CN110298878A - A kind of the determination method, apparatus and electronic equipment of target object three-dimensional pose - Google Patents
A kind of the determination method, apparatus and electronic equipment of target object three-dimensional pose Download PDFInfo
- Publication number
- CN110298878A CN110298878A CN201810236231.0A CN201810236231A CN110298878A CN 110298878 A CN110298878 A CN 110298878A CN 201810236231 A CN201810236231 A CN 201810236231A CN 110298878 A CN110298878 A CN 110298878A
- Authority
- CN
- China
- Prior art keywords
- coordinate system
- target object
- vision positioning
- dimensional pose
- transition matrix
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a kind of determination method, apparatus of target object three-dimensional pose and electronic equipments.The described method includes: obtaining the image comprising vision positioning mark of video camera acquisition;According to the image, the transition matrix of vision positioning mark coordinate system and camera coordinate system is determined, as the first transition matrix;Obtain three-dimensional pose of the target object in vision positioning mark coordinate system;According to three-dimensional pose and first transition matrix of the target object in vision positioning mark coordinate system, three-dimensional pose of the target object relative to camera coordinate system is determined, wherein vision positioning is identified as the plate with specific pattern.Since the pattern of vision positioning mark is specific, coordinate points thereon can be determined accurately, thus may determine that the transition matrix of vision positioning mark coordinate system and camera coordinate system can accurately determine three-dimensional pose of the target object relative to camera coordinate system in turn.
Description
Technical field
The present invention relates to field of artificial intelligence, more particularly to a kind of target object three-dimensional pose determination method,
Device and electronic equipment.
Background technique
With the continuous development of artificial intelligence, various smart machines using more and more extensive, wherein utilize mechanical arm pair
Equipment carries out operation and realizes that equipment operation is one of technology with important application prospects, for example, making using mechanical arm
During coffee, the button that mechanical arm presses coffee machine can use, operation coffee machine carries out production concentrated coffee, foaming etc.
Task.
When being operated using mechanical arm to equipment, the three-dimensional pose of general device be it is fixed, then equipment and machine
Relative positional relationship between tool arm can determine, and then also relationship can determine the shifting of mechanical arm depending on the relative position
Dynamic scheme, control mechanical arm are moved according to mobile scheme, when mechanical arm is mobile to be completed, can control mechanical arm to setting
It is standby to be operated.
As it can be seen that the three-dimensional pose of equipment is fixed and invariable, machine in the mode that above-mentioned mechanical arm operates equipment
Tool arm is to carry out according to fixed mobile scheme mobile and operated to equipment, it is clear that once equipment moves, thirdly
Dimension pose changes, then can not determine that the three-dimensional pose after equipment changes, mechanical arm also can not just operate equipment.
Summary of the invention
The determination method, apparatus for being designed to provide a kind of target object three-dimensional pose and electronics of the embodiment of the present invention are set
It is standby, accurately to determine the three-dimensional pose of target object.Specific technical solution is as follows:
In a first aspect, the embodiment of the invention provides a kind of determination method of target object three-dimensional pose, the method packet
It includes:
Obtain the image comprising vision positioning mark of video camera acquisition, wherein the vision positioning is identified as with spy
Determine the plate of pattern;
According to described image, the transition matrix of vision positioning mark coordinate system and camera coordinate system is determined, as first
Transition matrix;
Obtain three-dimensional pose of the target object in vision positioning mark coordinate system;
According to three-dimensional pose and the first conversion square of the target object in vision positioning mark coordinate system
Battle array, determines three-dimensional pose of the target object relative to the camera coordinate system.
Optionally, described according to described image, determine the conversion square of vision positioning mark coordinate system and camera coordinate system
The step of battle array, comprising:
According to the characteristic point information that vision positioning in described image identifies, the video camera is demarcated, described in acquisition
The transition matrix of vision positioning mark coordinate system and camera coordinate system.
Optionally, the step of three-dimensional pose for obtaining target object in vision positioning mark coordinate system, packet
It includes:
Obtain the relative positional relationship of the target object and vision positioning mark and the geometry of the target object
Parameter;
According to the geometric parameter and the relative positional relationship, determine that the target object is identified in the vision positioning
Three-dimensional pose in coordinate system.
Optionally, the method also includes:
According to the relative positional relationship of the video camera and mechanical arm, the camera coordinate system and mechanical arm coordinate are determined
The transition matrix of system, as the second transition matrix;
Three-dimensional pose according to second transition matrix and the target object relative to the camera coordinate system, really
Fixed three-dimensional pose of the target object relative to the mechanical arm coordinate system.
Optionally, the method also includes:
Determine the operating point information of the target object;
According to the current three-dimensional pose of the mechanical arm and the target object relative to the mechanical arm coordinate system three
Pose is tieed up, determines the mobile scheme of the mechanical arm;
It is mobile according to the mobile scheme to control the mechanical arm;
When the moving is done, mechanical arm is controlled according to the operating point information to operate the target object.
Optionally, the coordinate system of the vision positioning mark coordinate system and the target object is overlapped.
Second aspect, the embodiment of the invention provides a kind of determining device of target object three-dimensional pose, described device packets
It includes:
Image collection module, for obtaining the image comprising vision positioning mark of video camera acquisition, wherein the vision
Positioning identifier is the plate with specific pattern;
First transition matrix determining module, for determining vision positioning mark coordinate system and video camera according to described image
The transition matrix of coordinate system, as the first transition matrix;
Three-dimensional pose obtains module, for obtaining three-dimensional position of the target object in vision positioning mark coordinate system
Appearance;
Three-dimensional pose determining module, for the three-dimensional according to the target object in vision positioning mark coordinate system
Pose and first transition matrix, determine three-dimensional pose of the target object relative to the camera coordinate system.
Optionally, the first transition matrix determining module includes:
Transition matrix determination unit, the characteristic point information for being identified according to vision positioning in described image, takes the photograph to described
Camera is demarcated, and the transition matrix of vision positioning the mark coordinate system and camera coordinate system is obtained.
Optionally, the three-dimensional pose acquisition module includes:
Parameter acquisition submodule, for obtain the target object and the vision positioning mark relative positional relationship and
The geometric parameter of the target object;
Three-dimensional pose acquisition submodule, for determining the mesh according to the geometric parameter and the relative positional relationship
Mark three-dimensional pose of the object in vision positioning mark coordinate system.
Optionally, described device further include:
Second transition matrix determining module determines institute for the relative positional relationship according to the video camera and mechanical arm
The transition matrix for stating camera coordinate system Yu mechanical arm coordinate system, as the second transition matrix;
Mechanical arm coordinate system three-dimensional pose determining module, for according to second transition matrix and the target object phase
For the three-dimensional pose of the camera coordinate system, three-dimensional position of the target object relative to the mechanical arm coordinate system is determined
Appearance.
Optionally, described device further include:
Operating point information determination module, for determining the operating point information of the target object;
Mobile scheme determining module, for according to the current three-dimensional pose of the mechanical arm and the target object relative to
The three-dimensional pose of the mechanical arm coordinate system determines the mobile scheme of the mechanical arm;
Mobile module is controlled, it is mobile according to the mobile scheme for controlling the mechanical arm;
Control and operation module, for when the moving is done, controlling mechanical arm to the target according to the operating point information
Object is operated.
Optionally, the coordinate system of the vision positioning mark coordinate system and the target object is overlapped.
The third aspect, the embodiment of the invention provides a kind of electronic equipment, including processor, communication interface, memory and
Communication bus, wherein processor, communication interface, memory complete mutual communication by communication bus;
Memory, for storing computer program;
Processor when for executing the program stored on memory, realizes the determination of above-mentioned target object three-dimensional pose
The step of method.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, the computer-readable storage
Dielectric memory contains computer program, and right above-mentioned target object three-dimensional position is realized when the computer program is executed by processor
The step of determination method of appearance.
In scheme provided in an embodiment of the present invention, what electronic equipment can obtain video camera acquisition first includes vision positioning
The image of mark determines the transition matrix of vision positioning mark coordinate system and camera coordinate system according to the image;Then it obtains
Three-dimensional pose of the target object in vision positioning mark coordinate system, it is fixed in vision further according to above-mentioned transition matrix and target object
Three-dimensional pose in bit identification coordinate system determines three-dimensional pose of the target object relative to camera coordinate system, due to vision positioning
The pattern of mark be it is specific, coordinate points thereon can be determined accurately, thus may determine that vision positioning mark coordinate system with
The transition matrix of camera coordinate system can accurately determine three-dimensional position of the target object relative to camera coordinate system in turn
Appearance.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of flow diagram of the determination method of target object three-dimensional pose provided in an embodiment of the present invention;
Fig. 2 (a) is a kind of schematic diagram of vision positioning mark;
Fig. 2 (b) is the schematic diagram of another vision positioning mark;
Fig. 3 is the idiographic flow schematic diagram of step S103 in embodiment illustrated in fig. 1;
Fig. 4 is side of the object relative to the three-dimensional pose of mechanical arm coordinate system that set the goal really based on embodiment illustrated in fig. 1
A kind of flow diagram of formula;
Fig. 5 is a kind of flow diagram of the mode operated to target object based on embodiment illustrated in fig. 1;
Fig. 6 is a kind of structural schematic diagram of the determining device of target object three-dimensional pose provided in an embodiment of the present invention;
Fig. 7 is a kind of structural schematic diagram of the device operated to target object based on embodiment illustrated in fig. 6;
Fig. 8 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
In order to accurately determine the three-dimensional pose of target object, it is three-dimensional that the embodiment of the invention provides a kind of target objects
Determination method, apparatus, electronic equipment and the computer readable storage medium of pose.
A kind of determination method for being provided for the embodiments of the invention target object three-dimensional pose first below is introduced.
A kind of determination method of target object three-dimensional pose provided by the embodiment of the present invention can be applied to it needs to be determined that
Any electronic equipment of target object three-dimensional pose is not done specific herein for example, can be controller, tablet computer, computer etc.
It limits, hereinafter referred to as electronic equipment.
As shown in Figure 1, a kind of determination method of target object three-dimensional pose, which comprises
S101 obtains the image comprising vision positioning mark of video camera acquisition;
Wherein, the vision positioning is identified as the plate with specific pattern.
S102 determines the transition matrix of vision positioning mark coordinate system and camera coordinate system according to described image, as
First transition matrix;
S103 obtains three-dimensional pose of the target object in vision positioning mark coordinate system;
S104, according to three-dimensional pose and described first turn of the target object in vision positioning mark coordinate system
Matrix is changed, determines three-dimensional pose of the target object relative to the camera coordinate system.
As it can be seen that electronic equipment can obtain video camera acquisition first includes view in scheme provided in an embodiment of the present invention
The image for feeling positioning identifier determines the transition matrix of vision positioning mark coordinate system and camera coordinate system according to the image;So
Three-dimensional pose of the target object in vision positioning mark coordinate system is obtained afterwards, is existed further according to above-mentioned transition matrix and target object
Three-dimensional pose in vision positioning mark coordinate system determines three-dimensional pose of the target object relative to camera coordinate system, due to view
Feeling the pattern of positioning identifier is specifically, and coordinate points thereon can be determined accurately, thus may determine that vision positioning mark is sat
Mark system and the transition matrix of camera coordinate system can accurately determine target object relative to camera coordinate system in turn
Three-dimensional pose.
In above-mentioned steps S101, video camera can acquire the image comprising vision positioning mark, and electronic equipment can obtain
The image for taking video camera to acquire.Wherein, what above-mentioned target object was referred to is the object it needs to be determined that its three-dimensional pose, is not had
There is any other limiting meaning.For example, target object can be button, box, equipment etc. arbitrarily it needs to be determined that its three-dimensional pose
Object.
Above-mentioned vision positioning mark is the plate with specific pattern, vision positioning mark have accurate pattern dimension and
Frame, and its pattern for including is usually left-right asymmetry, and the coordinate of each point can be determined accurately thereon, is such as schemed
Shown in 2, Fig. 2 (a) and Fig. 2 (b) show the schematic diagram that two kinds of vision positionings identify.Fig. 2 (a) and Fig. 2 (b) is only of the invention real
The schematic diagram for applying the vision positioning mark of example offer, does not have any limiting meaning.Patterns coordinate can be used can accurately really
Fixed any plate is identified as vision positioning, for example, can be set according to the true form or house mark pattern of target object
Vision positioning mark is counted, the attribute or mark identity of company of target object, and available more aesthetic feeling can be embodied in this way
Vision positioning mark.
After obtaining the above-mentioned image comprising vision positioning mark, electronic equipment can execute above-mentioned steps S102, i.e. basis
The image determines the transition matrix of vision positioning mark coordinate system and camera coordinate system.In one embodiment, vision is fixed
Bit identification coordinate system can be the coordinate system that some point is established in view-based access control model positioning identifier.For example, can be with vision positioning mark
The central point of knowledge is origin, and the front-right of the central point rotates counterclockwise 90 degree of direction for Y-axis, vertically to being X-axis, by X-axis
It is identified in the vision positioning and upwardly direction is Z axis, and then establish vision positioning mark coordinate system.
Since vision positioning mark has specific pattern, the coordinate of each point can be determined accurately thereon, therefore, be led to
Cross in above-mentioned image vision positioning mark and coordinate transformation relation, electronic equipment can determine vision positioning mark coordinate system with
The transition matrix of camera coordinate system.In order to which scheme understands and describes clearly, it is subsequent will be true according to the image to electronic equipment
The concrete mode for determining the transition matrix of vision positioning mark coordinate system and camera coordinate system carries out citing introduction.
In above-mentioned steps S103, three-dimensional position of the available target object of electronic equipment in vision positioning mark coordinate system
Appearance.In one embodiment, the fixation position of target object, vision positioning mark can be placed or be pasted on to vision positioning mark
Know coordinate system to determine, then electronic equipment is also assured that three-dimensional position of the target object in vision positioning mark coordinate system
Appearance.
Determine that vision positioning identifies the transition matrix and target object of coordinate system and camera coordinate system in vision positioning mark
Know coordinate system in three-dimensional pose after, electronic equipment can execute above-mentioned steps S104, according to vision positioning identify coordinate system with
Three-dimensional pose of the transition matrix and target object of camera coordinate system in vision positioning mark coordinate system, determines target object
Three-dimensional pose relative to camera coordinate system.
From vision positioning mark coordinate system to the conversion of camera coordinate system, can be indicated by transition matrix.If
Coordinate of the target object in vision positioning mark coordinate system is X, and coordinate of the target object in camera coordinate system is X', that
X'=E*X, wherein E is the transition matrix that vision positioning identifies coordinate system and camera coordinate system.
Based on this, in above-mentioned steps S104, electronic equipment coordinate system can be identified according to vision positioning and video camera is sat
The three-dimensional pose of the transition matrix and target object of system in vision positioning mark coordinate system is marked, determines target object relative to taking the photograph
The three-dimensional pose of camera coordinate system.
It is above-mentioned according to described image as a kind of embodiment of the embodiment of the present invention, determine that vision positioning identifies coordinate
The step of system and the transition matrix of camera coordinate system, may include:
According to the characteristic point information that vision positioning in described image identifies, the video camera is demarcated, described in acquisition
The transition matrix of vision positioning mark coordinate system and camera coordinate system.
Since vision positioning mark is the plate with specific pattern, the coordinate of each point is accurately to determine thereon
, therefore, electronic equipment can be according to characteristic point information of the vision positioning mark in above-mentioned image, the internal reference matrix of video camera
And video camera imaging principle, the coordinate for calculating the characteristic point that vision positioning identifies in the image are right in camera coordinate system
The coordinate answered.Since vision positioning mark coordinate system is some point foundation in view-based access control model positioning identifier, electronics is set
The standby coordinate that can also determine the characteristic point of vision positioning mark in the image corresponding seat in vision positioning mark coordinate system
Mark.
In turn, the coordinate for the characteristic point that electronic equipment can be identified according to vision positioning in the image is in camera coordinates
In system in corresponding coordinate and the image coordinate of the characteristic point of vision positioning mark in vision positioning mark coordinate system
The characteristic point coordinate of vision positioning mark in the image is calculated in camera coordinate system and vision positioning mark in corresponding coordinate
Know the transformational relation between coordinate system, that is, the transition matrix of vision positioning mark coordinate system and camera coordinate system.
Based on this, electronic equipment, can basis after the image comprising vision positioning mark for obtaining video camera acquisition
The characteristic point information that vision positioning identifies in the image demarcates the video camera for acquiring the image, is also obtained with view
Feel the transition matrix of positioning identifier coordinate system and camera coordinate system.
As it can be seen that in this embodiment, electronic equipment can be identified according to vision positioning in the image that the video camera of acquisition acquires
Characteristic point information, video camera is demarcated, so obtain vision positioning mark coordinate system and camera coordinate system conversion
Matrix, that is, the first transition matrix, due to the coordinate that vision positioning identifies the characteristic point in corresponding image be can be accurate
Determining, therefore can accurately determine that vision positioning identifies the transition matrix of coordinate system and camera coordinate system using which,
It can three-dimensional pose in order to subsequent accurate determining target object relative to the camera coordinate system.
As a kind of embodiment of the embodiment of the present invention, as shown in figure 3, above-mentioned acquisition target object is fixed in the vision
The step of three-dimensional pose in bit identification coordinate system, may include:
S301, obtain the target object and vision positioning mark relative positional relationship and the target object
Geometric parameter;
The a certain fixed position of target object can be placed or be pasted on to above-mentioned vision positioning mark, then the position is can
It is obtained in a manner of through measurement etc., electronic equipment is also assured that target object and the relative position of vision positioning mark close
System.
For example, vision positioning mark and target object can be placed on an operating platform, vision positioning identifies and mesh
The position of mark object is fixed, and the relative positional relationship that target object is identified with vision positioning is also assured that.In another example target
Object is the button of an equipment, and vision positioning mark can be pasted on a position by the button, then the button and vision
The relative positional relationship of positioning identifier is also assured that.
Electronic equipment can also obtain target in addition to the relative positional relationship for obtaining target object and vision positioning mark
The geometric parameter of object.Wherein, the geometric parameter of target object can be the parameter that can indicate target object actual size.Example
Such as, it is assumed that target object is a cylindrical button, then the geometric parameter of target object can be the radius of button top plane
And height of button etc.;In another example target object is a rectangular box, then the geometric parameter of target object can be
The length and width of box and high.
S302 determines that the target object is fixed in the vision according to the geometric parameter and the relative positional relationship
Three-dimensional pose in bit identification coordinate system.
After the relative positional relationship of target object and vision positioning mark and the geometric parameter of target object has been determined, electronics
Equipment can be according to the relative positional relationship of the geometric parameter of target object and determined target object and vision positioning mark, really
Set the goal three-dimensional pose of the object in vision positioning mark coordinate system.
For example, using the central point of vision positioning mark as origin, the front-right of the central point is counterclockwise by X-axis to for X-axis
The direction of 90 degree of rotation is Y-axis, and perpendicular to vision positioning mark and upwardly direction is Z axis, and then establishes vision positioning mark
Know coordinate system.Target object is a square box, a length of 8 centimetres of rib, is placed in the original of vision positioning mark coordinate system
The front-right of point is to bottom center is in X-axis, apart from 5 centimetres of position of origin, then being also assured that the target object
Vision positioning mark coordinate system in three-dimensional frame apex coordinate be (1, -4,0), (9, -4,0), (Isosorbide-5-Nitrae, 0), (9,4,
0), (1, -4,8), (9, -4,8), (Isosorbide-5-Nitrae, 8) and (9,4,8).
Due to object three-dimensional frame can with apex coordinate can characterize the three-dimensional position and posture of object, can be with
It is fixed in vision that target object is identified using the apex coordinate of three-dimensional frame of the target object in vision positioning mark coordinate system
Three-dimensional pose in bit identification coordinate system, then electronic equipment is also assured that target object identifies coordinate system in vision positioning
In three-dimensional pose be (1, -4,0), (9, -4,0), (Isosorbide-5-Nitrae, 0), (9,4,0), (1, -4,8), (9, -4,8), (Isosorbide-5-Nitrae, 8) and
(9,4,8).
Certainly, in order to facilitate the subsequent three-dimensional pose according to target object in vision positioning mark coordinate system and first turn
Matrix is changed, determines three-dimensional pose of the target object relative to camera coordinate system, it can also be by target object in vision positioning mark
The apex coordinate for knowing the three-dimensional frame in coordinate system is converted to a matrix, indicates that target object is identified in vision positioning with the matrix
Three-dimensional pose in coordinate system, this is all reasonable.
As it can be seen that in this embodiment, the relative positional relationship of the available target object of electronic equipment and vision positioning mark
And the geometric parameter of target object, and then according to geometric parameter and relative positional relationship, determine target object in vision positioning mark
Know the three-dimensional pose in coordinate system, can rapidly and accurately determine three-dimensional position of the target object in vision positioning mark coordinate system
Appearance, the progress conducive to subsequent determining target object relative to the three-dimensional pose step of camera coordinate system.
As a kind of embodiment of the embodiment of the present invention, as shown in figure 4, the determination side of above-mentioned target object three-dimensional pose
Method can also include:
S401 determines the camera coordinate system and machinery according to the relative positional relationship of the video camera and mechanical arm
The transition matrix of arm coordinate system, as the second transition matrix;
It, generally can be by mechanical arm to mesh after determining the three-dimensional pose of target object due in many application scenarios
It marks object and carries out some operations, to complete certain tasks.Therefore, three of target object relative to camera coordinate system are being determined
After tieing up pose, it is thus necessary to determine that three-dimensional pose of the target object relative to mechanical arm coordinate system, so that mechanical arm can be to object
Body is operated.
For example, mechanical arm needs to press the button on coffee machine under the application scenarios of mechanical arm production coffee
Operation, under the scene, the button of coffee machine can be used as target object, then in the button that coffee machine has been determined relative to taking the photograph
After the three-dimensional pose of camera coordinate system, it is thus necessary to determine that three-dimensional pose of the button of coffee machine relative to mechanical arm coordinate system, it is mechanical
Arm could carry out pressing operations to the button of coffee machine.
So, in this case, electronic equipment has determined three-dimensional position of the target object relative to camera coordinate system
After appearance, three of target object relative to mechanical arm coordinate system can be determined according to the relative positional relationship of video camera and mechanical arm
Tie up pose.
It is understood that the position of current time mechanical arm be it is determining, the position of video camera be also it is determining, that
, electronic equipment can determine the relative positional relationship of video camera and mechanical arm.In turn, electronic equipment can be according to camera shooting
The relative positional relationship of machine and mechanical arm determines the mapping relations of camera coordinate system Yu mechanical arm coordinate system, that is, determines
The transition matrix of camera coordinate system and mechanical arm coordinate system.Due to the relative positional relationship according to video camera and mechanical arm, really
The transition matrix for determining camera coordinate system and mechanical arm coordinate system can be using the determination side of transition matrix between arbitrary system
Formula carries out, and is not specifically limited and illustrates herein.
S402, the three-dimensional position according to second transition matrix and the target object relative to the camera coordinate system
Appearance determines three-dimensional pose of the target object relative to the mechanical arm coordinate system.
After the transition matrix that above-mentioned camera coordinate system and mechanical arm coordinate system has been determined, electronic equipment can be by target
Three-dimensional pose of the object relative to camera coordinate system obtains target object relative to mechanical arm coordinate system by coordinate transform
Three-dimensional pose.Target object can also be indicated relative to the three-dimensional pose of mechanical arm coordinate system by a matrix.
For example, target object is indicated relative to the three-dimensional pose of camera coordinate system by matrix M, camera coordinate system with
Second transition matrix of mechanical arm coordinate system by matrix N indicate, then, three-dimensional of the target object relative to mechanical arm coordinate system
Pose can be indicated by matrix L=M*N.
As it can be seen that in the present embodiment, electronic equipment can be according to the relative positional relationship of video camera and mechanical arm, and determination is taken the photograph
The transition matrix of camera coordinate system and mechanical arm coordinate system, in turn, according to the transition matrix and target object relative to video camera
The three-dimensional pose of coordinate system determines three-dimensional pose of the target object relative to mechanical arm coordinate system, Ke Yizhun by coordinate transform
It determines three-dimensional pose of the target object relative to mechanical arm coordinate system, target object is operated convenient for subsequent mechanical arm.
For having determined target object relative to the three-dimensional pose of mechanical arm coordinate system the case where for electronic equipment, as
A kind of embodiment of the embodiment of the present invention, as shown in figure 5, the determination method of above-mentioned target object three-dimensional pose can also wrap
It includes:
S501 determines the operating point information of the target object;
After electronic equipment determines three-dimensional pose of the target object relative to mechanical arm coordinate system, target may further determine that
The operating point information of object.Wherein, operating point information includes the concrete mode for the operation that mechanical arm needs to carry out target object
Etc. information.For different target objects, operating point information can be different, and specifying information included by operating point information can be with
The operation that target object carries out is determined according to actual needs, is not specifically limited herein.
For example, target object is cup, if mechanical arm needs to carry out grasping manipulation, corresponding operation to cup
Point information can be for crawl;If mechanical arm needs to carry out cup to topple over operation, corresponding operating point information is just
It can be to topple over.In another example target object is button, if mechanical arm needs to carry out pressing operations to button, correspond to
Operating point information can be with to press.In another example target object is food, if mechanical arm needs carry out cutting behaviour to material object
Make, then its corresponding operating point information can be for cutting.
S502, according to the current three-dimensional pose of the mechanical arm and the target object relative to the mechanical arm coordinate system
Three-dimensional pose, determine the mobile scheme of the mechanical arm;
The position of current time mechanical arm is determining, and mechanical arm coordinate system is established based on mechanical arm itself, because
This, the current three-dimensional pose of the available mechanical arm of electronic equipment.In turn, according to the current three-dimensional pose and object of mechanical arm
Three-dimensional pose of the body relative to mechanical arm, electronic equipment can determine the mobile scheme of mechanical arm, and mechanical arm is according to the movement side
Case is mobile, so that it may be moved at target object.
It is mobile according to the mobile scheme to control the mechanical arm by S503;
S504 controls mechanical arm according to the operating point information and operates to the target object when the moving is done.
After the mobile scheme that mechanical arm has been determined, electronic equipment can control mechanical arm and be moved according to the movement scheme
It is dynamic.After the completion of movement, electronic equipment can control mechanical arm and carry out to target object according to the operating point information of target object
Operation.
In order to operate to target object, the end of mechanical arm can install end-of-arm tooling, for grasping to object
Make.As needed to object carry out operation difference, end-of-arm tooling can be different tools, for example, can for gripper,
Knife, spoon, pen etc., are not specifically limited herein.
For example, target object is button, operating point information is to press, then the end-of-arm tooling of mechanical arm can be machinery
Pawl after the completion of electronic equipment controls mechanical arm movement, can carry out pressing operations to button by gripper in turn.Example again
Such as, target object is apple, and operating point information is cutting, then the end-of-arm tooling of mechanical arm can be fruit knife, in turn, electronics
After the completion of equipment controls mechanical arm movement, cutting operation can be carried out to apple by fruit knife.
As it can be seen that in the present embodiment, electronic equipment can determine the operating point information of target object, according to working as mechanical arm
The three-dimensional pose of preceding three-dimensional pose and target object relative to mechanical arm coordinate system determines the mobile scheme of mechanical arm, and then controls
Mechanical arm processed is mobile according to mobile scheme, when the moving is done, controls mechanical arm according to operating point information and carries out to target object
Operation.Mechanical arm can be made to realize the operation that is needed to the target object of free-position of view-based access control model, accuracy and flexibly
Property is higher.
As a kind of embodiment of the embodiment of the present invention, the coordinate of above-mentioned vision positioning mark coordinate system and target object
System can be overlapped.
Vision positioning identifies coordinate system and the coordinate system of target object is overlapped, that is, the coordinate origin of the two is identical, sits
Mark system is also identical.In one embodiment, vision positioning mark can be pasted on target object.For example, target object
For button, vision positioning identifies the top planes that can be pasted on the button;If target object is cup, vision positioning mark
It can be pasted on the outside of the cup body of the cup, in this way, electronic equipment more easily view-based access control model positioning identifier can determine that this is pressed
The three-dimensional pose of button or cup will not influence the operation to button or cup.
In another embodiment, vision positioning mark can be placed on target object.For example, target object is one
Box, vision positioning mark can be placed on the box, in this way, electronic equipment can more easily view-based access control model positioning identifier
It determines the three-dimensional pose of the box, the operation to box will not be influenced.
As it can be seen that the coordinate system of vision positioning mark coordinate system and target object can be overlapped, in this way, electronics in this implementation
Equipment more easily view-based access control model positioning identifier can determine the three-dimensional pose of target object, will not influence to target object
Operation.
Corresponding to the determination method of above-mentioned target object three-dimensional pose, the embodiment of the invention provides a kind of target objects three
Tie up the determining device of pose.
A kind of determining device of target object three-dimensional pose provided in an embodiment of the present invention is introduced below.
As shown in fig. 6, a kind of determining device of target object three-dimensional pose, the device include:
Image collection module 610, for obtaining the image comprising vision positioning mark of video camera acquisition;
Wherein, the vision positioning is identified as the plate with specific pattern.
First transition matrix determining module 620, for determining vision positioning mark coordinate system and camera shooting according to described image
The transition matrix of machine coordinate system, as the first transition matrix;
Three-dimensional pose obtains module 630, for obtaining three-dimensional of the target object in vision positioning mark coordinate system
Pose;
Three-dimensional pose determining module 640, for being identified in coordinate system according to the target object in the vision positioning
Three-dimensional pose and first transition matrix, determine three-dimensional pose of the target object relative to the camera coordinate system.
As it can be seen that electronic equipment can obtain video camera acquisition first includes view in scheme provided in an embodiment of the present invention
The image for feeling positioning identifier determines the transition matrix of vision positioning mark coordinate system and camera coordinate system according to the image;So
Three-dimensional pose of the target object in vision positioning mark coordinate system is obtained afterwards, is existed further according to above-mentioned transition matrix and target object
Three-dimensional pose in vision positioning mark coordinate system determines three-dimensional pose of the target object relative to camera coordinate system, due to view
Feeling the pattern of positioning identifier is specifically, and coordinate points thereon can be determined accurately, thus may determine that vision positioning mark is sat
Mark system and the transition matrix of camera coordinate system can accurately determine target object relative to camera coordinate system in turn
Three-dimensional pose.
As a kind of embodiment of the embodiment of the present invention, above-mentioned first transition matrix determining module 620 may include:
Transition matrix determination unit (is not shown) in Fig. 6, the characteristic point for being identified according to vision positioning in described image
Information demarcates the video camera, obtains the transition matrix of vision positioning the mark coordinate system and camera coordinate system.
As a kind of embodiment of the embodiment of the present invention, above-mentioned three-dimensional pose obtains module 640 and may include:
Parameter acquisition submodule (is not shown) in Fig. 6, for obtaining the target object and vision positioning mark
The geometric parameter of relative positional relationship and the target object;
Three-dimensional pose acquisition submodule (is not shown) in Fig. 6, for being closed according to the geometric parameter and the relative position
System determines three-dimensional pose of the target object in vision positioning mark coordinate system.
As a kind of embodiment of the embodiment of the present invention, the determining device of above-mentioned target object three-dimensional pose can also be wrapped
It includes:
Second transition matrix determining module (being not shown in Fig. 6), for the opposite position according to the video camera and mechanical arm
Relationship is set, determines the transition matrix of the camera coordinate system Yu mechanical arm coordinate system, as the second transition matrix;
Mechanical arm coordinate system three-dimensional pose determining module (being not shown in Fig. 6), for according to second transition matrix and
Three-dimensional pose of the target object relative to the camera coordinate system determines the target object relative to the mechanical arm
The three-dimensional pose of coordinate system.
As a kind of embodiment of the embodiment of the present invention, as shown in fig. 7, above-mentioned target object three-dimensional pose determines dress
Setting to include:
Operating point information determination module 710, for determining the operating point information of the target object;
Mobile scheme determining module 720, for according to the mechanical arm current three-dimensional pose and the target object phase
For the three-dimensional pose of the mechanical arm coordinate system, the mobile scheme of the mechanical arm is determined;
Mobile module 730 is controlled, it is mobile according to the mobile scheme for controlling the mechanical arm;
Control and operation module 740, for when the moving is done, controlling mechanical arm to the mesh according to the operating point information
Mark object is operated.
As a kind of embodiment of the embodiment of the present invention, the coordinate of above-mentioned vision positioning mark coordinate system and target object
System can be overlapped.
The embodiment of the invention also provides a kind of electronic equipment, as shown in figure 8, include processor 801, communication interface 802,
Memory 803 and communication bus 804, wherein processor 801, communication interface 802, memory 803 are complete by communication bus 804
At mutual communication;
Memory 803, for storing computer program;
Processor 801 when for executing the program stored on memory, realizes following steps:
Obtain the image comprising vision positioning mark of video camera acquisition, wherein the vision positioning is identified as with spy
Determine the plate of pattern;
According to described image, the transition matrix of vision positioning mark coordinate system and camera coordinate system is determined, as first
Transition matrix;
Obtain three-dimensional pose of the target object in vision positioning mark coordinate system;
According to three-dimensional pose and the first conversion square of the target object in vision positioning mark coordinate system
Battle array, determines three-dimensional pose of the target object relative to the camera coordinate system.
As it can be seen that electronic equipment can obtain video camera acquisition first includes view in scheme provided in an embodiment of the present invention
The image for feeling positioning identifier determines the transition matrix of vision positioning mark coordinate system and camera coordinate system according to the image;So
Three-dimensional pose of the target object in vision positioning mark coordinate system is obtained afterwards, is existed further according to above-mentioned transition matrix and target object
Three-dimensional pose in vision positioning mark coordinate system determines three-dimensional pose of the target object relative to camera coordinate system, due to view
Feeling the pattern of positioning identifier is specifically, and coordinate points thereon can be determined accurately, thus may determine that vision positioning mark is sat
Mark system and the transition matrix of camera coordinate system can accurately determine target object relative to camera coordinate system in turn
Three-dimensional pose.
The communication bus that above-mentioned electronic equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral Component
Interconnect, PCI) bus or expanding the industrial standard structure (Extended Industry Standard
Architecture, EISA) bus etc..The communication bus can be divided into address bus, data/address bus, control bus etc..For just
It is only indicated with a thick line in expression, figure, it is not intended that an only bus or a type of bus.
Communication interface is for the communication between above-mentioned electronic equipment and other equipment.
Memory may include random access memory (Random Access Memory, RAM), also may include non-easy
The property lost memory (Non-Volatile Memory, NVM), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be storage device that at least one is located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
CPU), network processing unit (Network Processor, NP) etc.;It can also be digital signal processor (Digital Signal
Processing, DSP), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing
It is field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete
Door or transistor logic, discrete hardware components.
Wherein, above-mentioned according to described image, determine the transition matrix of vision positioning mark coordinate system and camera coordinate system
The step of, may include:
According to the characteristic point information that vision positioning in described image identifies, the video camera is demarcated, described in acquisition
The transition matrix of vision positioning mark coordinate system and camera coordinate system.
Wherein, the step of three-dimensional pose of the above-mentioned acquisition target object in vision positioning mark coordinate system, can be with
Include:
Obtain the relative positional relationship of the target object and vision positioning mark and the geometry of the target object
Parameter;
According to the geometric parameter and the relative positional relationship, determine that the target object is identified in the vision positioning
Three-dimensional pose in coordinate system.
Wherein, the above method can also include:
According to the relative positional relationship of the video camera and mechanical arm, the camera coordinate system and mechanical arm coordinate are determined
The transition matrix of system, as the second transition matrix;
Three-dimensional pose according to second transition matrix and the target object relative to the camera coordinate system, really
Fixed three-dimensional pose of the target object relative to the mechanical arm coordinate system.
Wherein, the above method can also include:
Determine the operating point information of the target object;
According to the current three-dimensional pose of the mechanical arm and the target object relative to the mechanical arm coordinate system three
Pose is tieed up, determines the mobile scheme of the mechanical arm;
It is mobile according to the mobile scheme to control the mechanical arm;
When the moving is done, mechanical arm is controlled according to the operating point information to operate the target object.
Wherein, the coordinate system of above-mentioned vision positioning mark coordinate system and the target object can be overlapped.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer readable storage medium memory
Computer program is contained, the computer program realizes following steps when being executed by processor:
Obtain the image comprising vision positioning mark of video camera acquisition, wherein the vision positioning is identified as with spy
Determine the plate of pattern;
According to described image, the transition matrix of vision positioning mark coordinate system and camera coordinate system is determined, as first
Transition matrix;
Obtain three-dimensional pose of the target object in vision positioning mark coordinate system;
According to three-dimensional pose and the first conversion square of the target object in vision positioning mark coordinate system
Battle array, determines three-dimensional pose of the target object relative to the camera coordinate system.
As it can be seen that computer program is performed in scheme provided in an embodiment of the present invention, video camera can be obtained first and adopted
The image comprising vision positioning mark of collection determines turn of vision positioning mark coordinate system and camera coordinate system according to the image
Change matrix;Then obtain three-dimensional pose of the target object in vision positioning mark coordinate system, further according to above-mentioned transition matrix and
Three-dimensional pose of the target object in vision positioning mark coordinate system determines three-dimensional of the target object relative to camera coordinate system
Pose, since the pattern of vision positioning mark is specifically that coordinate points thereon can be determined accurately, thus may determine that vision
The transition matrix of positioning identifier coordinate system and camera coordinate system can accurately determine target object relative to camera shooting in turn
The three-dimensional pose of machine coordinate system.
Wherein, above-mentioned according to described image, determine the transition matrix of vision positioning mark coordinate system and camera coordinate system
The step of, may include:
According to the characteristic point information that vision positioning in described image identifies, the video camera is demarcated, described in acquisition
The transition matrix of vision positioning mark coordinate system and camera coordinate system.
Wherein, above-mentioned acquisition target object is the step of the vision positioning identifies the three-dimensional pose in coordinate system, comprising:
Obtain the relative positional relationship of the target object and vision positioning mark and the geometry of the target object
Parameter;
According to the geometric parameter and the relative positional relationship, determine that the target object is identified in the vision positioning
Three-dimensional pose in coordinate system.
Wherein, the above method can also include:
According to the relative positional relationship of the video camera and mechanical arm, the camera coordinate system and mechanical arm coordinate are determined
The transition matrix of system, as the second transition matrix;
Three-dimensional pose according to second transition matrix and the target object relative to the camera coordinate system, really
Fixed three-dimensional pose of the target object relative to the mechanical arm coordinate system.
Wherein, the above method can also include:
Determine the operating point information of the target object;
According to the current three-dimensional pose of the mechanical arm and the target object relative to the mechanical arm coordinate system three
Pose is tieed up, determines the mobile scheme of the mechanical arm;
It is mobile according to the mobile scheme to control the mechanical arm;
When the moving is done, mechanical arm is controlled according to the operating point information to operate the target object.
Wherein, the coordinate system of above-mentioned vision positioning mark coordinate system and the target object can be overlapped.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Each embodiment in this specification is all made of relevant mode and describes, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device reality
For applying example, electronic equipment embodiment, computer readable storage medium, since it is substantially similar to the method embodiment, so retouching
That states is fairly simple, and the relevent part can refer to the partial explaination of embodiments of method.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (10)
1. a kind of determination method of target object three-dimensional pose, which is characterized in that the described method includes:
Obtain the image comprising vision positioning mark of video camera acquisition, wherein the vision positioning is identified as with specific pattern
The plate of case;
According to described image, the transition matrix of vision positioning mark coordinate system and camera coordinate system is determined, as the first conversion
Matrix;
Obtain three-dimensional pose of the target object in vision positioning mark coordinate system;
According to three-dimensional pose and first transition matrix of the target object in vision positioning mark coordinate system, really
Fixed three-dimensional pose of the target object relative to the camera coordinate system.
2. determining that vision positioning mark is sat the method according to claim 1, wherein described according to described image
The step of mark system and the transition matrix of camera coordinate system, comprising:
According to the characteristic point information that vision positioning in described image identifies, the video camera is demarcated, the vision is obtained
The transition matrix of positioning identifier coordinate system and camera coordinate system.
3. being sat the method according to claim 1, wherein the acquisition target object is identified in the vision positioning
The step of marking the three-dimensional pose in system, comprising:
Obtain the relative positional relationship of the target object and vision positioning mark and the geometric parameter of the target object;
According to the geometric parameter and the relative positional relationship, determine that the target object identifies coordinate in the vision positioning
Three-dimensional pose in system.
4. the method according to claim 1, wherein the method also includes:
According to the relative positional relationship of the video camera and mechanical arm, the camera coordinate system and mechanical arm coordinate system are determined
Transition matrix, as the second transition matrix;
Three-dimensional pose according to second transition matrix and the target object relative to the camera coordinate system, determines institute
State three-dimensional pose of the target object relative to the mechanical arm coordinate system.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
Determine the operating point information of the target object;
Three-dimensional position according to the current three-dimensional pose of the mechanical arm and the target object relative to the mechanical arm coordinate system
Appearance determines the mobile scheme of the mechanical arm;
It is mobile according to the mobile scheme to control the mechanical arm;
When the moving is done, mechanical arm is controlled according to the operating point information to operate the target object.
6. -5 any method according to claim 1, which is characterized in that the vision positioning mark coordinate system and the mesh
The coordinate system for marking object is overlapped.
7. a kind of determining device of target object three-dimensional pose, which is characterized in that described device includes:
Image collection module, for obtaining the image comprising vision positioning mark of video camera acquisition, wherein the vision positioning
It is identified as the plate with specific pattern;
First transition matrix determining module, for determining vision positioning mark coordinate system and camera coordinates according to described image
The transition matrix of system, as the first transition matrix;
Three-dimensional pose obtains module, for obtaining three-dimensional pose of the target object in vision positioning mark coordinate system;
Three-dimensional pose determining module, for the three-dimensional pose according to the target object in vision positioning mark coordinate system
With first transition matrix, three-dimensional pose of the target object relative to the camera coordinate system is determined.
8. device according to claim 7, which is characterized in that the first transition matrix determining module includes:
Transition matrix determination unit, the characteristic point information for being identified according to vision positioning in described image, to the video camera
It is demarcated, obtains the transition matrix of vision positioning the mark coordinate system and camera coordinate system.
9. a kind of electronic equipment, which is characterized in that including processor, communication interface, memory and communication bus, wherein processing
Device, communication interface, memory complete mutual communication by communication bus;
Memory, for storing computer program;
Processor when for executing the program stored on memory, realizes any method and step of claim 1-6.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer in the computer readable storage medium
Program realizes claim 1-6 any method and step when the computer program is executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810236231.0A CN110298878B (en) | 2018-03-21 | 2018-03-21 | Method and device for determining three-dimensional pose of target object and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810236231.0A CN110298878B (en) | 2018-03-21 | 2018-03-21 | Method and device for determining three-dimensional pose of target object and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110298878A true CN110298878A (en) | 2019-10-01 |
CN110298878B CN110298878B (en) | 2021-03-12 |
Family
ID=68025367
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810236231.0A Active CN110298878B (en) | 2018-03-21 | 2018-03-21 | Method and device for determining three-dimensional pose of target object and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110298878B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111015654A (en) * | 2019-12-18 | 2020-04-17 | 深圳市优必选科技股份有限公司 | Visual positioning method and device for robot, terminal equipment and storage medium |
CN111427446A (en) * | 2020-03-04 | 2020-07-17 | 青岛小鸟看看科技有限公司 | Virtual keyboard display method and device of head-mounted display equipment and head-mounted display equipment |
CN112836558A (en) * | 2019-11-25 | 2021-05-25 | 杭州海康机器人技术有限公司 | Mechanical arm tail end adjusting method, device, system, equipment and medium |
CN113008135A (en) * | 2019-12-20 | 2021-06-22 | 北京外号信息技术有限公司 | Method, apparatus, electronic device, and medium for determining position of target point in space |
CN113084795A (en) * | 2021-02-26 | 2021-07-09 | 北京空间飞行器总体设计部 | Visual measurement system and method applied to meter-taking sampling mechanical arm |
CN113081270A (en) * | 2021-03-09 | 2021-07-09 | 北京铸正机器人有限公司 | Tail end clamping device for robotic surgery |
CN113390426A (en) * | 2020-10-16 | 2021-09-14 | 北京猎户星空科技有限公司 | Positioning method, positioning device, self-moving equipment and storage medium |
CN113696190A (en) * | 2021-10-28 | 2021-11-26 | 深圳市越疆科技有限公司 | Teaching track point acquisition method, device, mechanical arm, system and medium |
CN114078158A (en) * | 2020-08-14 | 2022-02-22 | 边辕视觉科技(上海)有限公司 | Method for automatically acquiring characteristic point parameters of target object |
CN114266876A (en) * | 2021-11-30 | 2022-04-01 | 北京百度网讯科技有限公司 | Positioning method, visual map generation method and device |
CN115414117A (en) * | 2022-08-31 | 2022-12-02 | 北京长木谷医疗科技有限公司 | Method and device for determining position coordinates of execution tail end of orthopedic surgery robot |
CN112836558B (en) * | 2019-11-25 | 2024-06-28 | 杭州海康机器人股份有限公司 | Mechanical arm tail end adjusting method, device, system, equipment and medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101576379A (en) * | 2009-05-12 | 2009-11-11 | 四川大学 | Fast calibration method of active projection three dimensional measuring system based on two-dimension multi-color target |
CN101839692A (en) * | 2010-05-27 | 2010-09-22 | 西安交通大学 | Method for measuring three-dimensional position and stance of object with single camera |
CN103895042A (en) * | 2014-02-28 | 2014-07-02 | 华南理工大学 | Industrial robot workpiece positioning grabbing method and system based on visual guidance |
CN104729534A (en) * | 2015-03-12 | 2015-06-24 | 北京空间飞行器总体设计部 | Monocular visual error measurement system for cooperative target and error limit quantification method |
CN105278454A (en) * | 2015-11-05 | 2016-01-27 | 合肥图迅电子科技有限公司 | Robot hand-eye positioning algorithm based on mechanical arm visual positioning system |
CN105783726A (en) * | 2016-04-29 | 2016-07-20 | 无锡科技职业学院 | Curve-welding-seam three-dimensional reconstruction method based on line structure light vision detection |
CN106023193A (en) * | 2016-05-18 | 2016-10-12 | 东南大学 | Array camera observation method for detecting structure surface in turbid media |
CN106340044A (en) * | 2015-07-09 | 2017-01-18 | 上海振华重工电气有限公司 | Camera external parameter automatic calibration method and calibration device |
CN107256568A (en) * | 2017-05-08 | 2017-10-17 | 西安交通大学 | A kind of high-accuracy mechanical arm trick camera calibration method and calibration system |
CN107450376A (en) * | 2017-09-09 | 2017-12-08 | 北京工业大学 | A kind of service mechanical arm crawl attitude angle computational methods based on intelligent family moving platform |
-
2018
- 2018-03-21 CN CN201810236231.0A patent/CN110298878B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101576379A (en) * | 2009-05-12 | 2009-11-11 | 四川大学 | Fast calibration method of active projection three dimensional measuring system based on two-dimension multi-color target |
CN101839692A (en) * | 2010-05-27 | 2010-09-22 | 西安交通大学 | Method for measuring three-dimensional position and stance of object with single camera |
CN103895042A (en) * | 2014-02-28 | 2014-07-02 | 华南理工大学 | Industrial robot workpiece positioning grabbing method and system based on visual guidance |
CN104729534A (en) * | 2015-03-12 | 2015-06-24 | 北京空间飞行器总体设计部 | Monocular visual error measurement system for cooperative target and error limit quantification method |
CN106340044A (en) * | 2015-07-09 | 2017-01-18 | 上海振华重工电气有限公司 | Camera external parameter automatic calibration method and calibration device |
CN105278454A (en) * | 2015-11-05 | 2016-01-27 | 合肥图迅电子科技有限公司 | Robot hand-eye positioning algorithm based on mechanical arm visual positioning system |
CN105783726A (en) * | 2016-04-29 | 2016-07-20 | 无锡科技职业学院 | Curve-welding-seam three-dimensional reconstruction method based on line structure light vision detection |
CN106023193A (en) * | 2016-05-18 | 2016-10-12 | 东南大学 | Array camera observation method for detecting structure surface in turbid media |
CN107256568A (en) * | 2017-05-08 | 2017-10-17 | 西安交通大学 | A kind of high-accuracy mechanical arm trick camera calibration method and calibration system |
CN107450376A (en) * | 2017-09-09 | 2017-12-08 | 北京工业大学 | A kind of service mechanical arm crawl attitude angle computational methods based on intelligent family moving platform |
Non-Patent Citations (1)
Title |
---|
刘念: "复杂环境下的多工件定位研究", 《计算机技术与应用》 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112836558A (en) * | 2019-11-25 | 2021-05-25 | 杭州海康机器人技术有限公司 | Mechanical arm tail end adjusting method, device, system, equipment and medium |
CN112836558B (en) * | 2019-11-25 | 2024-06-28 | 杭州海康机器人股份有限公司 | Mechanical arm tail end adjusting method, device, system, equipment and medium |
CN111015654A (en) * | 2019-12-18 | 2020-04-17 | 深圳市优必选科技股份有限公司 | Visual positioning method and device for robot, terminal equipment and storage medium |
CN113008135A (en) * | 2019-12-20 | 2021-06-22 | 北京外号信息技术有限公司 | Method, apparatus, electronic device, and medium for determining position of target point in space |
CN113008135B (en) * | 2019-12-20 | 2023-09-05 | 北京移目科技有限公司 | Method, apparatus, electronic device and medium for determining a position of a target point in space |
CN111427446A (en) * | 2020-03-04 | 2020-07-17 | 青岛小鸟看看科技有限公司 | Virtual keyboard display method and device of head-mounted display equipment and head-mounted display equipment |
CN111427446B (en) * | 2020-03-04 | 2023-10-13 | 青岛小鸟看看科技有限公司 | Virtual keyboard display method and device of head-mounted display equipment and head-mounted display equipment |
CN114078158A (en) * | 2020-08-14 | 2022-02-22 | 边辕视觉科技(上海)有限公司 | Method for automatically acquiring characteristic point parameters of target object |
WO2022078513A1 (en) * | 2020-10-16 | 2022-04-21 | 北京猎户星空科技有限公司 | Positioning method and apparatus, self-moving device, and storage medium |
CN113390426A (en) * | 2020-10-16 | 2021-09-14 | 北京猎户星空科技有限公司 | Positioning method, positioning device, self-moving equipment and storage medium |
CN113084795A (en) * | 2021-02-26 | 2021-07-09 | 北京空间飞行器总体设计部 | Visual measurement system and method applied to meter-taking sampling mechanical arm |
CN113081270A (en) * | 2021-03-09 | 2021-07-09 | 北京铸正机器人有限公司 | Tail end clamping device for robotic surgery |
WO2023071481A1 (en) * | 2021-10-28 | 2023-05-04 | 深圳市越疆科技有限公司 | Method and apparatus for collecting teaching trajectory points, and robotic arm, system and medium |
CN113696190A (en) * | 2021-10-28 | 2021-11-26 | 深圳市越疆科技有限公司 | Teaching track point acquisition method, device, mechanical arm, system and medium |
CN114266876B (en) * | 2021-11-30 | 2023-03-28 | 北京百度网讯科技有限公司 | Positioning method, visual map generation method and device |
CN114266876A (en) * | 2021-11-30 | 2022-04-01 | 北京百度网讯科技有限公司 | Positioning method, visual map generation method and device |
CN115414117A (en) * | 2022-08-31 | 2022-12-02 | 北京长木谷医疗科技有限公司 | Method and device for determining position coordinates of execution tail end of orthopedic surgery robot |
Also Published As
Publication number | Publication date |
---|---|
CN110298878B (en) | 2021-03-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110298878A (en) | A kind of the determination method, apparatus and electronic equipment of target object three-dimensional pose | |
CN111452040B (en) | System and method for associating machine vision coordinate space in a pilot assembly environment | |
US20200061837A1 (en) | Method for industrial robot commissioning, industrial robot system and control system using the same | |
CN105818167B (en) | The method that hinged end effector is calibrated using long distance digital camera | |
CN104876021B (en) | Article alignment apparatus, article arrangement method and article movement system | |
US7440691B2 (en) | 360-° image photographing apparatus | |
US20190005725A1 (en) | Virtual object display system | |
CN103302666B (en) | Messaging device and information processing method | |
JP2020535509A (en) | Methods, devices and systems for automatically annotating target objects in images | |
JP2018111165A (en) | Calibration device of visual sensor, method and program | |
EP2728548A2 (en) | Automated frame of reference calibration for augmented reality | |
CN104596502A (en) | Object posture measuring method based on CAD model and monocular vision | |
WO2020138345A1 (en) | Article position management device, article position management system, article position management method, and program | |
JP7163760B2 (en) | POSITIONAL RELATIONSHIP DETECTION DEVICE AND POSITIONAL RELATIONSHIP DETECTION SYSTEM | |
CN110176032A (en) | A kind of three-dimensional rebuilding method and device | |
CN109961471A (en) | A kind of mask method, device and the electronic equipment of objects in images position | |
CN112077843B (en) | Robot graphical stacking method, computer storage medium and robot | |
JP2013099808A (en) | Assembling apparatus, and method thereof, assembling operation program | |
CN111890356A (en) | Mechanical arm coordinate system and camera coordinate system calibration method, device, equipment and medium | |
JP6447706B1 (en) | Calibration data generation apparatus, calibration data generation method, calibration system, and control program | |
CN110298877A (en) | A kind of the determination method, apparatus and electronic equipment of object dimensional pose | |
US11048345B2 (en) | Image processing device and image processing method | |
JP2021047475A (en) | Object position management device, objects, object position management system, object position management method and program | |
CN106461414A (en) | Attitude relationship calculation method for intelligent device, and the intelligent device | |
Tammaro et al. | Extending Industrial Digital Twins with Optical Object Tracking. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |