CN110097064A - One kind building drawing method and device - Google Patents
One kind building drawing method and device Download PDFInfo
- Publication number
- CN110097064A CN110097064A CN201910400106.3A CN201910400106A CN110097064A CN 110097064 A CN110097064 A CN 110097064A CN 201910400106 A CN201910400106 A CN 201910400106A CN 110097064 A CN110097064 A CN 110097064A
- Authority
- CN
- China
- Prior art keywords
- map
- warehouse compartment
- semantic feature
- feature point
- building
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000005457 optimization Methods 0.000 claims description 46
- 238000001514 detection method Methods 0.000 claims description 16
- 239000013598 vector Substances 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 9
- 238000012886 linear function Methods 0.000 claims description 8
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 230000006870 function Effects 0.000 description 20
- 230000008569 process Effects 0.000 description 16
- 230000000007 visual effect Effects 0.000 description 10
- 230000008859 change Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 102000006822 Agouti Signaling Protein Human genes 0.000 description 1
- 108010072151 Agouti Signaling Protein Proteins 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003716 rejuvenation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
Abstract
This application involves one kind to build drawing method and device.The drawing method of building includes: acquisition map, and the map includes semantic feature point；Based on preset positional relationship, at least partly location information of semantic feature point is updated in the map, and the map after being optimized.
Description
Technical field
The present invention relates to computer vision field more particularly to vision positioning and build figure field.
Background technique
Immediately positioning is a kind of with figure (Simultaneous Localization And Mapping, abbreviation SLAM) is built
Ambient enviroment map is established to reach the targets such as location navigation simultaneously by real-time tracking robot motion and in the process
Technology.
SLAM technical application is in multiple navigation and positioning field at present, but the map established by SLAM method is usually deposited
In the problem that precision is not high, positioning is wrong.Therefore it provides a kind of method for optimizing map is very necessary.
Summary of the invention
The one kind that is designed to provide of the application builds drawing method.This method can use the semanteme of object (for example, warehouse compartment)
Information (for example, the width information of warehouse compartment, warehouse compartment line position relationship, warehouse compartment corner location relationship) to map optimizes, and can
To build figure process using the map amendment after optimization.
On the one hand provide one kind builds drawing method to the application.The described method includes: obtaining map, the map includes semantic special
Sign point；Based on preset positional relationship, at least partly location information of semantic feature point is updated in the map, and optimized
Map afterwards.
In some embodiments, the semantic feature point in the map is the warehouse compartment angle point of warehouse compartment.The method is further
It include: to be determined by the location information of updated warehouse compartment angle point described excellent based on warehouse compartment depth direction and default warehouse compartment depth
The location information of other warehouse compartment angle points in map after change.
In some embodiments, the preset positional relationship include in the map mutual alignment difference in preset threshold
Semantic feature point in range corresponds to same semantic feature point.It is described to be based on preset positional relationship, it updates in the map extremely
The location information of small part semantic feature point, comprising: determine that semanteme of the mutual alignment difference in preset threshold range is special
Point is levied, semantic feature point of the mutual alignment difference in preset threshold range is merged.
In some embodiments, the preset positional relationship include in the map at least partly semantic feature point by same
One positional relationship function constraint.
In some embodiments, the same position relation function is linear function.It is described to be closed based on the same position
It is function, updates in the map at least partly location information of semantic feature point, comprising: the linear function is based on, to institute
It states in map at least partly semantic feature point and carries out straight line fitting.
In some embodiments, the preset positional relationship includes that at least partly semantic feature point is distributed in the map
On at least two straight lines and at least two straight line parallels or the intersection.It is described to be based on preset positional relationship, described in update
At least partly location information of semantic feature point in map, comprising: based on the parallel or intersection of at least two straight lines
Angle optimizes the direction vector of at least one straight line at least two straight lines.
In some embodiments, the preset positional relationship includes that at least partly semantic feature point is distributed in the map
Point-blank, and the distance of at least two semantic features point is pre-determined distance.It is described to be based on preset positional relationship, it updates
At least partly location information of semantic feature point in the map, comprising: be based on the pre-determined distance, update in the map extremely
The location information of small part semantic feature point.
In some embodiments, the map is established by following steps: obtaining overhead view image；It will be in the overhead view image
Semantic feature point matched with the semantic feature point in the map；The pose for building figure equipment is determined based on matching result；It is based on
The pose for building figure equipment updates the map.
In some embodiments, the method further includes: will in the map after the optimization it is at least partly semantic special
In Zheng Dian back projection to the overhead view image, the location information of the semantic feature point in the overhead view image is corrected.
In some embodiments, the method further includes: object is observed in the map after determining the optimization
Number；Judge whether the object has been observed preset times；The object in the overhead view image is determined based on judging result
Body detects whether correctly.
In some embodiments, the semantic feature point in the overhead view image and the semantic feature point in the map are library
The warehouse compartment angle point of position, warehouse compartment includes warehouse compartment line, and warehouse compartment angle point is located on warehouse compartment line.The method further includes: described in judgement
Whether the warehouse compartment angle point in overhead view image is located on the warehouse compartment line in the map after the optimization, and/or judges the top view
Whether the warehouse compartment angle point as in is associated with two warehouse compartments below in the map after the optimization；It bows based on described in judging result determination
Whether the warehouse compartment Corner Detection in visible image is correct.
In some embodiments, the method further includes same position relationships in the map after counting the optimization
The initial detecting state of object on function, and determine that the object on the same position relation function is final according to statistical result
Detecting state；The detecting state of the object in the overhead view image is corrected according to the final detecting state.
In some embodiments, the method further includes: in the map after counting the optimization object difference detect
The number of state, and the final detecting state of the object is determined according to statistical result；It is repaired according to the final detecting state
The detecting state of object in the just described overhead view image.
On the one hand provide one kind builds map device to the application, and described device includes at least one image acquisition equipment port, until
Few storage equipment, the storage equipment include one group of instruction；And it is communicated at least at least one described storage equipment
One processor.Wherein, when executing one group of instruction, at least one described processor is for executing the map device of building
Build drawing method.
Other feature will be set forth in part in the description in the application.By the elaboration, make the following drawings and
The content of embodiment narration becomes apparent for those of ordinary skills.Inventive point in the application can pass through
Practice is sufficiently illustrated using method described in detailed example discussed below, means and combinations thereof.
Detailed description of the invention
Exemplary embodiment disclosed in this application is described in detail in the following drawings.Wherein identical appended drawing reference is in attached drawing
Several views in indicate similar structure.Those of ordinary skill in the art will be understood that these embodiments be non-limiting,
Exemplary embodiment, the purpose that attached drawing is merely to illustrate and describes, it is no intended to it limits the scope of the present disclosure, other modes
Embodiment may also similarly complete the intention of the invention in the application.It should be appreciated that the drawings are not drawn to scale.Wherein:
Fig. 1 is shown builds drawing system according to shown in some embodiments of the present application；
Fig. 2 shows the flow charts that drawing method is built according to shown in some embodiments of the present application；
Fig. 3 shows the flow chart for optimizing the method for map according to shown in some embodiments of the present application；
Fig. 4 shows the schematic diagram in the parking lot according to shown in some embodiments of the present application.
Specific embodiment
Following description provides the specific application scene of the application and requirements, it is therefore an objective to those skilled in the art be enable to make
It makes and using the content in the application.To those skilled in the art, to the various partial modifications of the disclosed embodiments
Be it will be apparent that and without departing from the spirit and scope of the disclosure, the General Principle that will can be defined here
Applied to other embodiments and application.Therefore, the embodiment the present disclosure is not limited to shown in, but it is consistent most wide with claim
Range.
Term used herein is only used for the purpose of description specific example embodiments, rather than restrictive.For example, unless
Context is expressly stated otherwise, used herein above, singular " one ", "one" and "the" also may include plural form.
When used in this manual, the terms "include", "comprise" and/or " containing " are meant that associated integer, step, behaviour
Make, element and/or component exist, but be not excluded for other one or more features, integer, step, operation, element, component and/or
Other features, integer, step, operation, element, component can be added in the system/method.
In view of being described below, the operation of the related elements of these features of the disclosure and other features and structure and
The economy of combination and the manufacture of function and component may be significantly raising.With reference to attached drawing, all these formation disclosure
A part.It is to be expressly understood, however, that the purpose that attached drawing is merely to illustrate and describes, it is no intended to limit the disclosure
Range.
Process used in the disclosure shows the operation realized according to the system of some embodiments in the disclosure.It answers
This is expressly understood, and the operation of flow chart can be realized out of order.On the contrary, operation can be realized with reversal order or simultaneously.
Furthermore, it is possible to other one or more operations of flow chart addition.One or more operations can be removed from flow chart.
The one aspect of the application is related to one kind and builds drawing method.Specifically, this method includes building drawing method and optimization map
Method.It builds drawing method and can be common SLAM and build drawing method, the semantic information that also can use object builds figure.Optimize map
Method can be optimized according to the positional relationship to map of preset semantic feature point.Drawing method disclosed in the present application of building can be with
That applies the scene between multiple fields, such as parking lot, warehouse, factory or object with certain positional relationship builds figure.
Fig. 1 is shown builds drawing system according to shown in some embodiments of the present application.
It builds the available visual pattern of drawing system 100 and executes and build drawing method.The drawing method of building can refer to Fig. 2 and figure
3 description.As shown, building drawing system 100 may include image acquisition equipment 101 and builds map device 102.
Image acquisition equipment 101 is used to obtain the visual pattern of ambient enviroment.Image acquisition equipment 101 can be camera shooting
Head, such as monocular cam, binocular camera, three-dimensional camera, fisheye camera, reflected refraction camera, panoramic imagery camera.Figure
It is built on map device 102 as acquisition equipment 101 may be mounted at.
Building map device 102 is that can execute the exemplary computer device for building drawing method.It can as an example, building map device 102
Think vehicle.When image acquisition equipment 101 is installed on vehicle, image acquisition equipment 101 may be mounted at front part of vehicle, after
On at least one position in portion, left and right side.Correspondingly, the quantity of image acquisition equipment 101 can be one or more.
In some embodiments, building map device 102 may include communication port 150, in order to data communication.Build map device
102 can also include processor 120, and processor 120 is used for computer instructions in the form of one or more processors.
Computer instruction may include the routine for for example executing specific function described herein, program, object, component, data structure, mistake
Journey, module and function.For example, the available overhead view image of processor 120, and figure is built based on overhead view image.In another example processor
120 can update the location information of semantic feature point in map according to predeterminated position relationship, be optimized with this to map.
In some embodiments, processor 120 may include one or more hardware processors, such as microcontroller, micro-
Processor, Reduced Instruction Set Computer (RISC), specific integrated circuit (ASIC), specific to instruction-set processor of application
(ASIP), central processing unit (CPU), graphics processing unit (GPU), physical processing unit (PPU), micro controller unit, number
Word signal processor (DSP), field programmable gate array (FPGA), Advance RISC Machine (ARM), programmable logic device
(PLD), it is able to carry out any circuit or the processor etc. of one or more functions, or any combination thereof.
In some embodiments, building map device 102 may include internal communication bus 110, program storage and different form
Data store (for example, disk 170, read-only memory (ROM) 130 or random access memory (RAM) 140).Build map device
102 can also include being stored in ROM130, RAM140 and/or deposit the other kinds of non-transitory executed by processor 120
Program instruction in storage media.The present processes and/or process can be used as program instruction realization.Map device 102 is built also to wrap
I/O component 160 is included, supports the input/output between computer and other assemblies (for example, user interface elements).Build map device
102 can also receive programming and data by network communication.
Just to describe the problem, is built in map device 102 in this application and only describe a processor.However, should
Note that building map device 102 in the application can also include multiple processors, therefore, operation disclosed in this application and/or method
Step can be executed by a processor as described in the present disclosure, can also be combined by multiple processors and be executed.For example, if
The processor 120 that map device 102 is built in the application executes step A and step B, then it should be understood that step A and step B can also be with
It is jointly or separately executed by two different processors in information processing (for example, first processor executes step A, second processing
Device executes step B or the first and second processors execute step A and B jointly).
Fig. 2 shows the flow charts that drawing method is built according to shown in some embodiments of the present application.Process 200 can be implemented
For one group of instruction in the non-transitory storage medium built in map device 102.One group of instruction can be executed simultaneously by building map device 102
And it can correspondingly execute the step in process 200.
The operation of shown process 200 presented below, it is intended to be illustrative and be not restrictive.In some embodiments
In, process 200 can add one or more operation bidirectionals not described when realizing, and/or delete one or more herein
Described operation.In addition, shown in Fig. 2 and operations described below sequence limits not to this.
In 210, the available overhead view image of map device 102 is built.
