CN108280853A - Vehicle-mounted vision positioning method, device and computer readable storage medium - Google Patents
Vehicle-mounted vision positioning method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN108280853A CN108280853A CN201810025533.3A CN201810025533A CN108280853A CN 108280853 A CN108280853 A CN 108280853A CN 201810025533 A CN201810025533 A CN 201810025533A CN 108280853 A CN108280853 A CN 108280853A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- trolley
- angle point
- vision positioning
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
-
- 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
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Navigation (AREA)
Abstract
The invention discloses a kind of vehicle-mounted vision positioning methods, by when completing the installation of vehicle-mounted camera, obtaining the inside and outside parameter of the vehicle-mounted camera；Then in the angle point on detecting travelling route, the coordinate of the angle point and the relative position of the angle point and trolley are obtained；It is based on the angular coordinate and relative position later, obtains the location information of trolley.The invention also discloses a kind of vehicle-mounted vision positioning device and computer readable storage mediums.This method can make trolley after receiving the routing information planned in advance, identify the angle point at crossing, and then obtain the current position of trolley, eliminate the step of being laid with guide wire, rely solely on detection and identification that vehicle-mounted camera realizes angle point, so that trolley is advanced flexibly, cost is reduced, adaptability is enhanced.
Description
Technical field
The present invention relates to a kind of technical field of automatic control more particularly to vehicle-mounted vision positioning method, device and calculating
Machine readable storage medium storing program for executing.
Background technology
Currently, automated guided vehicle AGV (Automated Guided Vehicle) has been widely used for automating
Logistic storage field is all kinds of materials of storage and transportation and logistic storage system as the important equipment in modernization industry logistics system
System flexibility, integrated Effec-tive Function provide important guarantee.Simultaneously as AGV has intelligence degree height, travelling speed
Soon, the advantages that saving space, will be used wider and wider general.
For AGV as a kind of intelligent mobile robot, it is one that external environment perception, intelligent decision, movement control technology, which are melted,
Body assumes responsibility for the task that material in Intelligent logistics carries conveying.The intelligent AGV trolleies used in current logistic storage are according to guiding
The difference of mode is broadly divided into the types such as magnetic cuiding, optics/tape guidance, laser/infrared seeker and visual guidance.
Wherein, electromagnetism guide mode is more traditional, but due to needing to be laid with metallic cable in advance, because operating path changes difficulty, and
And it is more demanding to ground environment；Optics or tape guidance are similar with electromagnetism guiding, but need to paste on the ground reflective tape or
Person's tape, and periodic maintenance；Laser or infrared seeker needs assemble special scanner on AGV, and arrange enough
Reflecting plate, this mode is of high cost, and installation is complicated；Trackless independent navigation is one kind in visual guidance, and intelligent at present
A kind of highest guidance technology of degree.
The above is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that the above is existing skill
Art.
Invention content
The main purpose of the present invention is to provide a kind of vehicle-mounted vision positioning method, device and computer-readable storage mediums
Matter, it is intended to solve trackless independent navigation AGV or the technical issues of how other moving trolleys realize positioning in the process of moving.
To achieve the above object, the present invention provides a kind of vehicle-mounted vision positioning method, the method includes：
When completing the installation of vehicle-mounted camera, the inside and outside parameter of the vehicle-mounted camera is obtained；
In the angle point on detecting travelling route, obtain the angle point coordinate and the angle point and trolley it is opposite
Position；
Based on the angular coordinate and relative position, the location information of trolley is obtained.
Preferably, described when completing the installation of vehicle-mounted camera, obtain the step of the inside and outside parameter of the vehicle-mounted camera
Suddenly include：
When completing the installation of vehicle-mounted camera, the vehicle-mounted camera is demarcated；
The inside and outside parameter of vehicle-mounted camera is determined based on the calibration result.
Preferably, described in the angle point on detecting travelling route, obtain the coordinate of the angle point and the angle point
Include with the step of relative position of trolley：
In the process of moving, it is detected using vehicle-mounted camera angle steel joint；
In the angle point on detecting travelling route, the image coordinate of angle point is obtained；
Based on the image coordinate of the angle point, the relative position of the angle point and trolley is obtained.
Preferably, the image coordinate based on the angle point, the step of obtaining the relative position of the angle point and trolley
Including：
When getting the overhead view image of vehicle-mounted camera shooting, the image that trolley is obtained based on the overhead view image is sat
Mark；
The image coordinate of image coordinate and angle point based on the trolley calculates relative distance, is obtained based on the relative distance
Take global relative distance.
Preferably, described the step of being based on the angular coordinate and relative position, obtaining the location information of trolley, includes：
Obtain the global world coordinates of angle point；
The direction of travel of global world coordinates based on the angle point, global relative distance and trolley, determines that trolley exists
Position in global map.
Preferably, described when completing the installation of vehicle-mounted camera, obtain the step of the inside and outside parameter of the vehicle-mounted camera
Before rapid, the method further includes：
The route planning information for importing map and being generated based on the map, is counted and is recorded and passed through in trolley travelling route
Crossing type and each angle point world coordinates.
Preferably, after described the step of being based on the angular coordinate and relative position, obtaining the location information of trolley, institute
The method of stating further includes：
According to the path planned, control trolley turns to.
Preferably, the vehicle-mounted camera is wide-angle camera.
In addition, to achieve the above object, the present invention also provides a kind of vehicle-mounted vision positioning devices, which is characterized in that described
Vehicle-mounted vision positioning device includes：It memory, processor and is stored on the memory and can run on the processor
Vehicle-mounted vision positioning program, when the vehicle-mounted vision positioning program is executed by the processor realize as described in any of the above-described
Vehicle-mounted vision positioning method the step of.
In addition, to achieve the above object, the present invention also provides a kind of computer readable storage mediums, which is characterized in that institute
It states and is stored with vehicle-mounted vision positioning program on computer readable storage medium, the vehicle-mounted vision positioning program is executed by processor
The step of Shi Shixian vehicle-mounted vision positioning methods as described in any one of the above embodiments.
The present invention program, by when completing the installation of vehicle-mounted camera, obtaining the inside and outside parameter of the vehicle-mounted camera；
Then in the angle point on detecting travelling route, the coordinate of the angle point and the opposite position of the angle point and trolley are obtained
It sets；It is based on the angular coordinate and relative position later, obtains the location information of trolley；This method can make receiving in advance
After the routing information planned, the angle point at crossing is identified, and then obtain the current position of trolley, eliminate the step for being laid with guide wire
Suddenly, detection and identification that vehicle-mounted camera realizes angle point are relied solely on so that trolley is advanced flexibly, is reduced cost, is enhanced
Adaptability.
Description of the drawings
Fig. 1 is the knot of the vehicle-mounted affiliated terminal of vision positioning device in the hardware running environment that the embodiment of the present invention is related to
Structure schematic diagram；
Fig. 2 is the flow diagram of the vehicle-mounted vision positioning method first embodiment of the present invention；
Fig. 3 is the crossing schematic diagram of directly turning in the vehicle-mounted vision positioning method first embodiment of the present invention；
Fig. 4 is the T-shaped road junction schematic diagram in the vehicle-mounted vision positioning method first embodiment of the present invention；
Fig. 5 is the crossroad schematic diagram in the vehicle-mounted vision positioning method first embodiment of the present invention；
Fig. 6 is the acquisition in the vehicle-mounted vision positioning method second embodiment of the present invention when completing the installation of vehicle-mounted camera
The refinement flow diagram of the step of inside and outside parameter of the vehicle-mounted camera；
Fig. 7 be in the vehicle-mounted vision positioning method 3rd embodiment of the present invention in the angle point on detecting travelling route, obtain
The refinement flow diagram for the step of taking the coordinate and the relative position of the angle point and trolley of the angle point；
Fig. 8 is the image coordinate based on the angle point in the vehicle-mounted vision positioning method fourth embodiment of the present invention, obtains institute
The refinement flow diagram for the step of stating the relative position of angle point and trolley；
Fig. 9 is trolley and image relative position relation schematic diagram in the vehicle-mounted vision positioning method fourth embodiment of the present invention；
Figure 10 is that trolley shows with crossing angle point relative position relation in the vehicle-mounted vision positioning method fourth embodiment of the present invention
It is intended to；
Figure 11 be the present invention in the 5th embodiment of vision positioning method in be based on the angular coordinate and relative position, obtain
To trolley location information the step of refinement flow diagram.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, the affiliated terminal structure of device for the hardware running environment that Fig. 1, which is the embodiment of the present invention, to be related to shows
It is intended to.
Terminal of the embodiment of the present invention can be PC, can also be smart mobile phone, tablet computer, E-book reader, MP3
(Moving Picture Experts Group Audio Layer III, dynamic image expert's compression standard audio level 3)
Player, MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert's compression standard sound
Frequency level 3) the packaged type terminal device with display function such as player, pocket computer.
As shown in Figure 1, the terminal may include：Processor 1001, such as CPU, network interface 1004, user interface
1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing the connection communication between these components.
User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard), optional user interface
1003 can also include standard wireline interface and wireless interface.Network interface 1004 may include optionally that the wired of standard connects
Mouth, wireless interface (such as WI-FI interfaces).Memory 1005 can be high-speed RAM memory, can also be stable memory
(non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned processor
1001 storage device.
Optionally, terminal can also include camera, RF (Radio Frequency, radio frequency) circuit, sensor, audio
Circuit, WiFi module etc..Wherein, sensor such as optical sensor, motion sensor and other sensors.Specifically, light
Sensor may include ambient light sensor and proximity sensor, wherein ambient light sensor can according to the light and shade of ambient light come
The brightness of display screen is adjusted, proximity sensor can close display screen and/or backlight when mobile terminal is moved in one's ear.As
One kind of motion sensor, gravity accelerometer can detect in all directions the size of (generally three axis) acceleration, quiet
Size and the direction that can detect that gravity when only, the application that can be used to identify mobile terminal posture are (such as horizontal/vertical screen switching, related
Game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.；Certainly, mobile terminal can also match
The other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor are set, details are not described herein.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of terminal structure shown in Fig. 1, can wrap
It includes than illustrating more or fewer components, either combines certain components or different components arrangement.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage media
Believe module, Subscriber Interface Module SIM and vehicle-mounted vision positioning program.
In terminal shown in Fig. 1, network interface 1004 is mainly used for connecting background server, is carried out with background server
Data communicate；User interface 1003 is mainly used for connecting client (user terminal), with client into row data communication；And processor
1001 can be used for calling the vehicle-mounted vision positioning program stored in memory 1005.
In the present embodiment, vehicle-mounted vision positioning device includes：Memory 1005, processor 1001 and it is stored in described deposit
On reservoir 1005 and the vehicle-mounted vision positioning program that can be run on the processor 1001, wherein the calling of processor 1001 is deposited
When the vehicle-mounted vision positioning program stored in reservoir 1005, and execute following operation：
When completing the installation of vehicle-mounted camera, the inside and outside parameter of the vehicle-mounted camera is obtained；
In the angle point on detecting travelling route, obtain the angle point coordinate and the angle point and trolley it is opposite
Position；
Based on the angular coordinate and relative position, the location information of trolley is obtained.
Further, processor 1001 can call the vehicle-mounted vision positioning program stored in memory 1005, also execute
It operates below：
When completing the installation of vehicle-mounted camera, the vehicle-mounted camera is demarcated；
The inside and outside parameter of vehicle-mounted camera is determined based on the calibration result.
Further, processor 1001 can call the vehicle-mounted vision positioning program stored in memory 1005, also execute
It operates below：
In the process of moving, it is detected using vehicle-mounted camera angle steel joint；
In the angle point on detecting travelling route, the image coordinate of angle point is obtained；
Based on the image coordinate of the angle point, the relative position of the angle point and trolley is obtained.
Further, processor 1001 can call the vehicle-mounted vision positioning program stored in memory 1005, also execute
It operates below：
When getting the overhead view image of vehicle-mounted camera shooting, the image that trolley is obtained based on the overhead view image is sat
Mark；
The image coordinate of image coordinate and angle point based on the trolley calculates relative distance, is obtained based on the relative distance
Take global relative distance.
Further, processor 1001 can call the vehicle-mounted vision positioning program stored in memory 1005, also execute
It operates below：
Obtain the global world coordinates of angle point；
The direction of travel of global world coordinates based on the angle point, global relative distance and trolley, determines that trolley exists
Position in global map.
Further, processor 1001 can call the vehicle-mounted vision positioning program stored in memory 1005, also execute
It operates below：
The route planning information for importing map and being generated based on the map, is counted and is recorded and passed through in trolley travelling route
Crossing type and each angle point world coordinates.
Further, processor 1001 can call the vehicle-mounted vision positioning program stored in memory 1005, also execute
It operates below：
According to the path planned, control trolley turns to.
Further, processor 1001 can call the vehicle-mounted vision positioning program stored in memory 1005, also execute
It operates below：
The vehicle-mounted camera is wide-angle camera.
First embodiment of the invention provides a kind of vehicle-mounted vision positioning method, and with reference to Fig. 2, Fig. 2 is the vehicle-mounted vision of the present invention
The flow diagram of localization method first embodiment, the vehicle-mounted vision positioning method include：
Step S100 obtains the inside and outside parameter of the vehicle-mounted camera when completing the installation of vehicle-mounted camera；
It is to obtain the mode of camera inside and outside parameter to carry out calibration to camera or camera.The calibration of camera is in simple terms
It is the conversion from world coordinate system to image coordinate system, that is, seeks the process of final projection matrix.The process of calibration is general
It is divided into two parts, the first step is to be converted to camera coordinates system from world coordinate system, this step is conversion of the three-dimensional point to three-dimensional point,
Including outer parameter；Second step is to switch to image coordinate system from camera coordinates system, this step is conversion of the three-dimensional point to two-dimensional points, packet
Include intrinsic parameter.The reason of being demarcated to vehicle-mounted camera is that the distortion degree of each camera lens is different, utilizes the side of calibration
Formula can calibrate camera come the intrinsic parameter for solving camera and outer parameter, and obtained intrinsic parameter and outer parameter are used for it
Calculating afterwards.
Step S200, in the angle point on detecting travelling route, obtain the angle point coordinate and the angle point with
The relative position of trolley；
Automated guided vehicle AGV (Automated Guided Vehicle) is used as a kind of intelligent mobile robot, will
External environment perception, intelligent decision, movement control technology combine together, assume responsibility for material in Intelligent logistics and carry appointing for conveying
Business.Current logistic storage with intelligent AGV trolleies be broadly divided into this several class according to the difference of guide mode：Electromagnetic induction is led
Draw, optics/tape guidance, laser/infrared seeker and visual guidance etc..Electromagnetism guiding is a kind of more traditional method, skill
Art mature and reliable, cost is relatively low, but due to needing to bury metallic cable on the ground, and operating path changes difficulty, and
And also need to Land leveling.Optics, tape guidance are similar with electromagnetism guiding, need to paste reflective tape or tape on the ground, this
It is convenient that kind mode is guided than electromagnetism, but needs to do periodic maintenance to reflective tape or tape.And laser, infrared seeker be
Equipment can emit and receive the scanner of laser/infrared ray on AGV, and the surrounding of guide area arranges enough reflections as required
Plate, is oriented to and positioning accuracy is higher, but cost is also relatively high, and device installation is complicated, and position calculates also complicated.Visual guidance
It is most potential guide mode, there are mainly two types of modes, one is trackless independent navigation, this guidance technology intelligence journey
Highest is spent, there is also technical bottlenecks at present；Another is fixed_path guided, it is also desirable to a guide wire is drawn on the ground,
Path changes relatively easily, but guide wire is also required to do periodic maintenance.
The coordinate of angle point refers to the image coordinate of angle point, can be obtained by Corner Detection.What vehicle-mounted camera took
Picture is oblique-view image, needs that oblique-view image is converted to overhead view image using camera interior and exterior parameter.The size of image is solid
Fixed, that is, the width and height of image are certain.The overhead view image being converted to based on camera shooting establishes coordinate system, right
For a fixed image coordinate system, the image coordinate of angle point can be obtained by way of Corner Detection, and due to
The size of image is fixed, therefore the image coordinate of trolley can be calculated by formula, that is, trolley is in image coordinate
Position in system.After the specific coordinate put, it can determine by mathematical formulae at the distance between 2 points, for difference
The crossing of type, corresponding angle point quantity is also different, there is several angle points, just have several angle points to trolley distance.Pass through public affairs
What formula was calculated is distance on the image, it is also necessary to image distance is converted into the distance in reality, that is, in the overall situation
Distance in map, in order to which trolley is travelled according to ready-made path planning in advance.
Step S300 is based on the angular coordinate and relative position, obtains the location information of trolley.
The global world coordinates of angle point can be obtained by global map.Assuming that crossing angle point A (X1, Y1) and B (X2,
Y2) it is its global world coordinates, it is assumed that the global world coordinates of trolley is V (X, Y), there is following relational expression：
In the global relative distance L for getting trolley and angle pointAAnd LBWhen, it is anti-to solve above-mentioned relation formula, trolley can be obtained
Global world coordinates, to obtain the global world coordinates of trolley, that is, the position of trolley.
Further, in one embodiment, before step S100, the method further includes：
The route planning information for importing map and being generated based on the map, is counted and is recorded and passed through in trolley travelling route
Crossing type and each angle point world coordinates.
AGV control systems generally can be divided into three class control mode, be central control computer, ground controller and vehicle respectively
Upper controller.Respectively, center-controlling computer is the control command centre of whole system, it is controlled with the ground in each region
Device is communicated, and is managed to each ground controller；Ground controller is then responsible for being monitored the service conditions in region
Management such as the situation of monitoring field device, the utilization rate for counting AGV, traffic control, tracking loading and unloading, sets objectives ground
The type of the position of AGV and tote, quantity are simultaneously transferred to central control computer by location, the address of real-time storage trolley；Vehicle
Also chauffeur set controller, main task are to explain and execute from ground controller or ground control station transmission is made to upper controller
Instruction, record the position of AGV in real time, and monitor the safety device on vehicle.Wherein, Vehicle Controller is that system is dispatched on AGV vehicles
The core of system, major function include just positioning according to the present invention, and therefore, the vision positioning program in the present invention is also main
It is the supplement carried out to it in the prior art applied to AGV vehicle-mounted controls.
Before AGV is started running, the route planning information of central control system transmission can be received, meanwhile, current work
The map for making environment has been introduced into and is stored in AGV.AGV can be travelled when receiving route planning information in conjunction with map,
But still need during traveling and consider real-time road, therefore detected in real time by vehicle-mounted camera.It is advised in path
It draws in information, including the crossing type passed through in trolley travelling route, and each world coordinates of crossing angle point.Such as Fig. 3, figure
Shown in 4, Fig. 5, the corresponding corner location distribution in each type of crossing is all different.AGV trolleies are receiving route planning information
When, it can also receive the crossing type and sequence that can pass through in travelling route, and the global world coordinates of each crossing angle point.
Further, in one embodiment, after step S300, the method further includes：
According to the path planned, control trolley turns to.
After obtaining the location information of trolley, the next travel direction of trolley can be determined according to the path planned,
It is turned to planning path to control trolley.
The vehicle-mounted vision positioning method proposed in the present embodiment, by when completing the installation of vehicle-mounted camera, obtaining institute
State the inside and outside parameter of vehicle-mounted camera；Then in the angle point on detecting travelling route, obtain the angle point coordinate and
The relative position of the angle point and trolley；It is based on the angular coordinate and relative position later, obtains the location information of trolley；This
Method can make trolley after receiving the routing information planned in advance, identify the angle point at crossing, and then it is current to obtain trolley
Position, eliminate be laid with guide wire the step of, rely solely on vehicle-mounted camera realize angle point detection and identification so that trolley
It advances flexible, reduces cost, enhance adaptability.
Based on first embodiment, the second embodiment of the vehicle-mounted vision positioning method of the present invention is proposed, with reference to Fig. 6, step
S100 includes：
Step S110 demarcates the vehicle-mounted camera when completing the installation of vehicle-mounted camera；
It is to obtain the mode of camera inside and outside parameter to carry out calibration to camera or camera.The calibration of camera is in simple terms
It is the conversion from world coordinate system to image coordinate system, that is, seeks the process of final projection matrix.The process of calibration is general
It is divided into two parts, the first step is to be converted to camera coordinates system from world coordinate system, this step is conversion of the three-dimensional point to three-dimensional point,
Including outer parameter；Second step is to switch to image coordinate system from camera coordinates system, this step is conversion of the three-dimensional point to two-dimensional points, packet
Include intrinsic parameter.The reason of being demarcated to vehicle-mounted camera is that the distortion degree of each camera lens is different, utilizes the side of calibration
Formula can calibrate camera come the intrinsic parameter for solving camera and outer parameter, and obtained intrinsic parameter and outer parameter are used for it
Calculating afterwards.
Step S120 determines the inside and outside parameter of vehicle-mounted camera based on the calibration result.
When being transformed into image coordinate system from camera coordinates system, if it is known that a point X in camera coordinates system, by certain
Transformation, the point corresponding point x in image coordinate system can be obtained, this transformation is expressed as matrix form, x=PX,
Middle P is projection matrix.Aforesaid operations can be transformed into camera coordinates system photo coordinate system, but photo coordinate system and figure
Although in the same plane as coordinate system, origin is not same, and to obtain image coordinate system needs and add
Offset, it is camera intrinsic parameter and projection matrix P=K [I 0] that arrangement, which obtains a matrix K,.Similarly, from world coordinate system
Also to pass through the conversion of matrix, such as translation and rotation to camera coordinates system, final projection matrix P=[R t] can be obtained.
K is commonly referred to as the intrinsic parameter of camera, describes the build-in attribute of camera, including the position of focal length, principal point and pixel with it is true
The size etc. of environment.R and t is known as the outer parameter of camera, and R is a spin matrix, can be converted to three-dimensional rotation to
Amount, indicates that around x, y, the rotation angle of tri- axis of z, t be a translation vector respectively, is illustrated respectively in x, on tri- directions y, z
Translational movement.
The vehicle-mounted vision positioning method proposed in the present embodiment, by complete vehicle-mounted camera installation when, to described
Vehicle-mounted camera is demarcated；It is then based on the inside and outside parameter that the calibration result determines vehicle-mounted camera；Due to each camera shooting
Head all has difference in practical applications, therefore before the use, needs to demarcate the camera lens of camera, get correlation
Parameter, so as to be detected and calculate according to unified standard after ensureing.
Based on first embodiment, the 3rd embodiment of the vehicle-mounted vision positioning method of the present invention is proposed, with reference to Fig. 7, step
S200 includes：
Step S210 is detected using vehicle-mounted camera angle steel joint in the process of moving；
The optimum embodiment of the vehicle-mounted camera is a wide-angle camera, in addition to this it is possible to install multiple non-
Wide-angle camera.Typically, since wide-angle lens focal length is short, visual angle is wide, and the depth of field is very deep, therefore wide-angle camera is excellent
Point is that the scenery of large area can be shot in short-range.Become however, being susceptible to perspective in the picture of wide-angle lens
The focal length of the defect of shape and image distortion, camera lens is shorter, and the distance of shooting is closer, and this defect is more notable.Therefore it needs to carry
It is preceding that camera is demarcated, to realize the calibration of picture, it is ensured that the conversion of world coordinate system and image coordinate system is accurate as possible.
Vehicle-mounted camera detects angle point, serialograph in real time in the process of moving, and is sent to the processor of trolley
Image processing and analysis is carried out to the photo of shooting, the angle point for whether having in photo and meeting the requirements is determined, if there is taking angle
Point illustrates to need to handle there are angle point in the direction of advance of trolley.
Step S220 identifies the angle point in the angle point on detecting travelling route, and obtains the complete of the angle point
Office's world coordinates；
Since the world coordinates of all angle points has been stored in trolley in advance, the position close to angle point at one is often advanced to
When, camera shooting live-pictures on vehicle simultaneously carry out image procossing to photo, are gone out based on route planning information and Map recognition
Angle point, and obtain the coordinate of angle point.For any one photo, the size of image is fixed, and trolley is on overhead view image
Image coordinate can be calculated by the photo of shooting.
Step S230 obtains the relative position of the angle point and trolley based on the image coordinate of the angle point.
After knowing two point coordinates, so that it may which, to get at the distance between 2 points by formula, distance here is vehicle
Carry the image distance on the photo of camera shooting, it is also necessary to be converted to it, the distance in image is converted to globally
Distance in figure.
The vehicle-mounted vision positioning method proposed in the present embodiment, it is diagonal using vehicle-mounted camera by the process of moving
Point is detected；Then it in the angle point on detecting travelling route, identifies the angle point, and obtains the overall situation of the angle point
World coordinates；Image coordinate later based on the angle point, obtains the relative position of the angle point and trolley；By world coordinate system
The problems in be transformed into image coordinate system, realize the simplification of problem, it is only necessary to calculate complete after convert back the world sit
In mark system.
Based on 3rd embodiment, the fourth embodiment of the vehicle-mounted vision positioning method of the present invention is proposed, with reference to Fig. 8, step
S230 includes：
Step S231 obtains trolley when getting the overhead view image of vehicle-mounted camera shooting based on the overhead view image
Image coordinate；
In the image of any one vehicle-mounted camera shooting, a coordinate system is could set up, corresponding trolley is obtained and exists
Relative coordinate in image.For example, as shown in figure 9, dotted rectangle represents the overhead view image that camera acquires, image
Width is width, a height of height, and image coordinate system is established using the image upper left corner as origin o, wherein crossing angle point A (x1, y1) and
The image coordinate of B (x2, y2) can be obtained by Corner Detection, and coordinate of the small truck position V (x, y) on overhead view image can lead to
Formula below crossing is calculated：
X=width/2
Y=height+s
The image coordinate of step S232, image coordinate and angle point based on the trolley calculate relative distance, based on described
Relative distance obtains global relative distance.
As shown in Figure 10, then trolley and crossing angle point on the image at a distance from be：
Then in global map, the distance of small spacing crossing angle point A and B are：
LA=Scale*lA
LB=Scale*lB
The vehicle-mounted vision positioning method proposed in the present embodiment, by the overhead view image for getting vehicle-mounted camera shooting
When, the image coordinate of trolley is obtained based on the overhead view image；It is then based on the image coordinate of the trolley and the image of angle point
Coordinate calculates relative distance, and global relative distance is obtained based on the relative distance；
Based on first embodiment, the 5th embodiment of the vehicle-mounted vision positioning method of the present invention is proposed, referring to Fig.1 1, step
S300 includes：
Step S310 obtains the global world coordinates of angle point；
The global world coordinates of angle point can be obtained by global map.
The direction of travel of step S320, the global world coordinates based on the angle point, global relative distance and trolley,
Determine position of the trolley in global map.
Assuming that the angle point A (X1, Y1) and B (X2, Y2) at crossing are its global world coordinates, it is assumed that the global world of trolley is sat
It is designated as V (X, Y), there is following relational expression：
In the global relative distance L for getting trolley and angle pointAAnd LBWhen, it is anti-to solve above-mentioned relation formula, trolley can be obtained
Global world coordinates.
The vehicle-mounted vision positioning method proposed in the present embodiment, by the global world coordinates for obtaining angle point；It is then based on
The direction of travel of the global world coordinates of the angle point, global relative distance and trolley, determines trolley in global map
Position；The problems in image coordinate system is reverted in global world coordinate system, it is known that angle point is at a distance from small workshop and angle point
Global world coordinates after, the global world coordinates of trolley can be calculated, that is, our required small truck positions,
It is exactly position of the trolley in global map, so as to be advanced according to pre-set path planning guide trolleys or turned
It is curved.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with vehicle-mounted vision positioning program, following operation is realized when the vehicle-mounted vision positioning program is executed by processor：
When completing the installation of vehicle-mounted camera, the inside and outside parameter of the vehicle-mounted camera is obtained；
In the angle point on detecting travelling route, obtain the angle point coordinate and the angle point and trolley it is opposite
Position；
Based on the angular coordinate and relative position, the location information of trolley is obtained.
Further, following operation is also realized when the vehicle-mounted vision positioning program is executed by processor：
When completing the installation of vehicle-mounted camera, the vehicle-mounted camera is demarcated；
The inside and outside parameter of vehicle-mounted camera is determined based on the calibration result.
Further, following operation is also realized when the vehicle-mounted vision positioning program is executed by processor：
In the process of moving, it is detected using vehicle-mounted camera angle steel joint；
In the angle point on detecting travelling route, the image coordinate of angle point is obtained；
Based on the image coordinate of the angle point, the relative position of the angle point and trolley is obtained.
Further, following operation is also realized when the vehicle-mounted vision positioning program is executed by processor：
When getting the overhead view image of vehicle-mounted camera shooting, the image that trolley is obtained based on the overhead view image is sat
Mark；
The image coordinate of image coordinate and angle point based on the trolley calculates relative distance, is obtained based on the relative distance
Take global relative distance.
Further, following operation is also realized when the vehicle-mounted vision positioning program is executed by processor：
Obtain the global world coordinates of angle point；
The direction of travel of global world coordinates based on the angle point, global relative distance and trolley, determines that trolley exists
Position in global map.
Further, following operation is also realized when the vehicle-mounted vision positioning program is executed by processor：
The route planning information for importing map and being generated based on the map, is counted and is recorded and passed through in trolley travelling route
Crossing type and each angle point world coordinates.
Further, following operation is also realized when the vehicle-mounted vision positioning program is executed by processor：
According to the path planned, control trolley turns to.
Further, following operation is also realized when the vehicle-mounted vision positioning program is executed by processor：
The vehicle-mounted camera is wide-angle camera.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements include not only those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this
There is also other identical elements in the process of element, method, article or system.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be expressed in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions use so that a station terminal equipment (can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of vehicle-mounted vision positioning method, which is characterized in that the vehicle-mounted vision positioning method includes：
When completing the installation of vehicle-mounted camera, the inside and outside parameter of the vehicle-mounted camera is obtained；
In the angle point on detecting travelling route, the coordinate of the angle point and the opposite position of the angle point and trolley are obtained
It sets；
Based on the angular coordinate and relative position, the location information of trolley is obtained.
2. vehicle-mounted vision positioning method as described in claim 1, which is characterized in that described in the installation for completing vehicle-mounted camera
When, the step of inside and outside parameter for obtaining the vehicle-mounted camera includes：
When completing the installation of vehicle-mounted camera, the vehicle-mounted camera is demarcated；
The inside and outside parameter of vehicle-mounted camera is determined based on the calibration result.
3. vehicle-mounted vision positioning method as described in claim 1, which is characterized in that the angle on detecting travelling route
When point, the step of coordinate and the relative position of the angle point and trolley for obtaining the angle point, includes：
In the process of moving, it is detected using vehicle-mounted camera angle steel joint；
In the angle point on detecting travelling route, the image coordinate of angle point is obtained；
Based on the image coordinate of the angle point, the relative position of the angle point and trolley is obtained.
4. vehicle-mounted vision positioning method as claimed in claim 3, which is characterized in that the image based on the angle point is sat
The step of mark, the relative position for obtaining the angle point and trolley includes：
When getting the overhead view image of vehicle-mounted camera shooting, the image coordinate of trolley is obtained based on the overhead view image；
The image coordinate of image coordinate and angle point based on the trolley calculates relative distance, is obtained based on the relative distance complete
Office's relative distance.
5. vehicle-mounted vision positioning method as claimed in claim 4, which is characterized in that described based on the angular coordinate and opposite
Position, the step of obtaining the location information of trolley include：
Obtain the global world coordinates of angle point；
The direction of travel of global world coordinates based on the angle point, global relative distance and trolley, determines trolley in the overall situation
Position in map.
6. vehicle-mounted vision positioning method as described in claim 1, which is characterized in that described in the installation for completing vehicle-mounted camera
When, before the step of obtaining the inside and outside parameter of the vehicle-mounted camera, the method further includes：
The route planning information for importing map and being generated based on the map, is counted and records the road passed through in trolley travelling route
The world coordinates of mouth type and each angle point.
7. vehicle-mounted vision positioning method as described in claim 1, which is characterized in that described based on the angular coordinate and opposite
Position, after the step of obtaining the location information of trolley, the method further includes：
According to the path planned, control trolley turns to.
8. vehicle-mounted vision positioning method as described in any one of claim 1 to 7, which is characterized in that the vehicle-mounted camera is
Wide-angle camera.
9. a kind of vehicle-mounted vision positioning device, which is characterized in that the vehicle-mounted vision positioning device includes：Memory, processor
And the vehicle-mounted vision positioning program that is stored on the memory and can run on the processor, the vehicle-mounted vision positioning
It is realized such as the step of vehicle-mounted vision positioning method described in any item of the claim 1 to 8 when program is executed by the processor.
10. a kind of computer readable storage medium, which is characterized in that be stored with vehicle-mounted regard on the computer readable storage medium
Feel finder, is realized as described in any item of the claim 1 to 8 when the vehicle-mounted vision positioning program is executed by processor
The step of vehicle-mounted vision positioning method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810025533.3A CN108280853A (en) | 2018-01-11 | 2018-01-11 | Vehicle-mounted vision positioning method, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810025533.3A CN108280853A (en) | 2018-01-11 | 2018-01-11 | Vehicle-mounted vision positioning method, device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108280853A true CN108280853A (en) | 2018-07-13 |
Family
ID=62803483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810025533.3A Pending CN108280853A (en) | 2018-01-11 | 2018-01-11 | Vehicle-mounted vision positioning method, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108280853A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271892A (en) * | 2018-08-30 | 2019-01-25 | 百度在线网络技术（北京）有限公司 | A kind of object identification method, device, equipment, vehicle and medium |
| CN109636855A (en) * | 2018-12-24 | 2019-04-16 | 济南浪潮高新科技投资发展有限公司 | A kind of system and method for calibrating camera pose |
| CN109782755A (en) * | 2018-12-27 | 2019-05-21 | 广东飞库科技有限公司 | Control AGV calibrated, the method for AGV calibrating position, computer storage medium and AGV |
| CN109871745A (en) * | 2018-12-29 | 2019-06-11 | 百度在线网络技术（北京）有限公司 | Identify method, system and the vehicle of empty parking space |
| CN109977784A (en) * | 2019-02-28 | 2019-07-05 | 北京百度网讯科技有限公司 | For obtaining the method and device of information |
| CN110070581A (en) * | 2019-04-29 | 2019-07-30 | 达泊(东莞)智能科技有限公司 | Double vision open country localization method, apparatus and system |
| CN111760795A (en) * | 2019-07-16 | 2020-10-13 | 北京京东乾石科技有限公司 | Method and device for sorting goods |
| CN112541950A (en) * | 2019-09-20 | 2021-03-23 | 杭州海康机器人技术有限公司 | Method and device for calibrating external parameter of depth camera |
| CN112598922A (en) * | 2020-12-07 | 2021-04-02 | 安徽江淮汽车集团股份有限公司 | Parking space detection method, device, equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101425181A (en) * | 2008-12-15 | 2009-05-06 | 浙江大学 | Panoramic view vision auxiliary parking system demarcating method |
| CN101549683A (en) * | 2009-04-23 | 2009-10-07 | 上海交通大学 | Vehicle intelligent method for automatically identifying road pit or obstruction |
| US20100231717A1 (en) * | 2009-03-16 | 2010-09-16 | Tetsuya Sasaki | Image adjusting device, image adjusting method, and on-vehicle camera |
| US20130325209A1 (en) * | 2012-06-01 | 2013-12-05 | Innovative Electronics, Inc. | Brake controller |
| CN104835173A (en) * | 2015-05-21 | 2015-08-12 | 东南大学 | Positioning method based on machine vision |
| CN105066831A (en) * | 2015-09-09 | 2015-11-18 | 大族激光科技产业集团股份有限公司 | Calibration method of single or multi-robot system cooperative work coordinate system |
| CN105307115A (en) * | 2015-08-07 | 2016-02-03 | 浙江海洋学院 | Distributed vision positioning system and method based on action robot |
| CN106156723A (en) * | 2016-05-23 | 2016-11-23 | 北京联合大学 | A kind of crossing fine positioning method of view-based access control model |
| CN106910217A (en) * | 2017-03-17 | 2017-06-30 | 驭势科技（北京）有限公司 | Vision map method for building up, computing device, computer-readable storage medium and intelligent vehicle |
-
2018
- 2018-01-11 CN CN201810025533.3A patent/CN108280853A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101425181A (en) * | 2008-12-15 | 2009-05-06 | 浙江大学 | Panoramic view vision auxiliary parking system demarcating method |
| US20100231717A1 (en) * | 2009-03-16 | 2010-09-16 | Tetsuya Sasaki | Image adjusting device, image adjusting method, and on-vehicle camera |
| CN101549683A (en) * | 2009-04-23 | 2009-10-07 | 上海交通大学 | Vehicle intelligent method for automatically identifying road pit or obstruction |
| US20130325209A1 (en) * | 2012-06-01 | 2013-12-05 | Innovative Electronics, Inc. | Brake controller |
| CN104835173A (en) * | 2015-05-21 | 2015-08-12 | 东南大学 | Positioning method based on machine vision |
| CN105307115A (en) * | 2015-08-07 | 2016-02-03 | 浙江海洋学院 | Distributed vision positioning system and method based on action robot |
| CN105066831A (en) * | 2015-09-09 | 2015-11-18 | 大族激光科技产业集团股份有限公司 | Calibration method of single or multi-robot system cooperative work coordinate system |
| CN106156723A (en) * | 2016-05-23 | 2016-11-23 | 北京联合大学 | A kind of crossing fine positioning method of view-based access control model |
| CN106910217A (en) * | 2017-03-17 | 2017-06-30 | 驭势科技（北京）有限公司 | Vision map method for building up, computing device, computer-readable storage medium and intelligent vehicle |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271892A (en) * | 2018-08-30 | 2019-01-25 | 百度在线网络技术（北京）有限公司 | A kind of object identification method, device, equipment, vehicle and medium |
| CN109636855A (en) * | 2018-12-24 | 2019-04-16 | 济南浪潮高新科技投资发展有限公司 | A kind of system and method for calibrating camera pose |
| CN109782755A (en) * | 2018-12-27 | 2019-05-21 | 广东飞库科技有限公司 | Control AGV calibrated, the method for AGV calibrating position, computer storage medium and AGV |
| CN109782755B (en) * | 2018-12-27 | 2022-05-31 | 广东飞库科技有限公司 | Method for controlling AGV to calibrate and AGV to calibrate position, computer storage medium and AGV |
| CN109871745A (en) * | 2018-12-29 | 2019-06-11 | 百度在线网络技术（北京）有限公司 | Identify method, system and the vehicle of empty parking space |
| CN109871745B (en) * | 2018-12-29 | 2021-12-31 | 阿波罗智能技术(北京)有限公司 | Method and system for identifying empty parking space and vehicle |
| CN109977784A (en) * | 2019-02-28 | 2019-07-05 | 北京百度网讯科技有限公司 | For obtaining the method and device of information |
| CN109977784B (en) * | 2019-02-28 | 2021-03-23 | 北京百度网讯科技有限公司 | Method and device for acquiring information |
| CN110070581A (en) * | 2019-04-29 | 2019-07-30 | 达泊(东莞)智能科技有限公司 | Double vision open country localization method, apparatus and system |
| CN111760795A (en) * | 2019-07-16 | 2020-10-13 | 北京京东乾石科技有限公司 | Method and device for sorting goods |
| CN112541950A (en) * | 2019-09-20 | 2021-03-23 | 杭州海康机器人技术有限公司 | Method and device for calibrating external parameter of depth camera |
| CN112598922A (en) * | 2020-12-07 | 2021-04-02 | 安徽江淮汽车集团股份有限公司 | Parking space detection method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108280853A (en) | Vehicle-mounted vision positioning method, device and computer readable storage medium | |
| CN113108796B (en) | Navigation method, navigation device, storage medium and navigation equipment | |
| JP7341652B2 (en) | Information processing device, information processing method, program, and system | |
| EP3759562B1 (en) | Camera based localization for autonomous vehicles | |
| US20200356101A1 (en) | Time-dependent navigation of telepresence robots | |
| CN111784748B (en) | Target tracking method and device, electronic equipment and mobile carrier | |
| CN110795523B (en) | Vehicle positioning method and device and intelligent vehicle | |
| US11914388B2 (en) | Vehicle using spatial information acquired using sensor, sensing device using spatial information acquired using sensor, and server | |
| US20210024100A1 (en) | Hybrid human/av driver system | |
| CN109253735B (en) | Path planning method, device and storage medium | |
| CN109144049A (en) | System and method for controlling sensing device visual field | |
| CN112161618B (en) | Storage robot positioning and map construction method, robot and storage medium | |
| KR101711797B1 (en) | Automatic parking system for autonomous vehicle and method for controlling thereof | |
| CN109634263A (en) | Based on data synchronous automatic Pilot method, terminal and readable storage medium storing program for executing | |
| CN110440811A (en) | A kind of universal automatic navigation control method, device and equipment terminal | |
| CN112740268A (en) | Target detection method and device | |
| CN111081033B (en) | Method and device for determining orientation angle of vehicle | |
| CN111192341A (en) | Method and device for generating high-precision map, automatic driving equipment and storage medium | |
| US20200193835A1 (en) | Traffic control apparatus, traffic control system, traffic control method, and non-transitory computer recording medium | |
| CN111561938A (en) | AR navigation method and device | |
| US11507101B2 (en) | Vehicle using spatial information acquired using sensor, sensing device using spatial information acquired using sensor, and server | |
| KR102190743B1 (en) | AUGMENTED REALITY SERVICE PROVIDING APPARATUS INTERACTING WITH ROBOT and METHOD OF THEREOF | |
| CN110096051A (en) | Method and apparatus for generating vehicle control instruction | |
| CN108860167A (en) | Automatic Pilot control method and device based on block chain | |
| CN109618131B (en) | Method and equipment for presenting decision auxiliary information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180713 |