CN115116262A - Parking limit monitoring system based on image recognition - Google Patents

Parking limit monitoring system based on image recognition Download PDF

Info

Publication number
CN115116262A
CN115116262A CN202210358478.6A CN202210358478A CN115116262A CN 115116262 A CN115116262 A CN 115116262A CN 202210358478 A CN202210358478 A CN 202210358478A CN 115116262 A CN115116262 A CN 115116262A
Authority
CN
China
Prior art keywords
vehicle
image
parking space
parking
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.)
Granted
Application number
CN202210358478.6A
Other languages
Chinese (zh)
Other versions
CN115116262B (en
Inventor
陈亮
阳俊敏
陈东标
罗斌飞
晏勇斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangxi Zhongtian Intelligent Equipment Co Ltd
Original Assignee
Jiangxi Zhongtian Intelligent Equipment Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangxi Zhongtian Intelligent Equipment Co Ltd filed Critical Jiangxi Zhongtian Intelligent Equipment Co Ltd
Priority to CN202210358478.6A priority Critical patent/CN115116262B/en
Publication of CN115116262A publication Critical patent/CN115116262A/en
Application granted granted Critical
Publication of CN115116262B publication Critical patent/CN115116262B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/14Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/145Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
    • G08G1/148Management of a network of parking areas
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02TCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00Road transport of goods or passengers
    • Y02T10/10Internal combustion engine [ICE] based vehicles
    • Y02T10/40Engine management systems

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application provides a spacing monitoring system parks based on image recognition, and this application belongs to the artificial intelligence field, mainly is artificial intelligence technical field that parks. The application includes: the system comprises a server module, a customer service module, a signal transmission device and an output unit module; setting an image model and initializing parking space information; the client module acquires and processes vehicle information in real time to acquire wheel data and a vehicle contour connecting line; the client module transmits the real-time vehicle image, wheel image data and vehicle contour connecting line to the processor through the signal transmission device; the processor determines the stopping information of the vehicle according to the wheel image data and the vehicle contour line; the processor sends corresponding prompts to the output unit module through the signal transmission device according to the stop information of the vehicle. The application provides safe convenient monitoring for mechanical parking equipment's use, prevents on the one hand that the vehicle from cutting and rubbing parking equipment, and on the other hand because of the vehicle stops and makes parking equipment go forward the safety problem appear when stopping in the safe district.

Description

Parking limit monitoring system based on image recognition
The technical field is as follows:
the invention relates to the field of artificial intelligence, mainly relates to the technical field of artificial intelligence parking, and particularly relates to a parking limit monitoring system based on image recognition.
Background art:
with the increasing of domestic economic development and technical means, the demand for machine parking equipment is increased, and the safety and the reliability of the machine parking equipment need stricter requirements. At present, most of traditional mechanical parking equipment does not have safe and reliable monitoring on a vehicle parking area, and the existing monitoring systems and equipment mainly use agency foreign products, are little concerned with systems and equipment which have independent intellectual property rights and monitor parking by using an image recognition technology, and particularly have few researches on real-time online detection of large data quantity and few successful cases.
For example, patent publication No. CN111677355B discloses a push-pull type parking mechanism for vehicles and a three-dimensional mechanical parking facility thereof, which provides a conventional parking facility for fast parking and picking up vehicles, but does not properly monitor the vehicles not parked in a designated area to ensure the reliability and safety of the subsequent parking and picking up vehicles.
For example, patent publication No. CN113436438A discloses a method, system and apparatus for restricting parking in a dedicated parking space, which only uses image recognition technology to confirm information of a vehicle owner, so as to provide parking service.
This application provides safe convenient monitoring for mechanical parking equipment's use, can effectively guide the car owner to be correct on the one hand and berth in the safe area, and on the other hand can monitor because of the vehicle stops outside the safe area, leads to vehicle and parking equipment collision etc. to appear the safety problem during parking equipment operation to remind the car owner.
The invention content is as follows:
the application mainly aims to provide a parking limit monitoring system based on image recognition.
In order to achieve the purpose, the invention adopts the technical scheme that the parking limit monitoring system is based on image recognition;
a parking limit monitoring system based on image recognition comprises a server module 1, a customer service module 2, a signal transmission device 3 and an output unit module 4; the customer service end module is fixedly arranged above the parking space, the service end module 1 comprises a signal input device 11, a processor 12 and a memory 13, the customer service end module 2 comprises an image acquisition device 21 and an image processing device 22, and the output unit module comprises a voice device 41 and/or a video device 42;
the limit monitoring system comprises the following steps:
1) initialization: an image model is set and parking space information is input to the processor 12 through a signal input device.
2) Real-time acquisition and processing: when the vehicle stops, the image acquisition device 21 acquires the image of the vehicle in real time, the image processing device 22 performs image processing to obtain the image of the vehicle in real time and the data of the vehicle contour connecting line, and the image of the vehicle in real time and the vehicle contour connecting line are transmitted to the processor 12 through the signal transmission device 3;
3) and (4) position judgment: performing the operation of the step 2) at regular intervals, and when receiving the data of the connecting line of the vehicle profile of the current time, the processor 12 performs data comparison with the data of the connecting line of the vehicle profile of the last time to acquire the driving direction of the vehicle, and then determines the stopping information of the vehicle according to the driving direction of the vehicle, the data of the connecting line of the vehicle profile of the current time and the parking space information;
4) and (4) storage prompting: the processor 12 stores the image of the real-time vehicle in the memory 13, and the processor 12 issues a stop prompt to the output unit module 4 through the signal transmission device 3 according to the stop information of the vehicle.
According to the image recognition-based parking limit monitoring system, the parking space information in the step 1) comprises a map parking space image; the parking space image comprises a parking space area 5, a parking space boundary 6, a parking space safety area 7, a parking space safety area boundary 8, a parking space early warning area 9 and a parking space early warning area boundary 10; the parking space safety region 7 is located in the parking space region 5, the parking space early warning region 9 is located in the parking space safety region 7; the parking space area 5 is a closed quadrilateral area which is formed by parking space boundaries 6 and is adaptive to the size of a vehicle; the parking space safety zone 7 is a quadrilateral zone consisting of a parking space safety zone boundary 8; parking space safe area boundary 8 is at a distance from parking space boundary 6 and is parallel thereto; the parking space early warning area 6 is an area consisting of the parking space safe area boundary 7 and three early warning area boundaries 9; the three early warning area boundaries 9 are respectively away from the other three safe area boundaries except the safe area boundary at the vehicle entrance at a certain distance and are parallel to each other; the certain distance is 0.1-0.2m (meter); the parking space image comprises an image coordinate system, wherein an X axis of the coordinate system is parallel to an axle of a parked vehicle in the safety zone, and a Y axis of the coordinate system is perpendicular to the X axis.
