CN106127736A - One is parked detection method and processor - Google Patents
One is parked detection method and processor Download PDFInfo
- Publication number
- CN106127736A CN106127736A CN201610423351.2A CN201610423351A CN106127736A CN 106127736 A CN106127736 A CN 106127736A CN 201610423351 A CN201610423351 A CN 201610423351A CN 106127736 A CN106127736 A CN 106127736A
- Authority
- CN
- China
- Prior art keywords
- change
- pixel
- several picture
- detected object
- video camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 88
- 230000008859 change Effects 0.000 claims abstract description 87
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000007405 data analysis Methods 0.000 claims abstract description 8
- 230000000052 comparative effect Effects 0.000 claims abstract description 7
- 230000003287 optical effect Effects 0.000 claims description 54
- 238000004458 analytical method Methods 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 6
- 108010001267 Protein Subunits Proteins 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 8
- 230000007613 environmental effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000005452 bending Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The present invention provides one to park detection method and processor, detection method of parking is applied to moor car detector, described pool car detector includes: processor, light projector and the video camera being installed on vehicle, described method includes: described light projector projects detection light, described detection light intersects with the surface of detected object, forms several picture;Described several picture is shot by described video camera, obtains shooting image;Described processor detects the change in location data of pixel in described shooting image, cross section and the height of described detected object is drawn according to described change in location data analysis, by the cross section of described detected object and compare with the cross section threshold value prestored and height threshold the most respectively, obtain the park information relevant to described detected object according to comparative result.Use this park detection method and processor, detection of parking can be realized efficiently and accurately.
Description
Technical field
The present invention relates to automatic parking technical field, concrete, relate to one and park detection method and processor.
Background technology
Along with vehicle becomes increasingly popular, in modern metropolitan cities, " difficulty of parking " problem gradually manifests, in order to enable in limited space
Marking off more parking stall, the space of each parking stall is more and more narrow, shorter and shorter.For motorist, VEHICLES MUST PARK WITHIN THE MARKED BAY becomes
One no small challenge, automatic parking technology is becoming the high end configuration of various vehicle.During automatic parking, can be real
Can the now accurately detection to parking position directly affect the process of parking and be smoothed out.At present, parking stall measure is mainly by all kinds of
Sensor, such as ultrasonic sensor, laser sensor, the environmental information of shooting first-class acquisition vehicle periphery, searches after being analyzed
Rope goes out one piece and there is not barrier and the sufficiently large coffin of size, as parking place.The most existing parking stall of seeking
Technology is mainly ultrasonic radar, infrared ray sensing, laser radar etc., is all single-point range finding, sparse owing to measuring dot density, ripple
Beam angle is bigger than normal so that when barrier adjacent edges, and measured distance value error is big, affects the precision at edge, affects therewith
Parking stall measurement of length precision so that less, manually park difficulty, need automatically to moor into parking stall on the contrary cannot be automatic
Moor into, or perhaps bigger parking stall could automatically moor into.
Summary of the invention
It is an object of the invention to provide one to park detection method and processor, to improve parking stall of the prior art inspection
The problem that survey mode cannot meet actual demand.
Embodiments of the invention are achieved in that
First aspect, embodiments provides one and parks detection method, is applied to moor car detector, described pool
Car detector includes: processor, light projector and the video camera being installed on vehicle, and described method includes:
Described light projector projects detection light, and described detection light intersects with the surface of detected object, forms geometric graph
Picture;
Described several picture is shot by described video camera, obtains shooting image;
Described processor detects the change in location data of pixel in described shooting image, according to described change in location data
Analyze cross section and the height drawing described detected object, by the cross section of described detected object and the most respectively with prestore
Cross section threshold value and height threshold compare, obtain the park letter relevant to described detected object according to comparative result
Breath.
Further, the detection light that described light projector projects is an optical plane;Described optical plane and detected object
To intersect the several picture that formed be Rhizoma Dioscoreae (peeled) on surface;The shooting image that described video camera obtains is the image containing Rhizoma Dioscoreae (peeled).
Further, during described processor detects described shooting image, the step of the change in location data of pixel includes:
The described image containing Rhizoma Dioscoreae (peeled) is carried out pretreatment;
Detect each pixel that there occurs change in location in described Rhizoma Dioscoreae (peeled) relative to neighbor pixel;
Calculate the subpixel coordinates of each pixel that there occurs change in location, calculated described subpixel coordinates is made
For described change in location data.
Further, described processor is previously stored with calibrating parameters and the demarcation of described optical plane of described video camera
Parameter, the calibrating parameters of described optical plane includes the described optical plane position relative to described video camera;
Described cross section and the step bag of height drawing described detected object according to described change in location data analysis
Include:
Calibrating parameters and the calibrating parameters of described optical plane according to described video camera calculate and there occurs each of change in location
World coordinates corresponding to the subpixel coordinates of pixel, according to the subpixel coordinates institute of each pixel that there occurs change in location
Corresponding world coordinates analysis draws cross section and the height of described detected object.
Further, during described processor detects described shooting image, the step of the change in location data of pixel includes:
Obtain and the gray value of several picture in described shooting image and described shooting image are positioned at described several picture week
The gray value of the retroreflective regions enclosed;
The difference of the gray value of the retroreflective regions around gray value according to described several picture and described several picture is right
Described several picture is split;
Segmented described several picture is carried out medium filtering denoising;
The deformation position of the described several picture of segmented and denoising is carried out sub-pixel edge detection, obtains described shooting
The change in location data of pixel in image.
Second aspect, the embodiment of the present invention additionally provides a kind of processor, is applied to moor car detector, described in park inspection
Survey device includes: be installed on light projector on vehicle, video camera and described processor, and described light projector is used for projecting detection
Light, described detection light intersects with the surface of detected object, forms several picture, and described video camera is for described several picture
Shooting, obtain shooting image, described processor includes controller and memorizer, and in described memorizer, storage has Image Acquisition
Unit, change in location detector unit, analysis judging unit and result output unit;
Described image acquisition unit, for obtaining the shooting image that described video camera obtains;
Described change in location detector unit, for detecting the change in location data of pixel in described shooting image;
Described analysis judging unit, for drawing the transversal of described detected object according to described change in location data analysis
Face and height, by the cross section of described detected object and compare with the cross section threshold value prestored and height threshold the most respectively
Relatively;
Described result output unit, for obtaining the park information relevant to described detected object according to comparative result.
Further, the detection light that described light projector projects is an optical plane;Described optical plane and detected object
To intersect the several picture that formed be Rhizoma Dioscoreae (peeled) on surface;The shooting image that described video camera obtains is the image containing Rhizoma Dioscoreae (peeled);Institute
Stating the described shooting image that image acquisition unit gets is the image containing Rhizoma Dioscoreae (peeled).
Further, described change in location detector unit includes:
Pretreatment subelement, for carrying out pretreatment to the described image containing Rhizoma Dioscoreae (peeled);
Position detection sub-unit, for detecting each picture that there occurs change in location in described Rhizoma Dioscoreae (peeled) relative to neighbor pixel
Vegetarian refreshments;
Computation subunit, for calculating the subpixel coordinates of each pixel that there occurs change in location, by calculated
Described subpixel coordinates is as described change in location data.
Further, in described memorizer, also storage has the calibrating parameters of described video camera and the demarcation ginseng of described optical plane
Number, the calibrating parameters of described optical plane includes the described optical plane position relative to described video camera;
Described analysis judging unit, based on the calibrating parameters of the calibrating parameters according to described video camera and described optical plane
Calculate the world coordinates corresponding to subpixel coordinates of each pixel that there occurs change in location, according to there occurs each of change in location
World coordinates analysis corresponding to the subpixel coordinates of pixel draws cross section and the height of described detected object.
Further, described change in location detector unit includes:
Gray value obtains subelement, for obtaining the gray value of several picture in described shooting image and described shooting image
In the gray value of retroreflective regions that is positioned at around described several picture;
Image division sub-unit, the reflective areas around the gray value according to described several picture and described several picture
The difference of the gray value in territory, splits described several picture;
Denoising subelement, for carrying out medium filtering denoising by segmented described several picture;
Rim detection subelement, for carrying out sub-pix limit to the deformation position of the described several picture of segmented and denoising
Edge detects, and obtains the change in location data of pixel in described shooting image.
Park detection method and the processor that the embodiment of the present invention provides, by processor, light projector and video camera
Deng ingenious setting, enabling intersect with the surface of detected object to be formed by light projector projection being detected light
The analysis of several picture, show whether detected object is the position being suitable for parking, this detection mode of parking, it is possible to quickly essence
The environmental information of surrounding of parking really detected and be accurately detected idle parking position, relative to ultrasound wave of the prior art and
Laser detection mode, the scope of application is wider, and detection is more accurate, and cost performance is higher.
Further, park detection method and the processor that the embodiment of the present invention provides, the light that light projector is launched is permissible
The display lamp parked as position, side, informs that other drivers prepare to park, searching for the information of parking stall, do not have in prior art
Position, side display lamp of parking is had to compare, it is possible to be effectively improved the safety parked.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below by embodiment required use attached
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, and it is right to be therefore not construed as
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to according to this
A little accompanying drawings obtain other relevant accompanying drawings.
A kind of structured flowchart mooring car detector that Fig. 1 provides for the embodiment of the present invention.
A kind of light projector that Fig. 2 provides for the embodiment of the present invention and the scheme of installation of video camera.
The flow chart of a kind of detection method of parking that Fig. 3 provides for the embodiment of the present invention.
A kind of imaging schematic diagram that Fig. 4 provides for the embodiment of the present invention.
A kind of flow chart obtaining change in location data that Fig. 5 provides for the embodiment of the present invention.
The another kind of flow chart obtaining change in location data that Fig. 6 provides for the embodiment of the present invention.
A kind of image-forming principle schematic diagram that Fig. 7 provides for the embodiment of the present invention.
A kind of coordinate system schematic diagram that Fig. 8 provides for the embodiment of the present invention.
The structural representation of a kind of processor that Fig. 9 provides for the embodiment of the present invention.
The connection diagram of each unit of storage in a kind of memorizer that Figure 10 provides for the embodiment of the present invention.
The structural representation of a kind of change in location detector unit that Figure 11 provides for the embodiment of the present invention.
The structural representation of the another kind of change in location detector unit that Figure 12 provides for the embodiment of the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
The a part of embodiment of the present invention rather than whole embodiments.Generally implement with the present invention illustrated described in accompanying drawing herein
The assembly of example can be arranged with various different configurations and design.
Therefore, detailed description to the embodiments of the invention provided in the accompanying drawings is not intended to limit claimed below
The scope of the present invention, but be merely representative of the selected embodiment of the present invention.Based on the embodiment in the present invention, this area is common
The every other embodiment that technical staff is obtained under not making creative work premise, broadly falls into the model of present invention protection
Enclose.
Prior art use the single-point distance measuring methods such as ultrasonic radar, infrared ray sensing, laser radar visit to improve
Seeking parking stall, certainty of measurement is limited, and cost performance is the highest, it is impossible to the problem meeting actual demand, embodiments provides one
To the surface of inspected object projection detection light, by detection light is intersected formed geometric graph with the surface of detected object
The analysis of picture, show that detected object is if appropriate for the detection scheme of parking parked.
Detection method of parking in the embodiment of the present invention, is applied to pool car detector 100 as shown in Figure 1, described pool
Car detector 100 includes processor 101, light projector 102 and video camera 103, refering to Fig. 1.Wherein, processor 101, light are thrown
Emitter 102 and video camera 103 are installed on vehicle, and wherein, it is many that light projector 102 and video camera 103 may be mounted at vehicle
Individual position, as long as light projector 102 can project detection light to detected object such as parking position, video camera 103 can shoot
Formed several picture is intersected with detected object surface to detection light.Such as: as in figure 2 it is shown, light projector 102 He
Video camera 103 may be mounted at the side of vehicle, it is contemplated that practical situation, and light projector 102 and video camera 103 may be mounted at
The side of vehicle headstock, such as the side-lower of vehicle headstock.It should be noted that, Fig. 2 illustrate only light projector 102 and video camera
The schematic mounting means of one of which of 103.Alternatively, the headstock both sides of vehicle are mounted on light projector 102 and video camera
103, detection analysis vehicle left side and position, side, right side parked with realization.In actual applications, light projector 102 and video camera
103 can install along vehicle lengthwise direction or short transverse installation, it is preferable that light projector 102 and video camera 103 are long along vehicle
Degree direction is installed, because projector 102 and video camera 103 are apart from the most remote, accuracy of detection is the best, and headstock itself is the highest,
But longer, thus, light projector 102 and video camera 103 are installed more preferably along vehicle lengthwise direction.
The side-lower that light projector 102 and video camera 103 are arranged on vehicle headstock makes the headstock of vehicle through to be checked
When surveying object such as certain parking areas, light projector 102 can project detection light to object to be detected, and video camera 103 can be clapped
Taking the photograph detection light and intersect formed several picture with the surface of detected object, processor 101 is by transmitting video camera 103
Shooting image carry out detecting, analyzing, can show that inspected object is if appropriate for parking.Processor 101 judges examined right
As if appropriate for when parking, can be according to the speed v of vehicle and the vehicle traveling when detected object (parking areas)
Between t draw length L=vt of detected object, and then comprehensive descision detected object is if appropriate for parking.
It should be noted that in the embodiment of the present invention, analyze a Rhizoma Dioscoreae (peeled) and can obtain detected object one cross section and height
Degree.Parking stall is a series of cross sections on length L direction and height, and along with the movement of vehicle, detection light is thrown from diverse location
It is incident upon parking stall, forms multiple Rhizoma Dioscoreae (peeled), multiple Rhizoma Dioscoreae (peeled) are all analyzed i.e. can get continuous print cross section and height on length L direction
Degree.By length L of parking stall, the length of continuous print cross section and height and vehicle on length L direction, cross section and highly than
Right, can accurately draw if appropriate for parking.
In order to ensure accuracy of detection, alternatively, video camera is integrated with optical filter and polaroid, to reduce environmental light intensity pair
The impact of detection.Alternatively, light projector includes the multiple projectoies that can project the light of different colours, for example, it is possible to bag
Include three kinds of projectoies of the light that can project three kinds of colors of red, green, blue, be arranged such, three kinds of throwings can be controlled when implementing
Emitter projects light successively and detects respectively, guarantees, by repeated detection, the reliability detected of parking.
As it is shown on figure 3, said method comprising the steps of.
Step S301: described light projector 102 projects detection light, the surface phase of described detection light and detected object
Hand over, form several picture.
Wherein, light projector 102 can be structured light projector 102, and the embodiment of the present invention uses method of structured light to carry out
Detection.Method of structured light is a kind of active optical measurement technology, and ultimate principle is to detected right by structured light projector 102
As surface projects controllable luminous point, Rhizoma Dioscoreae (peeled) or bright finish structure, and obtained image, root by image acquiring device such as video camera 103
Utilize triangle principle etc. can be calculated the three-dimensional coordinate of detected object according to geometrical relationship.
In order to ensure detection efficiency, alternatively, in the embodiment of the present invention, the detection light that described light projector 102 projects
It it is an optical plane.It is Rhizoma Dioscoreae (peeled) that described detection light intersects formed several picture with the surface of detected object.
Step S302: described several picture is shot by described video camera 103, obtains shooting image.
Wherein, when the detection light that light projector 102 projects is an optical plane, described detection light and detected object
It is Rhizoma Dioscoreae (peeled) that the several picture formed is intersected on surface, when correspondingly, the shooting image that described video camera 103 obtains is for containing Rhizoma Dioscoreae (peeled)
Image.
Step S303: described processor 101 detects the change in location data of pixel in described shooting image.
As shown in Figure 4, when detected object is a plane, optical plane intersects with the surface of detected object and to be formed
Several picture is generally straight line 105 or smoothed curve.When a detected object not plane, when there is difference in height, optical plane will
Being deformed upon by the modulation of detected object surface configuration, now optical plane intersects with the surface of detected object and is formed
Several picture there is bending, such as: form folding line 104 or irregular curve, refering to Fig. 4.When several picture exists bending
Time, in image pixel then can exist visibility point change, such as, when optical plane is incident to vehicle B surface, optical plane with
There is " fracture " at the top of vehicle B in the several picture that vehicle B is crossed to form, forms breakpoint, and breakpoint location i.e. represents vehicle
Top.Thus, whether there is bending by analysis several picture and can show whether detected object is a plane.In order to ensure
Detection results, alternatively, during detection, the optical plane that light projector projects is vertical with vehicle heading, and projection
The optical axis of device is slanted through detected object, such as ground.
Step S304: described processor 101 draws the horizontal stroke of described detected object according to described change in location data analysis
Cross section and height, by the cross section of described detected object and carried out with the cross section threshold value prestored and height threshold the most respectively
Relatively.
Step S303 detects and has obtained shooting the change in location data of pixel in image, due to pixel in shooting image
The change in location of point is directly related with the change of detected object surface configuration, if learning, in shooting image, the position of pixel becomes
Changing the corresponding relation of data and the change of detected object surface configuration, processor 101 can be by the change in location to pixel
The analysis of data draws cross section and the height of detected object.
Alternatively, in the embodiment of the present invention, described processor 101, it is previously stored with the demarcation ginseng of described video camera 103
Number and the calibrating parameters of described optical plane, the calibrating parameters of described optical plane includes that described optical plane is relative to described video camera
The position of 103.Calibrating parameters according to video camera 103 can draw the shooting image of video camera 103 and the ratio of real image
Relation, can obtain exit plane projection formed several picture and the actual figure of object after object according to the calibrating parameters of optical plane
The proportionate relationship of picture.
Presetting by above-mentioned calibrating parameters, processor 101 just can be according to the calibrating parameters of described video camera 103 and described
The calibrating parameters of optical plane calculates the world coordinates corresponding to subpixel coordinates of each pixel that there occurs change in location, according to
There occurs that the world coordinates analysis corresponding to subpixel coordinates of each pixel of change in location draws described detected object
Cross section and height.
Step S305: described processor 101, obtains the park letter relevant to described detected object according to comparative result
Breath.
Assume that a certain detected object is a parking position, if parking position having been parked vehicle, as shown in Figure 4, on A car
The geometric figure that the region detection parking vehicle B is drawn by pool car detector 100 is folding line 104, picture in shooting image
The change in location data of vegetarian refreshments are the change in location in bending region, and the calculating by the world coordinates to deformation position pixel can
Draw relative position relation, such as: according to parameter, " breakaway poing " in figure is carried out calculating and can draw existing car in parking position
Height, carry out Rhizoma Dioscoreae (peeled) length calculating the width that can draw in parking position existing vehicle, thus may determine that and park
Existed in Wei have one fixed width be, height object, be not suitable for parking.Contrary, if parking position does not parks cars,
The geometric figure gone out is straight line 105, it is known that parking position is a horizontal plane, and the length of the straight line i.e. width of horizontal plane is the most permissible
Judging not exist in parking position vehicle, if horizontal plane width is more than vehicle width, then explanation is suitable for parking.
In actual applications, the change in location of pixel during processor 101 can use various ways detection shooting image
Data, list following two mode in the present embodiment.
First kind of way, as it is shown in figure 5, comprise the following steps.
Step S401: the described image containing Rhizoma Dioscoreae (peeled) is carried out pretreatment.
Step S402: detect each pixel that there occurs change in location in described Rhizoma Dioscoreae (peeled) relative to neighbor pixel.
Step S403: calculate the subpixel coordinates of each pixel that there occurs change in location, by calculated described Asia
Pixel coordinate is as described change in location data.
It should be noted that, in the application, it is also possible to after the image containing Rhizoma Dioscoreae (peeled) is carried out pretreatment, pass through optical losses
The method of line detection obtains the subpixel coordinates of optical losses point, and detection becomes containing the position of Rhizoma Dioscoreae (peeled) pixel in the image of Rhizoma Dioscoreae (peeled)
Change, find out and there occurs that the subpixel coordinates of obvious deformation is as change in location data relative to optical losses point.
The second way, as shown in Figure 6, comprises the following steps.
Step S501: obtain the gray value of several picture in described shooting image and described shooting image are positioned at described several
The gray value of the retroreflective regions of what image peripheral.
Step S502: according to the gray value of the retroreflective regions around the gray value of described several picture and described several picture
Difference, described several picture is split.
Step S503: segmented described several picture is carried out medium filtering denoising.
Step S504: the deformation position of the described several picture of segmented and denoising is carried out sub-pixel edge detection,
The change in location data of pixel in described shooting image.
In actual applications, the determination of the calibrating parameters of the calibrating parameters of video camera 103, optical plane and video camera 103, light
The installation site of projector 102 and towards relevant.In the embodiment of the present invention, alternatively, the Dan Ping proposed based on Zhang Zhengyou is used
Face gridiron pattern scaling method, demarcates the calibrating parameters of video camera 103, optical plane.Such as: can be by video camera 103 He
Light projector 102 is fixed on the side-lower of front lower place, the side such as headstock of vehicle, and holding position is constant, opens light projector 102, profit
Scaling board 200 image gathering several different positions and poses with video camera 103 (includes position when optical plane and scaling board 200 are coplanar
Appearance).Monoplane based on Zhang Zhengyou gridiron pattern standardizition, utilizes the scaling board 200 each pose of image that video camera 103 collects
Under angular coordinate (pixel coordinate and world coordinates), solve inside and outside parameter and the distortion factor of video camera 103, set up local generation
The world coordinates of measured point and the corresponding relation of its pixel coordinate in boundary's coordinate system, i.e. this pose lower plane.Utilize from all not
With pixel coordinate and the world coordinates of the angle point extracted in scaling board 200 image of pose, to video camera 103 inner parameter square
Battle array and distortion factor are optimized refinement.Set up the relation between optical plane and video camera 103 imaging, choose scaling board 200 He
Local world coordinate system when light is coplanar, as overall situation world coordinate system, finally determines the world of measured point on this pose lower plane
Corresponding relation between coordinate and its pixel coordinate.Framework refering to Fig. 7 and Fig. 8.Wherein, Zhang Zhengyou standardizition is between tradition
A kind of method between scaling method and self-calibrating method, it is high that it had both avoided traditional method equipment requirements, and complex operation etc. lacks
Point, the most relatively self-calibrating method precision is high, meets the calibration request of detection of parking.
Should be understood that and can also realize in image by setting up imaging model based on machine vision technique in actual applications
Pixel is corresponding with by side object actual coordinate, on this basis, in conjunction with calibration technique, image feature extraction techniques etc.
Realize detected object if appropriate for the reliable detection parked.
Owing to video camera 103 may be installed multiple positions of vehicle, a frame of reference is selected to describe video camera 103
Position, and with it, the position of any object in environment is described, this coordinate system is referred to as world coordinate system.Video camera 103 coordinate system
And the relation between world coordinate system can describe with translation vector with spin matrix.
In the embodiment of the present invention, project an optical plane by light projector 102 at traveling automobile side, project
Optical plane intersects with surrounding objects surface object, if body surface is a standard flat, light forms a bright straight line in space, no
Then optical plane will be deformed upon by object surface shape modulation.From another direction different from projecting direction, with shooting
Machine 103 shoots the image of this Rhizoma Dioscoreae (peeled) and detects the change in location of pixel in Rhizoma Dioscoreae (peeled), right by realizing the analysis of change in location
Park the reliable perception of environment.The present invention, can have based on laser radar with the parking stall measure of ultrasonic radar relative to existing
Effect ground improves the detection accuracy of automatic parking parking stall, can not only the environmental information that is above the ground level of perception, additionally it is possible to perception is less than
The environmental information on ground, detects data more fully, and cost is lower, applied range.
The embodiment of the present invention additionally provides a kind of processor 101, is applied to moor car detector 100.Described detection of parking
Device 100 includes being installed on light projector 102 on vehicle, video camera 103 and described processor 101.Described light projector 102 is used
In projecting detection light, described detection light intersects with the surface of detected object, forms several picture, and described video camera 103 is used
In described several picture is shot, obtain shooting image.
As it is shown in figure 9, described processor 101 includes controller 202 and memorizer 201, storing in described memorizer 201 has
Image acquisition unit 1011, change in location detector unit 1012, analysis judging unit 1013 and result output as shown in Figure 10
Unit 1014.
Wherein, image acquisition unit 1011 is for obtaining the shooting image that described video camera 103 obtains.
Change in location detector unit 1012 is for detecting the change in location data of pixel in described shooting image.About institute
Rheme is put the description of change-detection unit 1012 and specifically can be joined the description of step S303 in Fig. 3.That is, described step S303 can
To be performed by described change in location detector unit 1012.
Analyze judging unit 1013 for drawing the transversal of described detected object according to described change in location data analysis
Face and height, by the cross section of described detected object and compare with the cross section threshold value prestored and height threshold the most respectively
Relatively.Description about described analysis judging unit 1013 specifically can be joined the description of step S304 in Fig. 3.That is, described step
S304 can be performed by described analysis judging unit 1013.
Result output unit 1014 is for obtaining the park information relevant to described detected object according to comparative result.Close
The description of step S305 in the description of described result output unit 1014 specifically can be joined Fig. 3.That is, described step S305 can
To be performed by described result output unit 1014.
Alternatively, the detection light that described light projector 102 projects is an optical plane.Described detection light and detected object
To intersect the several picture that formed be Rhizoma Dioscoreae (peeled) on surface.The shooting image that described video camera 103 obtains is the image containing Rhizoma Dioscoreae (peeled).
The described shooting image that described image acquisition unit 1011 gets is the image containing Rhizoma Dioscoreae (peeled).
Wherein, change in location detector unit 1012 can have multiple implementation.Such as: as shown in figure 11, described position
Change-detection unit 1012 includes pretreatment subelement 1021, position detection sub-unit 1022 and computation subunit 1023.
Pretreatment subelement 1021 is for carrying out pretreatment to the described image containing Rhizoma Dioscoreae (peeled).About described pretreatment sub-list
The description of unit 1021 specifically can be joined the description of step S401 in Fig. 5.That is, described step S401 can be by described pretreatment
Unit 1021 performs.
Position detection sub-unit 1022 there occurs change in location for detecting in described Rhizoma Dioscoreae (peeled) relative to neighbor pixel
Each pixel.Description about described position detection sub-unit 1022 specifically can be joined the description of step S402 in Fig. 5.That is,
Described step S402 can be performed by described position detection sub-unit 1022.
Computation subunit 1023, for calculating the subpixel coordinates of each pixel that there occurs change in location, will be calculated
Described subpixel coordinates as described change in location data.Description about described computation subunit 1023 specifically can be joined figure
The description of step S403 in 5.That is, described step S403 can be performed by described computation subunit 1023.
The most such as: as shown in figure 12, described change in location detector unit 1012 includes that gray value obtains subelement 1024, figure
As segmentation subelement 1025, denoising subelement 1026 and rim detection subelement 1027.
Gray value obtains subelement 1024 for obtaining the gray value of several picture in described shooting image and described shooting
The gray value of the retroreflective regions being positioned in image around described several picture.Retouching of subelement 1024 is obtained about described gray value
State and specifically can join the description of step S501 in Fig. 6.That is, described step S501 can be obtained subelement by described gray value
1024 perform.
It is anti-that image division sub-unit 1025 is used for around the gray value according to described several picture and described several picture
The difference of the gray value in light region, splits described several picture.Description about described image division sub-unit 1025
Specifically can join the description of step S502 in Fig. 6.That is, described step S502 can be by described image division sub-unit 1025
Perform.
Wherein, denoising subelement 1026 is for carrying out medium filtering denoising by segmented described several picture.About institute
The description stating denoising subelement 1026 specifically can be joined the description of step S503 in Fig. 6.That is, described step S503 can be by institute
State denoising subelement 1026 to perform.
Rim detection subelement 1027 for carrying out sub-picture to the deformation position of the described several picture of segmented and denoising
Element rim detection, obtains the change in location data of pixel in described shooting image.About described rim detection subelement 1027
Description specifically can join the description of step S504 in Fig. 6.That is, described step S504 can be by described rim detection subelement
1027 perform.
Alternatively, described memorizer 201 also stores calibrating parameters and the demarcation of described optical plane having described video camera 103
Parameter, the calibrating parameters of described optical plane includes the described optical plane position relative to described video camera 103.Described analysis judges
Unit 1013, the calibrating parameters for the calibrating parameters according to described video camera 103 and described optical plane calculates and there occurs position
The world coordinates corresponding to subpixel coordinates of each pixel of change, according to the Asia picture of each pixel that there occurs change in location
Element world coordinates analysis corresponding to coordinate draws cross section and the height of described detected object.
The processor 101 that the embodiment of the present invention is provided, it realizes principle and the technique effect of generation and preceding method is real
Execute example to be similar to, for briefly describing, the not mentioned part of processor 101 embodiment part, refer in preceding method embodiment corresponding
Content.
Should be understood that the processor 101 in the embodiment of the present invention can include above-mentioned memorizer 201, the base of controller 202
On plinth, it is also possible to include mixed-media network modules mixed-media 203, refering to Fig. 9.
Memorizer 201 can be used for storing software program and module, such as the program in embodiment of the present invention Figure 10~Figure 12
Instruction/unit, controller 202 is stored in the software program in memorizer 201 and unit by operation, thus performs various merit
Can application and data process, the detection method of parking provided such as the embodiment of the present invention.Memorizer 201 can include depositing at random at a high speed
Reservoir, may also include nonvolatile memory, such as one or more magnetic storage device, flash memory or other are non-volatile
Solid-state memory.Software program and module in above-mentioned memorizer 201 may also include that operating system 221 and service module
222.Wherein operating system 221 can be Linux, Unix, Windows, Android or other are such as BIOS etc., and it can include respectively
Plant and be used for managing component software and/or the driving of system task (such as memory management, storage device control, power management etc.),
And can communication mutual with various hardware or component software, thus provide the running environment of other component softwares.Service module 222 is transported
Go on the basis of operating system 221, and monitor the request of automatic network by the network service of operating system 221, according to asking
Corresponding data have been asked to process.It is to say, service module 222 is provided for network service.
Mixed-media network modules mixed-media 203 is for setting up the communication connection between processor 101 and external communications terminals by network, it is achieved
The transmitting-receiving operation of network signal and data.Above-mentioned network signal can include wireless signal or wire signal.
Being appreciated that the structure shown in Fig. 9 is only signal, processor 101 may also include more more than shown in Fig. 9 or more
Few assembly, or there is the configuration different from shown in Fig. 9.Each assembly shown in Fig. 9 can use hardware, software or its group
Close and realize.
It should also be noted that similar label and letter represent similar terms, therefore, the most a certain Xiang Yi in following accompanying drawing
Individual accompanying drawing is defined, then need not it be defined further and explains in accompanying drawing subsequently.
Flow chart and block diagram in accompanying drawing show the system of multiple embodiments according to the present invention, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.In this, each square frame in flow chart or block diagram can generation
One module of table, program segment or a part for code, a part for described module, program segment or code comprises one or more use
Executable instruction in the logic function realizing regulation.It should also be noted that at some as in the realization replaced, square frame is marked
The function of note can also occur to be different from the order marked in accompanying drawing.Such as, two continuous print square frames can essentially base
Originally being performed in parallel, they can also perform sometimes in the opposite order, and this is depending on involved function.It is also noted that
It is, the combination of the square frame in each square frame in block diagram and/or flow chart and block diagram and/or flow chart, can be with performing rule
The special hardware based system of fixed function or action realizes, or can be by the group of specialized hardware with computer instruction
Incompatible realization.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.All within the spirit and principles in the present invention, that is made any repaiies
Change, equivalent, improvement etc., should be included within the scope of the present invention.It should also be noted that similar label and letter exist
Figure below represents similar terms, therefore, the most a certain Xiang Yi accompanying drawing is defined, is then not required in accompanying drawing subsequently
It is defined further and explains.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is not limited thereto, and any
Those familiar with the art, in the technical scope that the invention discloses, can readily occur in change or replace, should contain
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with described scope of the claims.
Claims (10)
1. park a detection method, be applied to moor car detector, it is characterised in that described pool car detector includes: peace
Processor, light projector and the video camera being loaded on vehicle, described method includes:
Described light projector projects detection light, and described detection light intersects with the surface of detected object, forms several picture;
Described several picture is shot by described video camera, obtains shooting image;
Described processor detects the change in location data of pixel in described shooting image, according to described change in location data analysis
Draw cross section and the height of described detected object, by the cross section of described detected object and the most respectively with the horizontal stroke prestored
Cross section threshold value and height threshold compare, and obtain the park information relevant to described detected object according to comparative result.
Detection method of parking the most according to claim 1, it is characterised in that the detection light that described light projector projects is
One optical plane;It is Rhizoma Dioscoreae (peeled) that described optical plane intersects formed several picture with the surface of detected object;Described video camera obtains
To shooting image be the image containing Rhizoma Dioscoreae (peeled).
Detection method of parking the most according to claim 2, it is characterised in that described processor detects in described shooting image
The step of the change in location data of pixel includes:
The described image containing Rhizoma Dioscoreae (peeled) is carried out pretreatment;
Detect each pixel that there occurs change in location in described Rhizoma Dioscoreae (peeled) relative to neighbor pixel;
Calculate the subpixel coordinates of each pixel that there occurs change in location, using calculated described subpixel coordinates as institute
Rheme puts delta data.
Detection method of parking the most according to claim 3, it is characterised in that take the photograph described in being previously stored with in described processor
The calibrating parameters of camera and the calibrating parameters of described optical plane, the calibrating parameters of described optical plane include described optical plane relative to
The position of described video camera;
Described according to described change in location data analysis draw described detected object cross section and height step include:
Calibrating parameters and the calibrating parameters of described optical plane according to described video camera calculate each pixel that there occurs change in location
Point the world coordinates corresponding to subpixel coordinates, according to there occurs change in location each pixel subpixel coordinates corresponding to
World coordinates analysis draw described detected object cross section and height.
Detection method of parking the most according to claim 2, it is characterised in that described processor detects in described shooting image
The step of the change in location data of pixel includes:
Obtain in the gray value of several picture in described shooting image and described shooting image and be positioned at around described several picture
The gray value of retroreflective regions;
The difference of the gray value of the retroreflective regions around gray value according to described several picture and described several picture, to described
Several picture is split;
Segmented described several picture is carried out medium filtering denoising;
The deformation position of the described several picture of segmented and denoising is carried out sub-pixel edge detection, obtains described shooting image
The change in location data of middle pixel.
6. a processor, it is characterised in that being applied to moor car detector, described pool car detector includes: be installed on car
Light projector, video camera and described processor on, described light projector is used for projecting detection light, and described detection light is with tested
The surface surveying object is intersected, and forms several picture, and described video camera, for shooting described several picture, obtains shooting figure
Picture, described processor includes controller and memorizer, and in described memorizer, storage has the detection of image acquisition unit, change in location single
Unit, analysis judging unit and result output unit;
Described image acquisition unit, for obtaining the shooting image that described video camera obtains;
Described change in location detector unit, for detecting the change in location data of pixel in described shooting image;
Described analysis judging unit, for according to described change in location data analysis draw described detected object cross section and
Highly, by the cross section of described detected object and compare with the cross section threshold value prestored and height threshold the most respectively;
Described result output unit, for obtaining the park information relevant to described detected object according to comparative result.
Processor the most according to claim 6, it is characterised in that the detection light that described light projector projects is that a light is put down
Face;It is Rhizoma Dioscoreae (peeled) that described optical plane intersects formed several picture with the surface of detected object;The bat that described video camera obtains
Taking the photograph image is the image containing Rhizoma Dioscoreae (peeled);The described shooting image that described image acquisition unit gets is the image containing Rhizoma Dioscoreae (peeled).
Processor the most according to claim 7, it is characterised in that described change in location detector unit includes:
Pretreatment subelement, for carrying out pretreatment to the described image containing Rhizoma Dioscoreae (peeled);
Position detection sub-unit, for detecting each pixel that there occurs change in location in described Rhizoma Dioscoreae (peeled) relative to neighbor pixel
Point;
Computation subunit, for calculating the subpixel coordinates of each pixel that there occurs change in location, by calculated described
Subpixel coordinates is as described change in location data.
Processor the most according to claim 8, it is characterised in that in described memorizer, also storage has the mark of described video camera
Determining parameter and the calibrating parameters of described optical plane, the calibrating parameters of described optical plane includes that described optical plane is relative to described shooting
The position of machine;
Described analysis judging unit, the calibrating parameters for the calibrating parameters according to described video camera and described optical plane calculates to be sent out
Give birth to the world coordinates corresponding to subpixel coordinates of each pixel of change in location, according to each pixel that there occurs change in location
The world coordinates analysis corresponding to subpixel coordinates of point draws cross section and the height of described detected object.
Processor the most according to claim 7, it is characterised in that described change in location detector unit includes:
Gray value obtains subelement, position in the gray value obtaining several picture in described shooting image and described shooting image
The gray value of the retroreflective regions around described several picture;
Image division sub-unit, the retroreflective regions around the gray value according to described several picture and described several picture
The difference of gray value, splits described several picture;
Denoising subelement, for carrying out medium filtering denoising by segmented described several picture;
Rim detection subelement, for carrying out sub-pixel edge inspection to the deformation position of the described several picture of segmented and denoising
Survey, obtain the change in location data of pixel in described shooting image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610423351.2A CN106127736A (en) | 2016-06-15 | 2016-06-15 | One is parked detection method and processor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610423351.2A CN106127736A (en) | 2016-06-15 | 2016-06-15 | One is parked detection method and processor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106127736A true CN106127736A (en) | 2016-11-16 |
Family
ID=57270728
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610423351.2A Pending CN106127736A (en) | 2016-06-15 | 2016-06-15 | One is parked detection method and processor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106127736A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107643049A (en) * | 2017-09-26 | 2018-01-30 | 沈阳理工大学 | Vehicle position detection system and method on weighbridge based on monocular structure light |
CN107719361A (en) * | 2017-10-10 | 2018-02-23 | 深圳市豪恩汽车电子装备股份有限公司 | Automatic parking householder method and system based on image vision |
CN112132089A (en) * | 2020-09-28 | 2020-12-25 | 天津天地伟业智能安全防范科技有限公司 | Excavator behavior analysis method based on 3D convolution and optical flow |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101308014A (en) * | 2008-07-09 | 2008-11-19 | 北京理工大学 | System and method for determining position posture adopting multi- bundle light |
CN103112453A (en) * | 2013-02-01 | 2013-05-22 | 奇瑞汽车股份有限公司 | Intelligence parking auxiliary system |
CN103600707A (en) * | 2013-11-06 | 2014-02-26 | 同济大学 | Parking position detecting device and method of intelligent parking system |
CN105513410A (en) * | 2015-11-25 | 2016-04-20 | 成都臻识科技发展有限公司 | Parking stall identification method and apparatus based on invisible structured light projection |
-
2016
- 2016-06-15 CN CN201610423351.2A patent/CN106127736A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101308014A (en) * | 2008-07-09 | 2008-11-19 | 北京理工大学 | System and method for determining position posture adopting multi- bundle light |
CN103112453A (en) * | 2013-02-01 | 2013-05-22 | 奇瑞汽车股份有限公司 | Intelligence parking auxiliary system |
CN103600707A (en) * | 2013-11-06 | 2014-02-26 | 同济大学 | Parking position detecting device and method of intelligent parking system |
CN105513410A (en) * | 2015-11-25 | 2016-04-20 | 成都臻识科技发展有限公司 | Parking stall identification method and apparatus based on invisible structured light projection |
Non-Patent Citations (1)
Title |
---|
边琰 等: "基于线结构光的工件台阶特征尺寸测量方法研究", 《机床与液压》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107643049A (en) * | 2017-09-26 | 2018-01-30 | 沈阳理工大学 | Vehicle position detection system and method on weighbridge based on monocular structure light |
CN107643049B (en) * | 2017-09-26 | 2023-06-20 | 沈阳理工大学 | System and method for detecting vehicle position on wagon balance based on monocular structured light |
CN107719361A (en) * | 2017-10-10 | 2018-02-23 | 深圳市豪恩汽车电子装备股份有限公司 | Automatic parking householder method and system based on image vision |
CN112132089A (en) * | 2020-09-28 | 2020-12-25 | 天津天地伟业智能安全防范科技有限公司 | Excavator behavior analysis method based on 3D convolution and optical flow |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11320833B2 (en) | Data processing method, apparatus and terminal | |
KR102614323B1 (en) | Create a 3D map of a scene using passive and active measurements | |
US10591277B2 (en) | Method and system for measuring outermost dimension of a vehicle positioned at an inspection station | |
Bounini et al. | Autonomous vehicle and real time road lanes detection and tracking | |
KR102420476B1 (en) | Apparatus and method for estimating location of vehicle and computer recordable medium storing computer program thereof | |
JP2020085886A (en) | Vehicle, vehicle positioning system, and method for positioning vehicle | |
CN110174093A (en) | Localization method, device, equipment and computer readable storage medium | |
US20110205340A1 (en) | 3d time-of-flight camera system and position/orientation calibration method therefor | |
CN106289159B (en) | Vehicle distance measurement method and device based on distance measurement compensation | |
CN110008893A (en) | A kind of automobile driving running deviation automatic testing method based on vehicle-mounted imaging sensor | |
CN109141347A (en) | Vehicle-mounted vidicon distance measuring method and device, storage medium and electronic equipment | |
KR20200001471A (en) | Apparatus and method for detecting lane information and computer recordable medium storing computer program thereof | |
CN209181784U (en) | A kind of video grammetry device applied to automated parking system | |
CN109859260A (en) | Determine the method, apparatus and computer readable storage medium of parking stall position | |
CN107390285A (en) | A kind of foreign body detection system for airfield runway based on structure light | |
CN106127736A (en) | One is parked detection method and processor | |
US20190362512A1 (en) | Method and Apparatus for Estimating a Range of a Moving Object | |
CN108680157A (en) | A kind of planing method, device and the terminal in detection of obstacles region | |
CN207816198U (en) | Vehicle length measuring device and vehicle outer profile measuring system | |
CN111160132B (en) | Method and device for determining lane where obstacle is located, electronic equipment and storage medium | |
US20230177724A1 (en) | Vehicle to infrastructure extrinsic calibration system and method | |
CN107462742A (en) | Speed measurement method, measurement apparatus, measuring system and vehicle | |
CN111316324A (en) | Automatic driving simulation system, method, equipment and storage medium | |
CN109579798A (en) | A kind of video grammetry method and measuring equipment applied to automated parking system | |
CN108122244B (en) | Video speed measuring method and device for video image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161116 |
|
RJ01 | Rejection of invention patent application after publication |