CN108320575A - A kind of guiding of parking stall and reverse vehicle searching system and its parking space-detecting device, method - Google Patents
A kind of guiding of parking stall and reverse vehicle searching system and its parking space-detecting device, method Download PDFInfo
- Publication number
- CN108320575A CN108320575A CN201810218914.3A CN201810218914A CN108320575A CN 108320575 A CN108320575 A CN 108320575A CN 201810218914 A CN201810218914 A CN 201810218914A CN 108320575 A CN108320575 A CN 108320575A
- Authority
- CN
- China
- Prior art keywords
- parking
- parking stall
- image
- information
- vehicle
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012937 correction Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 238000003702 image correction Methods 0.000 claims abstract description 9
- 230000000903 blocking effect Effects 0.000 claims abstract description 8
- 230000002123 temporal effect Effects 0.000 claims description 42
- 241000251468 Actinopterygii Species 0.000 claims description 33
- 238000003384 imaging method Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000003709 image segmentation Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000005070 sampling Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000005389 magnetism Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013211 curve analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
- G08G1/142—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces external to the vehicles
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of guiding of parking stall and reverse vehicle searching system and its parking space-detecting device, method, the parking space-detecting device to include：Video image acquisition unit, the video data for obtaining parking stall in garage parking by fish-eye camera；Image correction unit, for carrying out distortion correction to fish-eye camera the image collected data；Parking stall coordinate demarcates unit, for being demarcated to the coordinate on parking stall according to the image after distortion correction；Parking stall image extraction unit is extracted for the image to unicom region parking stall；Processing unit is blocked in parking stall, for parking stall to be divided into several sub-regions, and distributes different weights to handle the occlusion issue of parking stall；Parking stall identifying processing unit, the handling result for blocking processing unit according to parking stall judge whether there is vehicle on parking stall, through the invention, user can be improved and find the efficiency of free parking space in parking lot, while improving the pick-up efficiency of user.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of guiding of parking stall and reverse vehicle searching system and its stop
Stall testing apparatus, method.
Background technology
With the continuous improvement of social progress and living standards of the people, people buy the desire for consumer goods of private car increasingly
Strongly, in some more flourishing big cities of China, the problem of quantity of vehicle is more and more, and the thing followed is parking difficulty,
In order to solve this problem, large parking lot quantity is also more and more, stops and picks up the car in order to facilitate driver, truck space guiding system
It comes into being.
Whether the parking stall is usually detected in parking lot in each parking stall using ultrasound, the sensors such as earth magnetism a vehicle, before parking stall
Indicator light shows that testing result, driver then differentiate whether parking stall is occupied according to indicator light before parking stall, has single-point monitoring, applies
The work period is long and the shortcomings that being unfavorable for later maintenance, needs to buy a certain number of ultrasounds or earth magnetism for large parking lot
Sensor and corresponding parking stall indicator light, cost are higher.
It is found by investigation, on each parking stall, there are one parking stall indicator lights in existing a part of parking lot, this is undoubtedly
The cost in parking lot can be greatly increased, installation and wiring are also complex, are unfavorable for later maintenance.And parking lot is without unification
Car plate harvester can not carry out the vehicle in parking lot information collection and quantity controls, when driver picks up the car, when needing with parking
Memory find the vehicle of oneself, take and laborious.
In order to guide the personnel of controlling quickly and accurately to find parking stall, application No. is promulgateds by the State Council in CN201210259422.1
Bright patent " a kind of truck space guiding system and parking stall bootstrap technique " discloses a kind of truck space guiding system comprising video integration
Device, Car license recognition instrument, controller, data processing centre and at least one picture pick-up device；Picture pick-up device is for obtaining regarding for parking stall
Frequency information；Video set is grown up to be a useful person the video information sent for receiving at least one picture pick-up device, by the video information into
Row sequence, and it is sent to Car license recognition instrument successively；Car license recognition instrument is used to receive video set and grows up to be a useful person the video information of transmission, according to
The video information determines on parking stall whether there is vehicle, to obtain parking space information, the parking space information is sent to controller, and can
To identify license board information, the recognition result of the car plate is sent to data processing centre；Controller, for receiving Car license recognition
The parking space information that instrument is sent controls parking stall indicator light according to the parking space information；Data processing centre, for receiving Car license recognition
The license plate recognition result that instrument is sent, parking stall guidance information is provided a user according to the license plate recognition result.However such system
System often wastes a large amount of time when underground garage stops and finds parking stall using complicated, car owner need. while driving
Pay attention to the indicator light on parking stall, safety is poor, and efficiency is low.
Application No. is a kind of 201710447805.4 Chinese invention patent " parking stalls based on image procossing and pattern-recognition
Bootstrap technique and system " provides a kind of parking stall bootstrap technique and system based on image procossing and pattern-recognition, receives camera
Image to be detected of acquisition, described image to be detected include：Mark rod and multiple parking stalls, the mark rod need to be arranged described more
A parking stall corresponds to four vertex of rectangular area or cornerwise two points, by identifying the mark in the parking field picture
Bar, and according to the vehicle within the scope of the location determination mark rod of the mark rod, and determine the number of the vehicle, compare again later
The vehicle number and the parking stall number in the range, if the number of the vehicle is equal to the parking stall number, it is determined that do not have
Empty parking space, if the number of the vehicle is less than the parking stall number, it is determined that there is parking stall.However, this use monitoring camera knot
The mode for closing mark rod not only increases cost, and increases the complexity of installation, larger to existing parking lot transformation difficulty,
It is unfavorable for later maintenance, debugging and upgrading simultaneously.
Invention content
In order to overcome the deficiencies of the above existing technologies, it guides purpose of the present invention is to provide a kind of parking stall and reversely seeks
Vehicle system and its parking space-detecting device, method are found the efficiency of free parking space to improve user in parking lot, are carried simultaneously
The pick-up efficiency of high user.
In view of the above and other objects, the present invention proposes a kind of parking space-detecting device, including：
Video image acquisition unit, the video data for obtaining parking stall in garage parking by fish-eye camera；
Image correction unit, for carrying out distortion correction to fish-eye camera the image collected data；
Parking stall coordinate demarcates unit, for being demarcated to the coordinate on parking stall according to the image after distortion correction；
Parking stall image extraction unit is extracted for the image to unicom region parking stall；
Processing unit is blocked in parking stall, for parking stall to be divided into several sub-regions, and distributes different weights to locate
Manage the occlusion issue of parking stall；
Parking stall identifying processing unit, the handling result for blocking processing unit according to parking stall judge whether have on parking stall
Vehicle.
Preferably, image correction unit further comprises：
Fish eye images image coordinate cutting unit is image for the pixel coordinate of fish eye images to be converted to coordinate origin
Pixel coordinate on center；
Target image image coordinate cutting unit, for the image after fish eye images distortion correction to be denoted as target image,
Carry out the amendment on both horizontally and vertically to the pixel coordinate of target image, and by the coordinate of the target image after pixel correction
Shift of origin is obtained to the upper left corner of target image by the transformed target image pixel of coordinate system；
Map unit is used for according to the imaging law of pin-hole imaging model and the imaging characteristics of flake imaging model, will
Target image after coordinate modification is mapped to the fish eye images under panorama picture of fisheye lens model, and then is rectified according to fish eye images
Target image after just；
Correcting unit, the mapping relations obtained according to the map unit correct the fish eye images of acquisition；
Interpolation process unit obtains final process for fish eye images to be completed with the image after distortion correction into row interpolation
Image afterwards.
