CN110276826A - A kind of construction method and system of electric network operation environmental map - Google Patents
A kind of construction method and system of electric network operation environmental map Download PDFInfo
- Publication number
- CN110276826A CN110276826A CN201910438134.4A CN201910438134A CN110276826A CN 110276826 A CN110276826 A CN 110276826A CN 201910438134 A CN201910438134 A CN 201910438134A CN 110276826 A CN110276826 A CN 110276826A
- Authority
- CN
- China
- Prior art keywords
- map
- sub
- electric network
- network operation
- key frame
- 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
- 230000007613 environmental effect Effects 0.000 title claims abstract description 35
- 238000010276 construction Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 35
- 230000009466 transformation Effects 0.000 claims abstract description 28
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 230000015654 memory Effects 0.000 claims description 23
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000012216 screening Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 11
- 230000001052 transient effect Effects 0.000 description 6
- 238000004804 winding Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 238000007873 sieving Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/32—Image data format
Abstract
The present invention provides the construction methods and system of a kind of electric network operation environmental map, this method comprises: obtaining each sub- map and the corresponding key frame images of each sub- map for the electric network operation environment established stage by stage；Closed loop detection is carried out to the corresponding key frame images of each sub- map respectively, generates each overlapping image between each sub- map；Each sub- map corresponding pose under global coordinate system is calculated separately according to each overlapping image, and each sub- map is carried out by sub- map splicing according to the corresponding pose of each sub- map, generates the global map of electric network operation environment.By implementing the present invention, the establishment process of global map is converted to the foundation of the sub- map in part stage by stage, it is built in the big indoor power transformation operation environment of figure scale so as to avoid existing vision SLAM method in environment complexity and builds the problem of figure error even builds greatly figure failure, improve the accuracy for build to electric network operation environment figure, and substantially reduce and build the figure time, it improves and builds figure efficiency.
Description
Technical field
The present invention relates to three-dimensional map constructing technology fields, and in particular to a kind of construction method of electric network operation environmental map
And system.
Background technique
With industrial automation, intelligentized continuous development, substation's internal structure is highly integrated, and logical relation is more multiple
It is miscellaneous, cause the task difficulty of operating personnel to be continuously increased.If the three-dimensional map of substation can be established, melt in three-dimensional map
It closes job content and Heuristics can be to provide intuitive and convenient task instruction for operating personnel.Be conducive to promote power grid scene
Work quality, efficiency and the level of security of operation.Wherein, it using the wearable device of inspection worker, works in Daily Round Check
In to establish the threedimensional model of substation's operating environment be a kind of effective way for building figure simultaneously.
(simultaneous localization and mapping, positioning and map structuring, simple immediately by vision SLAM
Claim SLAM) it is one kind using camera as unique external sensor, self poisoning is carried out in circumstances not known and at the same time creation
A kind of technology of environmental map.It is traditional due to, with environment complexity, building the features such as figure scale is big in indoor power transformation operation environment
Vision SLAM method usually occurs building the case where figure error even builds greatly figure failure in the present context.
Summary of the invention
In view of this, the embodiment of the invention provides the construction method and system of a kind of electric network operation environmental map, with gram
Traditional SLAM method usually occurs building figure error under power transformation operation environment greatly or even builds figure failure clothes indoors in the prior art
The problem of.
The embodiment of the invention provides a kind of construction methods of electric network operation environmental map, comprising: acquisition is established stage by stage
Electric network operation environment each sub- map and the corresponding key frame images of each sub- map；Respectively to each sub- map
Corresponding key frame images carry out closed loop detection, generate each overlapping image between each sub- map；According to each overlapping
Image calculates separately each sub- map corresponding pose under global coordinate system, and according to the corresponding pose of each sub- map
Each sub- map is subjected to sub- map splicing, generates the global map of the electric network operation environment.
Optionally, described that closed loop detection is carried out to the corresponding key frame images of each sub- map, generate each son ground
Each overlapping image between figure, comprising: closed loop inspection is carried out to the corresponding key frame images of each sub- map using DBoW2 algorithm
It surveys, generates each closed loop matching characteristic point pair；Using Epipolar geometry constrained procedure to each closed loop matching characteristic point to sieving
Choosing, and reject each closed loop matching characteristic point pair for being unsatisfactory for the Epipolar geometry constrained procedure requirement；After screening
Each closed loop matching characteristic point pair generates each overlapping image.
It is optionally, described that according to each overlapping image to calculate separately each sub- map corresponding under global coordinate system
Pose, comprising: the three-dimensional point cloud of the overlapping region between each sub- map is generated according to each overlapping image；According to described
The three-dimensional point cloud of overlapping region between each sub- map calculates each transformation between each sub- map using point cloud registration algorithm
Relationship；Each sub- map corresponding pose under global coordinate system is calculated separately according to each transformation relation, and according to institute
It states the corresponding pose of each sub- map and each sub- map is subjected to sub- map splicing, generate the global map.
Optionally, the three-dimensional point cloud that the overlapping region between each sub- map is generated according to the overlapping image,
It include: to obtain each key frame images comprising the overlapping image, and obtain the corresponding pose of each key frame images
Information；The three-dimensional point cloud of single-frame images is generated according to each key frame images respectively；It is corresponding according to each key frame images
Posture information, the corresponding three-dimensional point cloud of each key frame images is spliced, the three of the overlapping region are generated
Dimension point cloud.
It is optionally, described that according to each transformation relation to calculate separately each sub- map corresponding under global coordinate system
Pose, comprising: construct the oriented weighted graph of each sub- map respectively according to each transformation relation；Respectively to each described oriented
Weighted graph carries out depth-first traversal, calculates each sub- map corresponding pose under global coordinate system.
Optionally, the construction method of the electric network operation environmental map, further includes: obtain the electric network operation environment
Job information；The job information is added in the global map, complete global map is generated.
Optionally, the construction method of the electric network operation environmental map, further includes: to the complete global map,
Each sub- map, each key frame images, each overlapping image and the corresponding pose of each sub- map are stored.
The embodiment of the invention also provides a kind of building systems of electric network operation environmental map in vision SLAM, comprising:
Data obtaining module, each sub- map and each sub- map for obtaining the electric network operation environment established stage by stage are corresponding
Key frame images；It is overlapped image generation module, for carrying out closed loop to the corresponding key frame images of each sub- map respectively
Detection generates each overlapping image between each sub- map；Global map constructs module, for according to each overlapping image
Calculate separately each sub- map corresponding pose under global coordinate system, and according to the corresponding pose of each sub- map by institute
It states each sub- map and carries out sub- map splicing, generate the global map of the electric network operation environment.
The embodiment of the invention also provides a kind of electronic equipment, comprising: memory and processor, the memory and described
Connection is communicated with each other between processor, computer instruction is stored in the memory, the processor is by executing the meter
The instruction of calculation machine, the construction method of the electric network operation environmental map is provided thereby executing the embodiment of the present invention.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
Computer instruction, the computer instruction are used to that the computer to be made to execute offer of the embodiment of the present invention power grid to make
The construction method of industry environmental map.
Technical solution of the present invention has the advantages that
The embodiment of the invention provides a kind of construction methods of electric network operation environmental map, are established stage by stage by acquisition
Each sub- map and the corresponding key frame images of each sub- map of electric network operation environment respectively carry out each key frame images
Closed loop is detected to obtain the overlapping image between each sub- map, is then calculated each sub- map according to overlapping image and is sat in the overall situation
Pose under mark system, and each sub- map is stitched together according to pose and generates the global map of electric network operation environment, thus logical
The foundation that the establishment process of global map is converted to the sub- map in part stage by stage is crossed, the figure between each sub- map is then passed through
As overlapping relation, pose of each sub- map under global coordinate system is calculated, and then can be according to pose by each part
Figure is stitched together to form complete global map, and it is big in environment complexity to build figure scale so as to avoid existing vision SLAM method
Indoor power transformation operation environment in build figure error greatly in addition build figure failure the problem of, improve and electric network operation environment carried out to build figure
Accuracy, and substantially reduce and build the figure time, improve and build figure efficiency.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow chart of the construction method of the electric network operation environmental map in the embodiment of the present invention；
Fig. 2A is the schematic diagram of the topological relation between the sub- map of difference in the embodiment of the present invention；
Fig. 2 B is another schematic diagram of the topological relation between the sub- map of difference in the embodiment of the present invention；
Fig. 3 is the structural schematic diagram of the building system of the electric network operation environmental map in the embodiment of the present invention；
Fig. 4 is the structural schematic diagram of the electronic equipment in the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
As long as technical characteristic involved in invention described below different embodiments does not constitute punching each other
It is prominent to be combined with each other.
The embodiment of the invention provides a kind of construction methods of electric network operation environmental map, as shown in Figure 1, the electric network operation
The construction method of environmental map specifically includes:
Step S1: each sub- map and the corresponding key of each sub- map of the electric network operation environment established stage by stage are obtained
Frame image.
Specifically, in practical applications, the staff of electric network operation environment can be divided by being equipped with RGB-D sensor
The operating environment of section scanning power grid, obtains the ambient image in different location stage in electric network operation environment, and obtain according to these
Each sub- map of the different location of the image creation environment taken.While creating each sub- map of environment, save for fixed
Position sub- map correlation map data for example: facility information and job information in electric network operation environment etc. and each each son
The RGB-D image of key frame in map.It should be noted that a in embodiments of the present invention, the creation of every sub- map
Journey can be realized using the map constructing method in the prior art suitable for small scale, to obtain more accurate son ground
Figure, selected concrete methods of realizing, the present invention is not limited thereto.
Step S2: closed loop detection is carried out to the corresponding key frame images of each sub- map respectively, is generated between each sub- map
Each overlapping image.
Specifically, in one embodiment, in above-mentioned step S2, closed loop is carried out to the corresponding key frame images of each sub- map
Detection generates each overlapping image between each sub- map, specifically comprises the following steps:
Step S21: closed loop detection is carried out to the corresponding key frame images of each sub- map using DBoW2 algorithm, generation is respectively closed
Ring matching characteristic point pair.In practical applications, the detailed process of the detection of the closed loop between sub- map is realized using DBoW2 algorithm are as follows:
Feature is extracted from one group of training image first, this group of training image is made of the key frame images between two sub- maps of difference,
The feature of extraction k-means++ algorithm is clustered again, by description Subspace partition at k class.Then empty in every height of division
Between in, continue with k-means++ algorithm and cluster, until will describe son be generated as the number of plies for L tree structure.
So, there are two frames to wait for the key frame I and I ' of winding, feature detection is carried out to image and is described with feature, by each spy
Sign obtains BoW2 vector V by the dictionary of tree structure1=[v1,…,vn] and V2=[v '1,…,v′n], according to BoW2 vector
Image similarity formula between available I and I ' is referring to following formula:
Wherein, L1-scores(V1,V2) indicate to measure vector V with L1 norm1And V2Between similarity, viIndicate vector
V1In certain dimension value, v 'iIndicate vector V2In with dimension value.It should be noted that above-mentioned real using DBoW2 algorithm
The detailed process of closed loop detection between existing sub- map is only to briefly describe, and specific detailed process referring to using in the prior art
DBoW2 algorithm carries out the scheme of closed loop detection, is no longer repeated herein.
Step S22: it using Epipolar geometry constrained procedure to each closed loop matching characteristic point to screening, and rejects and is unsatisfactory for
Each closed loop matching characteristic point pair that Epipolar geometry constrained procedure requires.In practical applications, indoors in substation, due to
There is a large amount of similar features, and there is no the spatial neighborhood relations for utilizing characteristic point for DBoW2 algorithm itself, therefore this
The winding of mistake is easy to produce in environment.In embodiments of the present invention, the winding of mistake is excluded by Epipolar geometry constraint,
Ensure all closed loop matching characteristic points to being all accurate.Due to matched feature in two images of Epipolar geometry constraint requirements
Point needs to meet certain transformation relation, thus the closed loop of mistake is not able to satisfy this transformation relation therefore is excluded, thus real
Show the rejecting to wrong winding, and then improves the accuracy that the subsequent overall situation builds figure.
Step S23: according to each closed loop matching characteristic point pair after screening, each overlapping image is generated.In practical applications, two
Closed loop matching characteristic point in a key frame images after screening is to the image-region for being included, as the two key frame figures
As the overlapping image between two corresponding sub- maps.
Step S3: calculating separately each sub- map corresponding pose under global coordinate system according to each overlapping image, and according to
Each sub- map is carried out sub- map splicing by the corresponding pose of each sub- map, generates the global map of electric network operation environment.
Specifically, in one embodiment, in above-mentioned step S3, each sub- map is calculated separately complete according to each overlapping image
Corresponding pose under office's coordinate system, specifically comprises the following steps:
Step S31: the three-dimensional point cloud of the overlapping region between each sub- map is generated according to each overlapping image.In practical application
In, the specific generating principle of three-dimensional point cloud are as follows: according to the projection model of camera, it is assumed that any point p is in camera coordinates in space
Three-dimensional coordinate under system is pc=[x, y, z]T, imaging point coordinate in the picture is p=[u, v, d]T(wherein, u, v are indicated
The coordinate position of pixel under image coordinate system, d indicate the depth value of the pixel), then the corresponding relationship between them is as follows
Shown in formula:
D=zs
Wherein, fxAnd fyIndicate focal length of the camera on x, two axis of y, cxAnd cyFor the coordinate at the aperture center of camera, s
Indicate the scale factor of depth map.
Therefore, the three dimensional space coordinate that every bit in image can be restored according to colored and depth image, can be obtained by
Space coordinate is projected in world coordinates again, obtains all pixels point included in the overlapping region between each sub- map
Three-dimensional point cloud.
Step S32: each son is calculated using point cloud registration algorithm according to the three-dimensional point cloud of the overlapping region between each sub- map
Each transformation relation between map.In practical applications, the specific calculating process of the transformation relation are as follows: assuming that two width maps
M1, M2Coordinate under world coordinate system is respectively W1, W2, the transformation relation between two width maps isDue to two width
There is overlapping region between map, thus, it is supposed that a point P can be observed in two width maps,Respectively point P exists
W1, W2Coordinate under coordinate system, in the coordinate of known point PIn the case where, by utilizing ICP
(IterativeClosestPoint iteration closest approach algorithm, a kind of algorithm for point cloud registering) is come with calculating this two width
Transformation relation between figureSo that it meetsTransformation relation in the specific application process can
It can be due to sub- map M1, M2It is often apart from each other so that can not accurately calculateSo it is chosen at sub- map M1Selection can
Observe the key frame images K of P point1, and in sub- map M2Choose the key frame images K for being able to observe that P point2, then can obtain
To following formula:
Wherein,Indicates coordinate system W1In coordinate system K1Under coordinate,Indicates coordinate system K2In coordinate system K1Under
Coordinate, i.e. key frame K2With K1Between transformation relation,Indicate indicates coordinate system W2In coordinate system K2Under coordinate.
Therefore, it can be acquired first according to above-mentioned formulaI.e. adjacent closer two key frame images K1,K2Complete
Transformation relation under office's coordinate system, then can be in the hope of two width map M1, M2Between transformation relation
Step S33: calculating separately each sub- map corresponding pose under global coordinate system according to each transformation relation, and according to
Each sub- map is carried out sub- map splicing by the corresponding pose of each sub- map, generates global map.
Specifically, in one embodiment, in above-mentioned step S33, each sub- map is calculated separately according to each transformation relation and is existed
Corresponding pose, specifically comprises the following steps: under global coordinate system
Step S331: the oriented weighted graph of each sub- map is constructed respectively according to each transformation relation.
Step S332: carrying out depth-first traversal to each oriented weighted graph respectively, calculates each sub- map in global coordinate system
Under corresponding pose.
In practical applications, the transformation relation being calculated according to above-mentioned steps S32, can construct different sub- maps it
Between topological relation, it is assumed that M1、M2、M3... it is the three sub- maps established, Respectively
It is represented as sub- map M1、M2、M3Internal key frame images, constructed topological relation is as shown in Figure 2 A, and solid line indicates same in figure
Belong to the key frame images of identical sub- map, dotted line indicates the winding between each sub- map detected.According to winding detection
As a result the transformational relation between sub- map is calculatedFor under global coordinate system, sub- map MiWith MjBetween
Transformation matrix, topological map can simplify as the form of Weighted Directed Graph in figure as shown in Figure 2 B.By to this graph traversal,
Pose of all sub- maps under world coordinates can be calculated.It should be noted that in embodiments of the present invention to cum rights
Oriented graph traversal is realized by depth-first traversal algorithm, in practical applications, can also be realized using other algorithms,
The present invention is not limited thereto.
Specifically, in one embodiment, the construction method of above-mentioned electric network operation environmental map further include:
Step S4: the job information of electric network operation environment is obtained.In practical applications, which contains equipment
The information of information and operating environment, the information of equipment specifically include the letter such as ID, title, position, state and historical data of equipment
Breath, operating environment information are then the type information for containing region and some points for attention in the region, for example whether for danger
The information such as region.
Step S5: job information is added in global map, generates complete global map.In practical applications, it is
It is user-friendly, in the global map of creation in addition to comprising map for position and position coordinates other than, should also
It include the information of equipment present in map and some job informations of map environment.
Step S6: to complete global map, each sub- map, each key frame images, each overlapping image and each sub- map pair
The pose answered is stored.It in practical applications, can be using the map data structure of layering come the progress of to map related data
Storage, the map datum stored are divided into two parts of global map and each sub- map, creation when building figure of sub- map
And save, global map is calculated and is generated after building figure.Wherein, each sub- map includes the data of map, operation again
The information such as the image of information and key frame and positional relationship.The data of map for example may include the following contents: (1)
MapPoints, the specific quantity comprising MapPoints and their spatial position.(2)KeyFrames.Specifically include
The quantity of KeyFrame, the pose of each frame image, the feature of all characteristic points describes and saves these characteristic points in each frame
With the corresponding relationship of MapPoint.(3) relationship between different frame image saves the father's key frame and phase therewith of each frame key
Key frame even.By saving information above, complete map can be recovered.Wherein, job information contains the information of equipment
With the information of operating environment, the information of equipment specifically includes the information such as ID, title, position, state and the historical data of equipment, is made
Industry environmental information is then the type information for containing region and some points for attention in the region, for example whether being danger zone
Deng.
S1 to step S6 through the above steps, the construction method of electric network operation environmental map provided in an embodiment of the present invention,
By obtaining each sub- map and the corresponding key frame images of each sub- map of the electric network operation environment established stage by stage, respectively
Closed loop detection is carried out to obtain the overlapping image between each sub- map, then according to overlapping image meter to each key frame images
Pose of each sub- map under global coordinate system is calculated, and each sub- map is stitched together according to pose and generates electric network operation ring
The global map in border, to then be led to by the foundation that the establishment process of global map is converted to the sub- map in part stage by stage
The image overlapping relation between each sub- map is crossed, calculates pose of each sub- map under global coordinate system, and then can root
It is stitched together the sub- map in each part to form complete global map according to pose, so as to avoid existing vision SLAM method
It is built in the big indoor power transformation operation environment of figure scale in environment complexity and builds figure error greatly or even the problem of build figure failure, improved pair
Electric network operation environment build the accuracy of figure, and substantially reduces and build the figure time, improves and builds figure efficiency.
The embodiment of the invention also provides a kind of building systems of electric network operation environmental map, as shown in figure 3, the power grid is made
The building system of industry environmental map includes:
Data obtaining module 1, for obtaining each sub- map and each sub- map of the electric network operation environment established stage by stage
Corresponding key frame images.Detailed content is no longer gone to live in the household of one's in-laws on getting married herein referring to the associated description of step S1 in above method embodiment
It states.
It is overlapped image generation module 2, for carrying out closed loop detection to the corresponding key frame images of each sub- map respectively, is generated
Each overlapping image between each sub- map.Detailed content referring to step S2 in above method embodiment associated description, herein not
It is repeated again.
Global map constructs module 3, right under global coordinate system for calculating separately each sub- map according to each overlapping image
The pose answered, and each sub- map is carried out by sub- map splicing according to the corresponding pose of each sub- map, generate electric network operation environment
Global map.Detailed content is no longer repeated herein referring to the associated description of step S3 in above method embodiment.
By the cooperative cooperating of above-mentioned each component part, the structure of electric network operation environmental map provided in an embodiment of the present invention
System is built, by each sub- map and the corresponding key frame figure of each sub- map that obtain the electric network operation environment established stage by stage
Picture carries out closed loop detection to obtain the overlapping image between each sub- map, then according to weight to each key frame images respectively
Folded image calculates pose of each sub- map under global coordinate system, and each sub- map is stitched together according to pose and generates electricity
The global map of net operating environment, to be built by the way that the establishment process of global map is converted to the sub- map in part stage by stage
It is vertical, then by the image overlapping relation between each sub- map, pose of each sub- map under global coordinate system is calculated, into
And the sub- map in each part can be stitched together to form complete global map according to pose, so as to avoid existing vision
SLAM method builds in the big indoor power transformation operation environment of figure scale in environment complexity and builds the problem of figure error even builds greatly figure failure,
The accuracy for build to electric network operation environment figure is improved, and substantially reduces and builds the figure time, improves and builds figure efficiency.
A kind of electronic equipment is additionally provided according to embodiments of the present invention, as shown in figure 4, the electronic equipment may include processing
Device 901 and memory 902, wherein processor 901 can be connected with memory 902 by bus or other modes, in Fig. 4 with
For being connected by bus.
Processor 901 can be central processing unit (Central Processing Unit, CPU).Processor 901 may be used also
Think other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable GateArray, FPGA) either other programmable logic device, discrete gate or transistor logic,
The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.
Memory 902 is used as a kind of non-transient computer readable storage medium, can be used for storing non-transient software program, non-
Transient computer executable program and module, the construction method institute such as the electric network operation environmental map in the embodiment of the present invention are right
Program instruction/the module answered.Processor 901 by operation be stored in memory 902 non-transient software program, instruction and
Module, thereby executing the various function application and data processing of processor, i.e. power grid in realization above method embodiment is made
The construction method of industry environmental map.
Memory 902 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function；It storage data area can the data etc. that are created of storage processor 901.In addition,
Memory 902 may include high-speed random access memory, can also include non-transient memory, and a for example, at least disk is deposited
Memory device, flush memory device or other non-transient solid-state memories.In some embodiments, it includes opposite that memory 902 is optional
In the remotely located memory of processor 901, these remote memories can pass through network connection to processor 901.Above-mentioned net
The example of network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
One or more module is stored in memory 902, and when being executed by processor 901, it is real to execute the above method
Apply the construction method of the electric network operation environmental map in example.
Above-mentioned electronic equipment detail can be corresponded to refering to associated description corresponding in above method embodiment and effect
Understood, details are not described herein again.
It is that can lead to it will be understood by those skilled in the art that realizing all or part of the process in above-described embodiment method
Computer program is crossed to instruct relevant hardware and complete, program can be stored in a computer-readable storage medium, should
Program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, storage medium can be magnetic disk, CD, read-only
It is storage memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), fast
Flash memory (Flash Memory), hard disk (Hard Disk Drive, abbreviation: HDD) or solid state hard disk (Solid-State
Drive, SSD) etc.；Storage medium can also include the combination of the memory of mentioned kind.
Although being described in conjunction with the accompanying the embodiment of the present invention, those skilled in the art can not depart from the present invention
Spirit and scope in the case where various modifications and variations can be made, such modifications and variations are each fallen within by appended claims institute
Within the scope of restriction.
Claims (10)
1. a kind of construction method of electric network operation environmental map characterized by comprising
Obtain each sub- map of electric network operation environment established stage by stage and the corresponding key frame images of each sub- map；
Closed loop detection is carried out to the corresponding key frame images of each sub- map respectively, is generated each heavy between each sub- map
Folded image；
Each sub- map corresponding pose under global coordinate system is calculated separately according to each overlapping image, and according to described
Each sub- map is carried out sub- map splicing by the corresponding pose of each sub- map, generates the electric network operation environment globally
Figure.
2. the construction method of electric network operation environmental map according to claim 1, which is characterized in that described to each son
The corresponding key frame images of map carry out closed loop detection, generate each overlapping image between each sub- map, comprising:
Closed loop detection is carried out to the corresponding key frame images of each sub- map using DBoW2 algorithm, it is special to generate each closed loop matching
Sign point pair；
Using Epipolar geometry constrained procedure to each closed loop matching characteristic point to screening, and reject be unsatisfactory for it is described to pole
Each closed loop matching characteristic point pair that geometrical constraint method requires；
According to each closed loop matching characteristic point pair after screening, each overlapping image is generated.
3. the construction method of electric network operation environmental map according to claim 1, which is characterized in that described according to described each
Overlapping image calculates separately each sub- map corresponding pose under global coordinate system, comprising:
The three-dimensional point cloud of the overlapping region between each sub- map is generated according to each overlapping image；
Each sub- map is calculated using point cloud registration algorithm according to the three-dimensional point cloud of the overlapping region between each sub- map
Between each transformation relation；
Each sub- map corresponding pose under global coordinate system is calculated separately according to each transformation relation, and according to described
Each sub- map is carried out sub- map splicing by the corresponding pose of each sub- map, generates the global map.
4. the construction method of electric network operation environmental map according to claim 3, which is characterized in that described according to described heavy
Folded image generates the three-dimensional point cloud of the overlapping region between each sub- map, comprising:
Each key frame images comprising the overlapping image are obtained, and obtain the corresponding pose letter of each key frame images
Breath；
The three-dimensional point cloud of single-frame images is generated according to each key frame images respectively；
According to the corresponding posture information of each key frame images, by the corresponding three-dimensional point cloud of each key frame images into
Row splicing, generates the three-dimensional point cloud of the overlapping region.
5. the construction method of electric network operation environmental map according to claim 3, which is characterized in that described according to described each
Transformation relation calculates separately each sub- map corresponding pose under global coordinate system, comprising:
Construct the oriented weighted graph of each sub- map respectively according to each transformation relation；
Depth-first traversal is carried out to each oriented weighted graph respectively, it is corresponding under global coordinate system to calculate each sub- map
The pose.
6. the construction method of electric network operation environmental map according to claim 1-5, which is characterized in that also wrap
It includes:
Obtain the job information of the electric network operation environment；
The job information is added in the global map, complete global map is generated.
7. the construction method of electric network operation environmental map according to claim 6, which is characterized in that further include:
To the complete global map, each sub- map, each key frame images, each overlapping image and the corresponding pose of each sub- map
It is stored.
8. a kind of building system of electric network operation environmental map characterized by comprising
Data obtaining module, for obtaining each sub- map and each sub- map of the electric network operation environment established stage by stage
Corresponding key frame images；
It is overlapped image generation module, for carrying out closed loop detection to the corresponding key frame images of each sub- map respectively, is generated
Each overlapping image between each sub- map；
Global map constructs module, for calculating separately each sub- map under global coordinate system according to each overlapping image
Corresponding pose, and each sub- map is carried out by sub- map splicing according to the corresponding pose of each sub- map, described in generation
The global map of electric network operation environment.
9. a kind of electronic equipment characterized by comprising
Memory and processor communicate with each other connection, are stored in the memory between the memory and the processor
Computer instruction, the processor are described in any item thereby executing claim 1-7 by executing the computer instruction
The construction method of electric network operation environmental map.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer to refer to
It enables, the computer instruction is for making the computer thereby executing the described in any item electric network operation environment of claim 1-7
The construction method of map.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910438134.4A CN110276826A (en) | 2019-05-23 | 2019-05-23 | A kind of construction method and system of electric network operation environmental map |
| PCT/CN2020/092144 WO2020233724A1 (en) | 2019-05-23 | 2020-05-25 | Visual slam-based grid operating environment map construction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910438134.4A CN110276826A (en) | 2019-05-23 | 2019-05-23 | A kind of construction method and system of electric network operation environmental map |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110276826A true CN110276826A (en) | 2019-09-24 |
Family
ID=67960135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910438134.4A Pending CN110276826A (en) | 2019-05-23 | 2019-05-23 | A kind of construction method and system of electric network operation environmental map |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110276826A (en) |
| WO (1) | WO2020233724A1 (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110849380A (en) * | 2019-10-28 | 2020-02-28 | 北京影谱科技股份有限公司 | Map alignment method and system based on collaborative VSLAM |
| CN110968429A (en) * | 2019-12-20 | 2020-04-07 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for loop detection in directed graph |
| CN111174799A (en) * | 2019-12-24 | 2020-05-19 | Oppo广东移动通信有限公司 | Map construction method and device, computer readable medium and terminal equipment |
| WO2020233724A1 (en) * | 2019-05-23 | 2020-11-26 | 全球能源互联网研究院有限公司 | Visual slam-based grid operating environment map construction method and system |
| WO2021057743A1 (en) * | 2019-09-27 | 2021-04-01 | Oppo广东移动通信有限公司 | Map fusion method, apparatus, device and storage medium |
| CN112614171A (en) * | 2020-11-26 | 2021-04-06 | 厦门大学 | Air-ground integrated dynamic environment sensing system for cluster operation of engineering machinery |
| 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 |
| CN117315170A (en) * | 2023-09-12 | 2023-12-29 | 华大天元(北京)科技股份有限公司 | Construction method, device, equipment and medium of power grid operation environment map |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112380371A (en) * | 2020-11-27 | 2021-02-19 | 广东电网有限责任公司肇庆供电局 | Closed loop detection method based on local and convolutional neural network characteristics |
| CN112630745A (en) * | 2020-12-24 | 2021-04-09 | 深圳市大道智创科技有限公司 | Environment mapping method and device based on laser radar |
| CN112614185B (en) * | 2020-12-29 | 2022-06-21 | 浙江商汤科技开发有限公司 | Map construction method and device and storage medium |
| CN112668653A (en) * | 2020-12-30 | 2021-04-16 | 北京百度网讯科技有限公司 | Loop detection method, device, equipment and medium based on laser radar map |
| CN113012212B (en) * | 2021-04-02 | 2024-04-16 | 西北农林科技大学 | Depth information fusion-based indoor scene three-dimensional point cloud reconstruction method and system |
| CN113192174B (en) * | 2021-04-06 | 2024-03-26 | 中国计量大学 | Picture construction method and device and computer storage medium |
| CN113674409A (en) * | 2021-07-20 | 2021-11-19 | 中国科学技术大学先进技术研究院 | Vision-based multi-robot instant positioning and synchronous drawing establishing method, system and medium |
| KR102431122B1 (en) * | 2021-12-30 | 2022-08-10 | 주식회사 버넥트 | Method and system for map tartet tracking |
| CN114442621A (en) * | 2022-01-17 | 2022-05-06 | 浙江大学 | Autonomous exploration and mapping system based on quadruped robot |
| CN116481516B (en) * | 2023-06-21 | 2023-10-13 | 深圳市普渡科技有限公司 | Robot, map creation method, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106595659A (en) * | 2016-11-03 | 2017-04-26 | 南京航空航天大学 | Map merging method of unmanned aerial vehicle visual SLAM under city complex environment |
| CN107515891A (en) * | 2017-07-06 | 2017-12-26 | 杭州南江机器人股份有限公司 | A kind of robot cartography method, apparatus and storage medium |
| CN108090958A (en) * | 2017-12-06 | 2018-05-29 | 上海阅面网络科技有限公司 | A kind of robot synchronously positions and map constructing method and system |
| US20180211399A1 (en) * | 2017-01-26 | 2018-07-26 | Samsung Electronics Co., Ltd. | Modeling method and apparatus using three-dimensional (3d) point cloud |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19839397A1 (en) * | 1998-08-29 | 2000-03-02 | Readymix Betonbauteile Gmbh | Computer based construction of surface surrounding three dimensional object, based upon processing of digital data obtained from scanning of a three dimensional photograph |
| WO2003077204A2 (en) * | 2002-03-07 | 2003-09-18 | Medtronic, Inc. | Algorithm for accurate three-dimensional reconstruction of non-linear implanted medical devices in vivo |
| CN105843223B (en) * | 2016-03-23 | 2018-11-20 | 东南大学 | A kind of mobile robot three-dimensional based on space bag of words builds figure and barrier-avoiding method |
| CN106272423A (en) * | 2016-08-31 | 2017-01-04 | 哈尔滨工业大学深圳研究生院 | A kind of multirobot for large scale environment works in coordination with the method for drawing and location |
| CN106940186B (en) * | 2017-02-16 | 2019-09-24 | 华中科技大学 | A kind of robot autonomous localization and navigation methods and systems |
| CN107796397B (en) * | 2017-09-14 | 2020-05-15 | 杭州迦智科技有限公司 | Robot binocular vision positioning method and device and storage medium |
| CN110276826A (en) * | 2019-05-23 | 2019-09-24 | 全球能源互联网研究院有限公司 | A kind of construction method and system of electric network operation environmental map |
-
2019
- 2019-05-23 CN CN201910438134.4A patent/CN110276826A/en active Pending
-
2020
- 2020-05-25 WO PCT/CN2020/092144 patent/WO2020233724A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106595659A (en) * | 2016-11-03 | 2017-04-26 | 南京航空航天大学 | Map merging method of unmanned aerial vehicle visual SLAM under city complex environment |
| US20180211399A1 (en) * | 2017-01-26 | 2018-07-26 | Samsung Electronics Co., Ltd. | Modeling method and apparatus using three-dimensional (3d) point cloud |
| CN107515891A (en) * | 2017-07-06 | 2017-12-26 | 杭州南江机器人股份有限公司 | A kind of robot cartography method, apparatus and storage medium |
| CN108090958A (en) * | 2017-12-06 | 2018-05-29 | 上海阅面网络科技有限公司 | A kind of robot synchronously positions and map constructing method and system |
Non-Patent Citations (5)
| Title |
|---|
| 张国良等: "融合直接法与特征法的快速双目SLAM算法", 《机器人》 * |
| 欧阳宁 等: "基于图切割的多频带融合图像拼接", 微电子学与计算机 * |
| 秦绪佳 等: "基于最佳缝合线的序列遥感图像拼接融合方法", 计算机科学 * |
| 赵矿军: "基于RGB-D摄像机的室内三维彩色点云地图构建", 《哈尔滨商业大学学报(自然科学版)》 * |
| 韩文超 等: "基于POS系统的无人机遥感图像融合方法的研究与实现", 遥感信息 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020233724A1 (en) * | 2019-05-23 | 2020-11-26 | 全球能源互联网研究院有限公司 | Visual slam-based grid operating environment map construction method and system |
| WO2021057743A1 (en) * | 2019-09-27 | 2021-04-01 | Oppo广东移动通信有限公司 | Map fusion method, apparatus, device and storage medium |
| CN110849380B (en) * | 2019-10-28 | 2022-04-22 | 北京影谱科技股份有限公司 | Map alignment method and system based on collaborative VSLAM |
| CN110849380A (en) * | 2019-10-28 | 2020-02-28 | 北京影谱科技股份有限公司 | Map alignment method and system based on collaborative VSLAM |
| CN110968429A (en) * | 2019-12-20 | 2020-04-07 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for loop detection in directed graph |
| CN110968429B (en) * | 2019-12-20 | 2022-11-11 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for loop detection in directed graph |
| CN111174799B (en) * | 2019-12-24 | 2023-02-17 | Oppo广东移动通信有限公司 | Map construction method and device, computer readable medium and terminal equipment |
| CN111174799A (en) * | 2019-12-24 | 2020-05-19 | Oppo广东移动通信有限公司 | Map construction method and device, computer readable medium and terminal equipment |
| CN112614171A (en) * | 2020-11-26 | 2021-04-06 | 厦门大学 | Air-ground integrated dynamic environment sensing system for cluster operation of engineering machinery |
| CN112614171B (en) * | 2020-11-26 | 2023-12-19 | 厦门大学 | Air-ground integrated dynamic environment sensing system for engineering machinery cluster operation |
| 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 |
| CN117315170A (en) * | 2023-09-12 | 2023-12-29 | 华大天元(北京)科技股份有限公司 | Construction method, device, equipment and medium of power grid operation environment map |
| CN117315170B (en) * | 2023-09-12 | 2024-04-05 | 华大天元(北京)科技股份有限公司 | Construction method, device, equipment and medium of power grid operation environment map |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020233724A1 (en) | 2020-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110276826A (en) | A kind of construction method and system of electric network operation environmental map | |
| CN112894832B (en) | Three-dimensional modeling method, three-dimensional modeling device, electronic equipment and storage medium | |
| Sattler et al. | Benchmarking 6dof outdoor visual localization in changing conditions | |
| CN103703758B (en) | mobile augmented reality system | |
| Zhang et al. | Instance segmentation of lidar point clouds | |
| CN111695622B (en) | Identification model training method, identification method and identification device for substation operation scene | |
| CN108717710A (en) | Localization method, apparatus and system under indoor environment | |
| CN107179086A (en) | A kind of drafting method based on laser radar, apparatus and system | |
| CN107967457A (en) | A kind of place identification for adapting to visual signature change and relative positioning method and system | |
| CN108537876A (en) | Three-dimensional rebuilding method, device, equipment based on depth camera and storage medium | |
| KR20200040665A (en) | Systems and methods for detecting a point of interest change using a convolutional neural network | |
| CN109801358A (en) | A kind of substation's three-dimensional investigation method scanning and put cloud visual fusion based on SLAM | |
| CN102708355A (en) | Information processing device, authoring method, and program | |
| CN107784671A (en) | A kind of method and system positioned immediately for vision with building figure | |
| US20190051029A1 (en) | Annotation Generation for an Image Network | |
| CN109084749B (en) | Method and device for semantic positioning through objects in environment | |
| CN108367436A (en) | Determination is moved for the voluntary camera of object space and range in three dimensions | |
| CN112015187B (en) | Semantic map construction method and system for intelligent mobile robot | |
| Adreani et al. | A photorealistic 3D city modeling framework for smart city digital twin | |
| Sun et al. | Geographic, geometrical and semantic reconstruction of urban scene from high resolution oblique aerial images. | |
| Ma et al. | Location and 3-D visual awareness-based dynamic texture updating for indoor 3-D model | |
| Wang et al. | Construction Photo Localization in 3D Reality Models for Vision-Based Automated Daily Project Monitoring | |
| Zhou et al. | Street-view imagery guided street furniture inventory from mobile laser scanning point clouds | |
| Scheuermann et al. | Mobile augmented reality based annotation system: A cyber-physical human system | |
| Huang et al. | Overview of LiDAR point cloud target detection methods based on deep learning |
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: 20190924 |