning machine image recognition | |
CN107633491A (en) | A kind of area image Enhancement Method and storage medium based on target detection | |
CN107169953A (en) | Bridge concrete surface crack detection method based on HOG features | |
CN109670515A (en) | A kind of detection method and system changed for building in unmanned plane image | |
CN111507426B (en) | Non-reference image quality grading evaluation method and device based on visual fusion characteristics | |
Li et al. | Research on vehicle license plate location based on neural networks | |
CN109635733B (en) | Parking lot and vehicle target detection method based on visual saliency and queue correction | |
CN106530281A (en) | Edge feature-based unmanned aerial vehicle image blur judgment method and system | |
CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
CN107194393A (en) | A kind of method and device for detecting Provisional Number Plate | |
CN109635722B (en) | Automatic identification method for high-resolution remote sensing image intersection | |
CN106056078B (en) | Crowd density estimation method based on multi-feature regression type ensemble learning | |
CN107729814A (en) | A kind of method and device for detecting lane line | |
CN105787912A (en) | Classification-based step type edge sub pixel localization method | |
CN109741406A (en) | A kind of body color recognition methods under monitoring scene |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |