CN107845114A - Construction method, device and the electronic equipment of map - Google Patents
Construction method, device and the electronic equipment of map Download PDFInfo
- Publication number
- CN107845114A CN107845114A CN201711104367.8A CN201711104367A CN107845114A CN 107845114 A CN107845114 A CN 107845114A CN 201711104367 A CN201711104367 A CN 201711104367A CN 107845114 A CN107845114 A CN 107845114A
- Authority
- CN
- China
- Prior art keywords
- pose
- collecting device
- depth image
- map
- image
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 32
- 238000005457 optimization Methods 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000033001 locomotion Effects 0.000 description 5
- 238000005070 sampling Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 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
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Geometry (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
Abstract
The application provides a kind of construction method of map, device and electronic equipment, and an embodiment of methods described includes：The pose worked as former frame depth image and determine presently described collecting device gathered according to collecting device；Pose described in the historical depth image optimization gathered according to the collecting device, obtains object pose；Map is built according to the object pose.The pose for the historical depth image optimization present collection device that the embodiment can gather according to collecting device, obtain the higher object pose of precision, and based on object pose structure map, therefore, the error built up due to the passage of time can be reduced, so as to improve the precision of map structuring.
Description
Technical field
The application is related to technical field of navigation and positioning, the more particularly to a kind of construction method of map, device and electronic equipment.
Background technology
For at present, with being widely popularized for the technologies such as robot, unmanned and unmanned plane, in navigator fix technology
Vision positioning and view-based access control model positioning map structuring technology become more and more important.In the related art, typically pass through
When the mode of vision carries out map structuring, caused error can be built up over time so that map structuring
Error is increasing, and error is difficult to eliminate, so as to reduce the precision of map structuring.
The content of the invention
One of in order to solve the above-mentioned technical problem, the application provides a kind of construction method of map, device and electronic equipment.
According to the first aspect of the embodiment of the present application, there is provided a kind of construction method of map, including：
The pose worked as former frame depth image and determine presently described collecting device gathered according to collecting device；
Pose described in the historical depth image optimization gathered according to the collecting device, obtains object pose；
Map is built according to the object pose.
Optionally, the position worked as former frame depth image and determine presently described collecting device gathered according to collecting device
Appearance, including：
When predeterminable event does not occur, based on the current exercise data of the collecting device and described work as former frame depth map
Pose as determining presently described collecting device.
Optionally, the position worked as former frame depth image and determine presently described collecting device gathered according to collecting device
Appearance, in addition to：
When predeterminable event occurs, historical depth image based on collecting device collection and described work as former frame depth
Image determines the pose of presently described collecting device.
Optionally, pose described in the historical depth image optimization gathered according to the collecting device, including：
Part or all keys image are obtained in the historical depth image as target image；
The pose is optimized according to the target image.
Optionally, part or all keys image as target image, wrap in the acquisition historical depth image
Include：
The target image is obtained from the target data prestored；Wherein, described in the target data there is record
Key frame images in historical depth image.
Optionally, storage obtains the target data in the following way：
First key frame images are determined from the depth image of collecting device collection；
By the first key frame images stored record into the target data；
It is determined that after the first key frame images, each frame depth image gathered successively to the collecting device is carried out
Detection, to determine key frame images successively；Wherein, for any one frame depth image gathered successively, if the detection
Result indicate that the parallax of the frame depth image and former frame key frame images is more than default parallax, and with exceeding present count
The matching road sign point of amount, it is determined that the frame depth image is key frame images；
By the every frame key frame images determined successively successively stored record into the target data.
Optionally, it is described that the pose is optimized according to the target image, including：
When predeterminable event does not occur, institute is optimized according to the current exercise data of the target image and the collecting device
Rheme appearance.
Optionally, it is described that the pose is optimized according to the target image, in addition to：
When predeterminable event occurs, the pose is optimized according to the target image and the former frame depth image of working as.
According to the second aspect of the embodiment of the present application, there is provided a kind of construction device of map, including：
Determining module, for according to collecting device gather when former frame depth image determines presently described collecting device
Pose；
Optimization module, for pose described in the historical depth image optimization that is gathered according to the collecting device, obtain target
Pose；
Module is built, for building map according to the object pose.
According to the third aspect of the embodiment of the present application, there is provided a kind of electronic equipment, including memory, processor and be stored in
Above-mentioned first party is realized on memory and the computer program that can run on a processor, during the computing device described program
The construction method of map any one of face.
