CN108256543A - A kind of localization method and electronic equipment - Google Patents
A kind of localization method and electronic equipment Download PDFInfo
- Publication number
- CN108256543A CN108256543A CN201611248781.1A CN201611248781A CN108256543A CN 108256543 A CN108256543 A CN 108256543A CN 201611248781 A CN201611248781 A CN 201611248781A CN 108256543 A CN108256543 A CN 108256543A
- Authority
- CN
- China
- Prior art keywords
- candidate frame
- frame
- candidate
- frame set
- target device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of localization method and electronic equipment, the method includes：The first candidate frame set for being positioned to target device is obtained using the first localization method；The candidate frame for meeting preset condition is got rid of from the first candidate frame set using second of localization method, obtains the second candidate frame set；Using the candidate frame in the second candidate frame set, the location information of target device is determined.
Description
Technical field
The present invention relates to location technology more particularly to a kind of localization methods and electronic equipment.
Background technology
Synchronous positioning is a kind of common with building figure (SLAM, Simultaneous Localization and Mapping)
Robot vision relocation system, the system positioning main flow include：The local image characteristics of image are extracted first, and
Classified by establishing bag of words (BoW, Bag of words) model to local image characteristics, establish key frame data library.So
Afterwards key frame data library is carried out retrieving can be realized by BoW search methods resetting bit function.BoW has the retrieval rate fast
Feature, but precision also receives certain restrictions, much by the candidate frame that BoW is retrieved apart from present frame physical location very
Far.Although these frames are carried out with subsequent detection can exclude these frames, a large amount of time can be wasted.
Invention content
In order to solve the above technical problems, an embodiment of the present invention provides a kind of localization method and electronic equipments.
Localization method provided in an embodiment of the present invention, including：
The first candidate frame set for being positioned to target device is obtained using the first localization method；
The candidate frame for meeting preset condition is got rid of from the first candidate frame set using second of localization method, is obtained
To the second candidate frame set；
Using the candidate frame in the second candidate frame set, the location information of target device is determined.
In the embodiment of the present invention, it is described using the first localization method obtain for target device is positioned first
Candidate frame set, including：
The image data within the vision of the target device is acquired, as present frame；
Bag of words are established from described image extracting data characteristic, and according to the characteristic；
It searches more than one candidate frame to match with the present frame in the database based on the bag of words, obtains
First candidate frame set.
It is described to get rid of satisfaction from the first candidate frame set using second of localization method in the embodiment of the present invention
The candidate frame of preset condition obtains the second candidate frame set, including：
When acquisition is described when the current frame, using the location information of the communication positioning method acquisition target device, as institute
State the corresponding location information of present frame；
Based on the corresponding location information of the present frame, got rid of from the first candidate frame set and the present frame
Distance be more than or equal to predetermined threshold value candidate frame, obtain the second candidate frame set.
In the embodiment of the present invention, it is described using the first localization method obtain for target device is positioned first
Candidate frame set, including：
The image data within the vision of the target device is acquired, as present frame；
When acquisition is described when the current frame, using the location information of the communication positioning method acquisition target device, as institute
State the corresponding location information of present frame；
Based on the corresponding location information of the present frame, search to be less than with the distance of the present frame from database and preset
The candidate frame of threshold value obtains the first candidate frame set.
It is described to get rid of satisfaction from the first candidate frame set using second of localization method in the embodiment of the present invention
The candidate frame of preset condition obtains the second candidate frame set, including：
Bag of words are established from described image extracting data characteristic, and according to the characteristic；
Searched in the first candidate frame set based on the bag of words match with the present frame one with
Upper candidate frame obtains the second candidate frame set.
Electronic equipment provided in an embodiment of the present invention, including：
First positioning unit, for obtaining the first time for being positioned to target device using the first localization method
Select frame set；
Second positioning unit is met in advance for being got rid of from the first candidate frame set using second of localization method
If the candidate frame of condition, the second candidate frame set is obtained；
Determination unit, for using the candidate frame in the second candidate frame set, determining the location information of target device.
In the embodiment of the present invention, first positioning unit includes：
Image Acquisition subelement, for acquiring the image data within the vision of the target device, as present frame；
Bag of words subelement, for being built from described image extracting data characteristic, and according to the characteristic
Vertical bag of words；
Subelement is searched, for searching match with the present frame one in the database based on the bag of words
More than candidate frame obtains the first candidate frame set.
In the embodiment of the present invention, second positioning unit includes：
Communicate locator unit, for working as described in acquisition when the current frame, obtains the target using communication positioning method and sets
Standby location information, as the corresponding location information of the present frame；
Subelement is screened, for being based on the corresponding location information of the present frame, from the first candidate frame set
The candidate frame for being more than or equal to predetermined threshold value with the distance of the present frame is removed, obtains the second candidate frame set.
In the embodiment of the present invention, first positioning unit includes：
Image Acquisition subelement, for acquiring the image data within the vision of the target device, as present frame；
Communicate locator unit, for working as described in acquisition when the current frame, obtains the target using communication positioning method and sets
Standby location information, as the corresponding location information of the present frame；
First search subelement, for being based on the corresponding location information of the present frame, from database search with it is described
The distance of present frame is less than the candidate frame of predetermined threshold value, obtains the first candidate frame set.
In the embodiment of the present invention, second positioning unit includes：
Bag of words subelement, for being built from described image extracting data characteristic, and according to the characteristic
Vertical bag of words；
Second searches subelement, searches for being based on the bag of words in the first candidate frame set with it is described ought
More than one candidate frame that previous frame matches obtains the second candidate frame set.
In the technical solution of the embodiment of the present invention, obtain to position target device using the first localization method
The first candidate frame set；It is got rid of from the first candidate frame set using second of localization method and meets preset condition
Candidate frame obtains the second candidate frame set；Using the candidate frame in the second candidate frame set, the position of target device is determined
Information.Using the technical solution of the embodiment of the present invention, the location information that two kinds of localization methods determine target device is combined, it will be normal
Communication location technology (such as GPS positioning) is combined with vision re-positioning technology, using logical when with vision re-positioning technology
Believe candidate frame of the location technology screening part apart from present frame farther out, greatly reduce the calculation amount of candidate frame, reached reality
The effect of Shi Dingwei.
Description of the drawings
Fig. 1 is the flow diagram of the localization method of the embodiment of the present invention；
Fig. 2 is the Inverse Index data structure schematic diagrames of the embodiment of the present invention；
Fig. 3 is the structure composition schematic diagram one of the electronic equipment of the embodiment of the present invention；
Fig. 4 is the structure composition schematic diagram two of the electronic equipment of the embodiment of the present invention；
Fig. 5 is the structure composition schematic diagram three of the electronic equipment of the embodiment of the present invention.
Specific embodiment
The characteristics of in order to more fully hereinafter understand the embodiment of the present invention and technology contents, below in conjunction with the accompanying drawings to this hair
The realization of bright embodiment is described in detail, appended attached drawing purposes of discussion only for reference, is not used for limiting the embodiment of the present invention.
It is below the explanation with the relevant Key Term of the embodiment of the present invention：
SLAM：A kind of real-time positioning and the scheme for building figure, are mainly acquired using 2D cameras, 3D cameras and IMU around carrier
Consecutive image data, believed according to the current pose information of consecutive image data configuration three-dimensional environment map and carrier and position
Breath.
BoW：Bag of words for carrying out the fractionation of word level to image data, then build its index.
VIO：The SLAM implementation methods that hardware is merged with sensor quickly track the pose of camera using filtering, without
Safeguard global map.
GPS：Global positioning system, the system for being positioned and being navigated in real time in the world.
ORBSLAM：A kind of robot vision relocation system, positioning main flow include：The ORB of image is extracted first
Feature, and pass through and establish bag of words and classify to characteristics of image, then reality can be completed by establishing key frame data library
When reset bit function.BoW has the characteristics that retrieval rate is fast, but precision also receives certain restrictions, is much examined by BoW
The candidate frame that rope obtains is far apart from present frame physical location.
In the SLAM applications of large scene, due to the limitation of bag of words, candidate frame is possible and incorrect.Under VIO
Vision reorientation, drift about since there is no scale, therefore the add up error of pose will not be very big.It is positioned by common communication
Technology, such as global positioning system (GPS, Global Positioning System), wireless local area (WIFI, Wireless
Fidelity) location technology etc. carries out position screening to candidate frame, and it is candidate can be efficiently modified the vision reorientation based on BoW
Frame algorithm so that candidate frame can be quickly and accurately found under large scene.
The technical solution of the embodiment of the present invention combines two kinds of localization methods, wherein, communication location technology such as GPS positioning,
The calculation amount of the needs such as WIFI positioning is low, but position location is inaccurate；Vision positioning technology accuracy is high, but calculation amount
Greatly.Two kinds of localization methods are used in combination in the embodiment of the present invention, and the candidate frame of reorientation is first found with vision positioning method, recycle
The location technologies such as GPS, WIFI screen candidate frame, then estimate the location information of target device (such as camera) again.This hair
Bright embodiment not only remains vision positioning feature with high accuracy, and improves positioning speed by location technologies such as GPS, WIFI
Degree.
Fig. 1 be the embodiment of the present invention localization method flow diagram, as shown in Figure 1, the localization method include with
Lower step：
Step 101：The first candidate frame set for being positioned to target device is obtained using the first localization method.
The embodiment of the present invention is applied in target device, and target device can be robot, mobile terminal (put down by such as mobile phone
Plate computer etc.).Target device is built-in, and there are two types of alignment systems, respectively the first alignment system and the second alignment system.In one kind
In embodiment, the first alignment system is SLAM alignment systems, can be specifically ORBSLAM alignment systems, SLAM alignment systems
It is made of harvesters such as 2D cameras, 3D cameras and IMU, the position of target device can be positioned by the image collected data
It puts.Second alignment system is that either WIFI alignment systems GPS positioning system or WIFI alignment systems can for GPS positioning system
The position of target device is positioned by mobile network or wireless network.In another embodiment, the first alignment system is
GPS positioning system or WIFI alignment systems, the second alignment system are SLAM alignment systems, can be specifically ORBSLAM positioning
System.
In said program, localization method used by the first alignment system is known as the first localization method, second is determined
Localization method is known as second of localization method used by the system of position.
By taking the first alignment system is SLAM alignment systems as an example：It is described that the first localization method is utilized to obtain for target
The first candidate frame set that equipment is positioned, including：
The image data within the vision of the target device is acquired, as present frame；
Bag of words are established from described image extracting data characteristic, and according to the characteristic；
It searches more than one candidate frame to match with the present frame in the database based on the bag of words, obtains
First candidate frame set.
Here, a series of continuous ambient image data are stored in database, each ambient image data are known as frame,
When establishing database, by extracting characteristic (such as ORB features) in the picture and establishing bag of words according to the characteristic
Model；The bag of words of all frames are stored in database, at the same time, by the precise position information of each frame and communication position
Confidence is ceased to be stored in together as the attribute of frame.Later, the image data phase with acquiring can be retrieved by BoW in the database
Matched candidate frame.
In one example：From described image extracting data characteristic be desk and chair, corresponding bag of words
As desk and chair, search in the database it is all there are desks and the frame of chair, obtain the first candidate frame set.
By taking the first alignment system is GPS positioning system or WIFI alignment systems as an example：It is described to utilize the first localization method
The first candidate frame set for being positioned to target device is obtained, including：
The image data within the vision of the target device is acquired, as present frame；
When acquisition is described when the current frame, using the location information of the communication positioning method acquisition target device, as institute
State the corresponding location information of present frame；
Based on the corresponding location information of the present frame, search to be less than with the distance of the present frame from database and preset
The candidate frame of threshold value obtains the first candidate frame set.
Here it is possible to filtered out from database beforehand through communication positioning method before BoW retrievals are carried out with currently
The distance of frame is less than the candidate frame of predetermined threshold value, obtains the first candidate frame set.Then, it can be examined in the database by BoW
Rope retrieves the candidate frame to match with present frame in the first candidate frame set kind.
Step 102：It is got rid of from the first candidate frame set using second of localization method and meets preset condition
Candidate frame obtains the second candidate frame set.
It is SLAM alignment systems based on the first alignment system, the second alignment system is GPS positioning system or WIFI positioning system
System, it is described that the candidate frame for meeting preset condition is got rid of from the first candidate frame set using second of localization method, it obtains
To the second candidate frame set, including：
When acquisition is described when the current frame, using the location information of the communication positioning method acquisition target device, as institute
State the corresponding location information of present frame；
Based on the corresponding location information of the present frame, got rid of from the first candidate frame set and the present frame
Distance be more than or equal to predetermined threshold value candidate frame, obtain the second candidate frame set.
Here, the candidate frame to match with present frame is retrieved by BoW in the database first, obtains the first candidate frame
Set.Then, the candidate frame for being more than or equal to predetermined threshold value with the distance of the present frame is got rid of in the first candidate frame set,
Obtain the second candidate frame set.
It is GPS positioning system or WIFI alignment systems based on the first alignment system, the second alignment system SLAM positioning is
System, it is described that the candidate frame for meeting preset condition is got rid of from the first candidate frame set using second of localization method, it obtains
To the second candidate frame set, including：
Bag of words are established from described image extracting data characteristic, and according to the characteristic；
Searched in the first candidate frame set based on the bag of words match with the present frame one with
Upper candidate frame obtains the second candidate frame set.
Here, it is filtered out from database first by communication positioning method and is less than predetermined threshold value with the distance of present frame
Candidate frame obtains the first candidate frame set.Then, it can be retrieved by BoW and be examined in the first candidate frame set kind in the database
Rope is to the candidate frame to match with present frame.
Step 103：Using the candidate frame in the second candidate frame set, the location information of target device is determined.
In the embodiment of the present invention, candidate number of frames in the second candidate frame set obtained by two kinds of localization methods compared with
It is few, the specific location with the corresponding candidate frame of present frame can be rapidly determined using trigonometric ratio localization method.Then, will
The precise position information corresponding to candidate frame finally obtained, the location information as target device.
The embodiment of the present invention relocates skill according to the location information that GPS positioning technology or WIFI location technologies obtain to vision
The reorientation candidate frame that art obtains is screened, and gets rid of the number for apart from the distant candidate frame of present frame, reducing candidate frame
Amount, improves the speed of reorientation, alignment system is made to be more suitable for the environment of large scale.
The technical solution of the embodiment of the present invention is described in further detail with reference to concrete application scene.
Scene one：
In robot, using image collecting device of the fisheye camera as vision positioning system, pass through ORB feature extractions
The reorientation candidate frame of key frame (namely present frame) is searched on the database of real-time update with the method for BoW bag of words,
The quantity of candidate frame may have very much, and here, BoW is a kind of method of Rapid matching but simultaneously inaccurate, some candidate frames with
Current frame position is met very remote.
For this purpose, being judged with the location information based on GPS positioning all candidate frames, only retain apart from closer time
Select frame, can remove in this way it is most of apart from the far candidate frame of present frame, then to satisfactory candidate frame into advancing one
The operations such as the trigonometric ratio judgement of step, to determine the specific location of candidate frame to match with key frame.Here, the GPS of candidate frame
Positioning improves the speed of reorientation.
Such as：The first candidate frame collection is found in the database using BoW search methods (namely vision reorientation) to be combined into：
Image1, Image3, Image6, Image8, Image14, Image26, these candidate frames have identical key with present frame
Word, such as A buildings, B articles etc..Then, above-mentioned each candidate frame is judged according to the location information of GPS positioning, removed
Fall the candidate frame farther out apart from present frame, such as the distance of Image1, Image3, Image6, Image26 apart from present frame is more than
Predetermined threshold value gets rid of these candidate frames from the first candidate frame set, finally obtains the second candidate frame collection and is combined into：Image8、
Image14.In this way, the negligible amounts of the candidate frame finally obtained, then trigonometric ratio judgement is carried out to these candidate frames, determine with
The candidate frame that present frame matches is positioned.
Scene two：
GPS information can be added directly into BoW matching process.The matching process of BoW is to rely on inverted index
(Inverse Index) data structure.Data structure storage information is as shown in Figure 2：
Inverse index Word 1 store the key frame with same keyword Word1, here, with a key
For word Word1, it is, of course, also possible to store the key frame with two or more keywords, such as storage has identical pass
The key frame of keyword Word1 and Word2.These key frames relocate after passing through certain operation as candidate frame.
So the quantity of these frames is fewer, then candidate number of frames is fewer, then the calculation amount of reorientation will reduce.Therefore, Ke Yi
The location information based on GPS positioning is just added in when reading Inverse Index data structure informations to judge, is excluded apart from present frame
Key frame farther out reduces the quantity of candidate frame, so as to improve matching efficiency.
Such as：It is searched in the database after present frame distance is less than or equal to predetermined threshold value using GPS positioning method
Frame is selected, the first candidate frame collection is obtained and is combined into：Image 7、Image8、Image11、Image14、Image18、Image20、
Image23；Then, the second candidate is found in the first candidate frame set using BoW search methods (namely vision reorientation)
Frame collection is combined into：Image8, Image14, the candidate frame in the second candidate frame set have identical keyword with present frame, such as
A buildings, B articles etc..In this way, the negligible amounts of the candidate frame finally obtained, then trigonometric ratio judgement is carried out to these candidate frames, really
The candidate frame to match with present frame is made to be positioned.
Fig. 3 is the structure composition schematic diagram one of the electronic equipment of the embodiment of the present invention, as shown in figure 3, the electronic equipment
Including：
First positioning unit 31, for using the first localization method obtain for target device is positioned first
Candidate frame set；
Second positioning unit 32, for getting rid of satisfaction from the first candidate frame set using second of localization method
The candidate frame of preset condition obtains the second candidate frame set；
Determination unit 33, for using the candidate frame in the second candidate frame set, determining the position letter of target device
Breath.
It will be appreciated by those skilled in the art that before the realization function of each unit in electronic equipment shown in Fig. 3 can refer to
It states the associated description of localization method and understands.The function of each unit in electronic equipment shown in Fig. 3 can be by running on processing
Program on device and realize, can also be realized by specific logic circuit.
Fig. 4 is the structure composition schematic diagram two of the electronic equipment of the embodiment of the present invention, as shown in figure 4, the electronic equipment
Including：
First positioning unit 41, for using the first localization method obtain for target device is positioned first
Candidate frame set；
Second positioning unit 42, for getting rid of satisfaction from the first candidate frame set using second of localization method
The candidate frame of preset condition obtains the second candidate frame set；
Determination unit 43, for using the candidate frame in the second candidate frame set, determining the position letter of target device
Breath.
First positioning unit 41 includes：
Image Acquisition subelement 411, for acquiring the image data within the vision of the target device, as current
Frame；
Bag of words subelement 412, for from described image extracting data characteristic, and according to the characteristic
Establish bag of words；
Subelement 413 is searched, for searching what is matched with the present frame in the database based on the bag of words
More than one candidate frame obtains the first candidate frame set.
Second positioning unit 42 includes：
Communicate locator unit 421, for working as described in acquisition when the current frame, communication positioning method is utilized to obtain the target
The location information of equipment, as the corresponding location information of the present frame；
Subelement 422 is screened, for being based on the corresponding location information of the present frame, from the first candidate frame set
The candidate frame for being more than or equal to predetermined threshold value with the distance of the present frame is got rid of, obtains the second candidate frame set.
It will be appreciated by those skilled in the art that before the realization function of each unit in electronic equipment shown in Fig. 4 can refer to
It states the associated description of localization method and understands.The function of each unit in electronic equipment shown in Fig. 4 can be by running on processing
Program on device and realize, can also be realized by specific logic circuit.
Fig. 5 is the structure composition schematic diagram three of the electronic equipment of the embodiment of the present invention, as shown in figure 5, the electronic equipment
Including：
First positioning unit 51, for using the first localization method obtain for target device is positioned first
Candidate frame set；
Second positioning unit 52, for getting rid of satisfaction from the first candidate frame set using second of localization method
The candidate frame of preset condition obtains the second candidate frame set；
Determination unit 53, for using the candidate frame in the second candidate frame set, determining the position letter of target device
Breath.
First positioning unit 51 includes：
Image Acquisition subelement 511, for acquiring the image data within the vision of the target device, as current
Frame；
Communicate locator unit 512, for working as described in acquisition when the current frame, communication positioning method is utilized to obtain the target
The location information of equipment, as the corresponding location information of the present frame；
First searches subelement 513, for being based on the corresponding location information of the present frame, lookup and institute from database
The distance for stating present frame is less than the candidate frame of predetermined threshold value, obtains the first candidate frame set.
Second positioning unit 52 includes：
Bag of words subelement 521, for from described image extracting data characteristic, and according to the characteristic
Establish bag of words；
Second searches subelement 522, searches for being based on the bag of words in the first candidate frame set and institute
More than one candidate frame that present frame matches is stated, obtains the second candidate frame set.
It will be appreciated by those skilled in the art that before the realization function of each unit in electronic equipment shown in fig. 5 can refer to
It states the associated description of localization method and understands.The function of each unit in electronic equipment shown in fig. 5 can be by running on processing
Program on device and realize, can also be realized by specific logic circuit.
It, in the absence of conflict, can be in any combination between technical solution recorded in the embodiment of the present invention.
In several embodiments provided by the present invention, it should be understood that disclosed method and smart machine, Ke Yitong
Other modes are crossed to realize.Apparatus embodiments described above are only schematical, for example, the division of the unit, only
Only a kind of division of logic function, can have other dividing mode, such as in actual implementation：Multiple units or component can be tied
It closes or is desirably integrated into another system or some features can be ignored or does not perform.In addition, shown or discussed each group
Into the mutual coupling in part or direct-coupling or communication connection can be by some interfaces, equipment or unit it is indirect
Coupling or communication connection, can be electrical, mechanical or other forms.
The above-mentioned unit illustrated as separating component can be or may not be physically separate, be shown as unit
The component shown can be or may not be physical unit, you can be located at a place, can also be distributed to multiple network lists
In member；Part or all of unit therein can be selected according to the actual needs to realize the purpose of this embodiment scheme.
In addition, each functional unit in various embodiments of the present invention can be fully integrated into a second processing unit,
Can also be each unit individually as a unit, can also two or more units integrate in a unit；
The form that hardware had both may be used in above-mentioned integrated unit is realized, the form that hardware adds SFU software functional unit can also be used real
It is existing.
The above description is merely a specific embodiment, but protection scope of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in change or replacement, should all contain
Lid is within protection scope of the present invention.
Claims (10)
1. a kind of localization method, which is characterized in that the method includes：
The first candidate frame set for being positioned to target device is obtained using the first localization method；
The candidate frame for meeting preset condition is got rid of from the first candidate frame set using second of localization method, obtains
Two candidate frame set；
Using the candidate frame in the second candidate frame set, the location information of target device is determined.
2. localization method according to claim 1, which is characterized in that it is described utilize the first localization method obtain for pair
The first candidate frame set that target device is positioned, including：
The image data within the vision of the target device is acquired, as present frame；
Bag of words are established from described image extracting data characteristic, and according to the characteristic；
It searches more than one candidate frame to match with the present frame in the database based on the bag of words, obtains first
Candidate frame set.
3. localization method according to claim 2, which is characterized in that described to utilize second of localization method from described first
The candidate frame for meeting preset condition is got rid of in candidate frame set, obtains the second candidate frame set, including：
When the current frame, the location information of the target device being obtained using communication positioning method described in acquisition, work as described
The corresponding location information of previous frame；
Based on the corresponding location information of the present frame, got rid of from the first candidate frame set with the present frame away from
From the candidate frame more than or equal to predetermined threshold value, the second candidate frame set is obtained.
4. localization method according to claim 1, which is characterized in that it is described utilize the first localization method obtain for pair
The first candidate frame set that target device is positioned, including：
The image data within the vision of the target device is acquired, as present frame；
When the current frame, the location information of the target device being obtained using communication positioning method described in acquisition, work as described
The corresponding location information of previous frame；
Based on the corresponding location information of the present frame, searched from database and be less than predetermined threshold value with the distance of the present frame
Candidate frame, obtain the first candidate frame set.
5. localization method according to claim 4, which is characterized in that described to utilize second of localization method from described first
The candidate frame for meeting preset condition is got rid of in candidate frame set, obtains the second candidate frame set, including：
Bag of words are established from described image extracting data characteristic, and according to the characteristic；
More than one time to match with the present frame is searched in the first candidate frame set based on the bag of words
Frame is selected, obtains the second candidate frame set.
6. a kind of electronic equipment, which is characterized in that the electronic equipment includes：
First positioning unit, for obtaining the first candidate frame for being positioned to target device using the first localization method
Set；
Second positioning unit meets default item for being got rid of from the first candidate frame set using second of localization method
The candidate frame of part obtains the second candidate frame set；
Determination unit, for using the candidate frame in the second candidate frame set, determining the location information of target device.
7. electronic equipment according to claim 6, which is characterized in that first positioning unit includes：
Image Acquisition subelement, for acquiring the image data within the vision of the target device, as present frame；
Bag of words subelement, for establishing word from described image extracting data characteristic, and according to the characteristic
Bag model；
Subelement is searched, for searching more than one to match with the present frame in the database based on the bag of words
Candidate frame obtains the first candidate frame set.
8. electronic equipment according to claim 7, which is characterized in that second positioning unit includes：
Communicate locator unit, for working as described in acquisition when the current frame, communication positioning method is utilized to obtain the target device
Location information, as the corresponding location information of the present frame；
Subelement is screened, for being based on the corresponding location information of the present frame, is got rid of from the first candidate frame set
It is more than or equal to the candidate frame of predetermined threshold value with the distance of the present frame, obtains the second candidate frame set.
9. electronic equipment according to claim 6, which is characterized in that first positioning unit includes：
Image Acquisition subelement, for acquiring the image data within the vision of the target device, as present frame；
Communicate locator unit, for working as described in acquisition when the current frame, communication positioning method is utilized to obtain the target device
Location information, as the corresponding location information of the present frame；
First searches subelement, for being based on the corresponding location information of the present frame, is searched from database and described current
The distance of frame is less than the candidate frame of predetermined threshold value, obtains the first candidate frame set.
10. electronic equipment according to claim 9, which is characterized in that second positioning unit includes：
Bag of words subelement, for establishing word from described image extracting data characteristic, and according to the characteristic
Bag model；
Second searches subelement, is searched and the present frame for being based on the bag of words in the first candidate frame set
More than one candidate frame to match obtains the second candidate frame set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611248781.1A CN108256543A (en) | 2016-12-29 | 2016-12-29 | A kind of localization method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611248781.1A CN108256543A (en) | 2016-12-29 | 2016-12-29 | A kind of localization method and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108256543A true CN108256543A (en) | 2018-07-06 |
Family
ID=62721623
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611248781.1A Pending CN108256543A (en) | 2016-12-29 | 2016-12-29 | A kind of localization method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108256543A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111447553A (en) * | 2020-03-26 | 2020-07-24 | 云南电网有限责任公司电力科学研究院 | WIFI-based vision enhancement S L AM method and device |
| WO2021147916A1 (en) * | 2020-01-21 | 2021-07-29 | 北京达佳互联信息技术有限公司 | Image search method and apparatus |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103926933A (en) * | 2014-03-29 | 2014-07-16 | 北京航空航天大学 | Indoor simultaneous locating and environment modeling method for unmanned aerial vehicle |
| CN104580858A (en) * | 2014-12-26 | 2015-04-29 | 北京航天控制仪器研究所 | Multi-source imaging load for unmanned aerial vehicle |
| CN104936283A (en) * | 2014-03-21 | 2015-09-23 | 中国电信股份有限公司 | Indoor positioning method, server and system |
| CN105856230A (en) * | 2016-05-06 | 2016-08-17 | 简燕梅 | ORB key frame closed-loop detection SLAM method capable of improving consistency of position and pose of robot |
| CN106092104A (en) * | 2016-08-26 | 2016-11-09 | 深圳微服机器人科技有限公司 | The method for relocating of a kind of Indoor Robot and device |
| CN106153049A (en) * | 2016-08-19 | 2016-11-23 | 北京羲和科技有限公司 | A kind of indoor orientation method and device |
-
2016
- 2016-12-29 CN CN201611248781.1A patent/CN108256543A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104936283A (en) * | 2014-03-21 | 2015-09-23 | 中国电信股份有限公司 | Indoor positioning method, server and system |
| CN103926933A (en) * | 2014-03-29 | 2014-07-16 | 北京航空航天大学 | Indoor simultaneous locating and environment modeling method for unmanned aerial vehicle |
| CN104580858A (en) * | 2014-12-26 | 2015-04-29 | 北京航天控制仪器研究所 | Multi-source imaging load for unmanned aerial vehicle |
| CN105856230A (en) * | 2016-05-06 | 2016-08-17 | 简燕梅 | ORB key frame closed-loop detection SLAM method capable of improving consistency of position and pose of robot |
| CN106153049A (en) * | 2016-08-19 | 2016-11-23 | 北京羲和科技有限公司 | A kind of indoor orientation method and device |
| CN106092104A (en) * | 2016-08-26 | 2016-11-09 | 深圳微服机器人科技有限公司 | The method for relocating of a kind of Indoor Robot and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021147916A1 (en) * | 2020-01-21 | 2021-07-29 | 北京达佳互联信息技术有限公司 | Image search method and apparatus |
| CN113220928A (en) * | 2020-01-21 | 2021-08-06 | 北京达佳互联信息技术有限公司 | Image searching method and device, electronic equipment and storage medium |
| CN113220928B (en) * | 2020-01-21 | 2024-06-11 | 北京达佳互联信息技术有限公司 | Image searching method and device, electronic equipment and storage medium |
| CN111447553A (en) * | 2020-03-26 | 2020-07-24 | 云南电网有限责任公司电力科学研究院 | WIFI-based vision enhancement S L AM method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220075806A1 (en) | Natural language image search | |
| CN107967457B (en) | Site identification and relative positioning method and system adapting to visual characteristic change | |
| CN107430686B (en) | Crowd-sourced creation and updating of area description files for mobile device positioning | |
| EP3295129B1 (en) | Privacy filtering of area description file prior to upload | |
| CN104199906B (en) | A kind of recommendation method and device of shooting area | |
| CN106933867B (en) | Image query method and device | |
| EP3295730A1 (en) | Privacy-sensitive query for localization area description file | |
| CN111581423B (en) | Target retrieval method and device | |
| CN112445929B (en) | Visual positioning method and related device | |
| KR100489890B1 (en) | Apparatus and Method to Provide Stereo Video or/and Detailed Information of Geographic Objects | |
| CN102880854A (en) | Distributed processing and Hash mapping-based outdoor massive object identification method and system | |
| CN111950321A (en) | Gait recognition method and device, computer equipment and storage medium | |
| Morrison et al. | Scalable multirobot localization and mapping with relative maps: Introducing MOARSLAM | |
| CN104520848A (en) | Searching for events by attendants | |
| JP2010118059A (en) | Method, system and computer-readable recording medium for providing image data | |
| KR101307325B1 (en) | System for dual-searching image using region of interest set | |
| CN108256543A (en) | A kind of localization method and electronic equipment | |
| CN103530377A (en) | Scene information searching method based on binary feature codes | |
| CN106996785B (en) | Method and device for updating navigation data | |
| CN116721246A (en) | Continuous frame point cloud rapid labeling method and system | |
| CN112148924A (en) | Luggage case retrieval method and device and electronic equipment | |
| CN104850600A (en) | Method and device for searching images containing faces | |
| CN109597942B (en) | Method, device and equipment for pushing showcase information and storage medium | |
| CN108073668A (en) | Video index establishing method and device applying same | |
| US11500937B1 (en) | Data retrieval system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180706 |