CN106597367B - The fingerprint image searching method of steepest descending manner in a kind of fingerprint location - Google Patents
The fingerprint image searching method of steepest descending manner in a kind of fingerprint location Download PDFInfo
- Publication number
- CN106597367B CN106597367B CN201611061233.8A CN201611061233A CN106597367B CN 106597367 B CN106597367 B CN 106597367B CN 201611061233 A CN201611061233 A CN 201611061233A CN 106597367 B CN106597367 B CN 106597367B
- Authority
- CN
- China
- Prior art keywords
- search
- reference point
- euclidean distance
- fingerprint
- fingerprint 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0252—Radio frequency fingerprinting
Abstract
The invention belongs to radionavigation field of locating technology, a kind of fingerprint image searching method of steepest descending manner in fingerprint location is provided.The present invention is by gradually determining search center and searching for the neighbouring reference point RP in its periphery;Every one circle of search, then record this and enclose the Euclidean distance in all RP between the signal characteristic TP of user's actual measurement, using the smallest RP of Euclidean distance as the central point of next circle search.K RP nearest away from TP in signal space Euclidean distance is constantly updated in every layer of search process.When continuous search L times and K RP does not change, then assert that this K RP is finally to select, for the reference point of location estimation, and bring into KNN algorithm and resolved, instead of traditional method for carrying out sequential search to fingerprint image.The invention has the advantages that the available promotion of positioning accuracy, compared with the conventional method of not sub-clustering, search speed is faster compared with the conventional method positioned after sub-clustering.
Description
Technical field
The invention belongs to radionavigation field of locating technology, are related to fingerprint location technology, are related specifically to a kind of finger
The fingerprint image searching method of steepest descending manner in line positioning.
Background technique
Fingerprint location technology refers in by localization region, by the means of point-to-point measurement, by physical spatial location and letter
Mapping relations are established between number space characteristics, user can estimate self-position by comparing the mapping relations.Physical space position
It sets the mapping relations established between signal space feature generally to store by way of database, which is referred to as fingerprint
Figure;Fingerprint image is made of several reference points (RP), its physical location and signal characteristic vector are stored in each RP.
It is empty that RP all in the signal characteristic (TP) and fingerprint image of itself measurement is carried out signal in position fixing process by user
Between Euclidean distance calculating, investigate the similarity between the two, and record K nearest RP of the Euclidean distance between TP.Pass through this K
The position of a RP can make estimation to the position of user, i.e., positioned by KNN algorithm.
It is signal characteristic (TP) the most similar reference point (RP) for searching out K with user's actual measurement in fingerprint location, refers to
Line location algorithm needs are traversed on whole fingerprint image, calculate the Euclidean distance between all RP and TP, i.e., in fingerprint location
Often face that fingerprint image is excessive, positioning real-time bad problem excessive so as to cause the volumes of searches positioned every time.To accelerate to be somebody's turn to do
Process, conventional solution are the search work amounts in order to reduce system to fingerprint image, carry out sub-clustering to fingerprint image.User exists
The progress Euclidean distance operation between cluster head (can be considered a signal characteristic vector for characterizing entire cluster) is first passed through before specific positioning,
The cluster locating for itself is found out, and carries out traversal search on the fingerprint image of the cluster to position.Thus then by the search work of fingerprint image
Make classification to carry out, reduces volumes of searches.
But there are inborn contradictory problems for the method for sub-clustering, sub-clustering can then lose the meaning of sub-clustering too much, if sub-clustering is too
RP at least each cluster is still very much, does not have the effect for reducing volumes of searches equally.On the other hand, when the position of user is in
When the edge of cluster, since all RP are all located at certain side of user location, then position error can be introduced.Even if being drawn in advance when sub-clustering
Crossover region can not avoid this situation completely out.In addition, if occurring to will lead to biggish positioning mistake if cluster head identification mistake
Difference.Current sub-clustering means include the artificial sub-clustering of Subjective progress according to designer, and are carried out certainly according to mathematical algorithm
Dynamic sub-clustering.The former is likely to occur the disunity in cluster on signal characteristic domain, and the latter may cause not uniting on locational space domain
One.Therefore the two is likely to introduce error when cluster head identifies, to reduce positioning accuracy.