The technical scheme that embodiments herein provides can include the following benefits：
Construction method, device and the electronic equipment for the map that embodiments herein provides, by being adopted according to collecting device
The pose worked as former frame depth image and determine present collection device of collection, the historical depth image optimization gathered according to collecting device
The pose, obtains object pose, and map is built according to object pose.Because the present embodiment can be gone through according to what collecting device gathered
History depth image optimizes the pose of present collection device, obtains the higher object pose of precision, and based on object pose structure ground
Figure, it is thereby possible to reduce the error built up due to the passage of time, so as to improve the precision of map structuring.
It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not
The application can be limited.
Brief description of the drawings
Accompanying drawing herein is merged in specification and forms the part of this specification, shows the implementation for meeting the application
Example, and be used to together with specification to explain the principle of the application.
Fig. 1 is a kind of flow chart of the construction method of map of the application according to an exemplary embodiment；
Fig. 2 is the flow chart of the construction method of another map of the application according to an exemplary embodiment；
Fig. 3 is the flow chart of the construction method of another map of the application according to an exemplary embodiment；
Fig. 4 is a kind of block diagram of the construction device of map of the application according to an exemplary embodiment；
Fig. 5 is the block diagram of the construction device of another map of the application according to an exemplary embodiment；
Fig. 6 is the block diagram of the construction device of another map of the application according to an exemplary embodiment；
Fig. 7 is the block diagram of the construction device of another map of the application according to an exemplary embodiment；
Fig. 8 is the structural representation of a kind of electronic equipment of the application according to an exemplary embodiment.
Embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects be described in detail in claims, the application.
It is only merely for the purpose of description specific embodiment in term used in this application, and is not intended to be limiting the application.
" one kind " of singulative used in the application and appended claims, " described " and "the" are also intended to including majority
Form, unless context clearly shows that other implications.It is also understood that term "and/or" used herein refers to and wrapped
Containing the associated list items purpose of one or more, any or all may be combined.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used for same type of information being distinguished from each other out.For example, do not departing from
In the case of the application scope, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on linguistic context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determining ".
In order to implement the constructing plan of the map of the application offer, it is used to gather visual information it is possible, firstly, to prepare one
And the collecting device (e.g., navigator fix robot, or unmanned plane etc.) of Inertia information, it can set on the collecting device and regard
Feel information collecting device (e.g., the binocular camera for sampling depth image, or RGBD cameras etc.) and Inertia information collection dress
Put (e.g., Inertial Measurement Unit for gathering exercise data etc.).Then, collecting device free movement in target area is made,
And visual information and Inertia information are gathered in real time.The visual information and Inertia information collected can be handled in real time,
So as to construct the map of target area.It should be noted that processor can be provided with the collecting device, can directly lead to
Cross the processor and handle collecting visual information and Inertia information, to build map.It can also be incited somebody to action by the collecting device
The visual information and Inertia information collected by network transmission to another electronic equipment, to build map.The application is to this
Aspect does not limit.
As shown in figure 1, Fig. 1 is a kind of flow chart of the construction method of map according to an exemplary embodiment, should
Method can apply in electronic equipment.In the present embodiment, it will be understood by those skilled in the art that the electronic equipment can wrap
Include but be not limited to navigator fix robot, be unmanned plane, the mobile terminal device of such as smart mobile phone, laptop, flat
Plate computer and desktop computer etc..This method comprises the following steps：
In a step 101, the pose worked as former frame depth image and determine present collection device gathered according to collecting device.
In the present embodiment, can be based on the current exercise data of collecting device and when former frame depth image determines currently
The pose of collecting device, the historical depth image that can also be gathered based on collecting device and when former frame depth image determine it is current
The pose of collecting device.It is appreciated that the application to not limiting in this respect.
In the present embodiment, collecting device can include visual information harvester, can further include inertia letter
Cease harvester.Wherein, visual information harvester is used for real-time sampling depth image, and visual information harvester can be each
Kind is capable of the device of sampling depth image, can include but is not limited to binocular camera, or RGBD cameras etc..Inertia information collection dress
Put for gathering exercise data in real time, Inertia information harvester can include but is not limited to IMU (Inertial
Measurement Unit, Inertial Measurement Unit) etc..The application is not limited the particular hardware aspect set on collecting device.
Wherein, current exercise data is the various Inertia informations that collecting device currently collects, such as in three dimensions
The information such as the acceleration and angular speed of all directions.When former frame depth image is the frame depth that collecting device currently collects
View data.The historical depth image that can be gathered according to the current exercise data of collecting device and/or collecting device, with reference to adopting
The pose worked as former frame depth image and determine present collection device of collection equipment collection, wherein, pose can include position and appearance
State.
In a step 102, the pose of the historical depth image optimization present collection device gathered according to collecting device, is obtained
Object pose.
In the present embodiment, the error of the pose of above-mentioned present collection device accumulates change such as the passage of time
Greatly, therefore, the pose for the historical depth image optimization present collection device that can be gathered according to collecting device, so as to obtain more
Accurate object pose.Wherein, historical depth image can be the depth map that above-mentioned collecting device gathers before current time
Picture.Specifically, part or all keys image can be obtained in historical depth image as target image, according to target figure
As the pose of optimization present collection device.For example, it can optimize in the following way：Can be according to target image and collection
The pose of the current exercise data optimization present collection device of equipment, can also be according to target image and when former frame depth image
Optimize the pose of present collection device.It is appreciated that the application is not limited the concrete mode aspect of above-mentioned optimization.
In the present embodiment, key frame images can be preserved during collecting device sampling depth image
Historical depth image.In general, during collecting device sampling depth image, determine first key frame images (generally
First frame depth image of collection) after, a frame depth image is often gathered, is intended to detect whether the frame depth image meets to preset
Condition, the preparatory condition are to be more than default parallax with the parallax of former frame key frame images, and with more than predetermined number
Match road sign point.If meet the preparatory condition, it is determined that the frame depth image is key frame images, is finished in use laggard
Row preserves.If do not meet preparatory condition, it is determined that the frame depth image is not key frame images, then is lost after use
Abandon.
In the present embodiment, can be using all keys image as target image, can also will be nearer with current time
Period in collection Partial key two field picture as target image, the application to not limiting in this respect.
In step 103, map is built according to object pose.
In the present embodiment, it is possible, firstly, to determine work as former frame depth image in newly-increased road sign point (that is, with previous frame
Depth image compares the road sign point newly increased).It is then possible to according to the depth information when former frame depth image and target position
Appearance, it is determined that newly-increased road sign point and matching relative between road sign point (that is, the road sign point of matching compared with previous frame depth image)
Position relationship, and the positional information based on the relative position relation and the matching road sign point for having determined position, it is determined that currently
Increase the position of road sign point in one frame depth image newly.Finally, map is built according to the position of newly-increased road sign point in real time.
The construction method for the map that above-described embodiment of the application provides, works as former frame by what is gathered according to collecting device
Depth image determines the pose of present collection device, according to the historical depth image optimization of the collecting device collection pose, obtains
Object pose, map is built according to object pose.The historical depth image that can be gathered due to the present embodiment according to collecting device
Optimize the pose of present collection device, obtain the higher object pose of precision, and based on object pose structure map, therefore, can
To reduce the error built up due to the passage of time, so as to improve the precision of map structuring.
As shown in Fig. 2 the flow chart of the construction method of another maps of the Fig. 2 according to an exemplary embodiment, should
Embodiment describes the process for the pose for determining present collection device, and this method can apply in electronic equipment, including following
Step：
In step 201, when predeterminable event does not occur, based on the current exercise data of collecting device and the collecting device
The pose worked as former frame depth image and determine present collection device of collection.
In the present embodiment, when predeterminable event does not occur, can based on the current exercise data of collecting device and this adopt
The pose worked as former frame depth image and determine present collection device of collection equipment collection.Specifically, to be provided with binocular camera
And exemplified by IMU collecting device, pre-integration can be carried out to the current motion data that IMU is gathered, so as to according to pre- product first
The result divided determines current imu error item.Work as former frame depth image according to what binocular camera gathered, it is determined that current feature
Re-projection error item.Then, based on current imu error item and current feature re-projection error item, first object is obtained
Function.Finally, using LM (Levenberg-Marquardt, arranging literary Burger-Ma Kuaerte) Algorithm for Solving first object function,
So as to obtain the pose of present collection device.
In step 202, when predeterminable event occurs, historical depth image and the collection based on collecting device collection are set
The pose worked as former frame depth image and determine present collection device of standby collection.
In the present embodiment, when predeterminable event occurs, can based on collecting device gather historical depth image and should
The pose worked as former frame depth image and determine present collection device of collecting device collection.Specifically, can be from collecting device
Reference picture is obtained in the historical depth image of collection, the reference picture when former frame depth image has with exceeding predetermined number
Matching road sign point.It is determined that when the matching road sign point in former frame depth image relative to the reference picture, the reference chart is obtained
The pose as corresponding to, determine currently to adopt according to pose corresponding to the depth information and the reference picture when former frame depth image
Collect the pose of equipment.
In the present embodiment, predeterminable event can be that the data of collecting device collection exception occur, for example, predeterminable event can
With including：Abnormal event occurs for the current exercise data of collecting device；Or when former frame depth image and previous frame depth
The quantity that road sign point is matched in image is less than the event of predetermined number.It is appreciated that predeterminable event can also include other things
Part, the application are not limited the particular content aspect of predeterminable event.
In step 203, the pose of the historical depth image optimization present collection device gathered according to collecting device, is obtained
Object pose.
In step 204, map is built according to object pose.
It should be noted that for the step identical with Fig. 1 embodiments, no longer gone to live in the household of one's in-laws on getting married in above-mentioned Fig. 2 embodiments
State, related content can be found in Fig. 1 embodiments.
The construction method for the map that above-described embodiment of the application provides, when predeterminable event does not occur, is set based on collection
The pose worked as former frame depth image and determine present collection device that standby current exercise data and the collecting device gather.Pre-
If event occurs, historical depth image and collecting device collection based on collecting device collection work as former frame depth image
Determine the pose of present collection device.The pose of the historical depth image optimization present collection device gathered according to collecting device,
Object pose is obtained, map is built according to object pose.Because the present embodiment is when occurring anomalous event, can be set based on collection
For the historical depth image gathered and when former frame depth image determines the pose of present collection device.Therefore, collection is avoided
When the data of equipment collection occur abnormal, the problem of can not normally building map, the efficiency of map structuring is improved, also further
Improve the precision of map structuring.
As shown in figure 3, the flow chart of the structure of another maps of the Fig. 3 according to an exemplary embodiment, the implementation
The process of optimization pose is described in detail in example, and this method can apply in electronic equipment, comprise the following steps：
In step 301, when predeterminable event does not occur, based on the current exercise data of collecting device and the collecting device
The pose worked as former frame depth image and determine present collection device of collection.
In step 302, when predeterminable event occurs, based on collecting device collection historical depth image and work as former frame
Depth image determines the pose of present collection device.
In step 303, obtain historical depth image in part or all keys image as target image.
In the present embodiment, target image can be obtained from the target data prestored, wherein, remember in target data
Record has the key frame images in historical depth image.Specifically, can store to obtain target data in the following way：From adopting
First key frame images are determined in the depth image of collection equipment collection.By first key frame images stored record to target data
In, and it is determined that after first key frame images, each frame depth image gathered successively to collecting device detects, with successively
Determine key frame images.Wherein, for any one frame depth image gathered successively, if the result of detection indicates the frame depth map
As the parallax with former frame key frame images (that is, the key frame images closest with the collection moment of the frame depth image) is more than
Default parallax, and the matching road sign point with more than predetermined number, it is determined that the frame depth image is key frame images.Will be according to
Every frame key frame images of secondary determination successively stored record into the target data.
In step 304, it is excellent according to the exercise data that target image and collecting device are current when predeterminable event does not occur
Change the pose of present collection device, obtain object pose.
In the present embodiment, can be according to the current motion of target image and collecting device when predeterminable event does not occur
The pose of data-optimized present collection device.Specifically, it is first exemplified by being provided with binocular camera and IMU collecting device
Can first pre-integration be carried out to the current motion data that IMU is gathered, so as to determine current imu error according to the result of pre-integration
.The target image gathered according to binocular camera, determines feature re-projection error item corresponding to target image.Then, based on work as
Feature re-projection error item corresponding to preceding imu error item and target image, obtain the second object function.Further according to be optimized
The pose of present collection device determine constraints.Finally, literary Burger-horse (Levenberg-Marquardt, is arranged using LM
Kua Erte) algorithm, the second object function is solved according to constraints, so as to obtain object pose.
In step 305, when predeterminable event occurs, according to target image and when the optimization of former frame depth image is currently adopted
Collect the pose of equipment, obtain object pose.
In the present embodiment, can be according to target image and when former frame depth image optimizes when predeterminable event occurs
The pose of present collection device.Specifically, it may be determined that when the matching road in former frame depth image relative to target image
Punctuate, pose corresponding to the target image is obtained, it is corresponding according to the depth information and target image when former frame depth image
Pose determine the pose of present collection device.
Within step 306, map is built according to object pose.
It should be noted that for the step identical with Fig. 1 and Fig. 2 embodiments, no longer enter in above-mentioned Fig. 3 embodiments
Row repeats, and related content can be found in Fig. 1 and Fig. 2 embodiments.
The construction method for the map that above-described embodiment of the application provides, when predeterminable event does not occur, sets according to collection
The pose worked as former frame depth image and determine present collection device that standby current exercise data and the collecting device gather.Pre-
If event occur, based on collecting device collection historical depth image and when former frame depth image determines present collection device
Pose.Part or all keys image are as target image in acquisition historical depth image.When predeterminable event does not occur,
According to the pose of the current exercise data optimization present collection device of target image and collecting device, object pose is obtained.Pre-
If event occurs, according to target image and the pose when former frame depth image optimization present collection device, target position is obtained
Appearance, and map is built according to object pose.Because the present embodiment can be in the case where predeterminable event occur and occurred, equal energy
The pose of the historical depth image optimization present collection device gathered according to collecting device, obtains the higher object pose of precision,
And based on object pose structure map, when the data for avoiding collecting device collection occur abnormal, it can not normally optimize pose
Problem, further increases the efficiency of map structuring, also further increases the precision of map structuring.
It should be noted that although describing the operation of the application method with particular order in the accompanying drawings, still, this is not required that
Or imply and must perform these operations according to the particular order, or the operation having to carry out shown in whole could realize the phase
The result of prestige.On the contrary, the step of describing in flow chart can change execution sequence.Additionally or alternatively, it is convenient to omit some
Step, multiple steps are merged into a step and performed, and/or a step is decomposed into execution of multiple steps.
Corresponding with the construction method embodiment of aforementioned map, present invention also provides the implementation of the construction device of map
Example.
As shown in figure 4, Fig. 4 is a kind of construction device block diagram of map of the application according to an exemplary embodiment,
The device can include：Determining module 401, optimization module 402 and structure module 403.
Wherein it is determined that module 401, sets for what is gathered according to collecting device when former frame depth image determines currently to gather
Standby pose.
Optimization module 402, for the pose of the historical depth image optimization present collection device gathered according to collecting device,
Obtain object pose.
Module 403 is built, for building map according to object pose.
As shown in figure 5, Fig. 5 is the construction device frame of another map of the application according to an exemplary embodiment
Figure, on the basis of foregoing embodiment illustrated in fig. 4, determining module 401 can include the embodiment：First determination sub-module 501.
Wherein, the first determination sub-module 501, for when predeterminable event does not occur, based on the current motion of collecting device
Data and when former frame depth image determines the pose of present collection device.
As shown in fig. 6, Fig. 6 is the construction device frame of another map of the application according to an exemplary embodiment
Figure, on the basis of foregoing embodiment illustrated in fig. 5, determining module 401 can also include the embodiment：Second determination sub-module
502。
Wherein, the second determination sub-module 502, for when predeterminable event occurs, the history based on collecting device collection to be deep
Spend image and when former frame depth image determines the pose of present collection device.
As shown in fig. 7, Fig. 7 is the construction device frame of another map of the application according to an exemplary embodiment
Figure, on the basis of foregoing embodiment illustrated in fig. 4, optimization module 402 can include the embodiment：Acquisition submodule 701 and excellent
Beggar's module 702.
Wherein, acquisition submodule 701, for obtaining in historical depth image part or all keys image as target
Image.
Optimize submodule 702, for optimizing the pose of present collection device according to target image.
In some optional embodiments, acquisition submodule 701 is arranged to：Obtained from the target data prestored
Target image is taken, wherein, record has the key frame images in historical depth image in target data.
In other optional embodiments, optimization submodule 702 is arranged to：When predeterminable event does not occur, root
According to the pose of the current exercise data optimization present collection device of target image and collecting device.
In other optional embodiments, optimization submodule 702 is arranged to：When predeterminable event occurs, according to
Target image and the pose when former frame depth image optimization present collection device.
It should be appreciated that said apparatus can be set in advance in electronic equipment or server, download etc. can also be passed through
Mode and be loaded into electronic equipment or server.Corresponding module in said apparatus can be with electronic equipment or server
In module cooperate to realize the constructing plan of map.
For device embodiment, because it corresponds essentially to embodiment of the method, so related part is real referring to method
Apply the part explanation of example.Device embodiment described above is only schematical, wherein described be used as separating component
The unit of explanation can be or may not be physically separate, can be as the part that unit is shown or can also
It is not physical location, you can with positioned at a place, or can also be distributed on multiple NEs.Can be according to reality
Need to select some or all of module therein to realize the purpose of application scheme.Those of ordinary skill in the art are not paying
In the case of going out creative work, you can to understand and implement.
The embodiment of the present application additionally provides a kind of computer-readable recording medium, and the storage medium is stored with computer journey
Sequence, computer program can be used for the construction method for performing the map that above-mentioned Fig. 1 provides to Fig. 3 any embodiments.
Corresponding to the construction method of above-mentioned map, the embodiment of the present application also proposed shown in Fig. 8 according to the application's
The schematic configuration diagram of the electronic equipment of one exemplary embodiment.Fig. 8 is refer to, in hardware view, the electronic equipment includes processing
Device, internal bus, network interface, internal memory and nonvolatile memory, it is also possible that certainly hard required for other business
Part.Processor read from nonvolatile memory corresponding to computer program into internal memory then run, on logic level
Form the construction device of map.Certainly, in addition to software realization mode, the application is not precluded from other implementations, such as
Mode of logical device or software and hardware combining etc., that is to say, that the executive agent of following handling process is not limited to each
Logic unit or hardware or logical device.
Those skilled in the art will readily occur to the application its after considering specification and putting into practice invention disclosed herein
Its embodiment.The application is intended to any modification, purposes or the adaptations of the application, these modifications, purposes or
Person's adaptations follow the general principle of the application and including the undocumented common knowledges in the art of the application
Or conventional techniques.Description and embodiments are considered only as exemplary, and the true scope of the application and spirit are by following
Claim is pointed out.
It should be appreciated that the precision architecture that the application is not limited to be described above and is shown in the drawings, and
And various modifications and changes can be being carried out without departing from the scope.Scope of the present application is only limited by appended claim.
Claims (10)
1. a kind of construction method of map, it is characterised in that methods described includes：
The pose worked as former frame depth image and determine presently described collecting device gathered according to collecting device；
Pose described in the historical depth image optimization gathered according to the collecting device, obtains object pose；
Map is built according to the object pose.
2. according to the method for claim 1, it is characterised in that described to work as former frame depth map according to what collecting device gathered
Pose as determining presently described collecting device, including：
When predeterminable event does not occur, based on the current exercise data of the collecting device and it is described when former frame depth image it is true
The pose of fixed presently described collecting device.
3. according to the method for claim 1, it is characterised in that described to work as former frame depth map according to what collecting device gathered
Pose as determining presently described collecting device, in addition to：
When predeterminable event occurs, historical depth image based on collecting device collection and described work as former frame depth image
Determine the pose of presently described collecting device.
4. according to the method described in any one in claim 1-3, it is characterised in that described to be gathered according to the collecting device
Historical depth image optimization described in pose, including：
Part or all keys image are obtained in the historical depth image as target image；
The pose is optimized according to the target image.
5. according to the method for claim 4, it is characterised in that described to obtain in the historical depth image partly or entirely
Key frame images as target image, including：
The target image is obtained from the target data prestored；Wherein, record has the history in the target data
Key frame images in depth image.
6. according to the method for claim 5, it is characterised in that storage obtains the target data in the following way：
First key frame images are determined from the depth image of collecting device collection；
By the first key frame images stored record into the target data；
It is determined that after the first key frame images, each frame depth image gathered successively to the collecting device is examined
Survey, to determine key frame images successively；Wherein, for any one frame depth image gathered successively, if the detection
As a result indicate that the parallax of the frame depth image and former frame key frame images is more than default parallax, and have and exceed predetermined number
Matching road sign point, it is determined that the frame depth image is key frame images；
By the every frame key frame images determined successively successively stored record into the target data.
7. according to the method for claim 4, it is characterised in that described that the pose, bag are optimized according to the target image
Include：
When predeterminable event does not occur, institute's rheme is optimized according to the current exercise data of the target image and the collecting device
Appearance.
8. according to the method for claim 4, it is characterised in that it is described that the pose is optimized according to the target image, also
Including：
When predeterminable event occurs, the pose is optimized according to the target image and the former frame depth image of working as.
9. a kind of construction device of map, it is characterised in that described device includes：
Determining module, for the position worked as former frame depth image and determine presently described collecting device gathered according to collecting device
Appearance；
Optimization module, for pose described in the historical depth image optimization that is gathered according to the collecting device, obtain object pose；
Module is built, for building map according to the object pose.
10. a kind of electronic equipment, including memory, processor and storage are on a memory and the calculating that can run on a processor
Machine program, it is characterised in that the side any one of the claims 1-8 is realized during the computing device described program
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711104367.8A CN107845114B (en) | 2017-11-10 | 2017-11-10 | Map construction method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711104367.8A CN107845114B (en) | 2017-11-10 | 2017-11-10 | Map construction method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107845114A true CN107845114A (en) | 2018-03-27 |
| CN107845114B CN107845114B (en) | 2024-03-22 |
Family
ID=61680990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711104367.8A Active CN107845114B (en) | 2017-11-10 | 2017-11-10 | Map construction method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107845114B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846857A (en) * | 2018-06-28 | 2018-11-20 | 清华大学深圳研究生院 | The measurement method and visual odometry of visual odometry |
| CN109186618A (en) * | 2018-08-31 | 2019-01-11 | 平安科技（深圳）有限公司 | Map constructing method, device, computer equipment and storage medium |
| CN109431381A (en) * | 2018-10-29 | 2019-03-08 | 北京石头世纪科技有限公司 | Localization method and device, electronic equipment, the storage medium of robot |
| CN111044289A (en) * | 2019-12-26 | 2020-04-21 | 哈尔滨工业大学 | Large-scale high-speed rotation equipment alignment error measuring method based on closed-loop dynamic measurement |
| CN111091621A (en) * | 2019-12-11 | 2020-05-01 | 东南数字经济发展研究院 | Binocular vision synchronous positioning and composition method, device, equipment and storage medium |
| CN111552757A (en) * | 2020-04-30 | 2020-08-18 | 上海商汤临港智能科技有限公司 | Method, device and equipment for generating electronic map and storage medium |
| CN112634395A (en) * | 2019-09-24 | 2021-04-09 | 杭州海康威视数字技术股份有限公司 | Map construction method and device based on SLAM |
| CN112991515A (en) * | 2021-02-26 | 2021-06-18 | 山东英信计算机技术有限公司 | Three-dimensional reconstruction method, device and related equipment |
| CN114619453A (en) * | 2022-05-16 | 2022-06-14 | 深圳市普渡科技有限公司 | Robot, map construction method, and computer-readable storage medium |
| WO2022262152A1 (en) * | 2021-06-18 | 2022-12-22 | 深圳市商汤科技有限公司 | Map construction method and apparatus, electronic device, storage medium and computer program product |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120037270A (en) * | 2010-10-11 | 2012-04-19 | 삼성전자주식회사 | Voxel map generator and method thereof |
| CN105783913A (en) * | 2016-03-08 | 2016-07-20 | 中山大学 | SLAM device integrating multiple vehicle-mounted sensors and control method of device |
| CN106052683A (en) * | 2016-05-25 | 2016-10-26 | 速感科技（北京）有限公司 | Robot motion attitude estimating method |
| CN106997614A (en) * | 2017-03-17 | 2017-08-01 | 杭州光珀智能科技有限公司 | A kind of large scale scene 3D modeling method and its device based on depth camera |
| CN107025668A (en) * | 2017-03-30 | 2017-08-08 | 华南理工大学 | A kind of design method of the visual odometry based on depth camera |
| CN107160395A (en) * | 2017-06-07 | 2017-09-15 | 中国人民解放军装甲兵工程学院 | Map constructing method and robot control system |
-
2017
- 2017-11-10 CN CN201711104367.8A patent/CN107845114B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120037270A (en) * | 2010-10-11 | 2012-04-19 | 삼성전자주식회사 | Voxel map generator and method thereof |
| CN105783913A (en) * | 2016-03-08 | 2016-07-20 | 中山大学 | SLAM device integrating multiple vehicle-mounted sensors and control method of device |
| CN106052683A (en) * | 2016-05-25 | 2016-10-26 | 速感科技（北京）有限公司 | Robot motion attitude estimating method |
| CN106997614A (en) * | 2017-03-17 | 2017-08-01 | 杭州光珀智能科技有限公司 | A kind of large scale scene 3D modeling method and its device based on depth camera |
| CN107025668A (en) * | 2017-03-30 | 2017-08-08 | 华南理工大学 | A kind of design method of the visual odometry based on depth camera |
| CN107160395A (en) * | 2017-06-07 | 2017-09-15 | 中国人民解放军装甲兵工程学院 | Map constructing method and robot control system |
Non-Patent Citations (5)
| Title |
|---|
| W. NICHOLAS GREENE等: "Multi-level mapping: Real-time dense monocular SLAM", 《2016 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)》, 9 June 2016 (2016-06-09), pages 833 - 840 * |
| 付梦印等: "基于RGB-D数据的实时SLAM算法", 《机器人》 * |
| 付梦印等: "基于RGB-D数据的实时SLAM算法", 《机器人》, vol. 37, no. 6, 15 November 2015 (2015-11-15), pages 684 - 686 * |
| 李枫等: "结合SIFT算法的视频场景突变检测", 《中国光学》 * |
| 李枫等: "结合SIFT算法的视频场景突变检测", 《中国光学》, vol. 9, no. 1, 15 February 2016 (2016-02-15), pages 74 - 80 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846857A (en) * | 2018-06-28 | 2018-11-20 | 清华大学深圳研究生院 | The measurement method and visual odometry of visual odometry |
| CN109186618A (en) * | 2018-08-31 | 2019-01-11 | 平安科技（深圳）有限公司 | Map constructing method, device, computer equipment and storage medium |
| CN109431381B (en) * | 2018-10-29 | 2022-06-07 | 北京石头创新科技有限公司 | Robot positioning method and device, electronic device and storage medium |
| CN109431381A (en) * | 2018-10-29 | 2019-03-08 | 北京石头世纪科技有限公司 | Localization method and device, electronic equipment, the storage medium of robot |
| CN112634395B (en) * | 2019-09-24 | 2023-08-25 | 杭州海康威视数字技术股份有限公司 | Map construction method and device based on SLAM |
| CN112634395A (en) * | 2019-09-24 | 2021-04-09 | 杭州海康威视数字技术股份有限公司 | Map construction method and device based on SLAM |
| CN111091621A (en) * | 2019-12-11 | 2020-05-01 | 东南数字经济发展研究院 | Binocular vision synchronous positioning and composition method, device, equipment and storage medium |
| CN111044289A (en) * | 2019-12-26 | 2020-04-21 | 哈尔滨工业大学 | Large-scale high-speed rotation equipment alignment error measuring method based on closed-loop dynamic measurement |
| CN111044289B (en) * | 2019-12-26 | 2021-09-03 | 哈尔滨工业大学 | Large-scale high-speed rotation equipment alignment error measuring method based on closed-loop dynamic measurement |
| CN111552757B (en) * | 2020-04-30 | 2022-04-01 | 上海商汤临港智能科技有限公司 | Method, device and equipment for generating electronic map and storage medium |
| CN111552757A (en) * | 2020-04-30 | 2020-08-18 | 上海商汤临港智能科技有限公司 | Method, device and equipment for generating electronic map and storage medium |
| CN112991515A (en) * | 2021-02-26 | 2021-06-18 | 山东英信计算机技术有限公司 | Three-dimensional reconstruction method, device and related equipment |
| WO2022262152A1 (en) * | 2021-06-18 | 2022-12-22 | 深圳市商汤科技有限公司 | Map construction method and apparatus, electronic device, storage medium and computer program product |
| CN114619453A (en) * | 2022-05-16 | 2022-06-14 | 深圳市普渡科技有限公司 | Robot, map construction method, and computer-readable storage medium |
| CN114619453B (en) * | 2022-05-16 | 2022-09-20 | 深圳市普渡科技有限公司 | Robot, map construction method, and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107845114B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107845114A (en) | Construction method, device and the electronic equipment of map | |
| CN109727288B (en) | System and method for monocular simultaneous localization and mapping | |
| CN112797897B (en) | Method and device for measuring geometric parameters of object and terminal | |
| US11295532B2 (en) | Method and apparatus for aligning 3D model | |
| CN108985199A (en) | Detection method, device and the storage medium of commodity loading or unloading operation | |
| US9128959B2 (en) | Crowdsourced search and locate platform | |
| CN107888828A (en) | Space-location method and device, electronic equipment and storage medium | |
| CN110462683A (en) | Method, terminal and the computer readable storage medium of close coupling vision SLAM | |
| CN110276317B (en) | Object size detection method, object size detection device and mobile terminal | |
| CN111209978B (en) | Three-dimensional visual repositioning method and device, computing equipment and storage medium | |
| CN107990899A (en) | A kind of localization method and system based on SLAM | |
| US20140237386A1 (en) | Crowdsourced image analysis platform | |
| CN107203556B (en) | Method and device for adding new interest point information | |
| CN111833447A (en) | Three-dimensional map construction method, three-dimensional map construction device and terminal equipment | |
| CN111402413B (en) | Three-dimensional visual positioning method and device, computing equipment and storage medium | |
| CN110378942A (en) | Barrier identification method, system, equipment and storage medium based on binocular camera | |
| US11361548B2 (en) | Method and system for multi instance visual tracking based on observer motion modelling | |
| CN112819860A (en) | Visual inertial system initialization method and device, medium and electronic equipment | |
| EP3761268A1 (en) | System and method for integrating objects in monocular slam | |
| Morrison et al. | Scalable multirobot localization and mapping with relative maps: Introducing MOARSLAM | |
| CN113570716A (en) | Cloud three-dimensional map construction method, system and equipment | |
| CN112162561A (en) | Map construction optimization method, device, medium and equipment | |
| CN111882494A (en) | Pose graph processing method and device, computer equipment and storage medium | |
| CN114674328B (en) | Map generation method, map generation device, electronic device, storage medium, and vehicle | |
| CN115965939A (en) | Three-dimensional target detection method and device, electronic equipment, medium and vehicle |
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 |