The parking limit monitoring system based on image recognition can obtain coordinates of two ends of the boundary of a safe region according to an image coordinate system to obtain the boundary L of the safe region s1 -L s4 The equation:
L s1 :x=-(a+c)、L s2 :x=a+c、L s3 :x=-(b+c)、L s4 :x=b+c;
obtaining coordinates of two ends of the boundary of the early warning area according to the image coordinate system, and obtaining the boundary L of the early warning area p1 -L p4 The equation:
L p1 :x=-a、L p2 :x=a、L p3 :y=-b;
wherein a is the distance from the boundary of the early warning area to the Y axis, b is the distance from the boundary of the early warning area to the X axis, and c is the certain distance.
The parking limit monitoring system based on image recognition, the image processing device 22 in the step 2) performs image processing, and the image processing method comprises the following steps:
inputting the vehicle image into the image recognition model in the step 1), wherein the image recognition model comprises a CNN convolution neural network model, or a BP neural network model, or an image recognition model carried in Tensorflow software;
segmenting and extracting the vehicle in the vehicle image through an image recognition model to obtain a vehicle image;
carrying out structuralization processing on the vehicle image to obtain a vehicle contour connecting line; the vehicle contour connecting line is formed by connecting four end points corresponding to the outermost periphery of the vehicle in sequence along the clockwise direction or the anticlockwise direction.
Obtaining the coordinates of the vehicle contour connecting line ends according to the image coordinate system, and obtaining equations of the vehicle contour connecting lines l1, l2, l3 and l 4:
Figure RE-GDA0003712390400000041
wherein x 1 ,y 1 、x 2 ,y 2 、x 3 ,y 3 、x 4 ,y 4 The X, Y coordinates of the 4 endpoints of the vehicle contour are connected.
The image recognition-based parking limit monitoring system is characterized in that the data comparison in the step 3) is to calculate according to the coordinates of any endpoint of the vehicle contour connecting line at this time and the coordinates of the endpoint of the vehicle contour connecting line at the last time so as to obtain the driving direction of the vehicle, and specifically comprises the following steps:
converting the problem of the vehicle running direction into a solution of subtracting the coordinate of the connecting line end point i of the vehicle outline at the current time from the coordinate of the end point i of the last time to obtain a direction value { x i -x ni ,y i -y ni In which x i ,y i (i is more than or equal to 1 and less than or equal to 4) is the coordinate value of the current endpoint i, x ni ,y ni (i is more than or equal to 1 and less than or equal to 4) is the coordinate value of the last endpoint i.
The certain time is 0.2-1.0s (second).
According to the image recognition-based parking limit monitoring system, the parking information in the step 3) comprises vehicle parking completion information and information of a safety area where a vehicle is about to exit;
the vehicle parking completion information refers to that when the direction value is {0,0}, any end point of the vehicle profile connecting line of the current time is located in the parking space safety area 7, and specifically-a-c < x i < a + c and-b-c < y i <b+c;
The information of the safety area that the vehicle is going out of is arbitraryOne vehicle contour connecting line L1-L4 and any one early warning region boundary L p1 -L p3 When intersecting, and the direction of travel of the vehicle points to parking space boundary 6, specifically:
Figure RE-GDA0003712390400000051
the parking limit monitoring system based on image recognition comprises the parking prompt in the step 4), wherein the parking prompt comprises a parking completion prompt and a prompt of exiting the safe area;
the stop completion prompt means that the stop is completed through voice prompt by the voice device 41 or the stop completion is displayed by the video device 42;
the prompt of going out of the safe area refers to that the vehicle is prompted to go out of the safe area 7 of the parking space by voice through a voice device or the part of the vehicle marked to go out of the safe area 7 of the parking space is displayed through a video device.
The signal transmission device is a device capable of transmitting data in a gigabit Ethernet mode.
The application has the following beneficial effects:
1. on one hand, the method clearly reminds the owner of the vehicle to exit from the safe area, and can effectively guide the owner of the vehicle to stop in the safe area correctly.
2. On the other hand, the safety problem that the vehicle collides with the parking equipment and the like occurs when the parking equipment runs due to the fact that the vehicle is stopped outside the safety area can be monitored, and the vehicle owner is reminded.
3. The method and the device have certain adaptability, can flexibly set parameters in the initialization stage for the parking spaces with different sizes and the number of the parking spaces, and have good expansibility.
4. This application can take notes car owner's parking situation, can also carry out real-time manual monitoring inquiry to every parking stall, satisfies the parallel requirement of various control.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
Fig. 1 is a flowchart of an embodiment of a parking limit monitoring method based on image recognition according to an embodiment of the present application.
Fig. 2 is a block diagram of a parking limit monitoring method based on image recognition according to an embodiment of the present application.
Fig. 3 is a schematic diagram of a parking space after initialization based on the image recognition parking limit monitoring method in the embodiment of the present application.
Fig. 4 is a schematic view illustrating normal driving of a vehicle in a safe area of a parking space based on the image recognition parking limit monitoring method in the embodiment of the present application.
Fig. 5 is a schematic view of a safety area of a parking space where a vehicle is about to exit based on the image recognition parking limit monitoring method in the embodiment of the present application.
Fig. 6 is a schematic view illustrating a vehicle parking completion based on the image recognition parking limit monitoring method in the embodiment of the present application.
The specific implementation mode is as follows:
unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof in the description and claims of this application and the description of the figures above, are intended to cover non-exclusive inclusions.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
Example 1
A parking limit monitoring system based on image recognition comprises a service end module 1, a customer service end module 2, a signal transmission device 3 and an output unit module 4 as shown in figure 2, wherein the customer service end module is fixedly installed above a parking space, the service end module 1 comprises a signal input device 11, a processor 12 and a memory 13, the customer service end module 2 comprises an image acquisition device 21 and an image processing device 22, and the output unit module comprises a voice device 41 or a video device 42;
the limit monitoring system as shown in fig. 2 comprises the following steps:
1) initialization: setting an image model and inputting parking space information to the processor 12 through the signal input device; the parking space information comprises a map parking space image; the parking space image comprises a parking space area 5, a parking space boundary 6, a parking space safe area 7, a parking space safe area boundary 8, a parking space early warning area 9 and a parking space early warning area boundary 10; the parking space safety region 7 is located in the parking space region 5, the parking space early warning region 9 is located in the parking space safety region 7; the parking space area 5 is a closed quadrilateral area which is formed by parking space boundaries 6 and is adaptive to the size of a vehicle; the parking space safety zone 7 is a quadrilateral zone consisting of a parking space safety zone boundary 8; parking space safe area boundary 8 is at a distance from parking space boundary 6 and is parallel thereto; the parking space early warning area 6 is an area consisting of the parking space safe area boundary 7 and three early warning area boundaries 9; the three early warning area boundaries 9 are respectively away from and parallel to the other three safe area boundaries except the safe area boundary at the vehicle entrance; said certain distance is preferably 100cm (centimetres); the parking space image comprises an image coordinate system, wherein the X axis of the coordinate system is parallel to the axle of a parked vehicle in the safety area, and the Y axis is vertical to the X axis;
obtaining the boundary L of the safe region according to the coordinates of the two ends of the boundary of the safe region s1 -L s4 The equation:
L s1 :x=-(a+c)、L s2 :x=a+c、L s3 :x=-(b+c)、L s4 :x=b+c。
obtaining the boundary L of the early warning area according to the coordinates of the two ends of the boundary of the early warning area p1 -L p4 Equation (b)
L p1 :x=-a、L p2 :x=a、L p3 :y=-b;
Wherein a is the distance between the boundary of the early warning area and the Y axis, and is preferably 105cm (centimeter); b is the distance between the boundary of the early warning area and the X axis, and is preferably 245cm (centimeter); c is the certain distance.
2) Real-time acquisition and processing: when the vehicle stops, the image acquisition device 21 acquires an image of the vehicle in real time, the image processing device 22 performs image processing to obtain an image of the vehicle in real time and vehicle contour connection line data, and the image of the vehicle in real time and the vehicle contour connection line data are transmitted to the processor 12 through the signal transmission device 3; the image processing apparatus 22 performs image processing including:
inputting the vehicle image into the image recognition model in the step 1), wherein the image recognition model comprises a CNN convolution neural network model, or a BP neural network model, or an image recognition model carried in Tensorflow software;
segmenting and extracting the vehicle in the vehicle image through an image recognition model to obtain a vehicle image;
carrying out structural processing on the vehicle image to obtain a vehicle contour connecting line; the vehicle contour connecting line is formed by connecting four end points corresponding to the outermost periphery of the vehicle in sequence along the clockwise direction or the anticlockwise direction.
Obtaining the coordinates of the vehicle contour connecting line ends according to the image coordinate system, and obtaining equations of the vehicle contour connecting lines l1, l2, l3 and l 4:
Figure RE-GDA0003712390400000081
wherein x 1 ,y 1 、x 2 ,y 2 、x 3 ,y 3 、x 4 ,y 4 The X, Y coordinates of the 4 endpoints of the vehicle contour are connected.
3) And (4) position judgment: performing the operation of the step 2) at regular intervals, and when receiving the data of the connecting line of the vehicle profile of the current time, the processor 12 performs data comparison with the data of the connecting line of the vehicle profile of the last time to acquire the driving direction of the vehicle, and then determines the stopping information of the vehicle according to the driving direction of the vehicle, the data of the connecting line of the vehicle profile of the current time and the parking space information; the data comparison is to calculate according to the coordinate of any endpoint of the vehicle contour connecting line of this time and the coordinate of the endpoint of the vehicle contour connecting line of the last time so as to obtain the driving direction of the vehicle, and specifically comprises the following steps:
converting the problem of the vehicle running direction into a solution of subtracting the coordinate of the connecting line end point i of the vehicle outline at the current time from the coordinate of the end point i of the last time to obtain a direction value { x i -x ni ,y i -y ni In which x is i ,y i (i is more than or equal to 1 and less than or equal to 4) is the coordinate value of the current endpoint i, x ni ,y ni (i is more than or equal to 1 and less than or equal to 4) is the coordinate value of the last endpoint i. The certain time is preferably 1.0s (second);
the stop information comprises vehicle stop completion information and information that the vehicle is about to exit from a safety area;
the vehicle parking completion information refers to that when the direction value is {0,0}, any end point of the vehicle contour connecting line is located in the parking space safety area 5, specifically-a-c < x i < a + c and-b-c < y i <b+c;
The information of the safety zone where the vehicle is going out refers to any one vehicle contour connecting line L1-L4 and any one early warning zone boundary L p1 -L p3 When intersecting, and the direction of travel of the vehicle points to parking space boundary 6, specifically:
Figure RE-GDA0003712390400000091
4) and (4) storage prompting: the processor 12 stores the image of the real-time vehicle in the memory 13, and the processor 12 issues a stop prompt to the output unit module 4 through the signal transmission device 3 according to the stop information of the vehicle. Parking prompts, including a parking completion prompt and a prompt that the vehicle is about to exit the safe area;
the stop completion prompt means that the stop is completed through voice prompt by the voice device 41 or the stop completion is displayed by the video device 42;
the prompt of going out of the safe area refers to that the vehicle is prompted to go out of the safe area 5 by voice through a voice device or the marked vehicle part going out of the safe area 5 is displayed through a video device.
The application discloses a spacing monitoring system parks based on image recognition, signal transmission device is the device that can provide gigabit Ethernet's mode transmission data.
Example 2
As shown in fig. 4, the vehicle is normally driven in the parking space safety area.
Four endpoints x of the current vehicle contour connection line 1 ,y 1 、x 2 ,y 2 、x 3 ,y 3 、x 4 ,y 4 Coordinates (16,717), (-86,247), (89,207), and (191,676), respectively;
the equations for the vehicle contour connecting lines l1, l2, l3, l4 are obtained:
Figure RE-GDA0003712390400000101
Figure RE-GDA0003712390400000102
four end points x of the connecting line according to the last vehicle contour n1 ,y n1 、x n2 ,y n2 、x n3 ,y n3 、x n4 ,y n4 The coordinates are (108,805), (-95,370), (64,292) and (272,726), respectively, the coordinate of the endpoint i is 1, according to { x } i -x ni ,y i -y ni Obtaining a direction value (-92, -88), and knowing that the vehicle is running;
wherein a is preferably 105cm (centimeters); b is preferably 245cm (centimeter), c is preferably 10cm (centimeter), and the boundary L of the early warning area can be obtained p1 -L p3 The equation:
L p1 :x=-105、L p2 :x=105、L p3 :y=-245;
according to the method in step 3), the equations are connected and are not related to step 3)
Figure RE-GDA0003712390400000111
In either case, L1-L4 and L p1 -L p4 And the vehicles do not intersect, the vehicles do not drive into the early warning area, and the vehicles do not need to be prompted.
Example 3
As shown in fig. 5, the vehicle is about to exit the parking space safety zone by crossing the early warning zone boundary line.
Four endpoints x of the current vehicle contour connection line 1 ,y 1 、x 2 ,y 2 、x 3 ,y 3 、x 4 ,y 4 Coordinates (-5,677), (-107,207), (67,167), (169,636), respectively, from which the equations for the vehicle contour connecting lines l1, l2, l3, l4, respectively, can be derived:
Figure RE-GDA0003712390400000112
Figure RE-GDA0003712390400000113
wherein a is preferably 105cm (centimeters); b is preferably 245cm (cm), c is preferably 10cm (cm), and the product can be obtainedTo the boundary L of the early warning area p1 -L p3 The equation:
L p1 :x=-245、L p2 :x=245、L p3 :y=-105;
according to the method in step 3), the equations are connected to obtain L1 and L4, which are respectively connected with L p1 Intersecting;
four end points x of the connecting line according to the last vehicle contour n1 ,y n1 、x n2 ,y n2 、x n3 ,y n3 、x n4 ,y n4 The coordinates are (119,805), (-86,370), (75,292) and (281,726) respectively,
taking the coordinate of the endpoint i as 1 according to { x } i -x ni ,y i -y ni -obtaining a direction value (124, 128);
as can be seen by comparison, the vehicle already intersects with the boundary line of the early warning area, and the vehicle exits from the safety area of the parking space, and the video device 42 prompts that the vehicle is about to intersect with the boundary of the left rear half part of the parking space.
Example 4
As shown in fig. 6, the vehicle has been parked.
Four endpoints x of the current vehicle contour connection line 1 ,y 1 、x 2 ,y 2 、x 3 ,y 3 、x 4 ,y 4 Coordinates (-87, -233), (92, -236), (98,243), (81,248), respectively, from which the vehicle contour connecting lines l1, l2, l3, l4 equations are obtained:
Figure RE-GDA0003712390400000121
Figure RE-GDA0003712390400000122
four end points x of the connecting line according to the last vehicle contour n1 ,y n1 、x n2 ,y n2 、x n3 ,y n3 、x n4 ,y n4 The coordinates are (-87, -233), (92, -236) and (98,243) respectively)、(-81,248),
Taking the coordinate of the endpoint i as 1 according to { x } i -x ni ,y i -y ni Get the direction value (0,0), know the vehicle has stopped steadily;
wherein a is preferably 105cm (centimeters); b is preferably 245cm (centimeter), c is preferably 10cm (centimeter), and a parking space safe area boundary L can be obtained s1 -L s4 The equation:
L p1 :x=-115、L p2 :x=115、L p3 :y=-255、L p4 :y=255;
according to the method in step 3), the equations are combined to obtain the arbitrary terms
-a-c<x i < a + c and-b-c < y i < either of b and c, L1-L4 and L p1 -L p3 Without the intersection, the vehicle has been parked completely in the safe area, and the parking completion notification is provided to the vehicle via the video device 42.

Claims (8)

1. The utility model provides a spacing monitoring system parks based on image identification, includes server module (1), customer service end module (2), signal transmission device (3), output unit module (4), its characterized in that: the system comprises a customer service end module, a server end module and an output unit module, wherein the customer service end module is fixedly arranged above a parking space, the server end module (1) comprises a signal input device (11), a processor (12) and a memory (13), the customer service end module (2) comprises an image acquisition device (21) and an image processing device (22), and the output unit module comprises voice equipment (41) and/or video equipment (42);
the limit monitoring system comprises the following steps:
1) initialization: an image model is set and parking space information is input to a processor (12) through a signal input device.
2) Real-time acquisition and processing: when the vehicle stops, the image acquisition device (21) acquires an image of the vehicle in real time, the image processing device (22) performs image processing to obtain the image of the vehicle in real time and vehicle contour connecting line data, and the image of the vehicle in real time and the vehicle contour connecting line are transmitted to the processor (12) through the signal transmission device (3);
3) and (4) position judgment: the operation of the step 2) is carried out at regular intervals, when the processor (12) receives the data of the connecting line of the vehicle contour of the current time, the data of the connecting line of the vehicle contour of the last time are compared with the data of the connecting line of the vehicle contour of the previous time, so as to obtain the driving direction of the vehicle, and then the stopping information of the vehicle is determined according to the driving direction of the vehicle, the data of the connecting line of the vehicle contour of the current time and the parking space information;
4) and (4) storage prompting: the processor (12) stores the real-time vehicle image in the memory (13), and according to the vehicle stop information, the processor (12) sends a stop prompt to the output unit module (4) through the signal transmission device (3).
2. The image-based recognition parking limit monitoring system according to claim 1, wherein the parking space information in step 1) comprises a map parking space image;
the parking space image comprises a parking space area (5), a parking space boundary (6), a parking space safe area (7), a parking space safe area boundary (8), a parking space early warning area (9) and a parking space early warning area boundary (10), wherein the parking space safe area (7) is located in the parking space area (5), the parking space early warning area (9) is located in the parking space safe area (7);
the parking space area (5) is a closed quadrilateral area which is formed by parking space boundaries (6) and is adaptive to the size of a vehicle;
the parking space safety region (7) is a quadrilateral region formed by parking space safety region boundaries (8), and the parking space safety region boundaries (8) are at a certain distance from the parking space boundaries (6) and are parallel to each other;
the parking space early warning area (6) is an area consisting of a parking space safe area boundary (7) and three early warning area boundaries (9), and the three early warning area boundaries (9) are respectively away from and parallel to the other three safe area boundaries except the safe area boundary at the vehicle entrance; the certain distance is 0.1-0.2m (meter);
the parking space image comprises an image coordinate system, wherein an X axis of the coordinate system is parallel to an axle of a parked vehicle in the safety zone, and a Y axis of the coordinate system is perpendicular to the X axis.
3. The image recognition-based parking limit monitoring system of claim 2, wherein:
obtaining coordinates of two ends of the boundary of the safety region according to the image coordinate system to obtain the boundary L of the safety region s1 -L s4 The equation:
L s1 :x=-(a+c)、L s2 :x=a+c、L s3 :x=-(b+c)、L s4 :x=b+c;
obtaining coordinates of two ends of the boundary of the early warning area according to the image coordinate system, and obtaining the boundary L of the early warning area p1 -L p4 The equation:
L p1 :x=-a、L p2 :x=a、L p3 :y=-b;
wherein a is the distance from the boundary of the early warning area to the Y axis, b is the distance from the boundary of the early warning area to the X axis, and c is the certain distance.
4. The image-based recognition parking limit monitoring system according to claim 3, wherein the image processing device (22) in step 2) performs image processing, comprising:
inputting the vehicle image into the image recognition model in the step 1), wherein the image recognition model comprises a CNN convolution neural network model, or a BP neural network model, or an image recognition model carried in Tensorflow software;
segmenting and extracting the vehicle in the vehicle image through an image recognition model to obtain a vehicle image;
carrying out structural processing on the vehicle image to obtain a vehicle contour connecting line; the vehicle contour connecting line is formed by connecting four end points corresponding to the outermost periphery of the vehicle in sequence along the clockwise direction or the anticlockwise direction.
Obtaining the coordinates of the connecting line end points of the vehicle contour according to the image coordinate system, and obtaining equations of the connecting lines of the vehicle contour l1, l2, l3 and l 4:
Figure FDA0003583926160000031
wherein x 1 ,y 1 、x 2 ,y 2 、x 3 ,y 3 、x 4 ,y 4 The X, Y coordinates of the 4 endpoints of the vehicle contour are connected.
5. The image recognition-based parking limit monitoring system according to claim 1, wherein the data comparison in step 3) is to calculate according to coordinates of any endpoint of the connecting line of the current vehicle contour and coordinates of an endpoint of the connecting line of the last vehicle contour, so as to obtain a driving direction of the vehicle, and specifically comprises:
converting the problem of the vehicle running direction into a solution of subtracting the coordinate of the connecting line end point i of the vehicle outline at the current time from the coordinate of the end point i of the last time to obtain a direction value { x i -x ni ,y i -y ni In which x i ,y i (i is more than or equal to 1 and less than or equal to 4) is the coordinate value of the current endpoint i, x ni ,y ni (i is more than or equal to 1 and less than or equal to 4) is the coordinate value of the last endpoint i.
The certain time is 0.2-1.0s (second).
6. The image-based recognition parking limit monitoring system according to claim 1, wherein the parking information in step 3) includes vehicle parking completion information and vehicle leaving-soon safety area information;
the vehicle parking completion information refers to that when the direction value is {0,0}, any end point of the vehicle profile connecting line of the current time is positioned in the parking space safety area (7), and specifically, x is more than-a-c i < a + c and-b-c < y i <b+c;
The information of the safety zone where the vehicle is going out refers to any one vehicle contour connecting line L1-L4 and any one early warning zone boundary L p1 -L p3 When intersecting, and the direction of travel of the vehicle points to a parking space boundary (6), specifically:
Figure FDA0003583926160000041
7. the image-based recognition parking limit monitoring system of claim 1, wherein the parking prompt in step 4) comprises a parking completion prompt and a prompt to exit the safe area;
the parking completion prompt is used for prompting the completion of parking through a voice device (41) or displaying the completion of parking through a video device (42);
the prompt of going out of the safe area refers to that the vehicle is prompted to go out of the safe area (7) of the parking space through voice equipment or the marked part of the vehicle which is going out of the safe area (7) of the parking space is displayed through video equipment (42).
8. The system according to claim 1, wherein the signal transmission device is a device capable of providing gigabit ethernet for data transmission.
CN202210358478.6A 2022-04-07 2022-04-07 Parking limit monitoring system based on image recognition Active CN115116262B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210358478.6A CN115116262B (en) 2022-04-07 2022-04-07 Parking limit monitoring system based on image recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210358478.6A CN115116262B (en) 2022-04-07 2022-04-07 Parking limit monitoring system based on image recognition

Publications (2)

Publication Number Publication Date
CN115116262A true CN115116262A (en) 2022-09-27
CN115116262B CN115116262B (en) 2023-07-07

Family

ID=83325354

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210358478.6A Active CN115116262B (en) 2022-04-07 2022-04-07 Parking limit monitoring system based on image recognition

Country Status (1)

Country Link
CN (1) CN115116262B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116101229A (en) * 2023-04-13 2023-05-12 国网安徽省电力有限公司合肥供电公司 Battery replacement station battery replacement operation control system based on electric automobile

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005182504A (en) * 2003-12-19 2005-07-07 Matsushita Electric Ind Co Ltd Parking support system
WO2016168555A1 (en) * 2015-04-17 2016-10-20 General Electric Company Monitoring parking rule violations
CN110580822A (en) * 2019-08-08 2019-12-17 横琴善泊投资管理有限公司 Method and system for monitoring and managing internal parking spaces of parking lot
CN111091718A (en) * 2019-12-31 2020-05-01 广东华车智库智能科技有限公司 Parking monitoring early warning method and parking monitoring early warning system
US10713509B1 (en) * 2019-01-24 2020-07-14 Ford Global Technologies, Llc Parking assist system with parking spot occupancy readout
US20210020046A1 (en) * 2019-03-14 2021-01-21 Beijing Boe Display Technology Co., Ltd. Parking Management System and Parking Management Method
WO2021203717A1 (en) * 2020-04-08 2021-10-14 智慧互通科技有限公司 Method for recognizing roadside parking behavior in complex scenario on basis of video frames
US20210342606A1 (en) * 2020-04-30 2021-11-04 Boe Technology Group Co., Ltd. Parking Detection Method, System, Processing Device and Storage Medium
WO2021248833A1 (en) * 2020-06-12 2021-12-16 浙江驿公里智能科技有限公司 Anti-collision system and method for actively guiding vehicle stopping using camera
WO2022052501A1 (en) * 2020-09-11 2022-03-17 江苏小白兔智造科技有限公司 Vehicle type-based parking hall-free intelligent parking method

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005182504A (en) * 2003-12-19 2005-07-07 Matsushita Electric Ind Co Ltd Parking support system
WO2016168555A1 (en) * 2015-04-17 2016-10-20 General Electric Company Monitoring parking rule violations
US10713509B1 (en) * 2019-01-24 2020-07-14 Ford Global Technologies, Llc Parking assist system with parking spot occupancy readout
US20210020046A1 (en) * 2019-03-14 2021-01-21 Beijing Boe Display Technology Co., Ltd. Parking Management System and Parking Management Method
CN110580822A (en) * 2019-08-08 2019-12-17 横琴善泊投资管理有限公司 Method and system for monitoring and managing internal parking spaces of parking lot
CN111091718A (en) * 2019-12-31 2020-05-01 广东华车智库智能科技有限公司 Parking monitoring early warning method and parking monitoring early warning system
WO2021203717A1 (en) * 2020-04-08 2021-10-14 智慧互通科技有限公司 Method for recognizing roadside parking behavior in complex scenario on basis of video frames
US20210342606A1 (en) * 2020-04-30 2021-11-04 Boe Technology Group Co., Ltd. Parking Detection Method, System, Processing Device and Storage Medium
WO2021248833A1 (en) * 2020-06-12 2021-12-16 浙江驿公里智能科技有限公司 Anti-collision system and method for actively guiding vehicle stopping using camera
WO2022052501A1 (en) * 2020-09-11 2022-03-17 江苏小白兔智造科技有限公司 Vehicle type-based parking hall-free intelligent parking method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116101229A (en) * 2023-04-13 2023-05-12 国网安徽省电力有限公司合肥供电公司 Battery replacement station battery replacement operation control system based on electric automobile
CN116101229B (en) * 2023-04-13 2023-06-09 国网安徽省电力有限公司合肥供电公司 Battery replacement station battery replacement operation control system based on electric automobile

Also Published As

Publication number Publication date
CN115116262B (en) 2023-07-07

Similar Documents

Publication Publication Date Title
WO2020237664A1 (en) Driving prompt method, driving state detection method and computing device
CN102509418B (en) Fatigue driving estimation and early-warning method and device of multi-sensor information fusion
CN103473951B (en) A kind of Automatic Carpark Control System based on telepresenc
CN110077414A (en) A kind of vehicle driving safety support method and system based on driver status monitoring
CN103057470B (en) A kind of vehicle peccancy line ball pre-tip device and reminding method thereof
CN108437982A (en) A kind of automatic parking device and method
CN110203202A (en) A kind of lane-change auxiliary method for early warning and device based on Driver intention recognition
CN108638966A (en) A kind of automobile assistant driving system and auxiliary driving method based on blind area monitoring
DE102013222885B4 (en) Apparatus and method for controlling the driving of a vehicle
EP4144598A1 (en) System and method employing car seat belt to enhance safety of occupant
CN110126730A (en) Vehicle lane change based reminding method and system
CN115116262A (en) Parking limit monitoring system based on image recognition
CN108099961A (en) A kind of electronic driving system of train
CN107226093A (en) A kind of truck man fatigue driving determination methods
CN205594899U (en) Vehicle is crossed signal lamp and is reminded system
CN103192830B (en) A kind of self-adaptive visual lane departure warning device
CN110435652A (en) Lane departure warning method, system, device and storage medium
CN108010269A (en) A kind of driving based on car networking is divert one&#39;s attention monitoring, early warning system and method
CN108045305A (en) Central axle transport vehicle coupler operating angle is prompted and prior-warning device and method
CN114771545A (en) Intelligent safe driving system
CN117523537A (en) Dynamic judging method for dangerous degree of vehicle driving
CN206961331U (en) A kind of high threat vehicle monitoring early warning system
CN114559960A (en) Collision early warning system based on fusion of forward-looking camera and rear millimeter wave radar
CN109305171A (en) A kind of front vehicles driving posture observation device and its method
CN107330997A (en) A kind of preventing collision of vehicles porcelain system and method

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