Overhead view image can be directly acquired by building map device 102, can also be with indirect gain overhead view image.The indirect gain is bowed
Visible image comprising the following three steps:
First step builds the available at least visual pattern of map device 102.At least visual pattern can be with
It is that one or more image acquisition equipments 101 are obtained in synchronization, every visual pattern can correspond to same or different
Scenery, for example, in parking lot different regional areas scenery.
As an example, building 102 available four visual patterns of map device.Four visual patterns build figure by being mounted on
102 front of device, rear portion, left and right side four image acquisition equipments 101 synchronization obtain.
Second step, build map device 102 can by inverse perspective mapping by an at least visual pattern be converted to
A few sub- overhead view image.In conjunction with the example in first step, this four can be regarded by inverse perspective mapping by building map device 102
Feel that image is converted to four sub- overhead view images.Sub- overhead view image and visual pattern correspond.
Third step, the overhead view image can be spliced into for an at least sub- overhead view image by building map device 102.Knot
The example in first step and second step is closed, building map device 102 can use four image acquisition equipments 101 and build figure dress
The positional relationship between 102 is set, which is transformed under same image coordinate system, then again by same image
Sub- overhead view image under coordinate system is spliced into final overhead view image.It is to be understood that compared to sub- overhead view image, institute
The overhead view image for stating splicing has the bigger visual field.
In 220, building map device 102 can be by the semanteme in the semantic feature point and the map in the overhead view image
Feature Points Matching.
Semantic feature point is with semantic characteristic point.For example, figure can be built to parking lot by building map device 102, it is semantic special
Sign point can be warehouse compartment angle point or warehouse compartment entrance angle point.In another example figure, semantic feature point can be built to warehouse by building map device 102
It can be the anchor point of warehouse specific region.For another example figure can be built to graph region is built by building map device 102, semantic feature point can
Think the angle point of each building.Hereinafter, being described in more detail with building semantic feature point in figure to parking lot.
The warehouse compartment angle point is the anchor point of warehouse compartment.The anchor point of the warehouse compartment can be the vertex on warehouse compartment boundary line.
For example, the boundary line of non-font warehouse compartment A includes line segment 401, line segment 402, line segment 405 and line segment 408, anchor point packet with reference to Fig. 4
Include a little 411, point 412, point 415 and point 416.In the application, warehouse compartment boundary line is referred to as warehouse compartment line.
The warehouse compartment entrance angle point is one kind of warehouse compartment angle point, refers to the anchor point on the boundary line of warehouse compartment inlet.
For example, for warehouse compartment A as non-font parking stall, warehouse compartment entrance angle point is point 315 and point 316 with reference to Fig. 4.
Just to the purpose of explanation, building map device 102 can will be in the warehouse compartment entrance angle point and map in overhead view image
Warehouse compartment entrance corners Matching, and then determine the warehouse compartment entrance angle point being mutually matched in overhead view image and map.
In some embodiments, build map device 102 can according to two warehouse compartment entrance angle points in overhead view image and map it
Between distance determine the warehouse compartment entrance angle point that is mutually matched.When having one or more warehouse compartment angle points in map, to top view
When each of picture warehouse compartment corners Matching, the available one or more distances of map device 102 are built.At this point, building map device 102
Further judge whether the distance of aforementioned determination meets preset condition, is then in the warehouse compartment entrance angle point and map in overhead view image
Warehouse compartment entrance angle point be mutually matched.The preset condition refers to that distance is in preset threshold range, and the distance is aforementioned
It is minimum in one or more distances.
In 230, the pose for building figure equipment can be determined based on matching result by building map device 102.
The matching result be overhead view image in the semantic feature point being mutually matched in map.In conjunction in step 220
Example, the matching result be in overhead view image with the warehouse compartment entrance angle point that is mutually matched in map.Generally, the matching knot
Fruit is at least two pairs warehouse compartment entrance angle points being mutually matched, because at least two warehouse compartment entrance angle points can determine a warehouse compartment.
Building map device 102 can be based on the pose for building figure equipment described in the warehouse compartment angle point determination being mutually matched.
In some embodiments, the confidence level of each pair of warehouse compartment entrance angle point being mutually matched can be determined by building map device 102,
The pose for building map device is determined based on the confidence level.It confidence level and the warehouse compartment angle point that is mutually matched and builds at a distance from map device
And/or the number that the warehouse compartment angle point being mutually matched is observed in map by history is related.The warehouse compartment angle point being mutually matched is (as
Warehouse compartment angle point in figure) with build bigger at a distance from map device, confidence level is smaller；Warehouse compartment point (the library in such as map being mutually matched
Parallactic angle point) number that is observed by history is more, and confidence level is bigger.
In some embodiments, each pair of warehouse compartment angle point being mutually matched can be determined by formula (1) by building map device 102
Confidence level.Formula (1) is as follows:
Ck=Detkf(Obk)g(dk) formula (1)
Wherein, Ck is confidence level of the kth to the warehouse compartment angle point being mutually matched, and is kth to the library being mutually matched for Detk
Confidence level of the parallactic angle point in detection network (that is, deep neural network for detecting warehouse compartment angle point)；Obk is kth to mutual
The number that matched warehouse compartment angle point is observed by history；Dk be kth to the warehouse compartment angle point being mutually matched with build at a distance from figure equipment.
In some embodiments, the pose for building map device 102 can be determined by formula (2) by building map device 102.Formula
(2) as follows:
Wherein, TwvIt is variable to be optimized to build module and carriage transformation matrix of the figure equipment under global map coordinate system；TviFor
Image coordinate is to the transformation matrix for building figure device coordinate system；Pk_iSeat for kth to the warehouse compartment angle point being mutually matched on the image
Mark, PkCoordinate for kth to the warehouse compartment angle point being mutually matched under map.
In 240, the map can be updated based on the pose for building figure equipment by building map device 102.For example, building figure dress
Setting 102 can be calculated by trigonometric ratio in the determining new point map insertion map.
It should be noted that foregoing description builds drawing method just to the purpose of explanation, it is not intended to limit the application protection
Range.Drawing method is built in the application can be general SLAM and build figure, be also possible to build figure in conjunction with scenery semantic information.
Fig. 3 shows the flow chart for optimizing the method for map according to shown in some embodiments of the present application.Process 300 can
To be embodied as build in the non-transitory storage medium in map device 102 one group of instruction.Can be executed by building map device 102 by this group
It instructs and can correspondingly execute the step in process 300.
The operation of shown process 300 presented below, it is intended to be illustrative and be not restrictive.In some embodiments
In, process 300 can add one or more operation bidirectionals not described when realizing, and/or delete one or more herein
Described operation.In addition, being limited with the sequence of operations described below not to this shown in Fig. 3.
In 310, the available map of map device 102 is built.The map includes semantic feature point.The map can be
It is obtained by process 200.
In 320, building map device 102 can be updated at least partly semantic in the map based on preset positional relationship
The location information of characteristic point, and the map after being optimized.
The preset positional relationship refers to the positional relationship in map between semantic feature point, for example, at least partly language
Adopted characteristic point, which is located at, to be parallel to each other on two straight lines of (or vertical)；In another example when two semantic feature point positions are close pair
Answer same semantic feature point.The preset positional relationship can be according to the position between the semantic feature point for the practical scenery for building figure
The relationship of setting is set.
In some embodiments, the preset positional relationship include in map mutual alignment difference in preset threshold range
Interior semantic feature point corresponds to same semantic feature point.Building map device 102 can determine the mutual alignment difference in default threshold
The semantic feature point being worth in range, merges semantic feature point of the mutual alignment difference in preset threshold range.
In turn, the location information of semantic feature point in map can be updated by building map device 102, and the map after being optimized.
In some embodiments, the preset positional relationship include in map at least partly semantic feature point by same position
Set relation function constraint.The positional relationship function refers to the function of semantic constraints characteristic point position, such as linear function.Build figure
Device 102 can be based on the linear function, at least partly semantic feature point carries out straight line fitting in the map.
In some embodiments, the preset positional relationship include in map at least partly semantic feature point be distributed in
On few two straight lines and at least two straight lines are parallel to each other or intersect.Building map device 102 can be based at least two described
The angle that straight line is parallel to each other or intersects carries out the direction vector of at least one straight line at least two straight lines excellent
Change.
In some embodiments, the preset positional relationship include in map at least partly semantic feature point be distributed in one
On straight line and the distance of at least two semantic features point is pre-determined distance.In some embodiments, building map device 102 can
To be based on the pre-determined distance, at least partly location information of semantic feature point is updated in the map.
It is to be understood that building map device 102 can close according to one or more preset positions of foregoing description
It is that map optimizes.Below by taking the positional relationship between warehouse compartment angle point preset in the map of parking lot as an example, map device is built
The location information of warehouse compartment angle point in 102 to maps is updated, and the map after being optimized.
First, for parking lot map, preset positional relationship include in map mutual alignment difference in preset threshold model
Warehouse compartment angle point in enclosing corresponds to same warehouse compartment angle point.When warehouse compartment corner location differences more than two in map are smaller, build
Map device 102 can merge more than two warehouse compartment angle points, such as weight merges.
In some embodiments, weight merging can be carried out to warehouse compartment angle point according to formula (3) by building map device 102.Formula
(3) as follows:
Wherein, PmergeFor the warehouse compartment angular coordinate after merging, PiFor i-th of warehouse compartment angular coordinate, Ci_normFor i-th of library
The weight of parallactic angle point, after being normalized for the warehouse compartment angle point confidence level relative to all (that is, I) warehouse compartment angle point confidence level to be combined
Value.
Second, for parking lot map, the preset positional relationship include in map at least partly warehouse compartment angle point by same
The constraint of one linear function, i.e., at least partly warehouse compartment angle point is distributed on same straight line.Therefore, building map device 102 can be over the ground
At least partly warehouse compartment angle point in figure carries out straight line fitting.
As an example, warehouse compartment angle point 411,412,413 and 414 is located in a straight line with reference to Fig. 4, warehouse compartment angle point 415,
416, it 417 and 418 is located in a straight line, warehouse compartment angle point 411 and 415 is located in a straight line, warehouse compartment angle point 412 and 416
In on straight line, warehouse compartment angle point 415 and 417 is located in a straight line, and warehouse compartment angle point 414 and 418 is located in a straight line.It builds
Map device 102 can carry out straight line fitting to warehouse compartment angle point 411 to 418 according to above-mentioned positional relationship.
In some embodiments, straight line fitting can be carried out to warehouse compartment angle point according to formula (4) by building map device 102.Formula
(4) as follows:
Wherein,And diThe direction vector of respectively i-th straight line and biasing, PijFor j-th of warehouse compartment angle on i-th straight line
Point, CijFor the confidence level of j-th of warehouse compartment angle point on i-th straight line.
Third, for parking lot map, the preset positional relationship includes that the warehouse compartment angle point in map is distributed at least
On two straight lines and it is described two in straight line parallel or intersection.When two straight line intersections, angle can for 30 °, 60 °,
90 ° of (that is, two straight lines are vertical), 120 ° or any other angles.At this point, the parallel pass can be based on by building map device 102
The direction vector of system or the straight line (that is, warehouse compartment line) in specific angle to map optimizes.
Wherein, for non-font parking lot, the preset positional relationship include the warehouse compartment angle point in map be distributed in
On few two straight lines and two straight lines are parallel to each other or vertically.Therefore, building map device 102 can be parallel or vertical based on this
The direction vector of straight line in relationship to map optimizes.
As an example, the warehouse compartment angle point in map is distributed on warehouse compartment line 401 to 410 with reference to Fig. 4, warehouse compartment line 401 to
It is parallel to each other between 404, forms the first warehouse compartment line set；It is parallel to each other between warehouse compartment line 405 to 410, forms the second warehouse compartment line
Set.Any warehouse compartment line in any warehouse compartment line and the second warehouse compartment line set in the first warehouse compartment line set mutually hangs down
Directly.Map device 102 is built to be optimized according to the direction vector with the warehouse compartment line in above-mentioned parallel and/or vertical relation to map.
In some embodiments, building map device 102 can be according in formula (5), formula (6) and formula (7) to map
The direction vector of warehouse compartment line optimizes.Formula (5) is as follows to formula (7):
Wherein,ForDesired unit direction vector；For withThere may be all warehouse compartment lines of parallel relation
Unit direction vector；For withThere may be the unit direction vectors of all warehouse compartment lines of vertical relation；ForUnit
Orthogonal vectors,WithIt can be obtained by the method clustered；Cj_lineWith Ck_lineRespectivelyWithWeight, and be present in this
The confidence level of all warehouse compartment angle points on warehouse compartment line is related.BecauseFor withThere may be vertical relations, soIt is right's
Contribution is by orthogonal to thatIt generates.
4th, for parking lot map, the preset positional relationship include in map warehouse compartment angle point be distributed at least one
On straight line (that is, warehouse compartment line) and the distance between described at least two warehouse compartments angle point (that is, width or depth of warehouse compartment) is pre-
If distance.Therefore, the warehouse compartment angle point in the map can be carried out based on preset warehouse compartment width or depth by building map device 102
Optimization.The preset warehouse compartment width or depth can be according to national standard, professional standard, the experience of life or actual library bit wides
Degree or depth are determined.
Specifically, building map device 102 can be according to two warehouse compartment angle point in preset warehouse compartment width or depth adjustment map
The distance between, and then update the location information of two warehouse compartment angle points.
In some embodiments, the overall situation can be carried out in conjunction with above-mentioned four kinds of predeterminated positions relationship to map by building map device 102
Optimization.As an example, global optimization can be carried out according to formula (8) to map by building map device 102.
Wherein,For the set of all warehouse compartment line direction vectors；dopFor the set of all library bit line bias；PopIt is all
The set of warehouse compartment angle point；Twv_opFor the set for building all pose key frames of figure equipment.
Above four set are variable to be optimized.In some embodiments, building map device 102 can be according to formula (9)
Aforementioned four set is optimized to (14).
Formula (9) to (11) can guarantee the warehouse compartment line after optimization, warehouse compartment angle point and pose and the optimization of building figure equipment
Preceding numerical value is close, will not generate mutation.Formula (12) is the wide constraint of warehouse compartment, Pr1_opAnd Pr2_opIt is belonging respectively to same
Two warehouse compartment angle points (for example, warehouse compartment entrance angle point) of warehouse compartment, Lot_W are default warehouse compartment width information.Formula (13) is to build figure
The projection error for the warehouse compartment angle point that equipment pose is observed with it constrains, the pose and map office for building figure equipment after guaranteeing optimization
Parallactic angle point, which meets, sees projection relation, and formula (14) guarantees the warehouse compartment angle point P belonged on i-th warehouse compartment lineij_opStill position after optimization
In on warehouse compartment line.
When carrying out map optimization more than it should be noted that by taking the map of parking lot as an example, building map device 102 can be to whole
Warehouse compartment angle point operated, can also the warehouse compartment angle point to part operate.It can be only to complete for example, building map device 102
The warehouse compartment inlet angle point in portion is operated.Build figure when building the completion of map device 102, for each warehouse compartment, on map there is only
Two warehouse compartment entrance angle points, rather than complete four warehouse compartment angle points.At this point, warehouse compartment depth side can be based on by building map device 102
To with default warehouse compartment depth, other warehouse compartments in the map after the optimization are determined by the location information of updated warehouse compartment angle point
The location information of angle point.
It should be noted that above description is using non-font warehouse compartment shown in Fig. 4 as example.Certainly, warehouse compartment may be
Other warehouse compartments other than non-font parking stall.According to the variation of warehouse compartment type, the actual conditions of warehouse compartment can be combined to above-mentioned same
It Shi Dingwei and builds drawing method and makes some changes.It is to be understood that creative labor is not paid in above-mentioned change,
Above-mentioned change still this application claims within the scope of.
For example, vertex is not present on warehouse compartment boundary line when the boundary line of warehouse compartment is round and smooth curve (for example, round).
Building map device 102 can determine that the point on warehouse compartment boundary line on specific direction is anchor point, and then determine warehouse compartment angle point.Meanwhile
Warehouse compartment angle point can be fitted according to circular function by building map device 102.
In another example vertical relationship is not present between the warehouse compartment line of intersection when warehouse compartment is oblique line parking stall.Build map device
102 can optimize according to the direction vector of the warehouse compartment line in the corner dimension to map between the warehouse compartment line of intersection.
It should be noted that the above-mentioned optimization to parking lot map is only example.Herein disclosed optimization map
Method can be adapted for various maps.It can be according to the positional relationship pair in warehouse between each region for example, building map device 102
Warehouse map optimizes.It can be according to the positional relationship between each building to built-up area in another example building map device 102
Domain map optimizes.For another example build map device 102 can according to the positional relationship between dining table in dining room to dining room map into
Row optimization.It is understood that for the position between each object in a region, there are the map of specific relationship or objects
Body itself has the map of special characteristic (for example, round, rectangle), herein disclosed optimization method can be used to the ground
Figure optimizes.
Meanwhile the map after optimization can correct the detection of overhead view image and classification results in process 200.Below still with
For the map of parking lot, builds map device 102 and can correct parking lot and build in figure the detection of warehouse compartment and classification results in overhead view image.
In some embodiments, building map device 102 can be based on detecting in the map rejuvenation overhead view image after optimization
The location information of semantic feature point.It can be anti-by at least partly semantic feature point in the map after optimization for example, building map device 102
It projects on corresponding overhead view image, corrects the location information of the semantic feature point in the overhead view image.That is, building map device
102 can correct in the overhead view image by the warehouse compartment angle point back projection in the map after optimization into corresponding overhead view image
Warehouse compartment angle point location information.
In some embodiments, the inspection of object in overhead view image can be determined based on the map after optimization by building map device 102
It whether correct surveys.For example, building the number that map device 102 can be observed with object in the map after statistic op- timization；Judge the object
Whether body has been observed preset times, if the object has been observed preset times, it is determined that the object detection is correct, if not having
Have, it is determined that the object detection mistake.Quilt in map after building map device 102 in some embodiments and can determining the optimization
Observe the number of warehouse compartment；It is observed whether warehouse compartment reaches preset times described in judgement, if reaching preset times, the quilt
Observe that warehouse compartment detection is correct, it is otherwise described to be observed warehouse compartment mistake.
This is because the warehouse compartment accuracy rate for being observed preset times in map after optimization is relatively high, wherein described
Preset times are n times, and N is the integer greater than 1.When judging that the warehouse compartment is mutually matched with the warehouse compartment in corresponding overhead view image,
Building map device 102 can determine that the warehouse compartment detection in the overhead view image is correct.Otherwise, build map device 102 can determine it is described
Warehouse compartment in overhead view image detects mistake.
In some embodiments, warehouse compartment angle point in overhead view image can be determined based on the map after optimization by building map device 102
Detect whether it is correct.For example, building after whether the warehouse compartment angle point that map device 102 may determine that in overhead view image be located at the optimization
Map in warehouse compartment line on, and/or judge whether the warehouse compartment angle point in the overhead view image is associated with the map after the optimization
In two warehouse compartments below；Determine whether the warehouse compartment Corner Detection in the overhead view image is correct based on judging result.This be because
For for general warehouse compartment, all warehouse compartment angle points are respectively positioned on warehouse compartment line, and each warehouse compartment angle point can at most be located at
On two warehouse compartments.On the warehouse compartment line of map after the warehouse compartment angle point in overhead view image is located at optimization, and/or when in overhead view image
Warehouse compartment angle point be associated with two warehouse compartments below, building map device 102 may determine that the warehouse compartment Corner Detection in overhead view image is correct.
Otherwise, building map device 102 may determine that warehouse compartment Corner Detection mistake in overhead view image.
In some embodiments, warehouse compartment described in overhead view image can be determined based on the map after optimization by building map device 102
Whether the detecting state of angle point is correct.In some embodiments, the different detection shapes that map device 102 counts the warehouse compartment angle point are built
The number of state.It builds map device 102 and determines that the more detecting state of the detecting state number of the warehouse compartment angle point is current warehouse compartment angle
The detecting state of point.In some embodiments, the detecting state of the warehouse compartment angle point includes the warehouse compartment that the warehouse compartment angle point determines
Whether depth, the warehouse compartment that the warehouse compartment angle point determines are occupied.In the detection process, to the detecting state of the warehouse compartment angle point
It is counted, counts biggish detecting state and be considered the warehouse compartment detecting state that the warehouse compartment angle point determines, if there is mistake
Classification, then corrected.
For example, build map device 102 can be determined based on the map after optimization warehouse compartment in overhead view image depth direction whether
Correctly.The number when warehouse compartment is in different depth direction can be counted by building map device 102, such as towards the number and toward the north in south
Number, then the biggish depth direction of determined number (for example, towards south) be the warehouse compartment depth direction.
In some embodiments, building map device 102 can be determined in overhead view image based on the map after optimization to object
Whether the classification of detecting state is correct.The classification of the detecting state of the object may include that the depth direction of object is (also known as
Direction, such as the direction of warehouse compartment, i.e. direction where warehouse compartment entrance), whether be occupied.It can as an example, building map device 102
It is whether correct to the classification in Object Depth direction in overhead view image to be determined based on the map after optimization.Specifically, map device is built
102 can be initial with the object on same position relation function in the map after statistic op- timization depth direction, and according to statistics tie
Fruit determines the final depth direction of the object on the same position relation function；Institute is corrected according to the final depth direction
State the depth direction of the object in overhead view image.It can be with same position relationship in the map after statistic op- timization that is, building map device 102
The initial depth direction of warehouse compartment on function, and determine that the warehouse compartment on the same position relation function is final according to statistical result
Depth direction；The depth direction of the warehouse compartment in corresponding overhead view image is corrected according to the final depth direction.
The positional relationship function refers to the function of constrained body position.For warehouse compartment, the positional relationship function
It can be linear function.That is, building the depth that map device 102 can be initial with the warehouse compartment on same straight line in the map after statistic op- timization
Direction.
Need it is once more emphasized that, the implementation disclosed in this application for building each step in drawing method is not by the limit of sequence
System.For example, being closed when building map device 102 based on a variety of preset positional relationships optimization maps based on different preset positions
The operation of system's optimization map can be implemented simultaneously or not implement simultaneously, and sequencing is unrestricted.In another example when building map device
102 detections based on the map amendment overhead view image after optimization and when classification results, building the modified operation of map device 102 can be same
When implement or do not implement simultaneously, sequencing is unrestricted.
In conclusion after reading this detailed disclosures, it will be understood by those skilled in the art that aforementioned detailed disclosure
Content can be only presented in an illustrative manner, and can not be restrictive.Although not explicitly described or shown herein, this field skill
Art personnel are understood that improve and modify it is intended to include the various reasonable changes to embodiment.These change, improve and
It modifies and is intended to be proposed by the disclosure, and in the spirit and scope of the exemplary embodiment of the disclosure.
In addition, certain terms in the application have been used for describing implementation of the disclosure example.For example, " one embodiment ",
" embodiment " and/or " some embodiments " means to combine the special characteristic of embodiment description, and structure or characteristic may include
In at least one embodiment of the disclosure.Therefore, it can emphasize and it is to be understood that right in the various pieces of this specification
Two or more references of " embodiment " or " one embodiment " or " alternate embodiment " are not necessarily all referring to identical implementation
Example.In addition, special characteristic, structure or characteristic can be appropriately combined in one or more other embodiments of the present disclosure.
It should be appreciated that in the foregoing description of embodiment of the disclosure, in order to help to understand a feature, originally for simplification
Disclosed purpose, the application sometimes combine various features in single embodiment, attached drawing or its description.Alternatively, the application is again
Be by various characteristic dispersions in multiple the embodiment of the present invention.However, this be not to say that the combination of these features be it is necessary,
Those skilled in the art are entirely possible to come out a portion feature extraction as individual when reading the application
Embodiment understands.That is, embodiment in the application it can be appreciated that multiple secondary embodiments integration.And it is each
The content of secondary embodiment is also to set up when being less than individually all features of aforementioned open embodiment.
In some embodiments, the quantity or property for certain embodiments of the application to be described and claimed as are expressed
The number of matter is interpreted as in some cases through term " about ", " approximation " or " substantially " modification.For example, unless otherwise saying
Bright, otherwise " about ", " approximation " or " substantially " can indicate ± 20% variation of the value of its description.Therefore, in some embodiments
In, the numerical parameter listed in written description and the appended claims is approximation, can be tried according to specific embodiment
Scheme the required property obtained and changes.In some embodiments, numerical parameter should be according to the quantity of the effective digital of report simultaneously
It is explained by the common rounding-off technology of application.Although illustrating that some embodiments of the application list broad range of numerical value
Range and parameter are approximations, but numerical value reported as precisely as possible is all listed in specific embodiment.
Herein cited each patent, patent application, the publication and other materials of patent application, such as article, books,
Specification, publication, file, article etc. can be incorporated herein by reference.Full content for all purposes, in addition to
Its relevant any prosecution file history, may or conflicting any identical or any possibility inconsistent with this document
On any identical prosecution file history of the restrictive influence of the widest range of claim.Now or later and this document
It is associated.For example, if in description, definition and/or the use of term associated with any included material and this
The relevant term of document, description, definition and/or between there are it is any inconsistent or conflict when, be using the term in this document
It is quasi-.
Finally, it is to be understood that the embodiment of application disclosed herein is the explanation to the principle of the embodiment of the application.
Other modified embodiments are also within the scope of application.Therefore, herein disclosed embodiment it is merely exemplary rather than
Limitation.Those skilled in the art can take alternative configuration according to the embodiment in the application to realize the invention in the application.
Therefore, embodiments herein is not limited to which embodiment accurately described in application.
Claims (14)
1. it is a kind of operation on an electronic device build drawing method, which is characterized in that the described method includes:
Map is obtained, the map includes semantic feature point；
Based on preset positional relationship, at least partly location information of semantic feature point is updated in the map, and optimized
Map afterwards.
2. building drawing method as described in claim 1, which is characterized in that the semantic feature point in the map is the warehouse compartment of warehouse compartment
Angle point, the method further includes:
Based on warehouse compartment depth direction and default warehouse compartment depth, the optimization is determined by the location information of updated warehouse compartment angle point
The location information of other warehouse compartment angle points in map afterwards.
3. building drawing method as described in claim 1, which is characterized in that
The preset positional relationship includes semantic feature point of the mutual alignment difference in preset threshold range in the map
Corresponding same semantic feature point；
It is described to be based on preset positional relationship, update in the map at least partly location information of semantic feature point, comprising:
Determine semantic feature point of the mutual alignment difference in preset threshold range,
Semantic feature point of the mutual alignment difference in preset threshold range is merged.
4. building drawing method as described in claim 1, which is characterized in that the preset positional relationship include in the map extremely
Small part semantic feature point is constrained by same position relation function.
5. building drawing method as claimed in claim 4, which is characterized in that the same position relation function is linear function；
It is described to be based on the same position relation function, at least partly location information of semantic feature point is updated in the map,
Include:
Based on the linear function, at least partly semantic feature point carries out straight line fitting in the map.
6. building drawing method as described in claim 1, which is characterized in that
The preset positional relationship include in the map at least partly semantic feature point be distributed at least two straight lines and
At least two straight lines are parallel to each other or intersect；
It is described to be based on preset positional relationship, update in the map at least partly location information of semantic feature point, comprising:
It is straight at least one at least two straight lines based on the angle that at least two straight lines are parallel to each other or intersect
The direction vector of line optimizes.
7. building drawing method as described in claim 1, which is characterized in that
The preset positional relationship includes that at least partly the distribution of semantic feature point is point-blank and at least in the map
The distance of two semantic feature points is pre-determined distance；
It is described to be based on preset positional relationship, update in the map at least partly location information of semantic feature point, comprising:
Based on the pre-determined distance, at least partly location information of semantic feature point is updated in the map.
8. building drawing method as described in claim 1, which is characterized in that the map is established by following steps:
Obtain overhead view image；
Semantic feature point in the overhead view image is matched with the semantic feature point in the map；
The pose for building figure equipment is determined based on matching result；
The map is updated based on the pose for building figure equipment.
9. building drawing method as claimed in claim 8, which is characterized in that the method further includes:
At least partly in semantic feature point back projection to the overhead view image, the vertical view will be corrected in map after the optimization
The location information of semantic feature point in image.
10. building drawing method as claimed in claim 8, which is characterized in that the method further includes:
The number that object is observed in map after determining the optimization；
Judge whether the object has been observed preset times；
Determine whether the object detection in the overhead view image is correct based on judging result.
11. building drawing method as claimed in claim 8, which is characterized in that
The semantic feature point in semantic feature point and the map in the overhead view image is the warehouse compartment angle point of warehouse compartment, warehouse compartment packet
Warehouse compartment line is included, warehouse compartment angle point is located on warehouse compartment line；
The method further includes:
Judge whether the warehouse compartment angle point in the overhead view image is located on the warehouse compartment line in the map after the optimization, and/or sentences
Whether the warehouse compartment angle point to break in the overhead view image is associated with two warehouse compartments below in the map after the optimization；
Determine whether the warehouse compartment Corner Detection in the overhead view image is correct based on judging result.
12. building drawing method as claimed in claim 8, which is characterized in that the method further includes:
The initial detecting state of object in map after counting the optimization on same position relation function, and tied according to statistics
Fruit determines the final detecting state of the object on the same position relation function；
The detecting state of the object in the overhead view image is corrected according to the final detecting state.
13. building drawing method as claimed in claim 8, which is characterized in that the method further includes:
The number of object difference detecting state in map after counting the optimization, and the object is determined most according to statistical result
Whole detecting state；
The detecting state of the object in the overhead view image is corrected according to the final detecting state.
14. one kind builds map device, comprising:
At least one storage equipment, the storage equipment include one group of instruction；And
At least one processor communicated at least one described storage equipment, wherein described when executing one group of instruction
At least one processor makes the map device perform claim of building require any method in 1-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910400106.3A CN110097064B (en) | 2019-05-14 | 2019-05-14 | Picture construction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910400106.3A CN110097064B (en) | 2019-05-14 | 2019-05-14 | Picture construction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110097064A true CN110097064A (en) | 2019-08-06 |
| CN110097064B CN110097064B (en) | 2021-05-11 |
Family
ID=67448051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910400106.3A Active CN110097064B (en) | 2019-05-14 | 2019-05-14 | Picture construction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110097064B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110823225A (en) * | 2019-10-29 | 2020-02-21 | 北京影谱科技股份有限公司 | Positioning method and device under indoor dynamic situation |
| CN110956846A (en) * | 2019-12-11 | 2020-04-03 | 济宁市众帮来袭信息科技有限公司 | Parking service method, device and system and storage medium |
| CN111780771A (en) * | 2020-05-12 | 2020-10-16 | 驭势科技（北京）有限公司 | Positioning method, positioning device, electronic equipment and computer readable storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070293985A1 (en) * | 2006-06-20 | 2007-12-20 | Samsung Electronics Co., Ltd. | Method, apparatus, and medium for building grid map in mobile robot and method, apparatus, and medium for cell decomposition that uses grid map |
| CN102663357A (en) * | 2012-03-28 | 2012-09-12 | 北京工业大学 | Color characteristic-based detection algorithm for stall at parking lot |
| CN102963355A (en) * | 2012-11-01 | 2013-03-13 | 同济大学 | Intelligent auxiliary parking method and implementation system thereof |
| CN103577484A (en) * | 2012-08-07 | 2014-02-12 | 上海市测绘院 | Spatial orientation method of any deformation map |
| CN104417615A (en) * | 2013-09-06 | 2015-03-18 | 现代摩比斯株式会社 | Method for controlling steering wheel and system therefor |
| CN105469405A (en) * | 2015-11-26 | 2016-04-06 | 清华大学 | Visual ranging-based simultaneous localization and map construction method |
| CN105674993A (en) * | 2016-01-15 | 2016-06-15 | 武汉光庭科技有限公司 | Binocular camera-based high-precision visual sense positioning map generation system and method |
| CN106772389A (en) * | 2016-11-07 | 2017-05-31 | 纵目科技（上海）股份有限公司 | A kind of warehouse compartment detection method, system and mobile device |
| CN106910217A (en) * | 2017-03-17 | 2017-06-30 | 驭势科技（北京）有限公司 | Vision map method for building up, computing device, computer-readable storage medium and intelligent vehicle |
| CN107180215A (en) * | 2017-05-31 | 2017-09-19 | 同济大学 | Figure and high-precision locating method are built in parking lot based on warehouse compartment and Quick Response Code automatically |
| CN108318043A (en) * | 2017-12-29 | 2018-07-24 | 百度在线网络技术（北京）有限公司 | Method, apparatus for updating electronic map and computer readable storage medium |
-
2019
- 2019-05-14 CN CN201910400106.3A patent/CN110097064B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070293985A1 (en) * | 2006-06-20 | 2007-12-20 | Samsung Electronics Co., Ltd. | Method, apparatus, and medium for building grid map in mobile robot and method, apparatus, and medium for cell decomposition that uses grid map |
| CN102663357A (en) * | 2012-03-28 | 2012-09-12 | 北京工业大学 | Color characteristic-based detection algorithm for stall at parking lot |
| CN103577484A (en) * | 2012-08-07 | 2014-02-12 | 上海市测绘院 | Spatial orientation method of any deformation map |
| CN102963355A (en) * | 2012-11-01 | 2013-03-13 | 同济大学 | Intelligent auxiliary parking method and implementation system thereof |
| CN104417615A (en) * | 2013-09-06 | 2015-03-18 | 现代摩比斯株式会社 | Method for controlling steering wheel and system therefor |
| CN105469405A (en) * | 2015-11-26 | 2016-04-06 | 清华大学 | Visual ranging-based simultaneous localization and map construction method |
| CN105674993A (en) * | 2016-01-15 | 2016-06-15 | 武汉光庭科技有限公司 | Binocular camera-based high-precision visual sense positioning map generation system and method |
| CN106772389A (en) * | 2016-11-07 | 2017-05-31 | 纵目科技（上海）股份有限公司 | A kind of warehouse compartment detection method, system and mobile device |
| CN106910217A (en) * | 2017-03-17 | 2017-06-30 | 驭势科技（北京）有限公司 | Vision map method for building up, computing device, computer-readable storage medium and intelligent vehicle |
| CN107180215A (en) * | 2017-05-31 | 2017-09-19 | 同济大学 | Figure and high-precision locating method are built in parking lot based on warehouse compartment and Quick Response Code automatically |
| CN108318043A (en) * | 2017-12-29 | 2018-07-24 | 百度在线网络技术（北京）有限公司 | Method, apparatus for updating electronic map and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| BJOERN SONDERMANN，AND ETC: "Simultaneous Localization and Mapping Based on Semantic World Modelling", 《2014 EUROPEAN MODELLING SYMPOSIUM》 * |
| 于金山等: "基于云的语义库设计及机器人语义地图构建", 《机器人》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110823225A (en) * | 2019-10-29 | 2020-02-21 | 北京影谱科技股份有限公司 | Positioning method and device under indoor dynamic situation |
| CN110956846A (en) * | 2019-12-11 | 2020-04-03 | 济宁市众帮来袭信息科技有限公司 | Parking service method, device and system and storage medium |
| CN111780771A (en) * | 2020-05-12 | 2020-10-16 | 驭势科技（北京）有限公司 | Positioning method, positioning device, electronic equipment and computer readable storage medium |
| CN111780771B (en) * | 2020-05-12 | 2022-09-23 | 驭势科技（北京）有限公司 | Positioning method, positioning device, electronic equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110097064B (en) | 2021-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9805505B2 (en) | Estimation of object properties in 3D world | |
| CN110097064A (en) | One kind building drawing method and device | |
| CN109558879A (en) | A kind of vision SLAM method and apparatus based on dotted line feature | |
| CN109325998A (en) | A kind of indoor 3D modeling method, system and relevant apparatus based on point cloud data | |
| Song et al. | DynaVINS: a visual-inertial SLAM for dynamic environments | |
| CN108765489A (en) | A kind of pose computational methods, system, medium and equipment based on combination target | |
| JP2014238883A (en) | Method and device for drawing virtual object in real environment | |
| US12014459B2 (en) | Image processing device, image processing method, and program for forming an accurate three-dimensional map | |
| CN111581313B (en) | Semantic SLAM robustness improvement method based on instance segmentation | |
| CN103942535B (en) | Multi-target tracking method and device | |
| CN110119679A (en) | Object dimensional information estimating method and device, computer equipment, storage medium | |
| CN110260866A (en) | A kind of robot localization and barrier-avoiding method of view-based access control model sensor | |
| CN110132278A (en) | A kind of instant method and device for positioning and building figure | |
| Zhang et al. | A vertical and floor line-based monocular SLAM system for corridor environments | |
| Gaudillière et al. | Camera relocalization with ellipsoidal abstraction of objects | |
| CN113160401B (en) | Object-oriented visual SLAM lightweight semantic map creation method | |
| CN113313824B (en) | Three-dimensional semantic map construction method | |
| Zhang et al. | Monocular vision simultaneous localization and mapping using SURF | |
| CN109584347A (en) | A kind of augmented reality mutual occlusion processing method based on active apparent model | |
| CN115511970B (en) | Visual positioning method for autonomous parking | |
| CN103136513B (en) | A kind of ASM man face characteristic point positioning method of improvement | |
| Mostofi et al. | Indoor localization and mapping using camera and inertial measurement unit (IMU) | |
| CN110232711B (en) | Binocular vision real-time perception positioning method, system and device for marine product grabbing | |
| Murray | Patchlets: a method of interpreting correlation stereo 3D data | |
| CN113570713A (en) | Semantic map construction method and device for dynamic environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |