CN106541944B - A kind of warehouse compartment detection method, system and mobile device - Google Patents
A kind of warehouse compartment detection method, system and mobile device Download PDFInfo
- Publication number
- CN106541944B CN106541944B CN201610976121.9A CN201610976121A CN106541944B CN 106541944 B CN106541944 B CN 106541944B CN 201610976121 A CN201610976121 A CN 201610976121A CN 106541944 B CN106541944 B CN 106541944B
- Authority
- CN
- China
- Prior art keywords
- warehouse compartment
- image
- feature
- mobile device
- region
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 85
- 239000000284 extract Substances 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims description 62
- 238000012545 processing Methods 0.000 claims description 26
- 238000004891 communication Methods 0.000 claims description 20
- 230000002452 interceptive effect Effects 0.000 claims description 15
- 230000000007 visual effect Effects 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 6
- 230000000875 corresponding effect Effects 0.000 description 26
- 230000033001 locomotion Effects 0.000 description 20
- 230000009466 transformation Effects 0.000 description 18
- 238000005516 engineering process Methods 0.000 description 16
- 230000000694 effects Effects 0.000 description 15
- 230000008569 process Effects 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- 238000001914 filtration Methods 0.000 description 8
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 6
- 239000000203 mixture Substances 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 239000006002 Pepper Substances 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 4
- 238000013139 quantization Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 2
- 241000722363 Piper Species 0.000 description 2
- 235000016761 Piper aduncum Nutrition 0.000 description 2
- 235000017804 Piper guineense Nutrition 0.000 description 2
- 235000008184 Piper nigrum Nutrition 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 239000000654 additive Substances 0.000 description 2
- 230000000996 additive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000003990 capacitor Substances 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 229920000642 polymer Polymers 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000010897 surface acoustic wave method Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002604 ultrasonography 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
-
- 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
- G08G1/143—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces inside the vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
- B60R2300/806—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for aiding parking
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of warehouse compartment detection method, system and mobile device, according to the image that an at least camera is shot, forms the image of the certain viewing angles about the mobile device；Extract all straight lines in described image in the possibility warehouse compartment region near the mobile device；According to preset warehouse compartment feature, effective straight line in all straight lines is extracted as warehouse compartment line, each warehouse compartment location information in the possible warehouse compartment region is obtained according to the warehouse compartment line.The straight line in the warehouse compartment region in image that camera is shot is compared the present invention with warehouse compartment feature, warehouse compartment location information is extracted, and then can accurately orient the position of warehouse compartment, to provide assistance for automatic parking.
Description
Technical field
The present invention relates to automatic Pilot fields, more particularly to a kind of warehouse compartment detection method, system and mobile device.
Background technique
With the development of automotive automation technology, existing method for detecting parking stalls is to pass through ultrasonic distance measurement currently on the market
The variation of the distance of obstacle vehicle on the vehicle distances warehouse compartment of radar surveying traveling, to identify the warehouse compartment between obstacle vehicle.This
Kind warehouse compartment detection technique detection parking bit comparison lag, when spacious parking lot, ultrasonic wave can not judge specifically to stop
Where is position；And when parking stall is sideling to arrange, ultrasonic wave is difficult the warehouse compartment that accurate judgement sideling arranges, when vehicle is by library
When position, if parking stall line is lived by the car bumper of adjacent parking stall, ultrasonic wave will be examined because barrier is detected and not measure this
It is a parking stall.So there is certain limitation using ultrasound examination warehouse compartment.
Based on this, it is necessary to provide a kind of more effective warehouse compartment detection method, can more effectively identify warehouse compartment, be automobile
It parks and assistance is provided.
Summary of the invention
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide a kind of warehouse compartment detection method, system,
And mobile device, for solving the problems, such as warehouse compartment detection inaccuracy in the prior art.
In order to achieve the above objects and other related objects, the present invention provides a kind of warehouse compartment detection method, is applied to have extremely
In the mobile device of a few camera, the warehouse compartment detection method includes: the image shot according to the camera, is formed and is closed
In the image of the certain viewing angles of the mobile device；Extract the possibility warehouse compartment area in described image near the mobile device
All straight lines in domain；According to preset warehouse compartment feature, effective straight line in all straight lines is extracted as warehouse compartment line, with root
Each warehouse compartment location information in the possible warehouse compartment region is obtained according to the warehouse compartment line.
In a specific embodiment of the invention, the warehouse compartment detection method further include: to the image of camera shooting
It is pre-processed, the image about the mobile device is formed according to pretreated image；It is described pretreatment include at least with
One of under type: noise mode one: is removed to the image of each camera shooting；Mode two: according to preset calibration
Correction rule carries out calibration correction to the image of each camera shooting；Mode three: to the image of each camera shooting
Cut, piece together and video smoothing processing.
In a specific embodiment of the invention, the possibility warehouse compartment region near the mobile device includes being located at the movement
Region in the left side pre-determined distance of equipment, is located at the shifting at the region in the right side pre-determined distance of the mobile device
Move the region in the front preset distance of equipment, the region in the rear pre-determined distance of the mobile device, positioned at described
Region in the left front pre-determined distance of mobile device, the region in the right front pre-determined distance of the mobile device, position
In the region in the left back pre-determined distance of the mobile device or/and positioned at the right back pre-determined distance of the mobile device
Interior region.
In a specific embodiment of the invention, the warehouse compartment feature includes at least one of following characteristics or a variety of: special
Sign one: preset warehouse compartment shape；Feature two: warehouse compartment is by two parallel lines and a vertical line or special angle rectilinear(-al), institute
The spacing between parallel lines is stated in default warehouse compartment length range；Feature three: the straight line of warehouse compartment and the gray scale difference in other regions are formed
Value is greater than default gray scale difference value threshold value；Feature four: the shape of adjacent warehouse compartment is identical；Feature five: warehouse compartment is by two opposite line and one
Intersecting lens composition, the spacing between the opposite line is in default warehouse compartment length range；The opposite line and the intersecting lens
Angle is within the scope of predetermined angle.
In a specific embodiment of the invention, the warehouse compartment detection method further include: according to the warehouse compartment location information, mention
Take the physical location information at least two vertex of the warehouse compartment, and according to the physical location information at least two vertex,
Corresponding warehouse compartment figure is shown in preset interactive interface.
In order to achieve the above objects and other related objects, the present invention also provides a kind of warehouse compartment detection system, applied to having
In the mobile device of at least one camera, the warehouse compartment detection system includes that the processing being connected with camera communication fills
It sets, the processing unit includes: image forming module, to the image according to all camera shootings, is formed about institute
State the image of the certain viewing angles of mobile device；Lines detection module forms module communication with described image and is connected, to extract
State all straight lines in image in the possibility warehouse compartment region near the mobile device；Warehouse compartment position information acquisition module,
It is connected with lines detection module communication, it is effective straight in all straight lines to extract according to preset warehouse compartment feature
Line obtains each warehouse compartment location information in the possible warehouse compartment region as warehouse compartment line, according to the warehouse compartment line.
In a specific embodiment of the invention, the processing unit further include: warehouse compartment image display module, with the warehouse compartment
Position information acquisition module communication is connected, and according to the warehouse compartment location information, extracts the object at least two vertex of the warehouse compartment
Location information is managed, and according to the physical location information at least two vertex, is shown in preset interactive interface corresponding
Warehouse compartment figure.
In a specific embodiment of the invention, the warehouse compartment detection system further include: memory module, with the processing unit
In warehouse compartment position information acquisition module communication be connected, be stored with the preset warehouse compartment feature；The warehouse compartment feature is at least wrapped
Include one of following characteristics or a variety of: feature one: preset warehouse compartment shape；Feature two: warehouse compartment is by two parallel lines and one
Vertical line or special angle rectilinear(-al), the spacing between the parallel lines is in default warehouse compartment length range；Feature three: composition library
The straight line of position and the gray scale difference value in other regions are greater than default gray scale difference value threshold value；Feature four: the shape of adjacent warehouse compartment is identical；It is special
Sign five: warehouse compartment is made of two opposite lines and an intersecting lens, and the spacing between the opposite line is in default warehouse compartment length range；
The angle of the opposite line and the intersecting lens is within the scope of predetermined angle.
In order to achieve the above objects and other related objects, it the present invention also provides a kind of mobile device, is taken the photograph at least one
As head and the controller communicated to connect with the camera, image of the controller to receive the camera shooting,
And the controller operation is just like upper described in any item warehouse compartment detection methods.
The mobile device is automobile or smart phone.
In order to achieve the above objects and other related objects, the present invention also provides a kind of warehouse compartment detection method, the warehouse compartment inspections
Survey method includes: all straight lines extracted in an image in the possibility warehouse compartment region near mobile device；According to preset
Warehouse compartment feature extracts effective straight line in all straight lines as warehouse compartment line, obtains the possible library according to the warehouse compartment line
Each warehouse compartment location information in the region of position.
As described above, warehouse compartment detection method, system and mobile device of the invention, according to the image that camera is shot, shape
At the image of the certain viewing angles about the mobile device；Extract the possibility library in described image near the mobile device
All straight lines in the region of position；According to preset warehouse compartment feature, effective straight line in all straight lines is extracted as warehouse compartment line,
To obtain each warehouse compartment location information in the possible warehouse compartment region according to the warehouse compartment line.The figure that the present invention shoots camera
The straight line in the warehouse compartment region as in is compared with warehouse compartment feature, extracts warehouse compartment location information, and then can be accurate
The position of warehouse compartment is oriented, to provide assistance for automatic parking.
Detailed description of the invention
Fig. 1 is shown as the flow diagram of warehouse compartment detection method of the invention in one embodiment.
Fig. 2 is shown as interactive interface display schematic diagram in a specific embodiment of the invention.
Fig. 3 is shown as the warehouse compartment type schematic diagram applied in a specific embodiment of the invention.
Fig. 4 is shown as the warehouse compartment type schematic diagram applied in a specific embodiment of the invention.
Fig. 5 is shown as the module diagram of warehouse compartment detection system of the invention in one embodiment.
Component label instructions
10 methods
11~13 steps
21 automobiles
22 left areas
23 right areas
24 warehouse compartment figures
30 warehouse compartment detection systems
31 processing units
311 image forming modules
312 lines detection modules
313 warehouse compartment position information acquisition modules
32 memory modules
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in diagram then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It is likely more complexity.
Effective warehouse compartment detection, can preferably assist the operation of automated parking system, existing warehouse compartment usually has mark
The straight line of warehouse compartment profile, it is possible to find out warehouse compartment by detecting the straight line of warehouse compartment profile.Specifically referring to Fig. 1, display
For the flow diagram of warehouse compartment detection method of the invention in one embodiment.The warehouse compartment detection method 10, is applied to
In mobile device at least one camera, the mobile device is, for example, an automobile or smart phone, below with described
To be illustrated for automobile, the warehouse compartment detection method 10 includes: mobile device
11: according to the image of at least one camera shooting, forming the image of the certain viewing angles about the automobile；Institute
Stating certain viewing angles can determine according to the factors such as the type of camera and the installation site of camera, can also be according to user's
Demand carries out the adjustment of image aspects, such as only forms the image of the right side perspective about the automobile, in another example only forming pass
In the image of the left side perspective of the automobile.And in the description of the embodiments below, the image with certain viewing angles be include described
The front side of automobile, rear side, left side and right side the vertical view panoramic picture about the automobile for be illustrated, about institute
The vertical view panoramic picture for stating automobile is, for example, shown in Fig. 2, and the automobile 21 is in parking lot.And in concrete application, in root
It further include clapping the camera before being formed according to the image of camera shooting about the vertical view panoramic picture of the automobile
The image taken the photograph carries out pretreated process, and the pretreatment includes at least one of following manner:
Mode one: noise is removed to the image of each camera shooting；
Wherein, the digital picture in reality is subjected to imaging device and external environmental noise in digitlization and transmission process
Interference etc. influences, referred to as noisy image or noise image.The process for reducing noise in digital picture is known as image denoising.
Noise is the major reason of image interference.One images in practical applications there may be various noises,
These noises may generate in the transmission, it is also possible to generate in the processing such as quantization.It can be by it according to the relationship of noise and signal
Be divided into three kinds of forms: (f (x, y) indicates that given original picture, g (x, y) presentation image signal, n (x, y) indicate noise.
1) additive noise: this noise like is unrelated with input image signal, noisy image be represented by f (x, y)=g (x, y)+
The noise generated when the camera-scanning image of n (x, y), interchannel noise and vidicon just belongs to this noise like.
2) multiplicative noise: this noise like is related with picture intelligence, noisy image be represented by f (x, y)=g (x, y)+n (x,
Y) g (x, y), noise when flying-spot scanner scanned picture, the correlated noise in TV image, the grain noise in film just belong to
In this noise like.
3) quantizing noise: this noise like is unrelated with input image signal, is that there are quantization errors for quantizing process, then reflect
Receiving end and generate.
Usual image denoising filter includes following several:
1, mean filter
The particle being highly suitable in the image that removal is obtained by scanning using the mean filter of neighborhood averaging is made an uproar
Sound.The field method of average effectively inhibits noise, causes blooming as well as average, fog-level and field half
Diameter is directly proportional.
Geometric mean filter smoothness achieved can be compared with arithmetic equal value filter.But the meeting in filtering
Lose less pictorial detail.Harmonic wave mean filter is more preferable to " salt " noise effects, but is not suitable for " pepper " noise.It
It is good at handling other noises as Gaussian noise.Inverse harmonic wave mean filter is more suitable for handling impulsive noise.But it has
A disadvantage, exactly must be it is to be understood that noise be dark noise or bright noise.In order to select suitable filter order numerical symbol, such as
The symbol of fruit order, which has selected wrong, may cause catastrophic consequence.
2, adaptive wiener filter
It can adjust the output of filter according to the local variance of image, and local variance is bigger, the smooth work of filter
With stronger.Its final goal be make to restore image f^ (x, y) and original image f (x, y) mean square error e2=E [(f (x,
Y)-f^ (x, y) 2] it is minimum.The filter effect of this method is got well than mean filter effect, to the edge for retaining image and other
High frequency section is very useful, but calculation amount is larger.Wiener filter is best to the imaging filtering effect with white noise.
3, median filter
It is a kind of common Nonlinear Smoothing Filter.The basic principle is that a bit in digital picture or Serial No.
The value point a field in intermediate value its major function that replaces of each point value be to make the difference of surrounding pixel gray value bigger
Pixel change to take the value close with the pixel value of surrounding.So as to eliminate isolated noise spot, so median filtering is for filter
Except the salt-pepper noise of image is highly effective.Median filter can accomplish the edge for not only having removed noise but also capable of having protected image.To
Obtain relatively satisfactory recovery effect.Moreover, not needing the statistical property of image during actual operation.This also brings many sides
Just, but more to some details.Especially the more image of point, line, pinnacle details should not be using the method for median filtering.
4, morphology scratch filter
It will open and closure combines and can be used to filter out noise, it is optional first to there is noisy image to carry out opening operation
It is bigger than the size of noise to select structural element matrix, thus open the result is that by the noise remove in background.It is finally to previous
It walks obtained image and carries out closed procedure, the noise on image is removed.According to the characteristics of the method it is recognised that the method is suitable
Image type is that the object size in image is all bigger.And not tiny details, to such scene image partition
Effect can be relatively good.
5, Wavelet Denoising Method
This method remains most of wavelet coefficient comprising signal, therefore can preferably keep pictorial detail.It is small
Wave analysis, which carries out image denoising, mainly 3 steps:
(1) wavelet decomposition is carried out to picture intelligence；
(2) threshold value quantizing is carried out to the high frequency coefficient after hierachical decomposition；
(3) picture intelligence is reconstructed using 2-d wavelet.
Mode two: calibration correction is carried out according to image of the preset calibration correction rule to each camera shooting；
Mode three: the image of each camera shooting is cut, is pieced together and video smoothing is handled.Image mosaic
Exactly a series of pictures mutually to overlap for Same Scene is synthesized the image of a big wide viewing angle.After splicing
Image request it is farthest close with original image, be distorted it is as small as possible, without apparent suture.
The property of original image is to influence the most important factor of merging algorithm for images, and the mode that original image obtains is different,
Image integrity matter also has very big difference, needs using different stitching algorithms.The present invention selects one kind of following connecting method
Carry out the splicing of image:
I) cylinder/spherical surface/cubic panorama splicing
The intermediate scheme of panorama sketch mainly has spherical panoramic image, Cylindrical panoramic image and cubic panorama.Cylindrical panoramic image
It easily obtains, the scene of any sight can be generated, but restricted to the ken of vertical direction；The complete earth's surface of spherical panoramic image energy is entire
View space, but will lead to the scene torsional deformation at the two poles of the earth；The picture group that cubic panorama is generally 90 ° by 6 width wide-angles
At, be easy to the storage of data, convenient for display, be mainly used in three-dimension virtual reality field.
Cylinder model is the Panoramagram montage model most generallyd use, and this method requires camera around vertical rotation axis (such as three feet
Frame) make to horizontally rotate.After projecting image on a unified cylinder, Bonding Problem is translated on cylinder between image
Translation problem.The concentric circles stitching algorithm of the propositions such as Heung2YeungShum is a kind of method dependent on camera parameter.It should
Algorithm is considered as the variation of cylinder model.
II) based on the splicing of perspective transform
The not stringent limitation of movement of the splicing of perspective transform to camera.But the appearance of parallax in order to prevent, it is desired to quilt
The scenery of shooting is an approximate plane, and in shooting, it can be far considered as plane enough by subject distance camera.When acquisition
Be the fragment image or camera that put in order unknown motion mode it is unknown, this model can be used.
III) based on the splicing of affine transformation
Affine transformation is frequently as a kind of approximation based on perspective transform panorama sketch, camera tilt angles degree is little, focal length is sufficient
It can get preferable matching result affine transformation when enough big to be defined on continuous image.
IV) based on the image mosaic of image retrieval
With content-based image retrieval method carry out image mosaic be a kind of combination image data base, image retrieval,
The joining method of the technologies such as pattern-recognition.Original image is divided into many fritters first, then to each fritter, from image data base
Find visually most similar image therewith.Finally the image selected from database is formed with substitution method one big
Figure.
12: extracting all straight lines in described image in the possibility warehouse compartment region near the mobile device；It is described
Possibility warehouse compartment region near mobile device includes the region being located in the left side pre-determined distance of the mobile device, positioned at described
Region in the right side pre-determined distance of mobile device, is located at institute at the region in the front preset distance of the mobile device
State the region in the rear pre-determined distance of mobile device, the region in the left front pre-determined distance of the mobile device, position
In the region in the right front pre-determined distance of the mobile device, the area in the left back pre-determined distance of the mobile device
Domain or/and the region in the right back pre-determined distance of the mobile device.Such as in the present embodiment, set with the movement
Standby neighbouring possibility warehouse compartment region includes the region in the left side pre-determined distance of the mobile device and is located at the movement
The area for being illustrated, and being located in the left side pre-determined distance of the mobile device for region in the right side pre-determined distance of equipment
Domain and the region in the right side pre-determined distance of the mobile device are respectively the left area 22 of automobile 21 as shown in Figure 2
And right area 23, and only detect the straight line in the region.
Preferably, pass through hough change detection and extract the possibility library in the panoramic picture near the automobile
All straight lines in the region of position.Hough transform is a kind of parameter estimation techniques using voting principle.Its principle is to utilize image
Test problems in image space are transformed into parameter space by the point-line duality in space and Hough parameter space.By
Simple cumulative statistics is carried out in parameter space, then detects straight line in the method that Hough parameter space finds accumulator peak value.
The essence of Hough transform is to cluster the pixel in image space with certain relationship, these pixels can be used certain by searching
The parameter space that one analytical form connects accumulates corresponding points.In the case where parameter space is no more than two-dimensional situation, this transformation
There is ideal effect.
Principle by hough change detection straight line includes: for the straight line in plane, in cartesian coordinate system
In, it common are point slope form, two kinds of representation methods of two point form.However in hough transformation, consideration is another expression side
(r, theta) is used to indicate straight line likes:.Wherein r is distance of the straight line to origin, and theta is the vertical line of the straight line
With the angle of x-axis.The thought that straight line is detected using hough transformation is exactly: putting the straight line for assuming n direction for each, leads to
Normal n=180, the angle precision of the straight line detected at this time are 1 °, calculate separately (r, theta) coordinate of this n straight line, obtain n
A coordinate points.If the point to be judged shares N number of, finally obtained (r, theta) coordinate has N*n.This related N*n (r,
Theta) coordinate, wherein theta is discrete angle, shares 180 values.If multiple points are point-blank, must
There is this multiple point in theta=some value theta_i, the r of this multiple point is approximately equal in r_i.That is this multiple point
All on straight line (r_i, theta_i).In actual straight-line detection situation, if it exceeds the point of certain amount possess it is identical
(r, theta) coordinate, then it is determined that having straight line herein.
The method of the straight-line detection can also be that least square method is utilized to carry out straight line inspection in another embodiment
It surveys, or combines random Hough transformation (RHT) noise resisting ability characteristic high with least square method (LSM) fitting precision by force,
Straight-line detection or other line detection algorithms are carried out based on random Hough transformation and least square method.The straight-line detection side
Method can be used for that ambient noise to be relatively strong and straight line has certain curved image, and detection accuracy is high.Firstly, using random Hough transformation
The approximate location for determining straight line obtains straight line parameter and quantity；Then, using gained straight line parameter, the point calculated in image is arrived
The distance of straight line can determine the point set near every straight line according to distance, reject noise spot and noise；Finally, with minimum two
Multiplication is fitted each point concentrated, and obtains accurate straight line parameter.
13: according to preset warehouse compartment feature, extracting effective straight line in all straight lines as warehouse compartment line, according to institute
It states warehouse compartment line and obtains each warehouse compartment location information in the possible warehouse compartment region.Wherein, in another embodiment, the library
Position feature includes at least one of following characteristics or a variety of:
Feature one: preset warehouse compartment shape；The warehouse compartment shape is for example set as rectangle, and has vertically disposed multiple squares
Shape region, multiple rectangular areas disposed in parallel and the rectangular area for being inclined at an angle setting.When the straight line detected
The rectangular area for being vertically arranged, rectangular area being arranged in parallel or is obliquely installed can be constituted, and the rectangular area is big
When the small requirement with warehouse compartment national standard requires to match, then may determine that the rectangular area that the straight line detected is constituted
A warehouse compartment is corresponded to.
Feature two: warehouse compartment is by two parallel lines and a vertical line or special angle rectilinear(-al), between the parallel lines
Spacing is in default warehouse compartment length range；Two parallel lines are, for example, shown in Fig. 2 two on the length direction of warehouse compartment
The parallel lines at end, the vertical line are straight line along the warehouse compartment length direction and vertical with two parallel lines, and adjacent
Two groups of two parallel lines and a vertical line identify a warehouse compartment, and two adjacent distance between vertical lines are in preset library
Within the scope of bit width.The default warehouse compartment length range and default warehouse compartment width range according in national standard to corresponding vehicle
Warehouse compartment length and width requirement and be configured.For example, in national standard, to the warehouse compartment of vertically disposed kart
Width be 2.8 meters, so, default warehouse compartment width range herein can be 2.8 meters~3.0 meters.
Feature three: the gray scale difference value of the straight line and other regions that form warehouse compartment is greater than default gray scale difference value threshold value；Usual group
It is higher compared with the brightness of its peripheral region at the straight line of warehouse compartment profile, it can be by judging the gray scale in the region around straight line and straight line
Whether difference is greater than a threshold value as judging whether the straight line is a standard for forming effective straight line of warehouse compartment.
Feature four: the shape of adjacent warehouse compartment is identical, and general warehouse compartment will not isolate presence, it will usually have multiple identical setting sides
The warehouse compartment shape of formula is in a row, for example, adjacent warehouse compartment be vertically disposed warehouse compartment shape or be warehouse compartment shape disposed in parallel,
Or when being the warehouse compartment shape being obliquely installed, judge the region for a warehouse compartment region.
Feature five: warehouse compartment is made of two opposite lines and an intersecting lens, and the spacing between the opposite line is in default warehouse compartment
In length range；The angle of the opposite line and the intersecting lens is within the scope of predetermined angle.
Above five kinds of warehouse compartment features may be used solely to judge the presence of warehouse compartment, but in order to improve the essence of warehouse compartment detection
Degree, multiple features can be combined and come whether the region of comprehensive descision rectilinear(-al) is a warehouse compartment region.
For example, binding characteristic two and feature three, and the warehouse compartment detected is by two parallel lines and a vertical line or specific
Angle rectilinear(-al), the spacing between the parallel lines in default warehouse compartment length range, and form simultaneously warehouse compartment straight line and its
The gray scale difference value in his region is greater than default gray scale difference value threshold value and judges rectilinear(-al) when meeting feature two and feature three simultaneously
Region be an effective warehouse compartment region, improve warehouse compartment detection precision.
In another example binding characteristic two, feature three and feature four, and the warehouse compartment detected is by two parallel lines and one
Vertical line or special angle rectilinear(-al), the spacing between the parallel lines form library in default warehouse compartment length range simultaneously
The straight line of position and the gray scale difference value in other regions are greater than default gray scale difference value threshold value, and the shape of adjacent warehouse compartment is identical, i.e., simultaneously
When meeting feature two, feature three and feature four, judge the region of rectilinear(-al) for an effective warehouse compartment region.
In another example binding characteristic one, feature two, feature three and feature four, and the warehouse compartment detected and preset warehouse compartment
Shape is identical, and is made of two parallel lines and a vertical line, and the spacing between the parallel lines is in default warehouse compartment length range
It is interior, and form the straight line of warehouse compartment simultaneously and the gray scale difference value in other regions is greater than default gray scale difference value threshold value, and adjacent warehouse compartment
Shape is identical, i.e., when meeting feature one, feature two, feature three and feature four simultaneously, judges the region of rectilinear(-al) for a warehouse compartment
Region.
In another embodiment, or priority, and library first high to priority is arranged in the warehouse compartment feature of selection
Position feature is compared, and then is compared to the warehouse compartment feature that priority is taken second place, until in the warehouse compartment feature of application, priority
When minimum warehouse compartment feature all matches, judgement gets effective warehouse compartment.
For example, the warehouse compartment feature of selected characteristic two and feature three as application, and the priority of feature two is greater than warehouse compartment three
Priority, that is, when the straight line detected is in the case where meeting feature two, that is, the warehouse compartment detected is by two parallel lines and one
Vertical line or special angle rectilinear(-al), the spacing between the parallel lines is in default warehouse compartment length range, then judges to detect
Whether straight line out meets feature three, i.e. the straight line of composition warehouse compartment and the gray scale difference value in other regions is greater than default gray scale difference value threshold
Value, under conditions of meeting feature two, when also meeting feature three, judges the region of rectilinear(-al) for an effective warehouse compartment area
The precision of warehouse compartment detection is improved in domain.
In another example selected characteristic two, feature three and feature four are the warehouse compartment feature of application, the priority of feature two is big
It is greater than feature four in the priority of feature three, feature three, that is, the warehouse compartment detected is by two parallel lines and a vertical line or spy
Determine angle rectilinear(-al), when the spacing between the parallel lines is in default warehouse compartment length range, both meets the requirement of feature two, then
Further the straight line of detection composition warehouse compartment and the gray scale difference value in other regions are greater than default gray scale difference value threshold value, that is, meet feature three
Requirement, then the shape for further detecting adjacent warehouse compartment is identical, that is, meets the requirement of feature four, i.e., suitable with the preset priority
Sequence judges the region of rectilinear(-al) for an effective warehouse compartment region.
In another example selected characteristic one, feature two, feature three and feature four be application warehouse compartment feature, feature one it is excellent
First grade is greater than feature two, and the priority of feature two is greater than feature three, and the priority of feature three is greater than feature four, i.e., ought detect
When warehouse compartment is identical as preset warehouse compartment shape, meet the requirement of feature one, then further detects the straight line got and meet warehouse compartment
By two parallel lines and a vertical line or special angle rectilinear(-al), the spacing between the parallel lines is in default warehouse compartment length model
Interior requirement is enclosed, the requirement of feature two had both been met, then further detection forms the straight line of warehouse compartment and the gray scale difference value in other regions
Greater than default gray scale difference value threshold value, that is, meet the requirement of feature three, then the shape for further detecting adjacent warehouse compartment is identical, that is, meets
The requirement of feature four judges the region of rectilinear(-al) for an effective warehouse compartment region that is, with the preset priority orders.
Priority between the feature of selection can be manually set as the case may be, and can be with real-time perfoming tune
It is whole.
In an of the invention specific embodiment, the warehouse compartment detection method 10 further include: according to the warehouse compartment location information,
Extract the physical location information at least two vertex of the warehouse compartment, and according to the physical location information on four vertex,
Corresponding warehouse compartment figure is shown in preset interactive interface.Such as it can extract the physical location information on four vertex of the warehouse compartment
To show corresponding warehouse compartment figure in preset interactive interface.Further, multiple detections can be shown in the interactive interface
The warehouse compartment figure arrived, and after receiving user to the manually selecting of a warehouse compartment figure, according to automated parking system, automobile to be moored
Enter in corresponding warehouse compartment.
In the display interface of the warehouse compartment figure, also to by the graphical virtual of the automobile into the interface, and will
During automobile moors corresponding warehouse compartment, real-time display automobile moor into corresponding virtual screen, to make user timely
Understand the process and state parked.Preferably, when the warehouse compartment shown in the warehouse compartment figure and panoramic picture shown in interactive interface
When having deviation, user can manually adjust the warehouse compartment figure and be overlapped to corresponding preset warehouse compartment figure.Such as pass through warehouse compartment
The warehouse compartment figure that is shown in the panoramic picture of physical location information on four vertex be shown in warehouse compartment figure 24 in Fig. 2,
It can be seen that the correspondence warehouse compartment shown in the warehouse compartment figure 24 and the panoramic picture has certain deviation, user can according to it is upper and lower,
Left and right Image Adjusting operation, which is adjusted to warehouse compartment corresponding in the panoramic picture and is overlapped.
Further, the display of the warehouse compartment figure is for example realized using a touch display screen, the touching carried out by user
Control input, selects corresponding warehouse compartment.
Touch screen provides output interface and input interface simultaneously between equipment and user.Touch screen controller, which connects, to be transmitted/received
Send from/go to the electric signal of touch screen.The touch screen then shows visual output to user.This visual output may include text
Sheet, figure, video and any combination thereof.Certain or all visual outputs can be corresponding with user-interface object, hereinafter will
Its more details are described.
Touch screen also receives the input of user based on tactile and/or tactile contact.The touch screen forms one and receives use
The touch sensitive surface of family input.The touch screen and touch screen controller (together with associated module any in memory and/or
Instruction set is together) contact (and any movement or interruption of the touch) on detection touch screen, and what be will test connects
Thixotroping changes the interaction of the user interface object of such as one or more soft-key buttons with display on the touchscreen etc into.
In one exemplary embodiment, the contact point between touch screen and user corresponds to one or more hands of user
Refer to.LCD (liquid crystal display) technology or LPD (light emitting polymer displays) technology can be used in the touch screen, but in other realities
It applies and other display technologies can be used in example.
Any one of a variety of Touch technologies can be used to detect contact and its shifting in touch screen and touch screen controller
Dynamic or interruption, these Touch technologies include but is not limited to capacitor, resistance, infrared and surface acoustic wave techniques and other close biographies
Sensor array, or the other technologies for determining the one or more points being in contact with touch screen.User can be used any suitable
When object or accessory, such as stylus, finger etc., to contact touch screen.
The touch display screen also has a contact/motion module, and the contact/motion module is together with touch screen controller
To detect the contact with touch screen.Contact/the motion module includes associated for executing the detection of the contact with touch screen
The various component softwares of various operations, the operation for example, determine whether to be in contact, and determine whether the contact moves, and chase after
Movement on track touch screen, and determine whether the contact is interrupted and (whether stop contacting).Determine the mobile operation in contact point
It can include determining that rate (amplitude), speed (amplitude and direction) and/or acceleration (including amplitude and/or the side of contact point
To).In certain embodiments, contact/motion module also detects the contact on touch tablet with touch screen controller.
The touch display screen also has figure module in the process of running, which includes for being on the touchscreen
Now with display figure various known software components.Notice that term " figure " includes any object that can be shown to user, wraps
It includes but is not limited to text, webpage, icon (for example including the user interface object including soft-key button), digital picture, video, move
Draw etc..
In certain embodiments, figure module includes light intensity module.It is this kind of aobvious that the light intensity module controls user interface object
Show the light intensity of Drawing Object on the touchscreen.Intensity control may include the light intensity for increasing or reducing Drawing Object.Certain
In embodiment, described increase or reduce can follow predefined function.
The user interface state of user interface state module control equipment.The user interface state module may include locking
Module and unlocked state.Locking module detection is transformed into user interface lock state to by equipment, and equipment is transformed into lock
Determine the satisfaction of any one of one or more conditions of state condition.Unlocked state detection is transformed into user circle to by equipment
Face unlocked state, and equipment is transformed into the satisfaction of any one of one or more conditions of unlocked state.Below
In more details relevant to user interface state will be described.
Fig. 5 is further regarded to, the module diagram of warehouse compartment detection system of the invention in one embodiment is shown as.
The warehouse compartment detection system 30, applied in the mobile device at least one camera, the mobile device is, for example, one
Automobile or smart phone, hereinafter, illustrated using the mobile device as automobile, the warehouse compartment detection system 30 include with
The connected processing unit 31 of the camera communication, the processing unit 31 include:
Panoramic picture forms module 311, to the image according to all camera shootings, is formed about the movement
The image of the certain viewing angles of equipment；The certain viewing angles can according to the type of camera and the installation site of camera etc. because
Element determines, can also carry out according to the demand of user the adjustment of image aspects, such as only forms the right side view about the automobile
The image at angle, in another example only forming the image of the left side perspective about the automobile.And in the description of the embodiments below, with spy
The image for determining visual angle is the vertical view panorama sketch about the automobile on the front side for including the automobile, rear side, left side and right side
It is illustrated as, the vertical view panoramic picture about the automobile is, for example, shown in Fig. 2, and the automobile 21 is in parking lot
It is interior.It further include to described before the image shot according to the camera is formed about the vertical view panoramic picture of the automobile
The image of camera shooting carries out pretreated process, and the pretreatment includes at least one of following manner:
Mode one: noise is removed to the image of each camera shooting；
Wherein, the digital picture in reality is subjected to imaging device and external environmental noise in digitlization and transmission process
Interference etc. influences, referred to as noisy image or noise image.The process for reducing noise in digital picture is known as image denoising.
Noise is the major reason of image interference.One images in practical applications there may be various noises,
These noises may generate in the transmission, it is also possible to generate in the processing such as quantization.It can be by it according to the relationship of noise and signal
Be divided into three kinds of forms: (f (x, y) indicates that given original picture, g (x, y) presentation image signal, n (x, y) indicate noise.
1) additive noise: this noise like is unrelated with input image signal, noisy image be represented by f (x, y)=g (x, y)+
The noise generated when the camera-scanning image of n (x, y), interchannel noise and vidicon just belongs to this noise like.
2) multiplicative noise: this noise like is related with picture intelligence, noisy image be represented by f (x, y)=g (x, y)+n (x,
Y) g (x, y), noise when flying-spot scanner scanned picture, the correlated noise in TV image, the grain noise in film just belong to
In this noise like.
3) quantizing noise: this noise like is unrelated with input image signal, is that there are quantization errors for quantizing process, then reflect
Receiving end and generate.
Usual image denoising filter includes following several:
1, mean filter
The particle being highly suitable in the image that removal is obtained by scanning using the mean filter of neighborhood averaging is made an uproar
Sound.The field method of average effectively inhibits noise, causes blooming as well as average, fog-level and field half
Diameter is directly proportional.
Geometric mean filter smoothness achieved can be compared with arithmetic equal value filter.But the meeting in filtering
Lose less pictorial detail.Harmonic wave mean filter is more preferable to " salt " noise effects, but is not suitable for " pepper " noise.It
It is good at handling other noises as Gaussian noise.Inverse harmonic wave mean filter is more suitable for handling impulsive noise.But it has
A disadvantage, exactly must be it is to be understood that noise be dark noise or bright noise.In order to select suitable filter order numerical symbol, such as
The symbol of fruit order, which has selected wrong, may cause catastrophic consequence.
2, adaptive wiener filter
It can adjust the output of filter according to the local variance of image, and local variance is bigger, the smooth work of filter
With stronger.Its final goal be make to restore image f^ (x, y) and original image f (x, y) mean square error e2=E [(f (x,
Y)-f^ (x, y) 2] it is minimum.The filter effect of this method is got well than mean filter effect, to the edge for retaining image and other
High frequency section is very useful, but calculation amount is larger.Wiener filter is best to the imaging filtering effect with white noise.
3, median filter
It is a kind of common Nonlinear Smoothing Filter.The basic principle is that a bit in digital picture or Serial No.
The value point a field in intermediate value its major function that replaces of each point value be to make the difference of surrounding pixel gray value bigger
Pixel change to take the value close with the pixel value of surrounding.So as to eliminate isolated noise spot, so median filtering is for filter
Except the salt-pepper noise of image is highly effective.Median filter can accomplish the edge for not only having removed noise but also capable of having protected image.To
Obtain relatively satisfactory recovery effect.Moreover, not needing the statistical property of image during actual operation.This also brings many sides
Just, but more to some details.Especially the more image of point, line, pinnacle details should not be using the method for median filtering.
4, morphology scratch filter
It will open and closure combines and can be used to filter out noise, it is optional first to there is noisy image to carry out opening operation
It is bigger than the size of noise to select structural element matrix, thus open the result is that by the noise remove in background.It is finally to previous
It walks obtained image and carries out closed procedure, the noise on image is removed.According to the characteristics of the method it is recognised that the method is suitable
Image type is that the object size in image is all bigger.And not tiny details, to such scene image partition
Effect can be relatively good.
5, Wavelet Denoising Method
This method remains most of wavelet coefficient comprising signal, therefore can preferably keep pictorial detail.It is small
Wave analysis, which carries out image denoising, mainly 3 steps:
(1) wavelet decomposition is carried out to picture intelligence；
(2) threshold value quantizing is carried out to the high frequency coefficient after hierachical decomposition；
(3) picture intelligence is reconstructed using 2-d wavelet.
Mode two: calibration correction is carried out according to image of the preset calibration correction rule to each camera shooting.
Mode three: the image of each camera shooting is cut, is pieced together and video smoothing is handled.
Image mosaic is exactly that a series of pictures mutually to overlap for Same Scene is synthesized a big width
The image at visual angle.Spliced image request is farthest close with original image, and distortion is as small as possible, does not stitch significantly
Zygonema.
The property of original image is to influence the most important factor of merging algorithm for images, and the mode that original image obtains is different,
Image integrity matter also has very big difference, needs using different stitching algorithms.The present invention preferentially selects following connecting method
A kind of splicing carrying out image:
I) cylinder/spherical surface/cubic panorama splicing
The intermediate scheme of panorama sketch mainly has spherical panoramic image, Cylindrical panoramic image and cubic panorama.Cylindrical panoramic image
It easily obtains, the scene of any sight can be generated, but restricted to the ken of vertical direction；The complete earth's surface of spherical panoramic image energy is entire
View space, but will lead to the scene torsional deformation at the two poles of the earth；The picture group that cubic panorama is generally 90 ° by 6 width wide-angles
At, be easy to the storage of data, convenient for display, be mainly used in three-dimension virtual reality field.
Cylinder model is the Panoramagram montage model most generallyd use, and this method requires camera around vertical rotation axis (such as three feet
Frame) make to horizontally rotate.After projecting image on a unified cylinder, Bonding Problem is translated on cylinder between image
Translation problem.The concentric circles stitching algorithm of the propositions such as Heung2YeungShum is a kind of method dependent on camera parameter.It should
Algorithm is considered as the variation of cylinder model.
II) based on the splicing of perspective transform
The not stringent limitation of movement of the splicing of perspective transform to camera.But the appearance of parallax in order to prevent, it is desired to quilt
The scenery of shooting is an approximate plane, and in shooting, it can be far considered as plane enough by subject distance camera.When acquisition
Be the fragment image or camera that put in order unknown motion mode it is unknown, this model can be used.
III) based on the splicing of affine transformation
Affine transformation is frequently as a kind of approximation based on perspective transform panorama sketch, camera tilt angles degree is little, focal length is sufficient
It can get preferable matching result affine transformation when enough big to be defined on continuous image.
IV) based on the image mosaic of image retrieval
With content-based image retrieval method carry out image mosaic be a kind of combination image data base, image retrieval,
The joining method of the technologies such as pattern-recognition.Original image is divided into many fritters first, then to each fritter, from image data base
Find visually most similar image therewith.Finally the image selected from database is formed with substitution method one big
Figure.
Lines detection module 312 forms the communication of module 311 with described image and is connected, is in extract in described image
All straight lines in possibility warehouse compartment region near the mobile device；
Preferably, pass through hough change detection and extract the possibility library in the panoramic picture near the automobile
All straight lines in the region of position.Hough transform is a kind of parameter estimation techniques using voting principle.Its principle is to utilize image
Test problems in image space are transformed into parameter space by the point-line duality in space and Hough parameter space.By
Simple cumulative statistics is carried out in parameter space, then detects straight line in the method that Hough parameter space finds accumulator peak value.
The essence of Hough transform is to cluster the pixel in image space with certain relationship, these pixels can be used certain by searching
The parameter space that one analytical form connects accumulates corresponding points.In the case where parameter space is no more than two-dimensional situation, this transformation
There is ideal effect.
Principle by hough change detection straight line includes: for the straight line in plane, in cartesian coordinate system
In, it common are point slope form, two kinds of representation methods of two point form.However in hough transformation, consideration is another expression side
(r, theta) is used to indicate straight line likes:.Wherein r is distance of the straight line to origin, and theta is the vertical line of the straight line
With the angle of x-axis.The thought that straight line is detected using hough transformation is exactly: putting the straight line for assuming n direction for each, leads to
Normal n=180, the angle precision of the straight line detected at this time are 1 °, calculate separately (r, theta) coordinate of this n straight line, obtain n
A coordinate points.If the point to be judged shares N number of, finally obtained (r, theta) coordinate has N*n.This related N*n (r,
Theta) coordinate, wherein theta is discrete angle, shares 180 values.If multiple points are point-blank, must
There is this multiple point in theta=some value theta_i, the r of this multiple point is approximately equal in r_i.That is this multiple point
All on straight line (r_i, theta_i).In actual straight-line detection situation, if it exceeds the point of certain amount possess it is identical
(r, theta) coordinate, then it is determined that having straight line herein.
The method of the straight-line detection can also be that least square method is utilized to carry out straight line inspection in another embodiment
It surveys, or combines random Hough transformation (RHT) noise resisting ability characteristic high with least square method (LSM) fitting precision by force,
Straight-line detection is carried out based on random Hough transformation and least square method.The line detection method can be used for ambient noise it is relatively strong and
There is certain curved image in straight line, detection accuracy is high.Firstly, determining the approximate location of straight line with random Hough transformation, obtain
Straight line parameter and quantity；Then, using gained straight line parameter, the distance for calculating the point in image to straight line can be with according to distance
It determines the point set near every straight line, rejects noise spot and noise；Finally, being intended with least square method each point concentrated
It closes, obtains accurate straight line parameter.
Warehouse compartment position information acquisition module 313 is connected, to according to preset with the lines detection module 312 communication
Warehouse compartment feature extracts effective straight line in all straight lines as warehouse compartment line, to obtain the possibility according to the warehouse compartment line
Each warehouse compartment location information in warehouse compartment region.
In a specific embodiment of the invention, the processing unit 31 further include: warehouse compartment image display module, with the library
Position position information acquisition module communication is connected, and according to the warehouse compartment location information, extracts at least two vertex of the warehouse compartment
Physical location information, and according to the physical location information at least two vertex, it is shown in preset interactive interface corresponding
Warehouse compartment figure.Such as can extract the warehouse compartment four vertex physical location information to be shown in preset interactive interface
Corresponding warehouse compartment figure.Further, multiple warehouse compartment figures detected can be shown in the interactive interface, and are receiving user
To after the manually selecting of a warehouse compartment figure, according to automated parking system, automobile to be moored in corresponding warehouse compartment.
In the display interface of the warehouse compartment image display module, also to by the graphical virtual of the automobile to the interface
In, and during mooring automobile into corresponding warehouse compartment, real-time display automobile moor into corresponding virtual screen, to allow user
The process and state parked can be understood in time.Preferably, it is shown when in the warehouse compartment figure and panoramic picture shown in interactive interface
When the warehouse compartment shown has deviation, user can manually adjust the warehouse compartment figure and be overlapped to corresponding preset warehouse compartment figure.Such as
Pass through the warehouse compartment figure that the warehouse compartment figure that the physical location information on four vertex of warehouse compartment is shown in the panoramic picture is in Fig. 2
Shown in 24, it is seen that the correspondence warehouse compartment shown in the warehouse compartment figure 24 and the panoramic picture has certain deviation, and user can basis
Above and below, left and right Image Adjusting operation, by the warehouse compartment figure 24 adjust to warehouse compartment weight corresponding in the panoramic picture
It closes.
Further, the warehouse compartment image display module is, for example, a touch display screen, and the touch-control carried out by user is defeated
Enter, selects corresponding warehouse compartment.
Touch screen provides output interface and input interface simultaneously between equipment and user.Touch screen controller, which connects, to be transmitted/received
Send from/go to the electric signal of touch screen.The touch screen then shows visual output to user.This visual output may include text
Sheet, figure, video and any combination thereof.Certain or all visual outputs can be corresponding with user-interface object, hereinafter will
Its more details are described.
Touch screen also receives the input of user based on tactile and/or tactile contact.The touch screen forms one and receives use
The touch sensitive surface of family input.The touch screen and touch screen controller (together with associated module any in memory and/or
Instruction set is together) contact (and any movement or interruption of the touch) on detection touch screen, and what be will test connects
Thixotroping changes the interaction of the user interface object of such as one or more soft-key buttons with display on the touchscreen etc into.
In one exemplary embodiment, the contact point between touch screen and user corresponds to one or more hands of user
Refer to.LCD (liquid crystal display) technology or LPD (light emitting polymer displays) technology can be used in the touch screen, but in other realities
It applies and other display technologies can be used in example.
Any one of a variety of Touch technologies can be used to detect contact and its shifting in touch screen and touch screen controller
Dynamic or interruption, these Touch technologies include but is not limited to capacitor, resistance, infrared and surface acoustic wave techniques and other close biographies
Sensor array, or the other technologies for determining the one or more points being in contact with touch screen.User can be used any suitable
When object or accessory, such as stylus, finger etc., to contact touch screen.
The touch display screen also has a contact/motion module, and the contact/motion module is together with touch screen controller
To detect the contact with touch screen.Contact/the motion module includes associated for executing the detection of the contact with touch screen
The various component softwares of various operations, the operation for example, determine whether to be in contact, and determine whether the contact moves, and chase after
Movement on track touch screen, and determine whether the contact is interrupted and (whether stop contacting).Determine the mobile operation in contact point
It can include determining that rate (amplitude), speed (amplitude and direction) and/or acceleration (including amplitude and/or the side of contact point
To).In certain embodiments, contact/motion module also detects the contact on touch tablet with touch screen controller.
The touch display screen also has figure module in the process of running, which includes for being on the touchscreen
Now with display figure various known software components.Notice that term " figure " includes any object that can be shown to user, wraps
It includes but is not limited to text, webpage, icon (for example including the user interface object including soft-key button), digital picture, video, move
Draw etc..
In certain embodiments, figure module includes light intensity module.It is this kind of aobvious that the light intensity module controls user interface object
Show the light intensity of Drawing Object on the touchscreen.Intensity control may include the light intensity for increasing or reducing Drawing Object.Certain
In embodiment, described increase or reduce can follow predefined function.
The user interface state of user interface state module control equipment.The user interface state module may include locking
Module and unlocked state.Locking module detection is transformed into user interface lock state to by equipment, and equipment is transformed into lock
Determine the satisfaction of any one of one or more conditions of state condition.Unlocked state detection is transformed into user circle to by equipment
Face unlocked state, and equipment is transformed into the satisfaction of any one of one or more conditions of unlocked state.Below
In more details relevant to user interface state will be described.
In a specific embodiment of the invention, the warehouse compartment detection system 30 further include: memory module 32, with the processing
The communication of warehouse compartment position information acquisition module 313 in device 31 is connected, and is stored with the preset warehouse compartment feature；The warehouse compartment is special
Sign includes at least one of following characteristics or a variety of:
Feature one: preset warehouse compartment shape；It is vertically arranged when the straight line detected can constitute one, rectangle is arranged in parallel
Region or the rectangular area being obliquely installed, and the size of the rectangular area requires phase with the requirement in warehouse compartment national standard
Timing, then the rectangular area that may determine that the straight line detected is constituted has corresponded to a warehouse compartment.
Feature two: warehouse compartment is by two parallel lines and a vertical line or special angle rectilinear(-al), between the parallel lines
Spacing is in default warehouse compartment length range；Two parallel lines are, for example, shown in Fig. 2 two on the length direction of warehouse compartment
The parallel lines at end, the vertical line are straight line along the warehouse compartment length direction and vertical with two parallel lines, and adjacent
Two groups of two parallel lines and a vertical line identify a warehouse compartment, and two adjacent distance between vertical lines are in preset library
Within the scope of bit width.The default warehouse compartment length range and default warehouse compartment width range according in national standard to corresponding vehicle
Warehouse compartment length and width requirement and be configured.For example, in national standard, to the warehouse compartment of vertically disposed kart
Width be 2.8 meters, so, default warehouse compartment width range herein can be 2.8 meters~3.0 meters.
Feature three: the gray scale difference value of the straight line and other regions that form warehouse compartment is greater than default gray scale difference value threshold value；Usual group
It is higher compared with the brightness of its peripheral region at the straight line of warehouse compartment profile, it can be by judging the gray scale in the region around straight line and straight line
Whether difference is greater than a threshold value as judging whether the straight line is a standard for forming effective straight line of warehouse compartment.
Feature four: the shape of adjacent warehouse compartment is identical, and general warehouse compartment will not isolate presence, it will usually have multiple identical setting sides
The warehouse compartment shape of formula is in a row, such as adjacent warehouse compartment is vertically disposed warehouse compartment shape (such as Fig. 2) or is library disposed in parallel
Position shape (such as Fig. 3) or when being warehouse compartment shape (such as Fig. 4) being obliquely installed, judges the region for a warehouse compartment region.
Feature five: warehouse compartment is made of two opposite lines and an intersecting lens, and the spacing between the opposite line is in default warehouse compartment
In length range；The angle of the opposite line and the intersecting lens is within the scope of predetermined angle.
Above five kinds of warehouse compartment features may be used solely to judge the presence of warehouse compartment, but in order to improve the essence of warehouse compartment detection
Degree, multiple features can be combined and come whether the region of comprehensive descision rectilinear(-al) is a warehouse compartment region.
For example, binding characteristic two and feature three, and the warehouse compartment detected is by two parallel lines and a vertical line or specific
Angle rectilinear(-al), the spacing between the parallel lines in default warehouse compartment length range, and form simultaneously warehouse compartment straight line and its
The gray scale difference value in his region is greater than default gray scale difference value threshold value and judges rectilinear(-al) when meeting feature two and feature three simultaneously
Region be an effective warehouse compartment region, improve warehouse compartment detection precision.
In another example binding characteristic two, feature three and feature four, and the warehouse compartment detected is by two parallel lines and one
Vertical line or special angle rectilinear(-al), the spacing between the parallel lines form library in default warehouse compartment length range simultaneously
The straight line of position and the gray scale difference value in other regions are greater than default gray scale difference value threshold value, and the shape of adjacent warehouse compartment is identical, i.e., simultaneously
When meeting feature two, feature three and feature four, judge the region of rectilinear(-al) for an effective warehouse compartment region.
In another example binding characteristic one, feature two, feature three and feature four, and the warehouse compartment detected and preset warehouse compartment
Shape is identical, and is made of two parallel lines and a vertical line, and the spacing between the parallel lines is in default warehouse compartment length range
It is interior, and form the straight line of warehouse compartment simultaneously and the gray scale difference value in other regions is greater than default gray scale difference value threshold value, and adjacent warehouse compartment
Shape is identical, i.e., when meeting feature one, feature two, feature three and feature four simultaneously, judges the region of rectilinear(-al) for a warehouse compartment
Region.
In another embodiment, or priority, and library first high to priority is arranged in the warehouse compartment feature of selection
Position feature is compared, and then is compared to the warehouse compartment feature that priority is taken second place, until in the warehouse compartment feature of application, priority
When minimum warehouse compartment feature all matches, judgement gets effective warehouse compartment.
For example, the warehouse compartment feature of selected characteristic two and feature three as application, and the priority of feature two is greater than warehouse compartment three
Priority, that is, when the straight line detected is in the case where meeting feature two, that is, the warehouse compartment detected is by two parallel lines and one
Vertical line or special angle rectilinear(-al), the spacing between the parallel lines is in default warehouse compartment length range, then judges to detect
Whether straight line out meets feature three, i.e. the straight line of composition warehouse compartment and the gray scale difference value in other regions is greater than default gray scale difference value threshold
Value, under conditions of meeting feature two, when also meeting feature three, judges the region of rectilinear(-al) for an effective warehouse compartment area
The precision of warehouse compartment detection is improved in domain.
In another example selected characteristic two, feature three and feature four are the warehouse compartment feature of application, the priority of feature two is big
It is greater than feature four in the priority of feature three, feature three, that is, the warehouse compartment detected is by two parallel lines and a vertical line or spy
Determine angle rectilinear(-al), when the spacing between the parallel lines is in default warehouse compartment length range, both meets the requirement of feature two, then
Further the straight line of detection composition warehouse compartment and the gray scale difference value in other regions are greater than default gray scale difference value threshold value, that is, meet feature three
Requirement, then the shape for further detecting adjacent warehouse compartment is identical, that is, meets the requirement of feature four, i.e., suitable with the preset priority
Sequence judges the region of rectilinear(-al) for an effective warehouse compartment region.
In another example selected characteristic one, feature two, feature three and feature four be application warehouse compartment feature, feature one it is excellent
First grade is greater than feature two, and the priority of feature two is greater than feature three, and the priority of feature three is greater than feature four, i.e., ought detect
When warehouse compartment is identical as preset warehouse compartment shape, meet the requirement of feature one, then further detects the straight line got and meet warehouse compartment
By two parallel lines and a vertical line or special angle rectilinear(-al), the spacing between the parallel lines is in default warehouse compartment length model
Interior requirement is enclosed, the requirement of feature two had both been met, then further detection forms the straight line of warehouse compartment and the gray scale difference value in other regions
Greater than default gray scale difference value threshold value, that is, meet the requirement of feature three, then the shape for further detecting adjacent warehouse compartment is identical, that is, meets
The requirement of feature four judges the region of rectilinear(-al) for an effective warehouse compartment region that is, with the preset priority orders.
Priority between the feature of selection can be manually set as the case may be, and can be with real-time perfoming tune
It is whole.
The memory module 32 may include high-speed random access memory, and may also include nonvolatile memory,
Such as one or more disk storage equipments, flash memory device or other non-volatile solid-state memory devices.In certain embodiments,
Memory module 32 can also include the memory of one or more processors, such as via RF circuit or outside port and communication
The network attached storage of network access, wherein the communication network can be internet, one or more intranets, local area network
(LAN), wide area network (WLAN), storage area network (SAN) etc. or other are appropriately combined.Memory module controller controllable device
Access of the other assemblies of such as CPU and interface circuit etc to memory.
In another specific embodiment of the present invention, the processing unit 31 can be also integrated in a mobile electronic device, institute
Stating mobile electronic device is, for example, the smart phone communicated to connect with the camera, and, the processing unit 31 is set to institute
It states in electronic equipment, can reduce the data processing pressure of the car-mounted terminal of the automobile 10.The camera and the intelligence
The communication connection of mobile phone is to pass through Bluetooth, CDMA2000, GSM, Infrared (IR), ISM, RFID, UMTS/3GPPw/
One of wireless communication protocols such as HSDPA, UWB, WiMAX Wi-Fi and ZigBee carry out wireless communication.
Further, the processing unit 31 exists in the mobile electronic device with the formation of APP a kind of, opens institute
State the mode of APP, for example, user opens manually, the mobile electronic device detects what the car-mounted terminal of automobile 10 was sent
When automatic parking is requested, which opens the APP.
The mobile electronic device preferably includes memory, Memory Controller, one or more processors (CPU), connects
Mouthful circuit, RF (radio frequency) circuit, voicefrequency circuit, loudspeaker, microphone, input/output (I/O) subsystem, touch display screen, its
He exports or controls equipment and outside port.These components are communicated by one or more communication bus or signal wire.
The mobile electronic device can be any portable electronic device, including but not limited to laptop, plate electricity
Brain, smart phone, multimedia player, personal digital assistant (PDA) etc., it is also possible to including wherein two or multinomial groups
It closes.It should be appreciated that the equipment enumerated in the present embodiment is an example of portable electronic device, the component of the equipment can be with
There are more or fewer components than what is provided in diagram, or with different component Configurations.Various assemblies shown in figure can
To be realized with the combination of hardware, software or software and hardware, including one or more signal processings and/or special road.
The I/O subsystem provides the interface between the input/output peripheral hardware and interface circuit of equipment, input/output peripheral
Such as touch screen and other input/control devicess.The I/O subsystem includes touch screen controller and exports or control for other
One or more input controllers of control equipment.One or more of input controller receptions/transmission come from/goes to other are defeated
Enter or control the electric signal of equipment.Other described input/control devicess may include that physical button (such as press by push button, rocking bar
Button etc.), dial, slider switch, control stick etc..
Or in another embodiment, the data that the car-mounted terminal of the automobile 10 can also obtain the camera
Be sent in a cloud, and the processing unit 31 be integrated in in the associated server in the cloud, and by processing result
The car-mounted terminal is sent to be shown, the main processes of data are equally placed in cloud, the vapour can be reduced
The data processing pressure of vehicle 10.
Or in another embodiment, the data that the camera obtains are uploaded in a network platform, and with
The associated server set of the network platform at the processing unit 31 to it is described camera shooting overhead pass data handle, it is described
The car-mounted terminal of automobile 10 or other terminals, can by pre-registered user name password login to the network platform,
To obtain the processing result of the processing unit 31, and carry out the operations such as corresponding display.
And it is further, the warehouse compartment image display module can be the vehicle-mounted display terminal for being integrated in the automobile 10
In, or may be to be integrated in the smart phone.
The technical solution of the warehouse compartment detection system 30 is corresponding with the technical solution of the warehouse compartment detection method 10, owns
The description as described in the warehouse compartment detection method 10 can be applied in the present embodiment.
In conclusion warehouse compartment detection method, system and mobile device of the invention, according to the image that camera is shot, shape
At the image about the mobile device；It extracts in described image in the possibility warehouse compartment region near the mobile device
All straight lines；According to preset warehouse compartment feature, effective straight line in all straight lines is extracted as warehouse compartment line, according to
Warehouse compartment line obtains each warehouse compartment location information in the possible warehouse compartment region.The warehouse compartment in image that the present invention shoots camera
The straight line in region is compared with warehouse compartment feature, extracts warehouse compartment location information, and then can accurately orient warehouse compartment
Position, to provide assistance for automatic parking.So the present invention effectively overcomes various shortcoming in the prior art and has height
Value of industrial utilization.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (7)
1. a kind of warehouse compartment detection method, which is characterized in that applied to at least one camera mobile device on, the library
Position detecting method includes:
According to the image of at least one camera shooting, the image of the certain viewing angles about the mobile device is formed；
Extract all straight lines in described image in the possibility warehouse compartment region near the mobile device；
According to preset warehouse compartment feature, effective straight line in all straight lines is extracted as warehouse compartment line, according to the warehouse compartment line
Obtain each warehouse compartment location information in the possible warehouse compartment region；
According to the warehouse compartment location information, the physical location information at least two vertex of the warehouse compartment is extracted, and according to described
The physical location information at least two vertex shows corresponding warehouse compartment figure in preset interactive interface；
When the warehouse compartment shown in the warehouse compartment figure and panoramic picture shown in interactive interface has deviation, the warehouse compartment figure is manually adjusted
Shape is overlapped to corresponding preset warehouse compartment figure.
2. warehouse compartment detection method according to claim 1, it is characterised in that: the warehouse compartment detection method further include:
The image of camera shooting is pre-processed, is formed according to pretreated image about the mobile device
Image；The pretreatment includes at least one of following manner:
Mode one: noise is removed to the image of each camera shooting；
Mode two: calibration correction is carried out according to image of the preset calibration correction rule to each camera shooting；
Mode three: the image of each camera shooting is intercepted, is spliced and video smoothing is handled.
3. warehouse compartment detection method according to claim 1, it is characterised in that: the possibility warehouse compartment area near the mobile device
Domain includes the region being located in the left side pre-determined distance of the mobile device, in the right side pre-determined distance of the mobile device
Region, positioned at the mobile device front preset distance in region, positioned at the rear pre-determined distance of the mobile device
It is interior region, the region in the left front pre-determined distance of the mobile device, pre- positioned at the right front of the mobile device
If distance in region, the region in the left back pre-determined distance of the mobile device or/and be located at the mobile device
Right back pre-determined distance in region.
4. warehouse compartment detection method according to claim 1, it is characterised in that: the warehouse compartment feature includes in following characteristics
It is one or more:
Feature one: preset warehouse compartment shape；
Feature two: spacing of the warehouse compartment by two parallel lines and a vertical line or special angle rectilinear(-al), between the parallel lines
In default warehouse compartment length range；
Feature three: the gray scale difference value of the straight line and other regions that form warehouse compartment is greater than default gray scale difference value threshold value；
Feature four: the shape of adjacent warehouse compartment is identical；
Feature five: warehouse compartment is made of two opposite lines and an intersecting lens, and the spacing between the opposite line is in default warehouse compartment length
In range；The angle of the opposite line and the intersecting lens is within the scope of predetermined angle.
5. a kind of warehouse compartment detection system, it is characterised in that: applied to at least one camera mobile device on, the library
Position detecting system includes communicating the processing unit being connected with the camera, and the processing unit includes:
Image collection module is formed to the image according to all camera shootings about the specific of the mobile device
The image at visual angle；
Lines detection module obtains module communication with described image and is connected, is in the image to extract the certain viewing angles
All straight lines in possibility warehouse compartment region near the mobile device；
Warehouse compartment position information acquisition module is connected, to mention according to preset warehouse compartment feature with lines detection module communication
It takes effective straight line in all straight lines as warehouse compartment line, is obtained according to the warehouse compartment line each in the possible warehouse compartment region
Warehouse compartment location information；
Warehouse compartment image display module is connected with warehouse compartment position information acquisition module communication, according to the warehouse compartment location information,
The physical location information at least two vertex of the warehouse compartment is extracted, and according to the physical bit confidence at least two vertex
Breath, shows corresponding warehouse compartment figure in preset interactive interface；When the warehouse compartment figure and panoramic picture shown in interactive interface
When the warehouse compartment of middle display has deviation, manually adjusts the warehouse compartment figure and be overlapped to corresponding preset warehouse compartment figure.
6. warehouse compartment detection system according to claim 5, which is characterized in that the warehouse compartment detection system further include:
Memory module is connected with the warehouse compartment position information acquisition module communication in the processing unit, is stored with described preset
Warehouse compartment feature；The warehouse compartment feature includes one of following characteristics or a variety of:
Feature one: preset warehouse compartment shape；
Feature two: spacing of the warehouse compartment by two parallel lines and a vertical line or special angle rectilinear(-al), between the parallel lines
In default warehouse compartment length range；
Feature three: the gray scale difference value of the straight line and other regions that form warehouse compartment is greater than default gray scale difference value threshold value；
Feature four: the shape of adjacent warehouse compartment is identical；
Feature five: warehouse compartment is made of two opposite lines and an intersecting lens, and the spacing between the opposite line is in default warehouse compartment length
In range；The angle of the opposite line and the intersecting lens is within the scope of predetermined angle.
7. a kind of mobile device, it is characterised in that: there is at least one camera and such as any one of claim 5~6 institute
The warehouse compartment detection system stated；The mobile device includes automobile or smart phone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610976121.9A CN106541944B (en) | 2016-11-07 | 2016-11-07 | A kind of warehouse compartment detection method, system and mobile device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610976121.9A CN106541944B (en) | 2016-11-07 | 2016-11-07 | A kind of warehouse compartment detection method, system and mobile device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106541944A CN106541944A (en) | 2017-03-29 |
| CN106541944B true CN106541944B (en) | 2019-03-05 |
Family
ID=58394688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610976121.9A Active CN106541944B (en) | 2016-11-07 | 2016-11-07 | A kind of warehouse compartment detection method, system and mobile device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106541944B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6922671B2 (en) * | 2017-11-08 | 2021-08-18 | 株式会社アイシン | Vehicle control device and parking system |
| CN108569280B (en) * | 2017-12-15 | 2020-03-24 | 上海蔚来汽车有限公司 | Method and device for automatic parking, intelligent automobile and computer storage medium |
| CN110322680B (en) * | 2018-03-29 | 2022-01-28 | 纵目科技（上海）股份有限公司 | Single parking space detection method, system, terminal and storage medium based on designated points |
| CN109614913A (en) * | 2018-12-05 | 2019-04-12 | 北京纵目安驰智能科技有限公司 | A kind of oblique parking stall recognition methods, device and storage medium |
| CN110211420B (en) * | 2019-06-25 | 2021-11-30 | 重庆长安汽车股份有限公司 | Method and system for judging whether current scene is parking lot or not and computer readable storage medium |
| CN110443093B (en) * | 2019-07-31 | 2022-07-29 | 安徽大学 | Intelligent-oriented infrared digital panoramic system and warehouse management method thereof |
| CN110472580B (en) * | 2019-08-16 | 2022-04-05 | 北京茵沃汽车科技有限公司 | Method, device and storage medium for detecting parking stall based on panoramic image |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102045546A (en) * | 2010-12-15 | 2011-05-04 | 广州致远电子有限公司 | Panoramic parking assist system |
| CN104512335A (en) * | 2013-10-04 | 2015-04-15 | 爱信精机株式会社 | Parking support apparatus |
| CN104851076A (en) * | 2015-05-27 | 2015-08-19 | 武汉理工大学 | Panoramic 360-degree-view parking auxiliary system for commercial vehicle and pick-up head installation method |
| 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 |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007310591A (en) * | 2006-05-17 | 2007-11-29 | Auto Network Gijutsu Kenkyusho:Kk | Image processor and parking space determination method |
| JP5287344B2 (en) * | 2009-02-26 | 2013-09-11 | 日産自動車株式会社 | Parking assistance device and obstacle detection method |
| JP2012118656A (en) * | 2010-11-30 | 2012-06-21 | Suzuki Motor Corp | Parking frame detection device and parking frame detection method |
| KR20120086576A (en) * | 2011-01-26 | 2012-08-03 | 현대모비스 주식회사 | Parking Assist System |
| KR101877570B1 (en) * | 2012-04-04 | 2018-07-11 | 현대자동차주식회사 | Apparatus for setting parking position based on around view image and method thereof |
| KR101947826B1 (en) * | 2012-04-10 | 2019-02-13 | 현대자동차주식회사 | Method for recognizimg parking mark for vehicle |
| KR101470240B1 (en) * | 2013-11-14 | 2014-12-08 | 현대자동차주식회사 | Parking area detecting apparatus and method thereof |
-
2016
- 2016-11-07 CN CN201610976121.9A patent/CN106541944B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102045546A (en) * | 2010-12-15 | 2011-05-04 | 广州致远电子有限公司 | Panoramic parking assist system |
| CN104512335A (en) * | 2013-10-04 | 2015-04-15 | 爱信精机株式会社 | Parking support apparatus |
| CN104851076A (en) * | 2015-05-27 | 2015-08-19 | 武汉理工大学 | Panoramic 360-degree-view parking auxiliary system for commercial vehicle and pick-up head installation method |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106541944A (en) | 2017-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106541944B (en) | A kind of warehouse compartment detection method, system and mobile device | |
| CN106585627B (en) | Parking assisting system and automobile | |
| CN106772389A (en) | A kind of warehouse compartment detection method, system and mobile device | |
| CN106573576B (en) | The tracking object in bowl-type imaging system | |
| US11048953B2 (en) | Systems and methods for facial liveness detection | |
| US10262466B2 (en) | Systems and methods for adjusting a combined image visualization based on depth information | |
| CN106541914A (en) | A kind of automobile with photographic head and range unit | |
| CN104236478B (en) | Automatic vehicle overall size measuring system and method based on vision | |
| CN111257866A (en) | Target detection method, device and system for linkage of vehicle-mounted camera and vehicle-mounted radar | |
| CN110276317B (en) | Object size detection method, object size detection device and mobile terminal | |
| CN108352056A (en) | System and method for correcting wrong depth information | |
| US20040125207A1 (en) | Robust stereo-driven video-based surveillance | |
| US8805059B2 (en) | Method, system and computer program product for segmenting an image | |
| CN107507239A (en) | A kind of image partition method and mobile terminal | |
| CN110415555A (en) | A kind of recognition methods of effective scribing line parking stall and system based on deep learning | |
| CN104902246A (en) | Video monitoring method and device | |
| CN206900301U (en) | A kind of automobile with camera and range unit | |
| CN102901489A (en) | Pavement water accumulation and ice accumulation detection method and apparatus thereof | |
| US11282180B1 (en) | Object detection with position, pose, and shape estimation | |
| CN108010065A (en) | Low target quick determination method and device, storage medium and electric terminal | |
| CN109410234A (en) | A kind of control method and control system based on binocular vision avoidance | |
| US8682023B2 (en) | Interactive display recognition devices and related methods and systems for implementation thereof | |
| CN110371565A (en) | Intelligent warehousing system | |
| CN107832598B (en) | Unlocking control method and related product | |
| CN109785444A (en) | Recognition methods, device and the mobile terminal of real plane in 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |