CN107719361A - Automatic parking householder method and system based on image vision - Google Patents
Automatic parking householder method and system based on image vision Download PDFInfo
- Publication number
- CN107719361A CN107719361A CN201710934516.7A CN201710934516A CN107719361A CN 107719361 A CN107719361 A CN 107719361A CN 201710934516 A CN201710934516 A CN 201710934516A CN 107719361 A CN107719361 A CN 107719361A
- Authority
- CN
- China
- Prior art keywords
- frame
- parking
- motor vehicle
- image
- picture frame
- 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 37
- 238000012545 processing Methods 0.000 claims abstract description 65
- 238000001514 detection method Methods 0.000 claims abstract description 37
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 238000012216 screening Methods 0.000 claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000003708 edge detection Methods 0.000 claims abstract description 7
- 230000000877 morphologic effect Effects 0.000 claims description 22
- 238000005516 engineering process Methods 0.000 claims description 16
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 description 4
- 230000007704 transition Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000007717 exclusion Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 1
- 235000017491 Bambusa tulda Nutrition 0.000 description 1
- 241001330002 Bambuseae Species 0.000 description 1
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 1
- 239000011425 bamboo Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/06—Automatic manoeuvring for parking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The present embodiments relate to a kind of automatic parking householder method based on image vision and system, methods described to include：Gather target area video image；Extraction obtains picture frame frame by frame from video image；Picture frame is analyzed and processed frame by frame, calibrates parking bit line, and the processing specifically includes：Picture frame is pre-processed, rim detection, straight-line detection and preliminary screening just determine parking stall scope, non-targeted disturbing factor in rejection image frame, integrate the analysis processing result of each picture frame.The system includes：Video acquisition module, extraction module and image processing module, image processing module include again：Pretreatment unit, edge detection unit, just stop bit location, exclusive PCR unit and integrated treatment unit surely.The embodiment of the present invention is excluded by analyzing and processing the picture frame of target area frame by frame to non-targeted disturbing factor, so as to detect parking stall exactly, is conveniently realized that motor vehicle automatic stopping enters position, is reduced parking manoeuvres difficulty.
Description
Technical field
The present embodiments relate to automatic parking technical field, more particularly to a kind of automatic parking based on image vision are auxiliary
Aid method and system.
Background technology
Currently, increasingly mature with motor vehicle conventional art, automotive engineering research and development start to send out towards intelligent direction
Exhibition, automated parking system are a focuses of automotive engineering research and development.Automated parking system can allow driver only to need by simple
Operation, it is possible to realize that motor vehicle automatic stopping enters position, reduce parking manoeuvres difficulty.
Complete automated parking system includes parking stall detection module, Track Pick-up module and course changing control module.Wherein,
Parking stall detection module is as one of technological core, the success or failure of the whole automated parking system of relation.
The detection technique that current parking stall detection module uses is roughly divided into following several：Radar for backing car, rear-camera,
Side view shooting etc..This several technology cuts both ways：Though radar for backing car technology can definite judging distance, to the ditch after car,
Elongated rod-shaped thing such as reinforcing bar or bamboo pole of protrusion etc. can not perceive, and most vehicles or obstacle for depending on free parking space both sides
Thing, if the Obstacle Position of parking stall surrounding is very low, radar can not detect, and radar can not be accurate to continuous free parking space
It is determined that position；Rear-camera technology is intuitively true, but information of adjusting the distance can not perceive, it is impossible to provides parking space information, it is impossible to right
Driver guides；Side view camera technique can not obtain the image information of vehicle's surroundings, vision blind spot be present.
The Chinese patent literature of Application No. 201510924119.2 discloses a kind of 360 degree of auxiliary of parking of view-based access control model
Intelligent guidance system, on the basis of 360 degree of panoramic parking systems, utilize image processing algorithm, in a top view detection parking
Position, to the prompting of driver's parking space information, and according to the car detected by the parking space information detected mark on a display screen
Position and the relative position relation of Current vehicle, the optimal parking route of vehicle is calculated, and optimal parking route is labeled in display
On screen, stopping guide information is provided to driver.
But the parking stall detection technique of 360 degree of this view-based access control model auxiliary intelligent guidance systems of parking is not directed to
To the damaged processing of target or the exclusion to interference in actually detected scene, it is impossible to accurately detect parking stall.
The content of the invention
Technical problem to be solved of the embodiment of the present invention is, there is provided a kind of automatic parking auxiliary square based on figure vision
Method, it can accurately detect parking stall.
The further technical problems to be solved of the embodiment of the present invention are, there is provided a kind of automatic parking based on figure vision is auxiliary
Auxiliary system, it can accurately detect parking stall.
In order to solve the above technical problems, the embodiment of the present invention provides following technical scheme first：One kind is based on image vision
Automatic parking householder method, comprise the following steps：
Gather the video image of target area；
Extraction obtains picture frame frame by frame from video image；
Described image frame is analyzed and processed frame by frame, is calibrated parking bit line, is specifically included：
Picture frame is pre-processed, including at least the image to picture frame progress gray processing processing and to carrying out gray processing processing
Frame is filtered processing；
Rim detection is carried out to pretreated picture frame；
Straight-line detection and preliminary screening are carried out, just determines parking stall scope；
The non-targeted disturbing factor in the range of parking stall is just determined in rejection image frame, determines corresponding parking bit line in picture frame；
The analysis processing result of comprehensive each picture frame, demarcates parking stall line in the video image.
Further, it is described that pretreated picture frame progress rim detection is specifically included：
Self-adaption thresholding processing is carried out to described image frame；
The result handled based on Morphological scale-space technology the self-adaption thresholding is modified；
Rim detection is carried out to the result Jing Guo Morphological scale-space technology amendment.
Further, methods described also includes：
Calculated according to motor vehicle current vehicle speed and motor vehicle relative to the position relationship of the parking bit line of demarcation to obtain machine
Motor-car is parked travel route.
Further, the position relationship according to motor vehicle current vehicle speed and motor vehicle relative to the parking bit line of demarcation
Calculated and specifically included with obtaining motor vehicle travel route of parking：
Obtain motor vehicle current vehicle speed；
Determine position relationship of the motor vehicle relative to the parking bit line of demarcation；
Computing is carried out, motor vehicle is obtained and parks travel route.
Further, methods described also includes：
Control motor vehicle along the motor vehicle park travel route traveling, until motor vehicle completely drive into parking bit line in the range of.
On the other hand, the embodiment of the present invention further provides for following technical scheme：A kind of automatic pool based on image vision
Car accessory system, including：
Video acquisition module, for gathering the video image of target area；
Extraction module, for extraction to obtain picture frame frame by frame from video image；
Image processing module, for analyzing and processing described image frame frame by frame, parking bit line is calibrated, is specifically included：
Pretreatment unit, for being pre-processed to picture frame, gray processing processing is carried out and to carrying out including at least to picture frame
The picture frame of gray processing processing is filtered processing；
Edge detection unit, for carrying out rim detection to pretreated picture frame；
Just stop bit location surely, for carrying out straight-line detection and preliminary screening, just determines parking stall scope；
Exclusive PCR unit, for just determining the non-targeted disturbing factor in the range of parking stall in rejection image frame, determine picture frame
In corresponding parking bit line；
Integrated treatment unit, for integrating the analysis processing result of each picture frame, parking stall is demarcated in the video image
Line.
Further, the edge detection unit includes：
Adaptive thresholding subelement, for carrying out self-adaption thresholding processing to described image frame；
Morphological scale-space subelement, the result for being handled based on Morphological scale-space technology the self-adaption thresholding are repaiied
Just；
Rim detection subelement, for carrying out rim detection to the result Jing Guo Morphological scale-space technology amendment.
Further, the system also includes calculating route module, for according to motor vehicle current vehicle speed and motor vehicle phase
Calculated and parked travel route with obtaining motor vehicle for the position relationship of the parking bit line of demarcation.
Further, the calculating route module includes：
Speed unit, for obtaining motor vehicle current vehicle speed；
Position units, for determining position relationship of the motor vehicle relative to the parking bit line of demarcation；
Arithmetic element, for carrying out computing, obtain motor vehicle and park travel route.
Further, the system also includes control and drives module, for controlling motor vehicle to be parked row along the motor vehicle
Route running is sailed, until motor vehicle is completely driven into the range of parking bit line.
After adopting the above technical scheme, the embodiment of the present invention at least has the advantages that：The embodiment of the present invention passes through
The picture frame of target area is analyzed and processed frame by frame, and non-targeted disturbing factor is excluded, it is convenient so as to detect parking stall exactly
Realize that motor vehicle automatic stopping enters position, reduce parking manoeuvres difficulty.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of one alternative embodiment of automatic parking householder method of the present invention.
Fig. 2 is the step S32 schematic flow sheets of one alternative embodiment of automatic parking householder method of the present invention.
Fig. 3 is the schematic flow sheet of one alternative embodiment of automatic parking householder method of the present invention.
Fig. 4 is the step S4 schematic flow sheets of one alternative embodiment of automatic parking householder method of the present invention.
Fig. 5 is the schematic flow sheet of one alternative embodiment of automatic parking householder method of the present invention.
Fig. 6 is the structural representation of one alternative embodiment of automatic parking accessory system of the present invention.
Fig. 7 is the edge detection unit structural representation of real one alternative embodiment of automatic parking accessory system of the present invention.
Fig. 8 is the structural representation of one alternative embodiment of automatic parking accessory system of the present invention.
Fig. 9 is the calculating route module structural representation of real one alternative embodiment of automatic parking accessory system of the present invention.
Figure 10 is the structural representation of real one alternative embodiment of automatic parking accessory system of the present invention.
Embodiment
The application is described in further detail with specific embodiment below in conjunction with the accompanying drawings.It should be appreciated that following signal
Property embodiment and explanation be only used for explaining the application, be not intended as the restriction to the application, moreover, in the case where not conflicting,
The feature in embodiment and embodiment in the application can be combined with each other.
As shown in figure 1, the embodiment of the present invention provides a kind of automatic parking householder method based on image vision first, including
Following steps：
Step S1, the video image of target area is gathered；
Step S2, from video image, extraction obtains picture frame frame by frame；
Step S3, described image frame is analyzed and processed frame by frame, is calibrated parking bit line, is specifically included：
Step S31, picture frame is pre-processed, gray processing processing is carried out and to carrying out at gray processing including at least to picture frame
The picture frame of reason is filtered processing；
Step S32, rim detection is carried out to pretreated picture frame
Step S33, straight-line detection and preliminary screening are carried out, just determines parking stall scope；
Step S34, the non-targeted disturbing factor in the range of parking stall is just determined in rejection image frame, determines corresponding in picture frame stop
Parking stall line；
Step S35, the analysis processing result of comprehensive each picture frame, demarcates parking stall line in the video image.
In a specific embodiment, in step S31, gray processing processing is that coloured image is carried out gray processing processing,
Improve arithmetic speed；Filtering process is a kind of method for strengthening image, can effectively suppress, weaken and smooth various noises, protect
Marginal information is held, the spatial information of prominent image, constrains other irrelevant informations.
And in another specific embodiment, in step S33, Hough straight-line detections and preliminary screening can be used,
The specific method of Hough straight-line detections and preliminary screening is to set between minimum the straight length threshold value thresh1 and straight line of detection
Gap maximum threshold thresh2, if straight length is less than threshold value thresh1, straight line is not considered as, otherwise it is assumed that being straight line；
It is considered as two straight lines if rectilinear clearance is less than threshold value thresh2, is otherwise one.
In another specific embodiment, in step S34, excluding the method for non-targeted disturbing factor includes target breakage
Processing and interference straight line, which exclude, seek each vertical line intersection point and merge average and variance in intersection point and intersection point neighborhood, to be judged.
The damaged processing of target and interference straight line exclude, and are to carry out local exclusion to interference straight line, i.e., are excluded in regional area
The interference of ground texture noise, each pair straight line pair for taking Hough straight-line detections and straight line preliminary screening to confirm on former gray-scale map
Midpoint centered on, straight length be diagonal length local rectangular portions ROI, two methods can be used, method one is to this
Rectangular region image be expert on 1/4,3/4 at horizontal horizontal line on, the gray scale transition value of adjacent pixel is asked for respectively, to meeting
Transition threshold value, write down its position coordinates, and ask for respectively between the two away from；Similarly 1/4,3/4 in image column is vertical perpendicular
On line, seek gray scale transition value, and write down the position coordinates for meeting transition threshold value, ask for respectively on same line between the two away from, if
Two distance values are close and all in target width scope, then it is target to confirm the part, otherwise gives and rejects；Method two is pair
Above-mentioned regional area carries out self-adaption thresholding, then connected component labeling first, less isolated connection block is removed, to remaining
Prospect ration statisticses are done, that is, calculate the ratio value that foreground point accounts for whole local rectangular portions ROI, side then is extracted to binary map
Edge, the horizontal, progressive scan of vertical direction is carried out respectively, ask for threading number, when threading number is 4, show have through two edges
Line, show, through a line edge line, then both horizontally and vertically calculating the length of threading number identical line segment respectively when being 2
Degree, if threading number is 4 or the even number more than 4 and length meet threshold value and when ratio value meets given threshold, confirm the office
Portion is target, otherwise gives and rejects；Processing to parking bit line parts against wear fracture is excluded above-mentioned to the process that detects
All straightways afterwards, by slope is identical, intercept identical condition is clustered, is fitted, obtain that completely there is a fixed length relatively
The parking bit line straightway of degree, next judges whether have, intercept identical with its slope to be separated by the parallel of certain threshold value around it
Straight line pair.
It is the straight line negligible amounts in figure after being rejected by above-mentioned screening to seek each vertical line intersection point and merge intersection point, this
When ask for the intersection point of each vertical line, because parking stall is made up of vertical line, it is true to try to achieve the basic can of all intersection points
Determine the position on parking stall；To very close to multiple intersection points merge.
In intersection point neighborhood average and variance judge be take its neighborhood image and average, variance is judged, reject interference
Intersection point, that is, go unless intersection point corresponding to the line of parking stall.
The present embodiment is excluded by analyzing and processing the picture frame of target area frame by frame to non-targeted disturbing factor, so as to accurate
Parking stall really is detected, conveniently realizes that motor vehicle automatic stopping enters position, reduces parking manoeuvres difficulty.
As shown in Fig. 2 in the alternative embodiment of the present invention, the step S32 is specifically included：
Step S321, self-adaption thresholding processing is carried out to described image frame；
Step S322, the result handled based on Morphological scale-space technology the self-adaption thresholding is modified；
Step S323, rim detection is carried out to the result Jing Guo Morphological scale-space technology amendment.
The self-adaption thresholding is a kind of method that adaptive threshold value determines, it is the gamma characteristic by image, will
Figure is divided into background and target two parts, and the inter-class variance between background and target is bigger, illustrates the two-part of pie graph picture
Difference is bigger, when partial target mistake is divided into background or part background mistake is divided into target and all two parts difference can be caused to diminish, makes class
Between the maximum segmentation of variance mean misclassification probability minimum, effect is to realize the binarization segmentation of image, is stopped in present invention application
Parking stall line is significantly to be marked relatively on ground, and parking stall line target shows as the foreground area of image after thresholding, main to make
With being the binarization segmentation of realizing image.
The Morphological scale-space includes being used for eliminating isolated wisp, separating objects, smooth larger object at very thin point
The opening operation on border and the closed operation for filling minuscule hole, linking adjacent object, its smooth border, Morphological scale-space performance
For a kind of neighborhood operation form, construction unit region corresponding with bianry image carries out specific logic on each location of pixels
Computing, the result of logical operation are the respective element of output image, and its effect is depending on the size of construction unit, content and patrols
The property of computing is collected, main function is to be partitioned into target, and Morphological scale-space effect is to be partitioned into target.
The present embodiment is handled by self-adaption thresholding and Morphological scale-space, can be effectively by the rim detection for the bit line that stops
Out.
As shown in figure 3, in the alternative embodiment of the present invention, methods described also includes：
Step S4, according to motor vehicle current vehicle speed and motor vehicle relative to the position relationship of the parking bit line of demarcation calculated with
Motor vehicle is obtained to park travel route.
The present embodiment obtains travel route of accurately parking by calculating, so as to conveniently realize motor vehicle automatic stopping
Enter position, reduce parking manoeuvres difficulty.
As shown in figure 4, in the alternative embodiment of the present invention, the step S4 is specifically included：
Step S41, motor vehicle current vehicle speed is obtained；
Step S42, position relationship of the motor vehicle relative to the parking bit line of demarcation is determined；
Step S43, computing is carried out, motor vehicle is obtained and parks travel route.
The present embodiment determines position of the motor vehicle relative to the parking bit line of demarcation by obtaining motor vehicle current vehicle speed
Relation, motor vehicle can be obtained so as to carrying out computing and parked travel route, accurate travel route is obtained, conveniently realize motor vehicle
Automatic stopping enters position, reduces parking manoeuvres difficulty.
As shown in figure 5, in the alternative embodiment of the present invention, methods described also includes：
Step S5, motor vehicle is controlled to be parked travel route traveling along the motor vehicle, until motor vehicle completely drives into parking bit line
In the range of.
The present embodiment by control motor vehicle along calculate obtain the motor vehicle park travel route travel, can be automatic
Change realizes that motor vehicles parking enters position, reduces the influence of human factor, reduces parking manoeuvres difficulty, and can more accurately realize
Parking.
As shown in fig. 6, on the other hand, the embodiment of the present invention also provides a kind of automatic parking auxiliary system based on image vision
System, including：
Video acquisition module 1, for gathering the video image of target area；
Extraction module 2, for extraction to obtain picture frame frame by frame from video image；
Image processing module 3, for analyzing and processing described image frame frame by frame, parking bit line is calibrated, is specifically included：
Pretreatment unit 31, for being pre-processed to picture frame, gray processing processing is carried out and to entering including at least to picture frame
The picture frame of row gray processing processing is filtered processing；
Edge detection unit 32, for carrying out rim detection to pretreated picture frame；
Just stop bit location 33 surely, for carrying out straight-line detection and preliminary screening, and just determines parking stall scope；
Exclusive PCR unit 34, for just determining the non-targeted disturbing factor in the range of parking stall in rejection image frame, determine image
Corresponding parking bit line in frame；
Integrated treatment unit 35, for integrating the analysis processing result of each picture frame, parking is demarcated in the video image
Bit line.
The embodiment of the present invention analyzes and processes the picture frame of target area by image processing module 3 frame by frame, to non-targeted dry
Factor exclusion is disturbed, so as to accurately detect parking stall, realizes that motor vehicle automatic stopping enters position, reduces parking manoeuvres difficulty.
As shown in fig. 7, in the alternative embodiment of the present invention, the edge detection unit 32 includes：
Adaptive thresholding subelement 321, for carrying out self-adaption thresholding processing to described image frame；
Morphological scale-space subelement 322, for being repaiied based on Morphological scale-space technology to the result of the self-adaption thresholding
Just；
Rim detection subelement 323, for carrying out rim detection to the result Jing Guo Morphological scale-space technology amendment.
The embodiment of the present invention is carried out respectively by adaptive thresholding subelement 321 and Morphological scale-space subelement 322
Self-adaption thresholding processing and Morphological scale-space, can effectively be detected according to the result of self-adaption thresholding and Morphological scale-space
The edge of parking bit line.
As shown in figure 8, in the alternative embodiment of the present invention, the system also includes calculating route module 4, for root
Calculated according to motor vehicle current vehicle speed and motor vehicle relative to the position relationship of the parking bit line of demarcation to obtain motor vehicle pool
Car travel route.
The present embodiment calculates the accurate travel route of parking of acquisition by calculating route module 4, is realized so as to convenient
Motor vehicle automatic stopping enters position, reduces parking manoeuvres difficulty.
As shown in figure 9, in the alternative embodiment of the present invention, the calculating route module 4 includes：
Speed unit 41, for obtaining motor vehicle current vehicle speed；
Position units 42, for determining position relationship of the motor vehicle relative to the parking bit line of demarcation；
Arithmetic element 43, for carrying out computing, obtain motor vehicle and park travel route.
The embodiment of the present invention by speed unit 41 obtain motor vehicle current vehicle speed, such as can using CAN processing modules come
Motor vehicle current vehicle speed is obtained as speed unit 41, then parking stall of the motor vehicle relative to demarcation is determined by position units 42
The position relationship of line, obtain motor vehicle finally by arithmetic element 43 and park travel route, obtain accurate travel route, it is convenient
Realize that motor vehicle automatic stopping enters position, reduce parking manoeuvres difficulty.
As shown in Figure 10, in an alternative embodiment of the invention, the system also includes control and drives module 5, is used for
Control motor vehicle along the motor vehicle park travel route traveling, until motor vehicle completely drive into parking bit line in the range of.
The present embodiment drives module 5 by control and travels road to control motor vehicle to be parked along the motor vehicle for calculating acquisition
Line travels, and can automate and realize that motor vehicles parking enters position, reduce the influence of human factor, reduce parking manoeuvres difficulty, and
And it can more accurately realize parking.
In the alternative embodiment of the present invention, the system also includes display device, for showing captured video
Image and the parking bit line and motor vehicle demarcated are parked travel route, real for driver by providing clearly image information
When check that auxiliary is parked circuit and process.
If the function described in the embodiment of the present invention is realized in the form of software function module or unit and as independent
Production marketing in use, can be stored in a computing device read/write memory medium.Based on such understanding, the present invention
The part or the part of the technical scheme that embodiment contributes to prior art can be embodied in the form of software product
Come, the software product is stored in a storage medium, including some instructions are causing a computing device（Can be personal
Computer, server, mobile computing device or network equipment etc.）Perform each embodiment methods described of the present invention whole or
Part steps.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage（ROM, Read-Only Memory）、
Random access memory（RAM, Random Access Memory）, magnetic disc or CD etc. are various can be with store program codes
Medium.Each embodiment is described by the way of progressive in this specification, and what each embodiment stressed is and other realities
Apply the difference of example, between each embodiment same or similar part mutually referring to.
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of changes, modification can be carried out to these embodiments, replace without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention are limited by appended claims and its equivalency range.
Claims (10)
1. a kind of automatic parking householder method based on image vision, it is characterised in that comprise the following steps：
Gather the video image of target area；
Extraction obtains picture frame frame by frame from video image；
Described image frame is analyzed and processed frame by frame, is calibrated parking bit line, is specifically included：
Picture frame is pre-processed, including at least the image to picture frame progress gray processing processing and to carrying out gray processing processing
Frame is filtered processing；
Rim detection is carried out to pretreated picture frame；
Straight-line detection and preliminary screening are carried out, just determines parking stall scope；
The non-targeted disturbing factor in the range of parking stall is just determined in rejection image frame, determines corresponding parking bit line in picture frame；
The analysis processing result of comprehensive each picture frame, demarcates parking stall line in the video image.
2. the automatic parking householder method based on image vision as claimed in claim 1, it is characterised in that described pair of pretreatment
Picture frame afterwards carries out rim detection and specifically included：
Self-adaption thresholding processing is carried out to described image frame；
The result handled based on Morphological scale-space technology the self-adaption thresholding is modified；
Rim detection is carried out to the result Jing Guo Morphological scale-space technology amendment.
3. the automatic parking householder method based on image vision as claimed in claim 1, it is characterised in that methods described is also wrapped
Include：
Calculated according to motor vehicle current vehicle speed and motor vehicle relative to the position relationship of the parking bit line of demarcation to obtain machine
Motor-car is parked travel route.
4. the automatic parking householder method based on image vision as claimed in claim 3, it is characterised in that described according to motor-driven
Car current vehicle speed and motor vehicle are calculated relative to the position relationship of the parking bit line of demarcation is parked traveling with obtaining motor vehicle
Route specifically includes：
Obtain motor vehicle current vehicle speed；
Determine position relationship of the motor vehicle relative to the parking bit line of demarcation；
Computing is carried out, motor vehicle is obtained and parks travel route.
5. the automatic parking householder method based on image vision as described in claim 3 or 4, it is characterised in that methods described
Also include：
Control motor vehicle along the motor vehicle park travel route traveling, until motor vehicle completely drive into parking bit line in the range of.
6. a kind of automatic parking accessory system based on image vision, it is characterised in that the system includes：
Video acquisition module, for gathering the video image of target area；
Extraction module, for extraction to obtain picture frame frame by frame from video image；
Image processing module, for analyzing and processing described image frame frame by frame, parking bit line is calibrated, is specifically included：
Pretreatment unit, for being pre-processed to picture frame, gray processing processing is carried out and to carrying out including at least to picture frame
The picture frame of gray processing processing is filtered processing；
Edge detection unit, for carrying out rim detection to pretreated picture frame；
Just stop bit location surely, for carrying out straight-line detection and preliminary screening, just determines parking stall scope；
Exclusive PCR unit, for just determining the non-targeted disturbing factor in the range of parking stall in rejection image frame, determine picture frame
In corresponding parking bit line；
Integrated treatment unit, for integrating the analysis processing result of each picture frame, parking stall is demarcated in the video image
Line.
7. the automatic parking accessory system based on image vision as claimed in claim 6, it is characterised in that the rim detection
Unit includes：
Adaptive thresholding subelement, for carrying out self-adaption thresholding processing to described image frame；
Morphological scale-space subelement, the result for being handled based on Morphological scale-space technology the self-adaption thresholding are repaiied
Just；
Rim detection subelement, for carrying out rim detection to the result Jing Guo Morphological scale-space technology amendment.
8. the automatic parking accessory system based on image vision as claimed in claim 6, it is characterised in that the system is also wrapped
Calculating route module is included, for entering according to motor vehicle current vehicle speed and motor vehicle relative to the position relationship of the parking bit line of demarcation
Row calculates is parked travel route with obtaining motor vehicle.
9. the automatic parking accessory system based on image vision as claimed in claim 8, it is characterised in that the calculating route
Module includes：
Speed unit, for obtaining motor vehicle current vehicle speed；
Position units, for determining position relationship of the motor vehicle relative to the parking bit line of demarcation；
Arithmetic element, for carrying out computing, obtain motor vehicle and park travel route.
10. the automatic parking accessory system based on image vision as claimed in claim 8 or 9, it is characterised in that the system
Also include control and drive module, for controlling motor vehicle to be parked travel route traveling along the motor vehicle, until motor vehicle is complete
Drive into the range of parking bit line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710934516.7A CN107719361A (en) | 2017-10-10 | 2017-10-10 | Automatic parking householder method and system based on image vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710934516.7A CN107719361A (en) | 2017-10-10 | 2017-10-10 | Automatic parking householder method and system based on image vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107719361A true CN107719361A (en) | 2018-02-23 |
Family
ID=61208725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710934516.7A Pending CN107719361A (en) | 2017-10-10 | 2017-10-10 | Automatic parking householder method and system based on image vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107719361A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110390306A (en) * | 2019-07-25 | 2019-10-29 | 湖州宏威新能源汽车有限公司 | Detection method, vehicle and the computer readable storage medium of right angle parking stall |
| WO2020001347A1 (en) * | 2018-06-29 | 2020-01-02 | 比亚迪股份有限公司 | Automatic parking method, apparatus and system, and vehicle |
| CN110879947A (en) * | 2018-09-06 | 2020-03-13 | 山东理工大学 | Real-time human face three-dimensional measurement method based on one-time projection structured light parallel stripe pattern |
| CN111507158A (en) * | 2019-01-31 | 2020-08-07 | 斯特拉德视觉公司 | Method and device for detecting parking area by semantic segmentation |
| CN111508260A (en) * | 2019-01-30 | 2020-08-07 | 上海欧菲智能车联科技有限公司 | Vehicle parking space detection method, device and system |
| CN112001344A (en) * | 2020-08-31 | 2020-11-27 | 深圳市豪恩汽车电子装备股份有限公司 | Motor vehicle target detection device and method |
| CN113139526A (en) * | 2021-05-21 | 2021-07-20 | 一汽奔腾轿车有限公司 | Parking berth line identification method based on OpenCV |
| CN114419930A (en) * | 2022-03-30 | 2022-04-29 | 智能网联汽车(山东)协同创新研究院有限公司 | Intelligent information processing system of automobile internet of things |
| CN115416646A (en) * | 2022-08-10 | 2022-12-02 | 上海颖派汽车科技有限公司 | Pull type motor home and automatic parking method thereof |
| CN116524472A (en) * | 2023-06-30 | 2023-08-01 | 广汽埃安新能源汽车股份有限公司 | Obstacle detection method, device, storage medium and equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101016053A (en) * | 2007-01-25 | 2007-08-15 | 吉林大学 | Warning method and system for preventing collision for vehicle on high standard highway |
| JP2009292339A (en) * | 2008-06-05 | 2009-12-17 | Aisin Seiki Co Ltd | Parking assistant device |
| CN101984478A (en) * | 2010-08-03 | 2011-03-09 | 浙江大学 | Abnormal S-type driving warning method based on binocular vision lane marking detection |
| CN201825037U (en) * | 2010-07-08 | 2011-05-11 | 长安大学 | Lane departure alarm device for vehicles on highway |
| CN103600707A (en) * | 2013-11-06 | 2014-02-26 | 同济大学 | Parking position detecting device and method of intelligent parking system |
| CN103991449A (en) * | 2014-06-12 | 2014-08-20 | 北京联合大学 | Vehicle travelling control method and system |
| CN105355083A (en) * | 2015-12-14 | 2016-02-24 | 宁波裕兰信息科技有限公司 | Vision-based 360-degree parking assist intelligent guiding system |
| CN106127736A (en) * | 2016-06-15 | 2016-11-16 | 南京信必达智能技术有限公司 | One is parked detection method and processor |
-
2017
- 2017-10-10 CN CN201710934516.7A patent/CN107719361A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101016053A (en) * | 2007-01-25 | 2007-08-15 | 吉林大学 | Warning method and system for preventing collision for vehicle on high standard highway |
| JP2009292339A (en) * | 2008-06-05 | 2009-12-17 | Aisin Seiki Co Ltd | Parking assistant device |
| CN201825037U (en) * | 2010-07-08 | 2011-05-11 | 长安大学 | Lane departure alarm device for vehicles on highway |
| CN101984478A (en) * | 2010-08-03 | 2011-03-09 | 浙江大学 | Abnormal S-type driving warning method based on binocular vision lane marking detection |
| CN103600707A (en) * | 2013-11-06 | 2014-02-26 | 同济大学 | Parking position detecting device and method of intelligent parking system |
| CN103991449A (en) * | 2014-06-12 | 2014-08-20 | 北京联合大学 | Vehicle travelling control method and system |
| CN105355083A (en) * | 2015-12-14 | 2016-02-24 | 宁波裕兰信息科技有限公司 | Vision-based 360-degree parking assist intelligent guiding system |
| CN106127736A (en) * | 2016-06-15 | 2016-11-16 | 南京信必达智能技术有限公司 | One is parked detection method and processor |
Non-Patent Citations (2)
| Title |
|---|
| 张云飞: "基于机器视觉的车道偏离及碰撞预警技术研究", 《CNKI博硕论文库》 * |
| 石晴: "基于视觉的智能车车道保持技术研究", 《CNKI博硕论文库》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11541881B2 (en) | 2018-06-29 | 2023-01-03 | Byd Company Limited | Automatic parking method, device, system, and vehicle |
| WO2020001347A1 (en) * | 2018-06-29 | 2020-01-02 | 比亚迪股份有限公司 | Automatic parking method, apparatus and system, and vehicle |
| CN110879947A (en) * | 2018-09-06 | 2020-03-13 | 山东理工大学 | Real-time human face three-dimensional measurement method based on one-time projection structured light parallel stripe pattern |
| CN111508260A (en) * | 2019-01-30 | 2020-08-07 | 上海欧菲智能车联科技有限公司 | Vehicle parking space detection method, device and system |
| CN111507158A (en) * | 2019-01-31 | 2020-08-07 | 斯特拉德视觉公司 | Method and device for detecting parking area by semantic segmentation |
| CN111507158B (en) * | 2019-01-31 | 2023-11-24 | 斯特拉德视觉公司 | Method and device for detecting parking area by using semantic segmentation |
| CN110390306A (en) * | 2019-07-25 | 2019-10-29 | 湖州宏威新能源汽车有限公司 | Detection method, vehicle and the computer readable storage medium of right angle parking stall |
| CN110390306B (en) * | 2019-07-25 | 2021-08-10 | 湖州宏威新能源汽车有限公司 | Method for detecting right-angle parking space, vehicle and computer readable storage medium |
| CN112001344A (en) * | 2020-08-31 | 2020-11-27 | 深圳市豪恩汽车电子装备股份有限公司 | Motor vehicle target detection device and method |
| CN113139526A (en) * | 2021-05-21 | 2021-07-20 | 一汽奔腾轿车有限公司 | Parking berth line identification method based on OpenCV |
| CN114419930A (en) * | 2022-03-30 | 2022-04-29 | 智能网联汽车(山东)协同创新研究院有限公司 | Intelligent information processing system of automobile internet of things |
| CN115416646A (en) * | 2022-08-10 | 2022-12-02 | 上海颖派汽车科技有限公司 | Pull type motor home and automatic parking method thereof |
| CN115416646B (en) * | 2022-08-10 | 2023-05-16 | 上海颖派汽车科技有限公司 | Trailer type motor home and automatic parking method thereof |
| CN116524472A (en) * | 2023-06-30 | 2023-08-01 | 广汽埃安新能源汽车股份有限公司 | Obstacle detection method, device, storage medium and equipment |
| CN116524472B (en) * | 2023-06-30 | 2023-09-22 | 广汽埃安新能源汽车股份有限公司 | Obstacle detection method, device, storage medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107719361A (en) | Automatic parking householder method and system based on image vision | |
| CN107330376B (en) | Lane line identification method and system | |
| CN107862290B (en) | Lane line detection method and system | |
| CN105539293B (en) | Lane departure warning method and device and car steering accessory system | |
| US9002055B2 (en) | Methods and systems for matching keypoints and tracking regions between frames of video data | |
| CN109435942A (en) | A kind of parking stall line parking stall recognition methods and device based on information fusion | |
| CN108038416B (en) | Lane line detection method and system | |
| CN107066986A (en) | A kind of lane line based on monocular vision and preceding object object detecting method | |
| Danescu et al. | Detection and classification of painted road objects for intersection assistance applications | |
| CN110991489B (en) | Marking method, device and system for driving data | |
| EP1192597A1 (en) | Method of detecting objects within a wide range of a road vehicle | |
| CN103366156A (en) | Road structure detection and tracking | |
| CN101900567A (en) | No-texture clear path detection based on pixel | |
| CN101900566A (en) | Pixel-based texture-rich clear path detection | |
| CN112677977B (en) | Driving state identification method and device, electronic equipment and steering lamp control method | |
| CN104657735A (en) | Lane line detection method and system, as well as lane departure early warning method and system | |
| CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
| CN105718916A (en) | Lane line detection method based on Hough transform | |
| CN104700072A (en) | Lane line historical frame recognition method | |
| Wu et al. | A Real‐Time Embedded Blind Spot Safety Assistance System | |
| CN109002797B (en) | Vehicle lane change detection method, device, storage medium and computer equipment | |
| Siogkas et al. | Random-walker monocular road detection in adverse conditions using automated spatiotemporal seed selection | |
| CN106864458A (en) | It is a kind of automatic around barrier system and method, intelligent automobile | |
| CN104603841A (en) | Lane mark recognition device | |
| KR20130000023A (en) | Method for dectecting front vehicle using scene information of image |
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: 20180223 |
|
| RJ01 | Rejection of invention patent application after publication |