CN109816769A - Scene based on depth camera ground drawing generating method, device and equipment - Google Patents
Scene based on depth camera ground drawing generating method, device and equipment Download PDFInfo
- Publication number
- CN109816769A CN109816769A CN201711164388.9A CN201711164388A CN109816769A CN 109816769 A CN109816769 A CN 109816769A CN 201711164388 A CN201711164388 A CN 201711164388A CN 109816769 A CN109816769 A CN 109816769A
- Authority
- CN
- China
- Prior art keywords
- key frame
- frame
- module
- transformation matrix
- carriage transformation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000011159 matrix material Substances 0.000 claims abstract description 68
- 230000009466 transformation Effects 0.000 claims abstract description 65
- 238000004804 winding Methods 0.000 claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 238000012360 testing method Methods 0.000 claims abstract description 10
- 238000004590 computer program Methods 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 15
- 230000003252 repetitive effect Effects 0.000 claims description 11
- 238000003780 insertion Methods 0.000 claims description 10
- 230000037431 insertion Effects 0.000 claims description 10
- 108010001267 Protein Subunits Proteins 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000009432 framing Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Abstract
A kind of scene based on depth camera drawing generating method include: the video stream image frame for reading camera, obtain the key frame of the video stream image frame;Determine module and carriage transformation matrix of the key frame relative to initial key frame;Winding detection is carried out to the key frame, the pose of corresponding key frame is adjusted according to the winding testing result, three-dimensional point cloud map is constructed according to the pose of key frame adjusted.It only needs to acquire a small amount of effective key frame, the requirement to device hardware can greatly be reduced, and three-dimensional point cloud map is constructed in such a way that winding detects, the lower deployment cost of the navigation scheme in robot can be significantly reduced under the premise of location navigation demand under meeting three-dimensional space.
Description
Technical field
The invention belongs to vision robot field more particularly to a kind of scene based on depth camera drawing generating method,
Device and equipment.
Background technique
Autonomous mobile robot airmanship is an important research direction of field in intelligent robotics, wherein vision guided navigation
Mode has many advantages, such as to contain much information, flexibility is high, at low cost.It is mobile machine that robot vision, which positions simultaneously and builds diagram technology,
One Key technology of the robot systems such as people, flying robot, has the characteristics that indispensable.
Traditional two-dimensional laser SLAM (full name in English is Simultaneous Localization and Mapping, in
Literary full name is that robot positions simultaneously and builds figure) technology, so that constructing ground while robot is positioned in circumstances not known
Figure, then can carry out path planning and navigation based on this map.And three-dimensional laser radar price can rebuild three-dimensional map,
But price is costly.Although laser sensor can obtain the location information of ambient enviroment, do not have semantic level into
The ability of the higher level scene Recognition of row.And more popular figure, but its base can be positioned and build in real time based on ORB_SLAM2 at present
In the point map that the method for characteristic point causes built figure only sparse, the movement of practical more complicated scene but cannot be used for
Planning and navigation.And it is popular GPU (full name in English be Graphics Processing Unit, Chinese name be figure
Shape processor) on realize it is three-dimensional it is dense build figure scheme, have higher requirement to hardware device, position and lead in the case where meeting three-dimensional space
Under the premise of boat demand, the navigation lower deployment cost of robot is high.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of scene based on depth camera drawing generating method, device and
Equipment, with solve to realize in the prior art it is three-dimensional it is dense build figure when, have higher requirement to hardware device, meeting three-dimensional space
Under the premise of lower location navigation demand, the high problem of the navigation lower deployment cost of robot.
A kind of first aspect of the embodiment of the present invention with providing the scene based on depth camera drawing generating method, the base
In depth camera scene drawing generating method include:
The video stream image frame for reading camera, obtains the key frame of the video stream image frame;
Determine module and carriage transformation matrix of the key frame relative to initial key frame;
Winding detection is carried out to the key frame, the pose of corresponding key frame is adjusted according to the winding testing result,
Three-dimensional point cloud map is constructed according to the pose of key frame adjusted.
With reference to first aspect, described to obtain the video streaming image in the first possible implementation of first aspect
The step of key frame of frame includes:
It detects interval of the present frame apart from a upper key frame of video and is greater than predetermined space;
And feature point number is greater than predetermined value in detection current image frame;
And the characteristic point repetitive rate in detection current image frame in characteristic point and previous keyframe is less than predetermined value;
When meeting simultaneously, determine that present frame is the key frame of video streaming image.
With reference to first aspect, in second of possible implementation of first aspect, the determination key frame is opposite
Include: in the step of module and carriage transformation matrix of initial key frame
The key frame being inserted into using first calculates the key frame in rear insertion relative to upper one towards as world coordinate system
The module and carriage transformation matrix of key frame;
According to the module and carriage transformation matrix of two adjacent key frames, the pose for calculating key frame relative to initial frame converts square
Battle array.
The possible implementation of second with reference to first aspect, in the third possible implementation of first aspect, institute
The key frame being inserted into using first is stated towards as world coordinate system, calculates the key frame in rear insertion relative to previous keyframe
Module and carriage transformation matrix the step of include:
By nonlinear optimization method, objective function is usedIt calculates and is inserted rear
Module and carriage transformation matrix of the key frame entered relative to previous keyframe, wherein n is the spy that current key frame matches previous keyframe
Sign point quantity, exp (ξ^) it is module and carriage transformation matrix, piIt is closed herein for matched characteristic point
Three-dimensional coordinate when key frame under camera coordinates system, p 'iBe characterized a little in upper key frame under camera coordinates system three
Coordinate is tieed up, | | | |2Indicate L2 norm.
With reference to first aspect, in the 4th kind of possible implementation of first aspect, described detected according to the winding is tied
Fruit, the step of adjusting the pose of corresponding key frame include:
The bag of words vector of current key frame is compared with the bag of words vector of key frame before;
If the similarity of the bag of words vector for detecting current key frame and the bag of words vector of key frame before is more than pre-
When definite value, the module and carriage transformation matrix that similarity is more than two key frames of predetermined value is calculated, according to the module and carriage transformation matrix of calculating
Adjust current key frame, or adjustment current key frame and the key with the common trait point a predetermined level is exceeded of current key frame
Frame.
The second aspect of the embodiment of the present invention provides a kind of scene map creation device based on depth camera, the base
Include: in the scene map creation device of depth camera
Key frame acquiring unit obtains the key of the video stream image frame for reading the video stream image frame of camera
Frame;
Module and carriage transformation matrix determination unit, for determining that the key frame converts square relative to the pose of initial key frame
Battle array;
Three-dimensional point cloud construction unit, according to the winding testing result, is adjusted for carrying out winding detection to the key frame
The pose of whole corresponding key frame constructs three-dimensional point cloud map according to the pose of key frame adjusted.
In conjunction with second aspect, in the first possible implementation of second aspect, the key frame acquiring unit includes:
First detection sub-unit, for detecting interval of the present frame apart from a upper key frame of video greater than predetermined space;
And second detection sub-unit, it is greater than predetermined value for detecting feature point number in current image frame;
And third detection sub-unit, for detecting the characteristic point in current image frame in characteristic point and previous keyframe
Repetitive rate is less than predetermined value;
Key frame determines subelement, for when meeting simultaneously, determining that present frame is the key frame of video streaming image.
In conjunction with second aspect, in second of possible implementation of second aspect, the module and carriage transformation matrix determines single
Member includes:
First module and carriage transformation matrix determines subelement, for using first key frame being inserted into direction as world coordinates
System calculates module and carriage transformation matrix of the key frame relative to previous keyframe in rear insertion;
Second module and carriage transformation matrix determines subelement, for the module and carriage transformation matrix according to two adjacent key frames, meter
Calculate module and carriage transformation matrix of the key frame relative to initial frame.
The third aspect of the embodiment of the present invention provides a kind of map generating device, including memory, processor and deposits
The computer program that can be run in the memory and on the processor is stored up, the processor executes the computer journey
The scene as described in any one of first aspect based on depth camera is realized when sequence the step of drawing generating method.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, realizes when the computer program is executed by processor and is based on as described in any one of first aspect
The scene of depth camera drawing generating method the step of.
Existing beneficial effect is the key that the embodiment of the present invention compared with prior art: by obtaining in video streaming image
Frame determines module and carriage transformation matrix of the key frame relative to initial key frame, and in such a way that winding detects, adjusts corresponding close
The pose of key frame, and three-dimensional point cloud map is constructed according to key frame pose adjusted.Since the application only needs to acquire on a small quantity
Effective key frame can greatly reduce the requirement to device hardware, and construct three-dimensional point cloud in such a way that winding detects
Map can significantly reduce the deployment of the navigation scheme in robot under the premise of location navigation demand under meeting three-dimensional space
Cost.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 be the scene provided in an embodiment of the present invention based on depth camera drawing generating method implementation process signal
Figure;
Fig. 2 is the implementation process signal of the key frame approach provided in an embodiment of the present invention for obtaining the video stream image frame
Figure;
Fig. 3 is provided in an embodiment of the present invention according to the winding testing result, adjusts the pose side of corresponding key frame
The implementation process schematic diagram of method;
Fig. 4 is the schematic diagram of the scene map creation device provided in an embodiment of the present invention based on depth camera;
Fig. 5 is the schematic diagram of map generating device provided in an embodiment of the present invention.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
For a kind of scene based on depth camera provided by the embodiments of the present application the realization of drawing generating method as shown in Figure 1
Process, details are as follows:
In step s101, the video stream image frame for reading camera obtains the key frame of the video stream image frame.
Specifically, storing all picture frames collected since the pixel of camera video image is higher and higher and needing to consume
A large amount of hardware memory resource.The application selects significant picture frame to store as key frame, thus to hardware memory
The requirement of resource can be reduced greatly.
In the application during being scanned to scene, video stream image frame is read first, it is first determined first figure
Picture frame is that initial key frame successively detects subsequent image frames then according to the playing sequence of picture frame, is judged whether it is
Key frame.The process that detection judgement is carried out to video note, can be as shown in Figure 2, comprising the following steps:
In step s 201, interval of the detection present frame apart from a upper key frame of video is greater than predetermined space.
It, can also figure to be separated by between picture frame specifically, the interval, can refer to the time interval between picture frame
As the number of frame.Since picture frame is played out according to certain code rate, when determining interval is the time interval of picture frame
When, the number for the picture frame being separated by between picture frame can be determined accordingly, and vice versa.
In preferred embodiment, the predetermined space can be set as 20 picture frames.
In step S202, if interval of the present frame apart from a upper key frame of video is greater than predetermined space, detection is worked as
Feature point number is greater than predetermined value in preceding picture frame.
If interval of the present frame apart from a upper key frame of video be greater than predetermined space, such as be greater than 20 picture frames when,
It can start to carry out picture frame the detection of further feature point and compare.The detection of the characteristic point of described image frame, can be with
Using ORB (Oriented FAST and Rotated BRIEF) etc. can in CPU extract real-time feature algorithm.
After the characteristic point for including in detecting image, the number of characteristic point is counted, judges counted feature
Whether the number of point is greater than the predetermined value of feature.For example, the predetermined value can be 50 spies in a kind of optional embodiment
Sign point.
In step S203, if feature point number is greater than predetermined value in current image frame, detect in current image frame
Characteristic point repetitive rate in characteristic point and previous keyframe is less than predetermined value.
If detecting in current image frame that feature point number is greater than predetermined value, further to characteristic point in picture frame with
The repetitive rate of the characteristic point of previous keyframe is calculated, if repetitive rate is less than predetermined value, illustrates the interior of current image frame
Appearance is smaller with the repetitive rate of the content of previous keyframe, and current picture frame includes more new content, be can be used as new
Key frame.A kind of preferred embodiment, the predetermined value of the repetitive rate can be set as 90%.
In step S204, if the characteristic point repetitive rate in current image frame in characteristic point and previous keyframe is less than in advance
Definite value determines that present frame is the key frame of video streaming image.
The sequencing of above-mentioned three kinds of detection modes can need to be adjusted flexibly according to actual detection.
That is, the application can enable picture frame to select key according to certain intervals by the interval of frame
Frame, and by the comparison of feature point number, so that the key frame of selection includes more content characteristic, and pass through repetitive rate
Judgement so that the content of the key frame selected is new content, so that the selection of key frame can reduce quantity, again
It can effectively ensure that the effective of content.
In step s 102, module and carriage transformation matrix of the key frame relative to initial key frame is determined.
The module and carriage transformation matrix can be used for describing the variation of the pose between two picture frames, determine a figure
As frame pose on the basis of, in conjunction with pose transformation matrices, can determine the pose of another picture frame.
Wherein, the step of module and carriage transformation matrix of the determination key frame relative to initial key frame may include:
A. the key frame being inserted into using first calculates the key frame in rear insertion relative to upper towards as world coordinate system
The module and carriage transformation matrix of one key frame.
Specifically, then the key frame pose being inserted into using first uses nonlinear optimization towards as world coordinate system
Method, such as using ICP (full name in English be Iterative Closest Point, Chinese name be neighbour's iterative algorithm)
The key frame being newly inserted into is solved with respect to the European transformation T of previous keyframe, i.e. module and carriage transformation matrix, it is assumed that key frame matches at this time
The characteristic point quantity of previous keyframe is n, then the objective function of nonlinear optimization is as follows:
Wherein: exp (ξ^) it is module and carriage transformation matrix T, piFor matched characteristic point, in this key frame, camera is sat
Three-dimensional coordinate under mark system, p 'iIt is characterized the three-dimensional coordinate a little in upper key frame under camera coordinates system, camera is sat
Characteristic point three-dimensional coordinate under mark system can be acquired by following formula:
In formula: (u, v) is characterized pixel coordinate a little in the picture, the depth value of d characteristic point thus, can be directly from depth
It is obtained in figure.
B. according to the module and carriage transformation matrix of two adjacent key frames, the pose for calculating key frame relative to initial frame is converted
Matrix.
The module and carriage transformation matrix between frame and frame is accumulated, each key frame can be obtained with respect to world coordinate system, i.e., first
The module and carriage transformation matrix of key frame.
In step s 103, winding detection is carried out to the key frame, according to the winding testing result, adjustment is corresponding
The pose of key frame constructs three-dimensional point cloud map according to the pose of key frame adjusted.
Assuming that the module and carriage transformation matrix that winding key frame is calculated to current key frame after winding is Tc1, winding key frame
Module and carriage transformation matrix be T1w, then the pose adjusted under the world coordinate system of current key frame is Tcw'=Tc1*T1w, it is assumed that
The quantity for containing the key frame of a predetermined level is exceeded common trait with current key frame is n, then in current key framing control pose
Afterwards, for the module and carriage transformation matrix T under the world coordinate system of adjacent key frame iiwIt is adjusted as the following formula:
Wherein 1≤i≤n, TcwIt is the module and carriage transformation matrix before current key framing control, Tcw' it is current key framing control
Module and carriage transformation matrix afterwards.
Since the solution error of module and carriage transformation matrix is inevitable, accumulated error is larger after repeatedly accumulating transformation matrix,
The pose of subsequent key frame can generate very big drift.Therefore, as shown in figure 3, it is described according to the winding testing result, adjustment
The step of pose of key frame includes: accordingly
In step S301, the bag of words vector of current key frame is compared with the bag of words vector of key frame before.
Key frame pose is corrected by global winding detection, in winding detection, by using bag of words, for
Each key frame is calculated and is saved a bag of words vector (i.e. for describing the vector that the bag of words of picture frame are constituted), works as pass
When key frame detects winding, the bag of words vector of this key frame is compared with the bag of words vector of key frame before, it is certain when reaching
When similarity, then it is assumed that detect winding.Reach key when certain value with the similarity of the bag of words vector of current key frame
Frame, referred to as winding key frame.
In step s 302, if detecting the bag of words vector and the bag of words vector of key frame before of current key frame
When similarity is more than predetermined value, the module and carriage transformation matrix that similarity is more than two key frames of predetermined value is calculated, according to calculating
Module and carriage transformation matrix adjusts current key frame, or adjustment current key frame and be more than pre- with the common trait point of current key frame
The key frame of fixed number amount.
Module and carriage transformation matrix of the current key frame obtained by calculation relative to winding key frame adjusts current key
Framing bit appearance, while containing according to this adjustment of matrix and current key frame the key frame pose of certain amount common trait point.
In scene scanning process, after obtaining some key frame module and carriage transformation matrix, that is, starts progress three-dimensional point cloud and exist
The relative coordinate integral-rotation of corresponding cloud of key frame is transformed to the world by the splicing under world coordinate system, the splicing for putting cloud
Under coordinate system, after the corresponding key frame pose of point cloud spliced is adjusted, this order cloud sheet section under world coordinate system
Pose should also be adjusted in time.So that the application is based on depth camera, scene and real can be scanned on the CPU of standard
When construct three-dimensional point cloud dense map, the hardware device condition used is of less demanding, can be light according to dense point cloud map
It is easy to get to 3 d grid map, can be significantly reduced in robot under the premise of location navigation demand under meeting three-dimensional space
The lower deployment cost of navigation scheme.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Fig. 4 is a kind of structural representation of the scene map creation device based on depth camera provided by the embodiments of the present application
Figure, details are as follows:
Scene map creation device described in the embodiment of the present application based on depth camera, comprising:
Key frame acquiring unit 401 obtains the pass of the video stream image frame for reading the video stream image frame of camera
Key frame;
Module and carriage transformation matrix determination unit 402, for determining that the key frame is converted relative to the pose of initial key frame
Matrix;
Three-dimensional point cloud construction unit 403 is detected according to the winding and is tied for carrying out winding detection to the key frame
Fruit adjusts the pose of corresponding key frame, constructs three-dimensional point cloud map according to the pose of key frame adjusted.
Preferably, the key frame acquiring unit includes:
First detection sub-unit, for detecting interval of the present frame apart from a upper key frame of video greater than predetermined space;
And second detection sub-unit, it is greater than predetermined value for detecting feature point number in current image frame;
And third detection sub-unit, for detecting the characteristic point in current image frame in characteristic point and previous keyframe
Repetitive rate is less than predetermined value;
Key frame determines subelement, for when meeting simultaneously, determining that present frame is the key frame of video streaming image.
Preferably, the module and carriage transformation matrix determination unit includes:
First module and carriage transformation matrix determines subelement, for using first key frame being inserted into direction as world coordinates
System calculates module and carriage transformation matrix of the key frame relative to previous keyframe in rear insertion;
Second module and carriage transformation matrix determines subelement, for the module and carriage transformation matrix according to two adjacent key frames, meter
Calculate module and carriage transformation matrix of the key frame relative to initial frame.
Scene map creation device described in Fig. 4 based on depth camera, with the scene described in Fig. 1 based on depth camera
Drawing generating method is corresponding.
Fig. 5 is the schematic diagram for the map generating device that one embodiment of the invention provides.As shown in figure 5, the ground of the embodiment
Figure generating device 5 includes: processor 50, memory 51 and is stored in the memory 51 and can be on the processor 50
The computer program 52 of operation, such as the scene map based on depth camera generate program.The processor 50 executes the meter
Above-mentioned each scene based on depth camera is realized when calculation machine program 52 the step in drawing generating method embodiment, such as Fig. 1
Shown step 101 is to 103.Alternatively, the processor 50 realizes that above-mentioned each device is implemented when executing the computer program 52
The function of each module/unit in example, such as the function of module 401 to 403 shown in Fig. 5.
Illustratively, the computer program 52 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 51, and are executed by the processor 50, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 52 in the map generating device 5 is described.For example, the computer program 52 can be with
It is divided into key frame acquiring unit, module and carriage transformation matrix determination unit and three-dimensional point cloud construction unit, each unit concrete function
It is as follows:
Key frame acquiring unit obtains the key of the video stream image frame for reading the video stream image frame of camera
Frame;
Module and carriage transformation matrix determination unit, for determining that the key frame converts square relative to the pose of initial key frame
Battle array;
Three-dimensional point cloud construction unit, according to the winding testing result, is adjusted for carrying out winding detection to the key frame
The pose of whole corresponding key frame constructs three-dimensional point cloud map according to the pose of key frame adjusted.
The map generating device 5 can be the calculating such as desktop PC, notebook, palm PC and cloud server
Equipment.The map generating device may include, but be not limited only to, processor 50, memory 51.Those skilled in the art can manage
Solution, Fig. 5 is only the example of map generating device 5, does not constitute the restriction of to map generating device 5, may include than diagram
More or fewer components perhaps combine certain components or different components, such as the map generating device can also wrap
Include input-output equipment, network access equipment, bus etc..
Alleged processor 50 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 51 can be the internal storage unit of the map generating device 5, such as map generating device 5
Hard disk or memory.The memory 51 is also possible to the External memory equipment of the map generating device 5, such as map life
The plug-in type hard disk being equipped on forming apparatus 5, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card) etc..Further, the memory 51 can also both include the map
The internal storage unit of generating device 5 also includes External memory equipment.The memory 51 is for storing the computer program
And other programs and data needed for the map generating device.The memory 51 can be also used for temporarily storing
Output or the data that will be exported.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, it can be with
It realizes by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of logical function partition, there may be another division manner in actual implementation, such as
Multiple units or components can be combined or can be integrated into another system, or some features can be ignored or not executed.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be through some interfaces, device
Or the INDIRECT COUPLING or communication connection of unit, it can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..Computer-readable Jie
Matter may include: can carry the computer program code any entity or device, recording medium, USB flash disk, mobile hard disk,
Magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium do not include be electric carrier signal and
Telecommunication signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of scene based on depth camera ground drawing generating method, which is characterized in that the scene based on depth camera
Drawing generating method includes:
The video stream image frame for reading camera, obtains the key frame of the video stream image frame;
Determine module and carriage transformation matrix of the key frame relative to initial key frame;
Winding detection is carried out to the key frame, the pose of corresponding key frame is adjusted according to the winding testing result, according to
The pose of key frame adjusted constructs three-dimensional point cloud map.
2. the scene according to claim 1 based on depth camera ground drawing generating method, which is characterized in that the acquisition institute
The step of stating the key frame of video stream image frame include:
It detects interval of the present frame apart from a upper key frame of video and is greater than predetermined space;
And feature point number is greater than predetermined value in detection current image frame;
And the characteristic point repetitive rate in detection current image frame in characteristic point and previous keyframe is less than predetermined value;
When meeting simultaneously, determine that present frame is the key frame of video streaming image.
3. the scene according to claim 1 based on depth camera ground drawing generating method, which is characterized in that the determining institute
The step of stating module and carriage transformation matrix of the key frame relative to initial key frame include:
For the key frame being inserted into using first towards as world coordinate system, calculating is crucial relative to upper one in the key frame of rear insertion
The module and carriage transformation matrix of frame;
According to the module and carriage transformation matrix of two adjacent key frames, module and carriage transformation matrix of the key frame relative to initial frame is calculated.
4. the scene according to claim 3 based on depth camera ground drawing generating method, which is characterized in that described with first
Towards world coordinate system is used as, the key frame calculated in rear insertion becomes the key frame of a insertion relative to the pose of previous keyframe
The step of changing matrix include:
By nonlinear optimization method, objective function is usedIt calculates in rear insertion
Module and carriage transformation matrix of the key frame relative to previous keyframe, wherein n is the characteristic point that current key frame matches previous keyframe
Quantity, exp (ξ ^) are module and carriage transformation matrix, piFor three-dimensional seat of the matched characteristic point in this key frame under camera coordinates system
Mark, p 'iIt is characterized the three-dimensional coordinate a little in upper key frame under camera coordinates system, | | | |2Indicate L2 norm.
5. the ground of the scene based on depth camera drawing generating method according to claim 1, which is characterized in that described according to
Winding testing result, the step of adjusting the pose of corresponding key frame include:
The bag of words vector of current key frame is compared with the bag of words vector of key frame before;
If the similarity of the bag of words vector for detecting current key frame and the bag of words vector of key frame before is more than predetermined value
When, the module and carriage transformation matrix that similarity is more than two key frames of predetermined value is calculated, is adjusted according to the module and carriage transformation matrix of calculating
Current key frame, or adjustment current key frame and the key frame with the common trait point a predetermined level is exceeded of current key frame.
6. a kind of scene map creation device based on depth camera, which is characterized in that the scene based on depth camera
Figure generating means include:
Key frame acquiring unit obtains the key frame of the video stream image frame for reading the video stream image frame of camera;
Module and carriage transformation matrix determination unit, for determining module and carriage transformation matrix of the key frame relative to initial key frame;
Three-dimensional point cloud construction unit, according to the winding testing result, adjusts phase for carrying out winding detection to the key frame
The pose for the key frame answered constructs three-dimensional point cloud map according to the pose of key frame adjusted.
7. the scene map creation device according to claim 1 based on depth camera, which is characterized in that the key frame
Acquiring unit includes:
First detection sub-unit, for detecting interval of the present frame apart from a upper key frame of video greater than predetermined space;
And second detection sub-unit, it is greater than predetermined value for detecting feature point number in current image frame;
And third detection sub-unit, it is repeated for detecting the characteristic point in current image frame in characteristic point and previous keyframe
Rate is less than predetermined value;
Key frame determines subelement, for when meeting simultaneously, determining that present frame is the key frame of video streaming image.
8. the scene map creation device according to claim 6 based on depth camera, which is characterized in that the pose becomes
Changing matrix determination unit includes:
First module and carriage transformation matrix determines subelement, and the key frame for being inserted into using first is counted towards as world coordinate system
Calculate module and carriage transformation matrix of the key frame relative to previous keyframe in rear insertion;
Second module and carriage transformation matrix determines subelement, for the module and carriage transformation matrix according to two adjacent key frames, calculates and closes
Module and carriage transformation matrix of the key frame relative to initial frame.
9. a kind of map generating device, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, which is characterized in that the processor realizes such as claim 1 when executing the computer program
To the scene described in 5 any one based on depth camera the step of drawing generating method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In realization is as described in any one of claim 1 to 5 based on the scene of depth camera when the computer program is executed by processor
The step of ground drawing generating method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711164388.9A CN109816769A (en) | 2017-11-21 | 2017-11-21 | Scene based on depth camera ground drawing generating method, device and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711164388.9A CN109816769A (en) | 2017-11-21 | 2017-11-21 | Scene based on depth camera ground drawing generating method, device and equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109816769A true CN109816769A (en) | 2019-05-28 |
Family
ID=66599694
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711164388.9A Pending CN109816769A (en) | 2017-11-21 | 2017-11-21 | Scene based on depth camera ground drawing generating method, device and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109816769A (en) |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110297491A (en) * | 2019-07-02 | 2019-10-01 | 湖南海森格诺信息技术有限公司 | Semantic navigation method and its system based on multiple structured light binocular IR cameras |
CN110648397A (en) * | 2019-09-18 | 2020-01-03 | Oppo广东移动通信有限公司 | Scene map generation method and device, storage medium and electronic equipment |
CN110866496A (en) * | 2019-11-14 | 2020-03-06 | 合肥工业大学 | Robot positioning and mapping method and device based on depth image |
CN110880187A (en) * | 2019-10-17 | 2020-03-13 | 北京达佳互联信息技术有限公司 | Camera position information determining method and device, electronic equipment and storage medium |
CN111060118A (en) * | 2019-12-27 | 2020-04-24 | 炬星科技(深圳)有限公司 | Scene map establishing method, device and storage medium |
CN111060948A (en) * | 2019-12-14 | 2020-04-24 | 深圳市优必选科技股份有限公司 | Positioning method, positioning device, helmet and computer readable storage medium |
CN111339226A (en) * | 2019-12-23 | 2020-06-26 | 深圳市香蕉智能科技有限公司 | Method and device for constructing map based on classification detection network |
CN111368015A (en) * | 2020-02-28 | 2020-07-03 | 北京百度网讯科技有限公司 | Method and device for compressing map |
CN111444852A (en) * | 2020-03-27 | 2020-07-24 | 深圳市银星智能科技股份有限公司 | Loop detection method and device and robot |
CN111881233A (en) * | 2020-06-28 | 2020-11-03 | 广州文远知行科技有限公司 | Distributed point cloud map construction method and device, server and computer readable storage medium |
CN111951397A (en) * | 2020-08-07 | 2020-11-17 | 清华大学 | Method, device and storage medium for multi-machine cooperative construction of three-dimensional point cloud map |
CN112086010A (en) * | 2020-09-03 | 2020-12-15 | 中国第一汽车股份有限公司 | Map generation method, map generation device, map generation equipment and storage medium |
CN112149471A (en) * | 2019-06-28 | 2020-12-29 | 北京初速度科技有限公司 | Loopback detection method and device based on semantic point cloud |
WO2021035966A1 (en) * | 2019-08-30 | 2021-03-04 | 浙江商汤科技开发有限公司 | Visual positioning method and related device |
CN112562052A (en) * | 2020-12-03 | 2021-03-26 | 广东工业大学 | Real-time positioning and mapping method for near-shore water area |
CN112710318A (en) * | 2020-12-14 | 2021-04-27 | 深圳市商汤科技有限公司 | Map generation method, route planning method, electronic device, and storage medium |
WO2021083242A1 (en) * | 2019-10-31 | 2021-05-06 | Oppo广东移动通信有限公司 | Map constructing method, positioning method and system, wireless communication terminal, and computer-readable medium |
CN112991515A (en) * | 2021-02-26 | 2021-06-18 | 山东英信计算机技术有限公司 | Three-dimensional reconstruction method, device and related equipment |
CN113129369A (en) * | 2020-01-16 | 2021-07-16 | 北京京东乾石科技有限公司 | Point cloud map initialization method and device |
CN113160130A (en) * | 2021-03-09 | 2021-07-23 | 北京航空航天大学 | Loop detection method and device and computer equipment |
CN113326769A (en) * | 2021-05-28 | 2021-08-31 | 北京三快在线科技有限公司 | High-precision map generation method, device, equipment and storage medium |
CN113447014A (en) * | 2021-08-30 | 2021-09-28 | 深圳市大道智创科技有限公司 | Indoor mobile robot, mapping method, positioning method, and mapping positioning device |
CN113674351A (en) * | 2021-07-27 | 2021-11-19 | 追觅创新科技(苏州)有限公司 | Robot and drawing establishing method thereof |
WO2022142049A1 (en) * | 2020-12-29 | 2022-07-07 | 浙江商汤科技开发有限公司 | Map construction method and apparatus, device, storage medium, and computer program product |
CN112710318B (en) * | 2020-12-14 | 2024-05-17 | 深圳市商汤科技有限公司 | Map generation method, path planning method, electronic device, and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103810711A (en) * | 2014-03-03 | 2014-05-21 | 郑州日兴电子科技有限公司 | Keyframe extracting method and system for monitoring system videos |
CN105856230A (en) * | 2016-05-06 | 2016-08-17 | 简燕梅 | ORB key frame closed-loop detection SLAM method capable of improving consistency of position and pose of robot |
CN105974932A (en) * | 2016-04-27 | 2016-09-28 | 中国人民解放军装甲兵工程学院 | Unmanned aerial vehicle control method |
CN107292949A (en) * | 2017-05-25 | 2017-10-24 | 深圳先进技术研究院 | Three-dimensional rebuilding method, device and the terminal device of scene |
-
2017
- 2017-11-21 CN CN201711164388.9A patent/CN109816769A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103810711A (en) * | 2014-03-03 | 2014-05-21 | 郑州日兴电子科技有限公司 | Keyframe extracting method and system for monitoring system videos |
CN105974932A (en) * | 2016-04-27 | 2016-09-28 | 中国人民解放军装甲兵工程学院 | Unmanned aerial vehicle control method |
CN105856230A (en) * | 2016-05-06 | 2016-08-17 | 简燕梅 | ORB key frame closed-loop detection SLAM method capable of improving consistency of position and pose of robot |
CN107292949A (en) * | 2017-05-25 | 2017-10-24 | 深圳先进技术研究院 | Three-dimensional rebuilding method, device and the terminal device of scene |
Non-Patent Citations (6)
Title |
---|
ELLON MENDES等: "ICP-based pose-graph SLAM", 《2016 IEEE INTERNATIONAL SYMPOSIUM ON SAFETY, SECURITY, AND RESCUE ROBOTICS (SSRR)》 * |
RA´ UL MUR-ARTAL,J.M.M. MONTIEL等: "ORB-SLAM:A Versatile and Accurate Monocular SLAM System", 《IEEETRANSACTIONSONROBOTICS》 * |
熊军林等: "基于RGB-D图像的具有滤波处理和位姿优化的同时定位与建图", 《中国科学技术大学学报》 * |
胡凌燕等: "基于RGB-D图像的三维同步定位与建图研究", 《***仿真学报》 * |
艾青林等: "基于ORB关键帧匹配算法的机器人SLAM实现", 《机电工程》 * |
贾松敏等: "RTM框架下基于分层拓扑结构的多机器人***地图拼接", 《机器人》 * |
Cited By (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112149471B (en) * | 2019-06-28 | 2024-04-16 | 北京初速度科技有限公司 | Loop detection method and device based on semantic point cloud |
CN112149471A (en) * | 2019-06-28 | 2020-12-29 | 北京初速度科技有限公司 | Loopback detection method and device based on semantic point cloud |
CN110297491A (en) * | 2019-07-02 | 2019-10-01 | 湖南海森格诺信息技术有限公司 | Semantic navigation method and its system based on multiple structured light binocular IR cameras |
TWI745818B (en) * | 2019-08-30 | 2021-11-11 | 大陸商浙江商湯科技開發有限公司 | Method and electronic equipment for visual positioning and computer readable storage medium thereof |
JP2022541559A (en) * | 2019-08-30 | 2022-09-26 | 浙江商▲湯▼科技▲開▼▲発▼有限公司 | Visual positioning method and related equipment |
JP7430243B2 (en) | 2019-08-30 | 2024-02-09 | 浙江商▲湯▼科技▲開▼▲発▼有限公司 | Visual positioning method and related equipment |
CN112445929A (en) * | 2019-08-30 | 2021-03-05 | 浙江商汤科技开发有限公司 | Visual positioning method and related device |
WO2021035966A1 (en) * | 2019-08-30 | 2021-03-04 | 浙江商汤科技开发有限公司 | Visual positioning method and related device |
CN110648397B (en) * | 2019-09-18 | 2023-05-16 | Oppo广东移动通信有限公司 | Scene map generation method and device, storage medium and electronic equipment |
CN110648397A (en) * | 2019-09-18 | 2020-01-03 | Oppo广东移动通信有限公司 | Scene map generation method and device, storage medium and electronic equipment |
CN110880187B (en) * | 2019-10-17 | 2022-08-12 | 北京达佳互联信息技术有限公司 | Camera position information determining method and device, electronic equipment and storage medium |
CN110880187A (en) * | 2019-10-17 | 2020-03-13 | 北京达佳互联信息技术有限公司 | Camera position information determining method and device, electronic equipment and storage medium |
WO2021083242A1 (en) * | 2019-10-31 | 2021-05-06 | Oppo广东移动通信有限公司 | Map constructing method, positioning method and system, wireless communication terminal, and computer-readable medium |
CN110866496A (en) * | 2019-11-14 | 2020-03-06 | 合肥工业大学 | Robot positioning and mapping method and device based on depth image |
CN111060948A (en) * | 2019-12-14 | 2020-04-24 | 深圳市优必选科技股份有限公司 | Positioning method, positioning device, helmet and computer readable storage medium |
CN111060948B (en) * | 2019-12-14 | 2021-10-29 | 深圳市优必选科技股份有限公司 | Positioning method, positioning device, helmet and computer readable storage medium |
US11416719B2 (en) | 2019-12-14 | 2022-08-16 | Ubtech Robotics Corp Ltd | Localization method and helmet and computer readable storage medium using the same |
CN111339226A (en) * | 2019-12-23 | 2020-06-26 | 深圳市香蕉智能科技有限公司 | Method and device for constructing map based on classification detection network |
CN111339226B (en) * | 2019-12-23 | 2023-11-24 | 深圳市香蕉智能科技有限公司 | Method and device for constructing map based on classification detection network |
CN111060118A (en) * | 2019-12-27 | 2020-04-24 | 炬星科技(深圳)有限公司 | Scene map establishing method, device and storage medium |
CN111060118B (en) * | 2019-12-27 | 2022-01-07 | 炬星科技(深圳)有限公司 | Scene map establishing method, device and storage medium |
CN113129369A (en) * | 2020-01-16 | 2021-07-16 | 北京京东乾石科技有限公司 | Point cloud map initialization method and device |
CN111368015A (en) * | 2020-02-28 | 2020-07-03 | 北京百度网讯科技有限公司 | Method and device for compressing map |
CN111368015B (en) * | 2020-02-28 | 2023-04-07 | 北京百度网讯科技有限公司 | Method and device for compressing map |
CN111444852A (en) * | 2020-03-27 | 2020-07-24 | 深圳市银星智能科技股份有限公司 | Loop detection method and device and robot |
CN111881233A (en) * | 2020-06-28 | 2020-11-03 | 广州文远知行科技有限公司 | Distributed point cloud map construction method and device, server and computer readable storage medium |
CN111951397A (en) * | 2020-08-07 | 2020-11-17 | 清华大学 | Method, device and storage medium for multi-machine cooperative construction of three-dimensional point cloud map |
CN112086010B (en) * | 2020-09-03 | 2022-03-18 | 中国第一汽车股份有限公司 | Map generation method, map generation device, map generation equipment and storage medium |
CN112086010A (en) * | 2020-09-03 | 2020-12-15 | 中国第一汽车股份有限公司 | Map generation method, map generation device, map generation equipment and storage medium |
CN112562052A (en) * | 2020-12-03 | 2021-03-26 | 广东工业大学 | Real-time positioning and mapping method for near-shore water area |
CN112710318A (en) * | 2020-12-14 | 2021-04-27 | 深圳市商汤科技有限公司 | Map generation method, route planning method, electronic device, and storage medium |
CN112710318B (en) * | 2020-12-14 | 2024-05-17 | 深圳市商汤科技有限公司 | Map generation method, path planning method, electronic device, and storage medium |
WO2022142049A1 (en) * | 2020-12-29 | 2022-07-07 | 浙江商汤科技开发有限公司 | Map construction method and apparatus, device, storage medium, and computer program product |
CN112991515A (en) * | 2021-02-26 | 2021-06-18 | 山东英信计算机技术有限公司 | Three-dimensional reconstruction method, device and related equipment |
CN113160130A (en) * | 2021-03-09 | 2021-07-23 | 北京航空航天大学 | Loop detection method and device and computer equipment |
CN113326769A (en) * | 2021-05-28 | 2021-08-31 | 北京三快在线科技有限公司 | High-precision map generation method, device, equipment and storage medium |
CN113674351A (en) * | 2021-07-27 | 2021-11-19 | 追觅创新科技(苏州)有限公司 | Robot and drawing establishing method thereof |
CN113674351B (en) * | 2021-07-27 | 2023-08-08 | 追觅创新科技(苏州)有限公司 | Drawing construction method of robot and robot |
CN113447014A (en) * | 2021-08-30 | 2021-09-28 | 深圳市大道智创科技有限公司 | Indoor mobile robot, mapping method, positioning method, and mapping positioning device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109816769A (en) | Scene based on depth camera ground drawing generating method, device and equipment | |
CN110168477B (en) | Deep learning system for cuboid detection | |
US10936911B2 (en) | Logo detection | |
US10872439B2 (en) | Method and device for verification | |
CN110310333B (en) | Positioning method, electronic device and readable storage medium | |
CN109960742B (en) | Local information searching method and device | |
CN109242961A (en) | A kind of face modeling method, apparatus, electronic equipment and computer-readable medium | |
CN108961327A (en) | A kind of monocular depth estimation method and its device, equipment and storage medium | |
CN108734120A (en) | Mark method, apparatus, equipment and the computer readable storage medium of image | |
US20220301295A1 (en) | Recurrent multi-task convolutional neural network architecture | |
US11145080B2 (en) | Method and apparatus for three-dimensional object pose estimation, device and storage medium | |
CN112070782B (en) | Method, device, computer readable medium and electronic equipment for identifying scene contour | |
CN110648363A (en) | Camera posture determining method and device, storage medium and electronic equipment | |
CN107644423B (en) | Scene segmentation-based video data real-time processing method and device and computing equipment | |
CN110598715A (en) | Image recognition method and device, computer equipment and readable storage medium | |
CN111161398A (en) | Image generation method, device, equipment and storage medium | |
CN117197388A (en) | Live-action three-dimensional virtual reality scene construction method and system based on generation of antagonistic neural network and oblique photography | |
JP2023131117A (en) | Joint perception model training, joint perception method, device, and medium | |
CN115018999A (en) | Multi-robot-cooperation dense point cloud map construction method and device | |
CN111079535B (en) | Human skeleton action recognition method and device and terminal | |
CN116704029A (en) | Dense object semantic map construction method and device, storage medium and electronic equipment | |
CN115393423A (en) | Target detection method and device | |
US11380121B2 (en) | Full skeletal 3D pose recovery from monocular camera | |
CN114757822A (en) | Binocular-based human body three-dimensional key point detection method and system | |
CN114299152A (en) | Method for acquiring attitude data and neural network construction method |
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: 20190528 |