Preferably, the parking stall image extraction unit further comprises：
Difference image acquiring unit is foreground image for choosing testing image, and a pair is background image without vehicle image, will
Foreground image after median filter process, seeks difference image with background image；
Binary conversion treatment unit, for carrying out binaryzation to the difference image；
Image segmentation unit, the region for unicom region area to be less than to set threshold value become background；
Combining unit, for merging neighbouring unicom region；
Extraction unit identifies parking stall after repeatedly learning using figure.
Preferably, the parking stall blocks processing unit and the parking stall being identified is again divided into several subregions, and
Different weights is distributed to every sub-regions, the weights distributed close to the region of neighbouring parking stall are less than the power far from neighbouring parking stall
Value.
In order to achieve the above objectives, the present invention also provides a kind of parking space detection method, include the following steps：
Step 1 obtains the video data on parking stall in garage parking by fish-eye camera；
Step 2 carries out distortion correction to fish-eye camera the image collected data；
Step 3 demarcates the coordinate on parking stall according to the image after correction；
Step 4 extracts the image on unicom region parking stall；
Parking stall is divided into several sub-regions by step 5, and is distributed different weights and asked to handle blocking for parking stall
Topic；
Step 6 judges whether there is vehicle on parking stall according to the handling result of step 5.
In order to achieve the above objectives, the present invention also provides a kind of parking stall guiding using aforementioned parking space-detecting device and reversely
Vehicle system is sought, including：
Car license recognition unit for acquiring vehicle license plate information and temporal information into current garage parking, and will be adopted
Vehicle license plate information, temporal information and the corresponding garage information collected is sent to system controller；
Parking space-detecting device, for acquiring the parking stall image information in garage parking in real time, according to parking stall image information
Processing obtain the remaining parking stall information of number in current garage parking, and by the remaining parking stall information of number of acquisition and it is corresponding when
Between information be sent to system controller and parking stall guide device；
System controller carries out comprehensive according to the information that the Car license recognition unit and parking space-detecting device received is sent
Analysis is closed, determines the parking information of vehicle；
Parking stall guide device, the parking stall information of number sent for receiving the parking space-detecting device, and according to
The parking condition of the information outputting parking position of reception.
Preferably, garage parking is divided into several subregions by the parking space-detecting device, after vehicle drives into garage parking, is led to
The subregion in garage where acquisition image recognition goes out vehicle, and the license board information of collection vehicle are crossed, it will be collected for the last time
The subarea number information of license board information, current temporal information and garage is sent to the system controller.
Preferably, the system controller is in license board information, the temporal information for receiving the Car license recognition unit transmission
And after garage number information or after parking space-detecting device last time is captured to license board information, whithin a period of time
The change for detecting the remaining empty parking space quantity in corresponding garage then judges the vehicle in current garage or the subregion in current garage
It inside stops, obtains the parking information of the vehicle.
Preferably, the system also includes reverse car seeking device, stop for receive that the system controller sends
Vehicle information, and user is provided and carries out vehicle query, it provides and seeks vehicle best route, to realize reverse car seeking purpose.
In order to achieve the above objectives, the present invention also provides a kind of guiding of parking stall and reverse car seeking method, include the following steps：
Step 1 enters garage parking using parking stall guide means guide vehicle, and acquisition enters the vehicle vehicle in current garage parking
Board information and temporal information, and collected vehicle license plate information, temporal information and corresponding garage information are sent to
System controller；
Step 2 acquires the parking stall image information in garage parking using parking space-detecting device, according to parking stall figure in real time
As the processing of information obtains the remaining parking stall information of number in current garage parking, and by the remaining parking stall information of number and phase of acquisition
The temporal information answered is sent to system controller and parking stall guide device；
Step 3, the system controller carry out comprehensive analysis according to the information that step 1 and step 2 receive, determine
The parking information of vehicle.
Compared with prior art, a kind of parking stall guiding of the present invention and reverse vehicle searching system and its parking space-detecting device, side
Method carries out license plate image acquisition, by inlet Car license recognition unit and garage by the way that garage parking is divided into several subregions
The acquisition information of parking space-detecting device integrates the parking subregion of determining vehicle, greatly reduces the number of Car license recognition unit
Amount, reduces cost, and improve user and find the efficiency of free parking space in parking lot, while improving the pick-up of user
Efficiency.
Description of the drawings
Fig. 1 is a kind of system structure diagram of parking space-detecting device of the present invention；
Fig. 2 is the detail structure chart of image correction unit in the specific embodiment of the invention；
Fig. 3 is the detail structure chart of parking stall image extraction unit in the specific embodiment of the invention
The system architecture for the parking stall guiding and reverse vehicle searching system that Fig. 4 is applied for the parking space-detecting device of the present invention
Figure；
Fig. 5 is the assembly connecting mode signal of the specific embodiment of a kind of parking stall guiding of the present invention and reverse vehicle searching system
Figure；
Fig. 6 is the application outdoor scene schematic diagram of the specific embodiment of a kind of parking stall guiding of the present invention and reverse vehicle searching system；
Fig. 7 is the step flow chart of a kind of parking stall guiding of the present invention and reverse car seeking method；
Fig. 8 is a kind of step flow chart of the parking space detection method of parking space-detecting device of the present invention；
Fig. 9 (A), (B) are parking garage scape schematic diagram in the specific embodiment of the invention；
Flake fault image is converted into flat image output effect schematic diagram in Figure 10 specific embodiment of the invention.
Specific implementation mode
Below by way of specific specific example and embodiments of the present invention are described with reference to the drawings, those skilled in the art can
Understand the further advantage and effect of the present invention easily by content disclosed in the present specification.The present invention can also pass through other differences
Specific example implemented or applied, details in this specification can also be based on different perspectives and applications, without departing substantially from
Various modifications and change are carried out under the spirit of the present invention.
Fig. 1 is a kind of system structure diagram of parking space-detecting device of the present invention.As shown in Figure 1, one kind of the present invention is stopped
Stall testing apparatus, parking stall for detecting garage parking simultaneously judge whether parking stall is empty comprising：
Video image acquisition unit 101, the video data for obtaining parking stall in garage parking by fish-eye camera.
In the specific embodiment of the invention, two fish-eye cameras can be placed in each garage parking, the visual angle of each fish-eye camera is 180
Degree, so that 100% covering is realized in sampling.Preferably, video image acquisition unit 101 (can also have by the existing CATV in garage
Line television network) camera acquisition video data.
Image correction unit 102, for carrying out distortion correction to fish-eye camera the image collected data.Such as Fig. 2 institutes
Show, image correction unit 102 further comprises：
Fish eye images image coordinate cutting unit 1021, for the pixel coordinate of fish eye images to be converted to corresponding position
Pixel：If the pixel coordinate of the fish eye images of fish-eye camera acquisition is (x1, y1), to the pixel (x1, y1) of fish eye images
Coordinate conversion is carried out, image coordinate origin is moved into picture centre from the image upper left corner, obtains the transformed fish eye images of coordinate
Pixel (x2, y2)；
Target image image coordinate cutting unit 1022, for the image after fish eye images distortion correction to be denoted as target figure
Picture, carries out the pixel coordinate of target image the amendment on both horizontally and vertically, and by the target image after pixel correction
Coordinate origin is transferred to the upper left corner of target image, obtains by the transformed target image pixel of coordinate system.Assuming that target figure
As certain upper pixel is (x3, y3), the pixel (x3, y3) of pair target image assumed carries out repairing on both horizontally and vertically
Just.The coordinate origin of target image after pixel correction is transferred to the upper left corner of target image, is obtained by coordinate system
Transformed target image pixel (x4, y4)；
Specifically, it is assumed that certain pixel is (x3, y3) on target image, and vertical correction term △ y are added in vertical direction,
Horizontal correction term △ x are added in horizontal direction, obtain revised ordinate x ' 3, y ' 3=y3+ △ y x ' 3=y3+ △ x,
Wherein, w, h are respectively the width and height of image, and Ky is ordinate correction factor, and Kx is abscissa correction factor,
F is fish eye lens focal length；
Map unit 1023, the imaging for imaging law and flake imaging model according to pin-hole imaging model are special
Target image after coordinate modification is mapped to the fish eye images under panorama picture of fisheye lens model by point, that is, carry out rectangular co-ordinate with
Polar conversion, and then the target image after being corrected according to fish eye images；
Correcting unit 1024, the mapping relations obtained according to map unit 1023 correct the fish eye images of acquisition；
Interpolation process unit 1025 carries out interpolation processing for fish eye images to be completed with the image after distortion correction, obtains
Image after final process.
Parking stall coordinate demarcates unit 103, for being demarcated to the coordinate on parking stall using video data.Have in the present invention
In body embodiment, coordinate calibration unit 103 in parking stall with the following method demarcates the coordinate to parking stall：
Background image of the current garage parking of a width without vehicle is selected, gray level image is converted into after pretreatment；
Video image is extracted from the video data of acquisition, chooses several as training dataset, the Background with extraction
As carrying out self study, the region often changed is set as parking area, completes the calibration of parking stall coordinate.
Parking stall image extraction unit 104 is extracted for the image to unicom region parking stall.Specifically, such as Fig. 3 institutes
Show, parking stall image extraction unit 104 further comprises：
Difference image acquiring unit 1041 is foreground image for choosing testing image, and it is background to choose one without vehicle image
Image seeks difference image by foreground image and background image after median filter process；
Binary conversion treatment unit 1042, for carrying out binaryzation to difference image using one-dimensional maximum variance between clusters；
Image segmentation unit 1043, the region for unicom region area to be less than to set threshold value become background, realize
The segmentation of image.In the specific embodiment of the invention, image segmentation unit 2043 is using three-dimensional Otsu (the big rules based on decomposition
Method) selection criteria of the method using the maximum between-cluster variance of target and background as threshold value, by the gamma characteristic of image, realization image
Segmentation, that is, target detection.
Combining unit 1044, for merging neighbouring unicom region.
Extraction unit 1045 identifies parking stall after repeatedly learning using figure.
Processing unit 105 is blocked in parking stall, for parking stall to be divided into several sub-regions, and distributes different weights
Handle the occlusion issue of parking stall；Specifically, parking stall block processing unit 105 parking stall being identified is again divided into it is several
Subregion, and different weights is distributed to every sub-regions, such as the weights distributed close to the region of neighbouring parking stall are less than far
Weights from neighbouring parking stall.
Parking stall identifying processing unit 106, the handling result for blocking processing unit 105 according to parking stall judge parking stall
Whether there is vehicle to block, if there is blocking, then illustrate that parking stall is occupied, parking stall not be sky, if unobstructed, illustrate parking stall not by
It occupies, parking stall is sky.
Specifically, parking stall identifying processing unit 106 seeks the ratio shared by each target by threshold classification device：
C marks off the areal come for single parking stall, and R (k) is to mark off the region unit come, WkFor k-th of region
Shared weight, G (i, j) are current bianry image, and S is the area on the parking stall；
If aP is final threshold value, if the target ratio detected is more than set threshold value aP, that is, illustrate the parking stall
It is occupied, otherwise, it is considered as the free time；Wherein a is in the learning process of training dataset according to priori by learning automatically really
It is fixed.
The system architecture for the parking stall guiding and reverse vehicle searching system that Fig. 4 is applied for the aforementioned parking space-detecting device of the present invention
Figure.As shown in figure 4, a kind of parking stall guiding of the present invention and reverse vehicle searching system, including：Car license recognition unit 10, parking stall detection
Device 20, system controller 30 and parking stall guide device 40.
Car license recognition unit 10, for acquiring the vehicle license plate information and temporal information into current garage parking and giving
Storage, while collected vehicle license plate information, temporal information and corresponding garage information are sent to system controller 30.
Car license recognition unit 10 includes image capture module, control module and memory module, wherein image capture module, which is set to, to stop
Garage port can be realized by photographic device, for collection vehicle image information and be stored in memory module, control mould
Block is handled to obtain license board information to the image of acquisition, and license plate number and temporal information are sent to system controller 30.Specifically
Ground says, Car license recognition unit 10 can by the way that photographic device is arranged in parking garage entrances, when vehicle enters garage parking by entrance,
Using the image information of the photographic device collection vehicle, and the temporal information of current vehicle entrance is recorded, passes through the figure to acquisition
The characters on license plate string information that vehicle is obtained as carrying out image procossing, by the license board information and temporal information of acquisition, such as " Zhejiang
B999AA”“15:24 " are stored, and are sent to system controller 30, and garage information here refers to the number in garage parking,
In the specific embodiment of the invention, a parking lot can stop comprising multiple garage parkings, such as garage parking A, B, C ... each
Vehicle recognition unit is arranged in the entrance in garage, and when there is vehicle to drive into, vehicle recognition unit can collect the car plate for driving into vehicle
Information, temporal information, and the license board information, temporal information and garage of collected vehicle number are sent to system controller
30。
Parking space-detecting device 20 is believed for acquiring the parking stall image information in garage parking in real time according to parking stall image
The processing of breath obtains the remaining parking stall information of number in current garage parking, and by the remaining parking stall information of number of acquisition and accordingly
Temporal information is sent to system controller 30 and parking stall guide device 40.In the specific embodiment of the invention, parking stall detection dress
It sets 20 and is set to inner part of parking lot, such as parking lot centre position, (each fish-eye camera regards using two fish-eye cameras
Angle is 180 degree, so that 100% covering is realized in sampling) it detects current garage parking residue empty parking space and quantity is kept to update, by the time
Information and the empty parking space information of number in garage send system controller to.Preferably, parking space-detecting device 20 can also and vehicle
The existing CATV cameras in library combine, combination acquisition image pattern is taken the photograph using two fish-eye cameras and CATV cable televisions
As head detection current garage parking residue parking stall and quantity is kept to update, temporal information and the empty parking space information of number in garage are transmitted
To system controller.
Preferably, garage parking is also divided into several subregions by parking space-detecting device 20, after vehicle drives into garage parking, is led to
The subregion in garage where acquisition image recognition goes out vehicle, and the license board information of collection vehicle are crossed, it will be collected for the last time
The subarea number information of license board information, current temporal information and garage is sent to system controller.That is, at this
In invention specific embodiment, a parking lot includes multiple garage parkings, and each garage parking is divided into as several subregions, every height
Region includes more than two parking stalls (the parking stall number that subregion includes is fewer, and accuracy is higher), is put in each garage parking
Two fish-eye cameras are set, the visual angle of each fish-eye camera is 180 degree, so that 100% covering is realized in sampling, when vehicle drives into
Start to stop behind the garage parking, be captured as the subregion where two fish-eye cameras identify vehicle, and by last time
To license board information, the subarea number information in current temporal information and garage be sent to system controller 30.
System controller 30, the information sent according to the Car license recognition unit 10 and parking space-detecting device 20 received
Comprehensive analysis is carried out, determines the parking information of vehicle.Such as when license board information, the time for receiving the transmission of Car license recognition unit 10
After information and garage number information, the residue in the garage of the transmission of parking space-detecting device 20 is received in a period of time end
The change of empty parking space quantity then can determine whether out that the vehicle stops in the garage, and determine the parking information of the vehicle, such as vehicle
The trade mark, corresponding garage parking and temporal information.Preferably, if system controller 30 also receives the hair of parking space-detecting device 20
The subarea number information in license board information, current temporal information and garage that the last time sent is captured, then last
After the primary candid photograph time, the change of remaining empty parking space quantity is detected in a period of time end, you can judge the vehicle at this
Stop in the subregion in garage, determine the parking information of the vehicle, the license plate number of the vehicle and corresponding garage parking and
Garage parking subarea number information.
Parking stall guide device 40, the parking stall information of number sent for receiving parking space-detecting device 20, and by its
It is shown, to prompt this garage of user to share the number on how many parking stall and remaining parking stall.In the specific embodiment of the invention
In, parking stall guide device 40 may be disposed among Entrance or parking garage entrances either garage parking and other eye-catching positions
It sets, so that car owner can conveniently see comprising memory module, control module and display module, wherein display module can be with
For a display screen, the information of number for showing total space and empty parking space, memory module is for storing total space and number of empty spaces
Mesh information simultaneously keeps updating, and further, parking stall guide device 40 can be divided into indoor guide device and entry pilot device two
Point, indoor guide device is for guiding vehicle to travel to garage parking, and entry pilot device is for showing garage total space and empty wagons
Bits number, display screen herein includes but not limited to CRT monitor, LCD display, light-emitting diode display, 3D display device, controls mould
The microcontroller that block uses includes but not limited to 51 series monolithics, MSP series monolithics, STM series monolithics etc..
Preferably, a kind of parking stall guiding of the present invention and reverse vehicle searching system further include reverse car seeking device 50, for receiving
The parking information that system controller 30 is sent, and user is provided and is inquired, and provide and seek vehicle best route, it is anti-to realize
To seeking vehicle purpose.In the specific embodiment of the invention, reverse car seeking device includes a local data base, main control module and many
In one inquiry terminal, the local data base is for storing the parking information sent from system controller, including car plate
Information, corresponding garage and subarea number and temporal information etc., main control module respectively with local data base and inquiry terminal
Connection, main control module include data memory module, and built-in car park areas map is the control centre of entire subsystem, master control
Module is stored in inside data memory module by transferring the information in local data base, inquiry terminal include input module and
Print out equipment, wherein input module are keyboard or touch screen, and the quantity of inquiry terminal setting can be adjusted arbitrarily, generally be set
It sets and enters parking lot only way which must be passed in personnel such as the lift ports, stairs port, hall of building, by calling in data memory module
Information of vehicles and electronic map, the exact position of vehicle is shown on the screen, and indicate and seek vehicle best route, to realize
Intelligent reverse car seeking function.That is, when motorist returns and picks up the car, only license plate number need to be inputted in inquiry terminal, system is just
Auto-matching can be carried out, vehicle exact position and best pick-up route are illustrated in terminal, car owner is made to be quickly found out oneself
Vehicle, the car seeking route of inquiry can select to print out.Preferably, reverse car seeking device can also be connected to cloud by Ethernet
Server is held, in order to carry out unitized management.
Fig. 5 is the assembly connecting mode schematic diagram of the specific embodiment of the invention.Fig. 6 is the application of the specific embodiment of the invention
Outdoor scene schematic diagram.Fig. 6 is a parking lot vertical view in the embodiment of the present invention, including many garage parking A, B, C ..., each garage parking
It is divided into multiple subregions (such as A1, A2 ... A 50), includes more than two parking stalls (subregion stopping of including per sub-regions
Parking stall number is fewer, and accuracy is higher) two fish-eye cameras are placed in each garage parking, the visual angle of each fish-eye camera is
180 degree, so that 100% covering is realized in sampling, while the present invention can also be combined with the existing CATV cameras in this garage, and combination is adopted
Collect image pattern.
After vehicle enters parking lot, under the guiding of parking stall direction board (parking stall guide device), some garages (such as
Garage A) before stop and drive into garage and start to stop, garage inlet by Car license recognition device (Car license recognition unit) collecting vehicle
License board information, current time and garage number information are stored in built in Car license recognition device by board information and temporal information
In memory and it is sent to system controller, then, some region that vehicle drives into garage parking A (is opened on the parking stall of (such as A1)
Begin parking, as the subregion (A1) where fish-eye camera identifies vehicle, and by last time capture license board information, when
The subarea number information (A1) of preceding temporal information and garage is sent to system controller, while fish-eye camera and CATV have
Line television camera constantly detects current garage parking residue parking stall and quantity is kept to update, by the empty parking space of temporal information and garage
Information of number sends system controller to, if examined in a period of time end after fish-eye camera last time captures the time
Measure the change of empty parking space quantity, you can judge that the vehicle stops in certain sub-regions in this garage.System controller is logical
It is analysis integrated to cross the information progress that reception fish-eye camera and Car license recognition device send over, you can to show that vehicle stops currently
It stops in some parking subregion (such as A1) of garage A, finally by system controller by analysis result, the car plate of some vehicle
Number and some corresponding garage parking and parking subarea number information be sent to and seek cart subsystem service terminal, data information with
Scheduled format is stored in the memory for seeking cart subsystem terminal built-in such as：(A, A1, Zhejiang B999AA), terminal keep information more
Newly；It, can be where the inquiry terminal of reverse car seeking device inputs the information inquiries to vehicle such as license plate number when user needs to pick up the car
Region, the main control module of reverse car seeking device directly can transfer the data of storage after receiving instruction in data memory module, and
It is shown on the display screen of inquiry terminal, with map label or area marking, shows the position of vehicle, and programme path.Vehicle
The main instruction by map and guiding measure selects best route to find vehicle, to realize intelligent reverse car seeking function.
Fig. 7 is the step flow chart of a kind of parking stall guiding of the present invention and reverse car seeking method.As shown in fig. 7, the present invention one
The guiding of kind parking stall and reverse car seeking method, include the following steps：
Step 701, enter garage parking using parking stall guide means guide vehicle, acquisition enters the vehicle vehicle in current garage parking
Board information and temporal information are simultaneously stored, while by collected vehicle license plate information, temporal information and corresponding vehicle
Library information is sent to system controller；In the specific embodiment of the invention, this step can be imaged by being arranged in parking garage entrances
Device is realized, that is, when vehicle enters the garage parking by entrance, using the image information of the photographic device collection vehicle, and
The temporal information that current vehicle enters is recorded, the characters on license plate string letter that image procossing obtains vehicle is carried out by the image to acquisition
Breath, by the license board information and temporal information of acquisition, such as " Zhejiang B999AA " " 15:24 " are stored, and are sent to system controller,
Here garage information refers to the number in garage parking, that is to say, that in the specific embodiment of the invention, parking lot can be with
Including the photographic device is arranged in multiple garage parkings, such as garage parking A, B, C ..., the entrance in each garage parking, sailed when there is vehicle
Fashionable, license board information, the temporal information of vehicle are driven into acquisition, and by the license board information of collected vehicle, temporal information and
Garage number is sent to system controller.
Step 702, the parking stall image information in garage parking is acquired in real time using parking space-detecting device, according to parking stall figure
As the processing of information obtains the remaining parking stall information of number in current garage parking, and by the remaining parking stall information of number and phase of acquisition
The temporal information answered is sent to system controller and parking stall guide device.In the specific embodiment of the invention, parking stall detection dress
It sets and may be disposed at inner part of parking lot, such as parking lot centre position, (each fish-eye camera regards using two fish-eye cameras
Angle is 180 degree, so that 100% covering is realized in sampling) it detects current garage parking residue empty parking space and quantity is kept to update, by the time
Information and the empty parking space information of number in garage send system controller to.Preferably, in step 702, garage can also be utilized
Existing CATV cameras, acquisition image pattern are combined with fish-eye camera, that is, utilize two fish-eye cameras and CATV wired
Television camera detects current garage parking residue parking stall and quantity is kept to update, and temporal information and the empty parking space number in garage are believed
Breath sends system controller to.
Preferably, in step 702, after driving into garage parking in vehicle, also it can go out vehicle institute by acquiring image recognition
Subregion in garage, and the license board information of collection vehicle, by the collected license board information of last time, current temporal information
And the subarea number information in garage is sent to system controller.That is, in the specific embodiment of the invention, one is stopped
Parking lot includes multiple garage parkings, and each garage parking is divided into as several subregions, includes more than two parking stalls per sub-regions
(the parking stall number that subregion includes is fewer, and accuracy is higher) places two fish-eye cameras, Mei Geyu in each garage parking
The visual angle of Eye imaging head is 180 degree, so that 100% covering is realized in sampling, starts to stop after vehicle drives into the garage parking, by this
Two fish-eye cameras identify the subregion where vehicle, and last time is captured license board information, the current time
Information and the subarea number information in garage are sent to system controller.
Step 703, system controller carries out comprehensive analysis according to the information that step 701 and step 702 receive, and determines vehicle
Parking information.Such as after receiving the license board information, temporal information and garage number information of step 701 transmission,
The change that the remaining empty parking space quantity in the garage of step 702 transmission is received in a period of time end, then can determine whether out the vehicle
It stops in the garage, and determines the parking information of the vehicle, such as license plate number, corresponding garage parking and temporal information.Compared with
Goodly, if system controller also receives license board information, the letter of current time that the last time sent in step 702 is captured
The subarea number information of breath and garage detects remaining sky then after last time captures the time in a period of time end
The change of parking stall quantity, you can judge that the vehicle stops in the subregion in this garage, determines the parking information of the vehicle,
The license plate number of the vehicle and corresponding garage parking and garage parking subarea number information.
Fig. 8 is the step flow chart of the parking space detection method of aforementioned parking space-detecting device of the invention., the present invention's
Parking space detection method includes the following steps：
Step 801, the video data that parking stall in garage parking is obtained by fish-eye camera, further, in step
801, video data is also obtained by the existing CATV cameras in garage.
Step 802, distortion correction is carried out to fish-eye camera the image collected data.Step 802 further comprises：
Step 8021, the pixel coordinate of fish eye images is converted to the pixel on corresponding position：If fish-eye camera acquires
The pixel coordinates of fish eye images be (x1, y1), coordinate conversion is carried out to the pixels (x1, y1) of fish eye images, by image coordinate
Origin moves to picture centre from the image upper left corner, obtains the pixel (x2, y2) of the transformed fish eye images of coordinate；
Step 8022, the image after fish eye images distortion correction is denoted as target image, to the pixel coordinate of target image
The amendment on both horizontally and vertically is carried out, and the coordinate origin of the target image after pixel correction is transferred to target image
The upper left corner is obtained by the transformed target image pixel of coordinate system.Assuming that certain pixel is (x3, y3) on target image, it is right
The pixel (x3, y3) of the target image of hypothesis carries out the amendment on both horizontally and vertically.By the target after pixel correction
The coordinate origin of image is transferred to the upper left corner of target image, obtain by the transformed target image pixel of coordinate system (x4,
y4)；
Step 8023, it is used for according to the imaging law of pin-hole imaging model and the imaging characteristics of flake imaging model, it will
Target image after coordinate modification is mapped to the fish eye images under panorama picture of fisheye lens model, that is, carries out rectangular co-ordinate and polar coordinates
Conversion, and then the target image after being corrected according to fish eye images；
Step 8024, the mapping relations obtained according to step 8023 correct the fish eye images of subsequent acquisition；
Step 8025, the image after distortion correction is completed into row interpolation to fish eye images, obtains the image after final process.
Step 803, the coordinate on parking stall is demarcated.In the specific embodiment of the invention, step 803 is using such as lower section
Method demarcates the coordinate to parking stall：
Background image of the width without vehicle is selected, gray level image is converted into after pretreatment；
Video image is extracted from the video data of monitoring, chooses several as training dataset, the Background with extraction
As carrying out self study, the region often changed is set as parking area, completes the calibration of parking stall coordinate.
Step 804, it is extracted for the image to unicom region parking stall.Specifically, step 804 further comprises：
Step 8041, it is foreground image to choose testing image, and a pair is background image without vehicle image, by foreground image and the back of the body
Scape image seeks difference image after median filter process；
Step 8042, binaryzation is carried out to difference image using one-dimensional maximum variance between clusters；
Step 8043, become background for unicom region area to be less than to the region of set threshold value.Of the invention specific
In embodiment, selection mark of the three-dimensional Otsu methods using the maximum between-cluster variance of target and background as threshold value based on decomposition is used
Standard realizes the segmentation i.e. target detection of image by the gamma characteristic of image；
Step 8044, neighbouring unicom region is merged；
Step 8045, after repeatedly learning parking stall is identified using figure.
Step 805, parking stall is divided into several sub-regions, and distributes different weights and is asked to handle blocking for parking stall
Topic；Specifically, the parking stall being identified is again divided into several subregions, and different power is distributed to per sub-regions
Weight, the weights distributed close to the region of neighbouring parking stall are less than the weights far from neighbouring parking stall.
Step 806, judge whether blocked on parking stall according to step 805, if there is blocking, then illustrate that parking stall is occupied
With parking stall is not sky, if unobstructed, illustrates that parking stall is unoccupied, and parking stall is sky.
Specifically, step 806 further comprises：
The ratio shared by each target is sought by threshold classification device：
If aP is final threshold value, if the target ratio detected is more than set threshold value aP, that is, illustrate the parking stall
It is occupied, otherwise, it is considered as the free time；Wherein a is in the learning process of training dataset according to priori by learning automatically really
It is fixed.
It is the emulation experiment of the application present invention below：The internets CS-C6P-7A3WFR type CMOS panorama is regarded using Haikang prestige
Fish eye camera, 3,000,000 pixel camera lenses, detecting distance reach 30m, it can be achieved that a wide range of image sampling, using automatic Car license recognition
System, the Car license recognition camera of 2,000,000 pixels, high brightness lattice LED display screen.The development environment that parking stall recognizer is selected is
Matlab, application scenarios are parking garage, the monitor video image of experimental data source Mr. Yu's cell underground parking, from stopping
The monitoring area in parking lot has chosen the monitoring image of two scenes, as shown in Fig. 9 (A), Fig. 9 (B), stops comprising 6 in scene one
Parking stall includes 3 parking stalls in scene two, extracts the monitoring image of 3026 scenes one from 7 days monitor videos, 2255
The monitoring image of scene two is as data set.
The processing of fish eye images distortion correction is known using the image change path curve analysis based on SVM, SVM with other patterns
Other method is very different, it shows prodigious advantage in solving the problems, such as small sample, non-linear and high dimensional pattern identification,
Since fish eye images are different in the distortion degree of different zones.By the extraction to each region angle point, can establish
The curve model in effective image change path, obtains the parameter of curve, by establish the picture point in space coordinates with its
Mapping relations on the plane of delineation between picture point convert flake fault image to flat image output.Effect is as shown in Figure 10.
In conclusion a kind of parking stall guiding of the present invention and reverse vehicle searching system and its parking space-detecting device, method, pass through
Garage parking is divided into several subregions and carries out license plate image acquisition, is examined by parking stall in inlet Car license recognition unit and garage
The acquisition information of device is surveyed to integrate the parking subregion of determining vehicle, greatly reduces the quantity of Car license recognition unit, is reduced
Cost, and improve user and find the efficiency of free parking space in parking lot, while improving the pick-up efficiency of user.
Compared with prior art, the invention has the advantages that：
1, the present invention carries out license plate image acquisition by the way that garage parking is divided into several subregions, passes through inlet Car license recognition
The combination of fish-eye camera is to determine the parking subregion of vehicle in unit and garage, and is incited somebody to action by power carrier or wireless mode
Various components connect, and present invention substantially reduces the quantity of Car license recognition unit, can not only reduce cost, but also can be with
Simplify installation and wiring, realizes relatively simple.
2, the present invention inquires terminal using reverse car seeking, can solve time and essence that car owner is wasted when picking up the car back and forth
Power problem.
3, comprehensive cover may be implemented using fish-eye camera and cable television camera combination acquisition image in the present invention
Lid, using flake distorted image correction, shows prodigious excellent in solving the problems, such as small sample, non-linear and high dimensional pattern identification
Gesture detects empty parking space using the present invention, has efficiently, the high advantage of accuracy rate indicates parking stall shape without using parking stall indicator light
State further reduces the cost.
4, full-automatic shutdown system may be implemented in the present invention, realizes unmanned management, and can be connected by Ethernet
To cloud server, in order to carry out unitized management to each parking lot.
5, the present invention can obtain the comprehensive without dead of parking lot by the combination of fish-eye camera and CATV television systems
Angle panorama sketch realizes the Intellectualized monitoring to entire parking lot.
6, present invention can apply to the management on parking stall in ultra-large type parking lot.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.Any
Field technology personnel can without violating the spirit and scope of the present invention, and modifications and changes are made to the above embodiments.Therefore,
The scope of the present invention, should be as listed in the claims.
Claims (10)
1. a kind of parking space-detecting device, including：
Video image acquisition unit, the video data for obtaining parking stall in garage parking by fish-eye camera；
Image correction unit, for carrying out distortion correction to fish-eye camera the image collected data；
Parking stall coordinate demarcates unit, for being demarcated to the coordinate on parking stall according to the image after distortion correction；
Parking stall image extraction unit is extracted for the image to unicom region parking stall；
Processing unit is blocked in parking stall, for parking stall to be divided into several sub-regions, and distributes different weights to handle vehicle
The occlusion issue of position；
Parking stall identifying processing unit, the handling result for blocking processing unit according to parking stall judge whether there is vehicle on parking stall.
2. a kind of parking space-detecting device as described in claim 1, which is characterized in that image correction unit further comprises：
Fish eye images image coordinate cutting unit is picture centre for the pixel coordinate of fish eye images to be converted to coordinate origin
Pixel coordinate on position；
Target image image coordinate cutting unit, for the image after fish eye images distortion correction to be denoted as target image, to mesh
The pixel coordinate of logo image carries out the amendment on both horizontally and vertically, and by the coordinate origin of the target image after pixel correction
It is transferred to the upper left corner of target image, is obtained by the transformed target image pixel of coordinate system；
Map unit is used for according to the imaging law of pin-hole imaging model and the imaging characteristics of flake imaging model, by coordinate
Revised target image is mapped to the fish eye images under panorama picture of fisheye lens model, and then after obtaining correction according to fish eye images
Target image；
Correcting unit, the mapping relations obtained according to the map unit correct the fish eye images of acquisition；
Interpolation process unit, for fish eye images to be completed with the image after distortion correction into row interpolation, after obtaining final process
Image.
3. a kind of parking space-detecting device as described in claim 1, which is characterized in that the parking stall image extraction unit is into one
Step includes：
Difference image acquiring unit is foreground image for choosing testing image, and a pair is background image without vehicle image, by foreground
Image after median filter process, seeks difference image with background image；
Binary conversion treatment unit, for carrying out binaryzation to the difference image；
Image segmentation unit, the region for unicom region area to be less than to set threshold value become background；
Combining unit, for merging neighbouring unicom region；
Extraction unit identifies parking stall after repeatedly learning using figure.
4. a kind of parking space-detecting device as described in claim 1, it is characterised in that：It blocks processing unit and will mark in the parking stall
Know parking stall out and be again divided into several subregions, and different weights is distributed to per sub-regions, close to neighbouring parking stall
The weights of region distribution be less than the weights far from neighbouring parking stall.
5. a kind of parking space detection method of parking space-detecting device as described in claim 1, includes the following steps：
Step 1 obtains the video data on parking stall in garage parking by fish-eye camera；
Step 2 carries out distortion correction to fish-eye camera the image collected data；
Step 3 demarcates the coordinate on parking stall according to the image after correction；
Step 4 extracts the image on unicom region parking stall；
Parking stall is divided into several sub-regions by step 5, and distributes different weights to handle the occlusion issue of parking stall；
Step 6 judges whether there is vehicle on parking stall according to the handling result of step 5.
6. parking stall guiding and the reverse vehicle searching system of a kind of application parking space-detecting device as described in claim 1, including：
Car license recognition unit for acquiring vehicle license plate information and temporal information into current garage parking, and will collect
Vehicle license plate information, temporal information and corresponding garage information be sent to system controller；
Parking space-detecting device, for acquiring the parking stall image information in garage parking in real time, according to the place to parking stall image information
Reason obtains the remaining parking stall information of number in current garage parking, and the remaining parking stall information of number of acquisition and corresponding time are believed
Breath is sent to system controller and parking stall guide device；
System controller, the information sent according to the Car license recognition unit and parking space-detecting device received carry out comprehensive point
Analysis, determines the parking information of vehicle；
Parking stall guide device, the parking stall information of number sent for receiving the parking space-detecting device, and according to reception
Information outputting parking position parking condition.
7. a kind of parking stall guiding as claimed in claim 6 and reverse vehicle searching system, it is characterised in that：The parking stall detection dress
It sets and garage parking is divided into several subregions, after vehicle drives into garage parking, go out vehicle place garage by acquiring image recognition
Subregion, and the license board information of collection vehicle, by the collected license board information of last time, current temporal information and garage
Subarea number information be sent to the system controller.
8. a kind of parking stall guiding as claimed in claims 6 or 7 and reverse vehicle searching system, it is characterised in that：The system control
Device stops after receiving the license board information, temporal information and garage number information of the Car license recognition unit transmission or in described
Stall testing apparatus last time is captured to after license board information, detects the remaining number of empty spaces in corresponding garage whithin a period of time
The change of amount then judges that the vehicle stops in the subregion in current garage or current garage, obtains the parking information of the vehicle.
9. a kind of parking stall guiding as claimed in claim 6 and reverse vehicle searching system, it is characterised in that：The system also includes anti-
To car finding device, the parking information sent for receiving the system controller, and user is provided and carries out vehicle query, it carries
For seeking vehicle best route, to realize reverse car seeking purpose.
10. a kind of parking stall guiding and reverse car seeking method, include the following steps：
Step 1 enters garage parking using parking stall guide means guide vehicle, and the vehicle license plate that acquisition enters current garage parking is believed
Breath and temporal information, and collected vehicle license plate information, temporal information and corresponding garage information are sent to system
Controller；
Step 2 acquires the parking stall image information in garage parking using parking space-detecting device in real time, believes according to parking stall image
The processing of breath obtains the remaining parking stall information of number in current garage parking, and by the remaining parking stall information of number of acquisition and accordingly
Temporal information is sent to system controller and parking stall guide device；
Step 3, the system controller carry out comprehensive analysis according to the information that step 1 and step 2 receive, determine vehicle
Parking information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810218914.3A CN108320575A (en) | 2018-03-16 | 2018-03-16 | A kind of guiding of parking stall and reverse vehicle searching system and its parking space-detecting device, method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810218914.3A CN108320575A (en) | 2018-03-16 | 2018-03-16 | A kind of guiding of parking stall and reverse vehicle searching system and its parking space-detecting device, method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108320575A true CN108320575A (en) | 2018-07-24 |
Family
ID=62898831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810218914.3A Pending CN108320575A (en) | 2018-03-16 | 2018-03-16 | A kind of guiding of parking stall and reverse vehicle searching system and its parking space-detecting device, method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108320575A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109087523A (en) * | 2018-07-27 | 2018-12-25 | 上海与德通讯技术有限公司 | A kind of parking method and server |
| CN109785354A (en) * | 2018-12-20 | 2019-05-21 | 江苏大学 | A kind of method for detecting parking stalls based on background illumination removal and connection region |
| CN109817013A (en) * | 2018-12-19 | 2019-05-28 | 新大陆数字技术股份有限公司 | Parking stall state identification method and device based on video flowing |
| CN110689761A (en) * | 2019-12-11 | 2020-01-14 | 上海赫千电子科技有限公司 | Automatic parking method |
| CN111524381A (en) * | 2020-03-23 | 2020-08-11 | 深圳市大拿科技有限公司 | Parking position pushing method, device and system and electronic equipment |
| CN111739332A (en) * | 2019-03-25 | 2020-10-02 | 大陆泰密克汽车系统（上海）有限公司 | Parking lot management system |
| CN111754468A (en) * | 2020-06-10 | 2020-10-09 | 深圳南方德尔汽车电子有限公司 | Parking space detection method and device based on projection, computer equipment and storage medium |
| CN112330601A (en) * | 2020-10-15 | 2021-02-05 | 浙江大华技术股份有限公司 | Parking detection method, device, equipment and medium based on fisheye camera |
| CN112950000A (en) * | 2021-02-05 | 2021-06-11 | 中广核工程有限公司 | Nuclear power station material processing method and system, computer equipment and storage medium |
| CN113353067A (en) * | 2021-07-14 | 2021-09-07 | 重庆大学 | Multi-environment detection and multi-mode matching parallel parking path planning system based on panoramic camera |
| CN113503870A (en) * | 2021-07-09 | 2021-10-15 | 姜江 | Vehicle positioning method, system and device based on camera image fingerprint |
| CN114882492A (en) * | 2022-07-11 | 2022-08-09 | 浙江大华技术股份有限公司 | License plate recognition method, device, terminal and computer readable storage medium |
| CN116137109A (en) * | 2023-04-17 | 2023-05-19 | 青岛益合泊朗创新科技有限公司 | Mechanical parking equipment control system and method based on cloud computing |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646342A (en) * | 2012-05-17 | 2012-08-22 | 上海海事大学 | Intelligent guiding and car locating system for parking lot |
| CN203520644U (en) * | 2013-09-06 | 2014-04-02 | 武汉纺织大学 | Parking lot reverse vehicle searching system based on machine vision |
| CN104112370A (en) * | 2014-07-30 | 2014-10-22 | 哈尔滨工业大学深圳研究生院 | Monitoring image based intelligent parking lot parking place identification method and system |
| CN105096653A (en) * | 2015-08-10 | 2015-11-25 | 电子科技大学 | Parking guidance method and parking guidance system |
| CN105206104A (en) * | 2015-11-09 | 2015-12-30 | 乐山师范学院 | Intelligent parking lot management method |
| CN106780374A (en) * | 2016-12-01 | 2017-05-31 | 哈尔滨工业大学 | A kind of fish eye images distortion correction method based on flake imaging model |
| CN106981216A (en) * | 2017-04-11 | 2017-07-25 | 厦门路桥信息股份有限公司 | A kind of ultrasonic wave combination video technique seek the method and system of car |
| CN107154152A (en) * | 2017-06-30 | 2017-09-12 | 深圳信路通智能技术有限公司 | Video stake equipment and parking management method |
-
2018
- 2018-03-16 CN CN201810218914.3A patent/CN108320575A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646342A (en) * | 2012-05-17 | 2012-08-22 | 上海海事大学 | Intelligent guiding and car locating system for parking lot |
| CN203520644U (en) * | 2013-09-06 | 2014-04-02 | 武汉纺织大学 | Parking lot reverse vehicle searching system based on machine vision |
| CN104112370A (en) * | 2014-07-30 | 2014-10-22 | 哈尔滨工业大学深圳研究生院 | Monitoring image based intelligent parking lot parking place identification method and system |
| CN105096653A (en) * | 2015-08-10 | 2015-11-25 | 电子科技大学 | Parking guidance method and parking guidance system |
| CN105206104A (en) * | 2015-11-09 | 2015-12-30 | 乐山师范学院 | Intelligent parking lot management method |
| CN106780374A (en) * | 2016-12-01 | 2017-05-31 | 哈尔滨工业大学 | A kind of fish eye images distortion correction method based on flake imaging model |
| CN106981216A (en) * | 2017-04-11 | 2017-07-25 | 厦门路桥信息股份有限公司 | A kind of ultrasonic wave combination video technique seek the method and system of car |
| CN107154152A (en) * | 2017-06-30 | 2017-09-12 | 深圳信路通智能技术有限公司 | Video stake equipment and parking management method |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109087523A (en) * | 2018-07-27 | 2018-12-25 | 上海与德通讯技术有限公司 | A kind of parking method and server |
| CN109817013A (en) * | 2018-12-19 | 2019-05-28 | 新大陆数字技术股份有限公司 | Parking stall state identification method and device based on video flowing |
| CN109785354A (en) * | 2018-12-20 | 2019-05-21 | 江苏大学 | A kind of method for detecting parking stalls based on background illumination removal and connection region |
| CN111739332B (en) * | 2019-03-25 | 2022-09-23 | 大陆泰密克汽车系统（上海）有限公司 | Parking lot management system |
| CN111739332A (en) * | 2019-03-25 | 2020-10-02 | 大陆泰密克汽车系统（上海）有限公司 | Parking lot management system |
| CN110689761B (en) * | 2019-12-11 | 2021-10-29 | 上海赫千电子科技有限公司 | Automatic parking method |
| CN110689761A (en) * | 2019-12-11 | 2020-01-14 | 上海赫千电子科技有限公司 | Automatic parking method |
| CN111524381B (en) * | 2020-03-23 | 2022-04-15 | 深圳市海雀科技有限公司 | Parking position pushing method, device and system and electronic equipment |
| CN111524381A (en) * | 2020-03-23 | 2020-08-11 | 深圳市大拿科技有限公司 | Parking position pushing method, device and system and electronic equipment |
| CN111754468A (en) * | 2020-06-10 | 2020-10-09 | 深圳南方德尔汽车电子有限公司 | Parking space detection method and device based on projection, computer equipment and storage medium |
| CN112330601A (en) * | 2020-10-15 | 2021-02-05 | 浙江大华技术股份有限公司 | Parking detection method, device, equipment and medium based on fisheye camera |
| WO2022078156A1 (en) * | 2020-10-15 | 2022-04-21 | Zhejiang Dahua Technology Co., Ltd. | Method and system for parking space management |
| CN112330601B (en) * | 2020-10-15 | 2024-03-19 | 浙江大华技术股份有限公司 | Fish-eye camera-based parking detection method, device, equipment and medium |
| CN112950000A (en) * | 2021-02-05 | 2021-06-11 | 中广核工程有限公司 | Nuclear power station material processing method and system, computer equipment and storage medium |
| CN113503870A (en) * | 2021-07-09 | 2021-10-15 | 姜江 | Vehicle positioning method, system and device based on camera image fingerprint |
| CN113353067A (en) * | 2021-07-14 | 2021-09-07 | 重庆大学 | Multi-environment detection and multi-mode matching parallel parking path planning system based on panoramic camera |
| CN114882492A (en) * | 2022-07-11 | 2022-08-09 | 浙江大华技术股份有限公司 | License plate recognition method, device, terminal and computer readable storage medium |
| CN114882492B (en) * | 2022-07-11 | 2022-11-22 | 浙江大华技术股份有限公司 | License plate recognition method, device, terminal and computer readable storage medium |
| CN116137109A (en) * | 2023-04-17 | 2023-05-19 | 青岛益合泊朗创新科技有限公司 | Mechanical parking equipment control system and method based on cloud computing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108320575A (en) | A kind of guiding of parking stall and reverse vehicle searching system and its parking space-detecting device, method | |
| CN105913685A (en) | Video surveillance-based carport recognition and intelligent guide method | |
| CN101739827B (en) | Vehicle detecting and tracking method and device | |
| JP4035910B2 (en) | Car color discrimination device | |
| Peng et al. | Drone-based vacant parking space detection | |
| CN202257707U (en) | Intelligent management system of parking lot | |
| CN102915638A (en) | Surveillance video-based intelligent parking lot management system | |
| CN106355886A (en) | Parking management system for open type parking lot and management method of parking management system | |
| US10824885B2 (en) | Method and apparatus for detecting braking behavior of front vehicle of autonomous vehicle | |
| CN103778786A (en) | Traffic violation detection method based on significant vehicle part model | |
| CN109817013A (en) | Parking stall state identification method and device based on video flowing | |
| CN104134352A (en) | Video vehicle characteristic detection system and detection method based on combination of long exposure and short exposure | |
| CN110781883A (en) | Parking space size identification system and method based on 360-degree all-round-looking camera | |
| CN106251695A (en) | Destination's parking stall intelligent recommendation system and method based on parking space state monitoring | |
| CN112308913B (en) | Vehicle positioning method and device based on vision and vehicle-mounted terminal | |
| CN115797873B (en) | Crowd density detection method, system, equipment, storage medium and robot | |
| CN103646544B (en) | Based on the vehicle behavioural analysis recognition methods of The Cloud Terrace and camera apparatus | |
| CN111967396A (en) | Processing method, device and equipment for obstacle detection and storage medium | |
| CN207909351U (en) | A kind of guiding of parking stall and reverse vehicle searching system | |
| CN105788351A (en) | Intelligent parking lot management system and intelligent parking lot management method based on video images | |
| CN202434068U (en) | Vehicle management system based on wireless sensor network | |
| CN205750537U (en) | AGV Path Recognition device based on coloured image | |
| CN107657832A (en) | A kind of parking stall bootstrap technique and system | |
| CN110473428A (en) | A kind of intelligent parking method, apparatus and system | |
| CN116778450A (en) | Parking space detection model training method, parking space detection method, training device and 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 |
Application publication date: 20180724 |
|
| RJ01 | Rejection of invention patent application after publication |