CN112560814A - Method for identifying vehicles entering and exiting parking spaces - Google Patents
Method for identifying vehicles entering and exiting parking spaces Download PDFInfo
- Publication number
- CN112560814A CN112560814A CN202110192625.2A CN202110192625A CN112560814A CN 112560814 A CN112560814 A CN 112560814A CN 202110192625 A CN202110192625 A CN 202110192625A CN 112560814 A CN112560814 A CN 112560814A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- coordinate
- parking space
- coordinates
- area
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Abstract
The invention discloses a method for identifying vehicles entering and exiting a parking space, which comprises the steps of obtaining a monitoring image and establishing a two-dimensional coordinate system; determining responsible parking spaces, wherein each responsible parking space obtains a corresponding coordinate area; intercepting live images from the live video at preset intervals to obtain vehicle two-dimensional coordinates of each vehicle in each live image; judging whether the two-dimensional coordinates of the vehicle in each field image have intersection points with the parking space coordinate set or not, obtaining coordinate intersection, and calculating the coordinate intersection area, namely the overlapping area of the vehicle and the parking space; and calculating the contact ratio of the vehicle and the parking space coordinate set according to the proportion of the coordinate intersection area and the vehicle area, and judging the state of the vehicle from the change trend of the contact ratio in the continuous multi-frame images. The method for identifying the vehicle entering and exiting the parking lot is completed through the camera and the analysis module, management personnel do not need to be configured on site, the labor management cost can be greatly reduced, and the method has higher identification efficiency.
Description
Technical Field
The invention relates to the technical field of intelligent parking, in particular to a method for identifying a vehicle entering and exiting a parking space.
Background
Along with the improvement of the urbanization process, parking spaces in cities are more and more, most parking spaces belong to pay parking, namely, parking cost can be caused when parking is carried out in a specified time period or all time periods. The existing parking charging system is obviously different according to the positions of parking spaces, for example, the parking spaces on two sides of a road are often provided with a geomagnetic device, at least one parking manager is arranged near the parking spaces, and the parking managers take pictures to confirm the entrance time and the exit time. The other type is the parking space of a parking lot, the parking space is usually arranged in an underground garage or a ground garage, a parking lot entrance and a parking lot exit are arranged, and the entrance and the exit time of the vehicle are detected by arranging a gate at the entrance and the exit, so that the related cost is calculated.
Therefore, no matter the roadside parking lot or the closed parking lot with the entrance and the exit, the information of the entrance and the exit of the vehicle needs to be acquired by a certain means, and the corresponding parking time is calculated according to the time difference of the entrance and the exit.
For roadside parking, the conventional method in the prior art is to confirm the time of vehicle entering and exiting through geomagnetic induction and manual operation of an administrator; the method has low automation degree and needs to consume a large amount of labor cost.
Disclosure of Invention
The invention aims to provide a method for identifying whether a vehicle enters or exits a parking space.
To achieve the above object, in one embodiment of the present invention, a method for identifying entry and exit of a vehicle into and out of a parking space is provided, which includes the following steps:
deploying cameras around parking spaces; acquiring a monitoring image of a monitoring area, mapping the monitoring image to a two-dimensional coordinate, and establishing a two-dimensional coordinate system;
determining responsible parking spaces from all parking spaces in the monitoring image, marking all the responsible parking spaces in a two-dimensional coordinate system, obtaining a corresponding coordinate area from each responsible parking space, marking the coordinate areas of all the responsible parking spaces as parking space coordinate sets, and marking the rest coordinate areas as non-parking space coordinate sets;
step (3) acquiring field video information, analyzing objects in the video, identifying vehicles and non-vehicle objects, and marking the identified vehicles;
intercepting field images from a field video at preset intervals, mapping the marked vehicles in each field image to a two-dimensional model from three dimensions, and obtaining the two-dimensional coordinates of each vehicle in each field image;
step (5) judging whether the two-dimensional coordinates of the vehicle in each field image have intersection points with the parking space coordinate set, identifying inflection point coordinates in the intersection point coordinates, obtaining coordinate intersection, and calculating the coordinate intersection area, namely the overlapping area of the vehicle and the parking space;
step (6) according to the proportion of the coordinate intersection area and the vehicle area, calculating the contact ratio of the vehicle and the parking space coordinate set, and judging the state of the vehicle from the change trend of the contact ratio in continuous multi-frame images;
when the contact ratio gradually increases and does not reach the highest threshold value, judging that the vehicle enters the field, and continuously capturing the entrance action at the moment to continuously acquire the license plate information;
when the contact ratio reaches the highest threshold value and the vehicle does not move, judging that the vehicle stops successfully, and recording the entrance information of the vehicle;
when the contact ratio is gradually reduced from the highest threshold value, judging that the vehicle leaves, continuously capturing the leaving action at the moment, and continuously acquiring the license plate information;
and when the contact ratio reaches the lowest threshold value, judging that the vehicle is successful in leaving, and recording the leaving information of the vehicle.
Preferably, in the two-dimensional coordinate system in step (2), the length direction of the parking space is taken as an abscissa, and the width direction is taken as an ordinate.
Preferably, in the step (5), the inflection point coordinate of the vehicle two-dimensional coordinate and the parking space coordinate set is different from the horizontal coordinate and the vertical coordinate of the adjacent intersection point coordinate; the algorithm of the coordinate intersection area or the coincidence area of the vehicle and the parking space is as follows:
the coordinate intersection comprises n inflection point coordinates which are sequentially a 1 st inflection point coordinate, a 2 nd inflection point coordinate and a second inflection point coordinate
Coordinates of the inflection points to coordinates of the nth inflection point;
wherein S is the intersection area of the coordinates,
is as follows
Coordinates of each inflection point
The abscissa of the (c) axis of the (c),
is as follows
Coordinates of each inflection point
The ordinate of (c).
Preferably, the entry information of the vehicle in the step (6) includes license plate information, entry time and entry photos of the vehicle.
Preferably, in the present invention, the highest threshold value of the degree of coincidence in step (6) is 100%, and the lowest threshold value is 0%.
In conclusion, the invention has the following advantages:
the method comprises the steps of mapping a vehicle from three dimensions to two dimensions to construct a two-dimensional coordinate system; the area of the overlapped area of the vehicle and the parking space is judged through the two-dimensional coordinate system of the vehicle, whether the vehicle enters the parking space is further judged, the parking state of the vehicle can be judged through judging the change trend of the contact ratio, and meanwhile, the information of the vehicle is identified, so that the relevant information of the vehicle entering and leaving can be obtained, and the charging of the vehicle is convenient to complete.
The method for identifying the vehicle entering and exiting the parking lot is completed through the camera and the analysis module, management personnel do not need to be configured on site, the labor management cost can be greatly reduced, and the method has higher identification efficiency.
Drawings
FIG. 1 is a flow chart of a method for identifying entry and exit of a vehicle into and out of a parking space in accordance with an embodiment of the present invention;
FIG. 2 is a schematic view of the installation of a camera in accordance with one embodiment of the present invention;
FIG. 3 is a schematic representation of the vehicle overlap ratio for three different entry conditions in accordance with an embodiment of the present invention;
FIG. 4 is a schematic illustration of three vehicle overlap ratios at different off-site conditions in accordance with an embodiment of the present invention;
FIG. 5 is a diagram illustrating inflection points in an embodiment of the present invention.
Detailed Description
Referring to fig. 1 and 2, the present invention provides a method for identifying entry and exit of a vehicle into and out of a parking space in one embodiment of the present invention, comprising the following steps:
deploying cameras around parking spaces; and acquiring a monitoring image of the monitoring area, mapping the monitoring image to a two-dimensional coordinate, and establishing a two-dimensional coordinate system.
The invention is suitable for open parking lots, i.e. parking lots without entrances and exits and gates at the entrances and exits, such as roadside parking lots. After the cameras, the configured storage module and the data analysis module are installed through the portal frame, the installation angle of each camera needs to be adjusted.
The two-dimensional coordinate system can take the length direction of the parking space or the street road edge as the horizontal coordinate and the width direction of the parking space or the axial direction of the road as the vertical coordinate; the intersection point of the road edge and the inner side of the parking space is used as the origin.
The two-dimensional coordinate system can be established by installing a camera to determine an installation angle, shooting an image, and then identifying and processing the image.
And (2) determining responsible parking spaces from all parking spaces in the monitoring image, marking all the responsible parking spaces in a two-dimensional coordinate system, obtaining a corresponding coordinate area from each responsible parking space, marking the coordinate areas of all the responsible parking spaces as parking space coordinate sets, and marking the rest coordinate areas as non-parking space coordinate sets.
And (3) acquiring the field video information, analyzing the objects in the video, identifying the vehicles and non-vehicle objects, and marking the identified vehicles.
According to the video analysis terminal, responsible parking spaces which are responsible for monitoring by the video analysis terminal are selected from the monitoring images, all the responsible parking spaces are marked in a two-dimensional coordinate system, and each responsible parking space obtains a corresponding coordinate area.
And the coordinate areas of all responsible parking spaces are marked as parking space coordinate sets, and the rest coordinate areas are marked as non-parking space coordinate sets. The parking space coordinate set may be continuous or discontinuous, and when the parking spaces are continuously arranged, the parking space coordinate set is continuous. For the conventional case, the parking spaces are mostly arranged consecutively, so that the set of parking space coordinates is also consecutive in this case.
In the prior art, most front-end equipment such as a camera and the like only have an information acquisition function, the acquired information is sent to a server, and then the server performs processing processes such as identification, logical operation and the like; however, this processing method will greatly increase the computational pressure of the server platform, and it is inconvenient for front-end adjustment.
For example, a front-end hardware device camera or the like may need to be replaced or debugged, and the replacement, adjustment and debugging of the camera will affect the shooting angle, and thus the two-dimensional coordinate system needs to be adjusted. In the processing mode in the prior art, if the camera sends the adjustment, the adjustment needs to be carried out through a server platform or a background, and because a background server is usually not in the same field as the front-end camera, the installation place of the camera is not fixed, and the camera is very widely distributed; therefore, the camera and the video analysis module are arranged in the parking lot area together at the front end, the analysis and processing module related to the video image is arranged at the front end, and the related problems can be adjusted simultaneously when the camera is adjusted, so that the output result can be consistent with the output result before debugging, and errors are avoided.
Meanwhile, a two-dimensional coordinate system adopted by the video analysis terminal at the front end of the invention can be established by using the same method, but the calculation of each video analysis terminal is independent, so that the data is convenient to call and test.
And (4) intercepting the live images from the live video at preset intervals, and mapping the marked vehicles in each live image from three dimensions to a two-dimensional model to obtain the two-dimensional coordinates of each vehicle in each live image.
The video analysis terminal comprises a camera, a storage module and an analysis module, and all analysis logic operation parts of the video analysis terminal can be completed through the analysis module.
And the analysis module intercepts live images from the live video every preset period, maps the vehicles in each live image to a two-dimensional model from three dimensions, and obtains the vehicle two-dimensional coordinates of each vehicle in each live image. In the period, field images can be intercepted at intervals of several seconds, and smaller interval time can be set to acquire images in each frame; thus, each image can be obtained in real time without error, but the amount of calculation increases.
In each intercepted field image, the vehicle is three-dimensional, so that the marked vehicle needs to be mapped from a three-dimensional model to a two-dimensional model, namely, a top view of the three-dimensional model is taken as the two-dimensional model; this enables the vehicle to be associated into a two-dimensional coordinate system.
And (5) judging whether the two-dimensional coordinates of the vehicle in each field image have intersection points with the parking space coordinate set, identifying inflection point coordinates in the intersection point coordinates, obtaining coordinate intersection, and calculating the coordinate intersection area, namely the overlapping area of the vehicle and the parking space.
In each scene image, the vehicle can be viewed as a two-dimensional coordinate set having a number of specific coordinate points. When the vehicle is superposed with the parking space, the two-dimensional coordinate set of the vehicle and the parking space coordinate set form a coincident point, namely an intersection point. The higher the degree of coincidence of the vehicle with the parking space, the higher the intersection point of the two will be.
The two-dimensional coordinate set of the vehicle forms a curve corresponding to the vehicle's profile, and the vehicle's top view or map is generally approximately rectangular. The inflection point in the present invention is understood to be a point at which the angle of the tangent on the curve changes. When a line is a straight line, at least one value on the X-axis or Y-axis is constant, and when a line is a curved line, the coordinate values on both the X-axis and Y-axis are changed. Therefore, the inflection point should be a point on a non-straight line. In order to appropriately reduce the inflection point and reduce the calculation amount, the vehicle may be squared, that is, the vehicle arc-shaped portion may be corrected to a straight line segment when the two-dimensional coordinates of the vehicle are established.
For example, in fig. 5 of the present invention, the inflection point is explained. Fig. 5 is a field image of a vehicle entering a parking space, in which coordinates a, b, c, and d, horizontal and vertical coordinate values of the four coordinates are different from other coordinates of the vehicle, and are a junction of two straight lines, where a tangent angle also changes, so that the coordinate point is an inflection point.
And (6) calculating the contact ratio of the vehicle and the parking space coordinate set according to the proportion of the coordinate intersection area and the vehicle area, and judging the state of the vehicle from the change trend of the contact ratio in continuous multi-frame images.
Referring to fig. 3 and 4, after a vehicle enters a parking space, since the size of the parking space is fixed, but the sizes of the vehicles are different, the overlap ratio calculation of the present invention uses the area of the vehicle as a denominator and the intersection area of the coordinates as a numerator, and the ratio of the two areas can obtain the overlap ratio data. When the contact ratio of the vehicle is higher, the area of the vehicle entering the parking space is larger.
And when the contact ratio gradually increases and does not reach the highest threshold value, judging that the vehicle enters the field, and continuously capturing the entrance action at the moment to continuously acquire the license plate information.
At the moment, the vehicle is indicated to enter the field, the corresponding field image can be intercepted and then filed to obtain the license plate information, and the license plate information can be determined by comparing a plurality of current images.
When the contact ratio reaches the highest threshold value and the vehicle does not move, judging that the vehicle stops successfully, and recording the entrance information of the vehicle;
when the contact ratio is gradually reduced from the highest threshold value, judging that the vehicle leaves, continuously capturing the leaving action at the moment, and continuously acquiring the license plate information;
and when the contact ratio reaches the lowest threshold value, judging that the vehicle is successful in leaving, and recording the leaving information of the vehicle.
In the invention, the two-dimensional coordinate system in the step (2) takes the length direction of the parking space as an abscissa and the width direction as an ordinate.
In the invention, the inflexion point coordinate of the vehicle two-dimensional coordinate and parking space coordinate set in the step (5) is different from the horizontal coordinate and the vertical coordinate of the adjacent intersection point coordinate; the algorithm of the coordinate intersection area or the coincidence area of the vehicle and the parking space is as follows:
the coordinate intersection comprises n inflection point coordinates which are sequentially a 1 st inflection point coordinate, a 2 nd inflection point coordinate and a second inflection point coordinate
Coordinates of the inflection points to coordinates of the nth inflection point;
wherein S is the intersection area of the coordinates,
is as follows
Coordinates of each inflection point
The abscissa of the (c) axis of the (c),
is as follows
Coordinates of each inflection point
The ordinate of (c).
In the invention, the vehicle entrance information in the step (6) comprises license plate information, entrance time and entrance photos of the vehicle.
In the present invention, the highest threshold value of the degree of coincidence in step (6) is 100%, and the lowest threshold value is 0%.
Claims (5)
1. A method for recognizing that a vehicle enters and exits a parking space is characterized by comprising the following steps:
deploying cameras around parking spaces; acquiring a monitoring image of a monitoring area, mapping the monitoring image to a two-dimensional coordinate, and establishing a two-dimensional coordinate system;
determining responsible parking spaces from all parking spaces in the monitoring image, marking all the responsible parking spaces in a two-dimensional coordinate system, obtaining a corresponding coordinate area from each responsible parking space, marking the coordinate areas of all the responsible parking spaces as parking space coordinate sets, and marking the rest coordinate areas as non-parking space coordinate sets;
step (3) acquiring field video information, analyzing objects in the video, identifying vehicles and non-vehicle objects, and marking the identified vehicles;
intercepting field images from a field video at preset intervals, mapping the marked vehicles in each field image to a two-dimensional model from three dimensions, and obtaining the two-dimensional coordinates of each vehicle in each field image;
step (5) judging whether the two-dimensional coordinates of the vehicle in each field image have intersection points with the parking space coordinate set, identifying coordinates of all inflection points in the intersection point coordinates, obtaining coordinate intersection, and calculating the coordinate intersection area, namely the overlapping area of the vehicle and the parking space;
step (6) according to the proportion of the coordinate intersection area and the vehicle area, calculating the contact ratio of the vehicle and the parking space coordinate set, and judging the state of the vehicle from the change trend of the contact ratio in continuous multi-frame images;
when the contact ratio gradually increases and does not reach the highest threshold value, judging that the vehicle enters the field, and continuously capturing the entrance action at the moment to continuously acquire the license plate information;
when the contact ratio reaches the highest threshold value and the vehicle does not move, judging that the vehicle stops successfully, and recording the entrance information of the vehicle;
when the contact ratio is gradually reduced from the highest threshold value, judging that the vehicle leaves, continuously capturing the leaving action at the moment, and continuously acquiring the license plate information;
and when the contact ratio reaches the lowest threshold value, judging that the vehicle is successful in leaving, and recording the leaving information of the vehicle.
2. The method of recognizing entry and exit of a vehicle into and out of a parking space of claim 1, wherein: and (3) the two-dimensional coordinate system in the step (2) takes the length direction of the parking space as an abscissa and the width direction as an ordinate.
3. The method of recognizing entry and exit of a vehicle into and out of a parking space of claim 1, wherein: in the step (5), the inflection point coordinates of the vehicle two-dimensional coordinates and the parking space coordinate set are different from the horizontal coordinates and the vertical coordinates of the adjacent intersection point coordinates; the algorithm of the coordinate intersection area or the coincidence area of the vehicle and the parking space is as follows:
the coordinate intersection comprises n inflection point coordinates which are sequentially a 1 st inflection point coordinate, a 2 nd inflection point coordinate and a second inflection point coordinate
Coordinates of the inflection points to coordinates of the nth inflection point;
wherein S is the intersection area of the coordinates,
is as follows
Coordinates of each inflection point
The abscissa of the (c) axis of the (c),
is as follows
Coordinates of each inflection point
The ordinate of (c).
4. The method of recognizing entry and exit of a vehicle into and out of a parking space of claim 1, wherein: and (4) the entrance information of the vehicle in the step (6) comprises license plate information, entrance time and entrance photos of the vehicle.
5. The method of recognizing entry and exit of a vehicle into and out of a parking space of claim 1, wherein: in the step (6), the highest threshold value of the contact ratio is 100%, and the lowest threshold value is 0%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110192625.2A CN112560814A (en) | 2021-02-20 | 2021-02-20 | Method for identifying vehicles entering and exiting parking spaces |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110192625.2A CN112560814A (en) | 2021-02-20 | 2021-02-20 | Method for identifying vehicles entering and exiting parking spaces |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112560814A true CN112560814A (en) | 2021-03-26 |
Family
ID=75036002
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110192625.2A Pending CN112560814A (en) | 2021-02-20 | 2021-02-20 | Method for identifying vehicles entering and exiting parking spaces |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112560814A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205691A (en) * | 2021-04-26 | 2021-08-03 | 超级视线科技有限公司 | Method and device for identifying vehicle position |
| CN113516852A (en) * | 2021-07-22 | 2021-10-19 | 珠海小可乐科技有限公司 | Multi-parking-space multi-target vehicle parking identification method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105869182A (en) * | 2016-06-17 | 2016-08-17 | 北京精英智通科技股份有限公司 | Parking space state detection method and parking space state detection system |
| CN106297400A (en) * | 2016-10-13 | 2017-01-04 | 北京悦畅科技有限公司 | A kind of parking position information of park processing method, server and system |
| CN107195198A (en) * | 2017-07-31 | 2017-09-22 | 重庆酷贝科技发展有限公司 | A kind of curb parking management method and its system based on image recognition technology |
| CN108766022A (en) * | 2018-06-11 | 2018-11-06 | 青岛串并联电子科技有限公司 | Parking position state identification method based on machine learning and system |
| CN111325858A (en) * | 2020-03-06 | 2020-06-23 | 赛特斯信息科技股份有限公司 | Method for realizing automatic charging management aiming at roadside temporary parking space |
| CN111768648A (en) * | 2020-06-10 | 2020-10-13 | 浙江大华技术股份有限公司 | Vehicle access determining method and system |
| CN112017467A (en) * | 2019-05-28 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Parking space detection method and device |
-
2021
- 2021-02-20 CN CN202110192625.2A patent/CN112560814A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105869182A (en) * | 2016-06-17 | 2016-08-17 | 北京精英智通科技股份有限公司 | Parking space state detection method and parking space state detection system |
| CN106297400A (en) * | 2016-10-13 | 2017-01-04 | 北京悦畅科技有限公司 | A kind of parking position information of park processing method, server and system |
| CN107195198A (en) * | 2017-07-31 | 2017-09-22 | 重庆酷贝科技发展有限公司 | A kind of curb parking management method and its system based on image recognition technology |
| CN108766022A (en) * | 2018-06-11 | 2018-11-06 | 青岛串并联电子科技有限公司 | Parking position state identification method based on machine learning and system |
| CN112017467A (en) * | 2019-05-28 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Parking space detection method and device |
| CN111325858A (en) * | 2020-03-06 | 2020-06-23 | 赛特斯信息科技股份有限公司 | Method for realizing automatic charging management aiming at roadside temporary parking space |
| CN111768648A (en) * | 2020-06-10 | 2020-10-13 | 浙江大华技术股份有限公司 | Vehicle access determining method and system |
Non-Patent Citations (2)
| Title |
|---|
| 孟焱等: "基于机器视觉的停车位状态检测技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李芹芳，张艳主编: "《地籍与房产测量》", 28 February 2017, 武汉大学出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205691A (en) * | 2021-04-26 | 2021-08-03 | 超级视线科技有限公司 | Method and device for identifying vehicle position |
| CN113516852A (en) * | 2021-07-22 | 2021-10-19 | 珠海小可乐科技有限公司 | Multi-parking-space multi-target vehicle parking identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3806064B1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| CN106373426B (en) | Parking stall based on computer vision and violation road occupation for parking monitoring method | |
| CN108765976B (en) | Roadside parallel parking information management system and method | |
| CN111476169B (en) | Complex scene road side parking behavior identification method based on video frame | |
| CN108765975B (en) | Roadside vertical parking lot management system and method | |
| CN105913685A (en) | Video surveillance-based carport recognition and intelligent guide method | |
| CN112560814A (en) | Method for identifying vehicles entering and exiting parking spaces | |
| CN108154146A (en) | A kind of car tracing method based on image identification | |
| CN111368615B (en) | Illegal building early warning method and device and electronic equipment | |
| CN113205692B (en) | Automatic identification method for road side parking position abnormal change | |
| CN104376332A (en) | License plate recognition method and device | |
| CN112084892B (en) | Road abnormal event detection management device and method thereof | |
| US11580659B2 (en) | Method for size estimation by image recognition of specific target using given scale | |
| CN111692978A (en) | Multi-source image data-based illegal building identification method | |
| CN113099181A (en) | Urban traffic parking safety intelligent analysis management method based on video monitoring | |
| CN110852151B (en) | Method and device for detecting shielding of berths in roads | |
| CN114241395A (en) | Roadside parking berth abnormity identification method and device based on berth number | |
| CN110826364A (en) | Stock position identification method and device | |
| Shaaban et al. | Parking space detection system using video images | |
| CN113901961B (en) | Parking space detection method, device, equipment and storage medium | |
| CN113158728B (en) | Parking space state detection method based on gray level co-occurrence matrix | |
| CN115249345A (en) | Traffic jam detection method based on oblique photography three-dimensional live-action map | |
| KR101327256B1 (en) | System and method of detecting vehicle using detecting shadow region of the vehicle by ptz camera | |
| CN114627653B (en) | 5G intelligent barrier gate management system based on binocular recognition | |
| CN117197050A (en) | Method for judging abnormal situation of well lid and computing equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210326 |