Summary of the invention
For, since sub-clustering brings accuracy decline problem, the present invention provides one kind more present in existing fingerprint location technology
Add the method for efficient fingerprint graph search.
The technical solution of the present invention is as follows:
The fingerprint image searching method of steepest descending manner in a kind of fingerprint location, which is gradually determining search
Suo Zhongxin simultaneously searches for the neighbouring reference point RP in its periphery.It is every search one circle, then record in all reference point RP of this circle with user
Euclidean distance between the signal characteristic TP of actual measurement, using the smallest reference point RP of Euclidean distance as the central point of next circle search.
First search center can be obtained by the predicted value of previous positioning result or filtering algorithm, in search process, according to RP with
Euclidean distance between TP constantly updates search center.In every layer of search process constantly update signal space Euclidean distance on away from TP most
K close RP.When continuous search L times and K RP does not change, then assert that this K RP is finally to select, estimate for position
The reference point of meter, and bring into KNN algorithm and resolved.
The present invention specifically includes the following steps:
Step 1: preset search upper limit L first;The center reference point RP searched for for the first time is calculated according to prior information(a, b);
Step 2: calculating RP(a, b)Euclidean distance between the signal characteristic TP of user's actual measurement, enables search counter Nc=0,
Set A=0;
Step 3: with RP(a, b)Centered on, search for reference point RP existing for its periphery, calculate respectively each reference point RP with
Signal space Euclidean distance between TP;
Step 4: K reference point RP nearest away from TP in signal space Euclidean distance in recording step 3 updates set A;
Step 5: with signal space Euclidean distance in set A and TP nearest RP for new search center reference point RP
’(a, b);
Step 6: whether two groups of set A of observation change: if changing, return step 3, Nc=0;If not changing,
Then Nc=Nc+ 1, and judge the size relation of Nc Yu preset search upper limit L, if NcNot less than L, then 7 are entered step, if NcIt is less than
L, then return step 3;
Step 7: the position of K reference point in set A being brought into KNN algorithm and is positioned, this positioning knot is obtained
Fruit (Xi, Yi);All steps are repeated, are positioned next time.
The invention has the advantages that improving fingerprint location system compared with the conventional method positioned after sub-clustering
The positioning accuracy of system, and faster than the traditional algorithm search speed of not sub-clustering.
Detailed description of the invention
Fig. 1 is work flow diagram of the present invention.
Fig. 2 is the positioning accuracy simulation result diagram of simulating, verifying.
Specific embodiment
A specific embodiment of the invention is described in detail below in conjunction with technical solution (and attached drawing).
Input/output variable of the present invention is respectively as follows:
Input: fingerprint image reference point signal characteristic database;Fingerprint image reference point spatial position data library;The signal of TP is special
Sign;The k value of KNN algorithm;The X-coordinate of previous positioning result;The Y coordinate of previous positioning result;Search for upper limit L.
Output: positioning result;The reference point number searched for.
In specific implementation the present invention the following steps are included:
Embodiment 1:
Step 1: preset search upper limit L=1 first;The center reference point RP searched for for the first time is calculated according to prior information(a, b);
Step 2: calculating RP(a, b)Euclidean distance between the signal characteristic TP of user's actual measurement, enables search counter Nc=0,
Set A=0;
Step 3: with RP(a, b)Centered on, search for reference point RP existing for its periphery, calculate respectively each reference point RP with
Signal space Euclidean distance between TP;
Step 4: 4 reference points RP, 4 reference point RP nearest away from TP in signal space Euclidean distance in recording step 3
For updating set A;
Step 5: with signal space Euclidean distance in set A and TP nearest RP for new search center reference point RP
’(a, b);
Step 6: whether two groups of set A of observation change: if changing, return step 3, Nc=0;If not changing,
Then Nc=Nc+ 1, and judge the size relation of Nc Yu preset search upper limit L, if NcNot less than L, then 7 are entered step, if NcIt is less than
L, then return step 3;
Step 7: the position of 4 reference points in set A being brought into KNN algorithm and is positioned, this positioning knot is obtained
Fruit (Xi, Yi);All steps are repeated, are positioned next time.
Embodiment 2:
It is 4 that preset search upper limit L, which is 5, K value, in the present embodiment, and other steps are same as Example 1.
Embodiment 3:
It is 4 that preset search upper limit L, which is 10, K value, in the present embodiment, and other steps are same as Example 1.
Fig. 2 is conventional fingerprint localization method and the positioning accuracy simulation result diagram obtained using localization method of the present invention, table 1
For the locating speed simulation result of simulating, verifying.From figure 2 it can be seen that the positioning accuracy after sub-clustering is minimum, variance is maximum;
And positioning accuracy of the invention is then suitable with the conventional method of not sub-clustering.When one-parameter selection is reasonable when L=5 () in such as figure,
Positioning accuracy of the invention is even higher than the conventional fingerprint location algorithm of not sub-clustering.Since the speed of fingerprint location is mainly by each
The quantity for the reference point for needing to search in positioning determines, from table 1 it follows that the searching for reference point quantity of cluster-dividing method is most
It is few, but combine the simulation result in Fig. 2 it is found that its positioning accuracy is minimum.Again it can be seen that reference point of the invention in table 1
Number of searches is lower than the conventional fingerprint positioning means of not sub-clustering, that is, locating speed is higher, and combines the analysis in Fig. 2, this hair
Bright positioning accuracy is higher.
Table 1 is the locating speed simulation result of simulating, verifying
Claims (1)
1. the fingerprint image searching method of steepest descending manner in a kind of fingerprint location, it is characterised in that following steps:
Step 1: preset search upper limit L first;The center reference point RP searched for for the first time is calculated according to prior information(a, b);
Step 2: calculating RP(a, b)Euclidean distance between the signal characteristic TP of user's actual measurement, enables search counter Nc=0, set A
=0;
Step 3: with RP(a, b)Centered on, search for reference point RP existing for its periphery, calculate respectively each reference point RP and TP it
Between signal space Euclidean distance;
Step 4: K reference point RP nearest away from TP in signal space Euclidean distance in recording step 3 updates set A;
Step 5: with signal space Euclidean distance in set A and TP nearest RP for new search center reference point RP '(a, b);
Step 6: whether two groups of set A of observation change: if changing, return step 3, Nc=0;If not changing, Nc=
Nc+ 1, and judge the size relation of Nc Yu preset search upper limit L, if NcNot less than L, then 7 are entered step, if NcLess than L, then return
Return step 3;
Step 7: the position of K reference point in set A being brought into KNN algorithm and is positioned, this positioning result (X is obtainedi,
Yi);All steps are repeated, are positioned next time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611061233.8A CN106597367B (en) | 2016-11-25 | 2016-11-25 | The fingerprint image searching method of steepest descending manner in a kind of fingerprint location |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611061233.8A CN106597367B (en) | 2016-11-25 | 2016-11-25 | The fingerprint image searching method of steepest descending manner in a kind of fingerprint location |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106597367A CN106597367A (en) | 2017-04-26 |
CN106597367B true CN106597367B (en) | 2019-02-01 |
Family
ID=58594759
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611061233.8A Active CN106597367B (en) | 2016-11-25 | 2016-11-25 | The fingerprint image searching method of steepest descending manner in a kind of fingerprint location |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106597367B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102427603A (en) * | 2012-01-13 | 2012-04-25 | 哈尔滨工业大学 | Positioning method of WLAN (Wireless Local Area Network) indoor mobile user based on positioning error estimation |
KR20120048355A (en) * | 2010-11-05 | 2012-05-15 | 목포대학교산학협력단 | Knn/pcm hybrid mehod for indoor location determination in waln |
CN103596267A (en) * | 2013-11-29 | 2014-02-19 | 哈尔滨工业大学 | Fingerprint map matching method based on Euclidean distances |
CN105424030A (en) * | 2015-11-24 | 2016-03-23 | 东南大学 | Fusion navigation device and method based on wireless fingerprints and MEMS sensor |
-
2016
- 2016-11-25 CN CN201611061233.8A patent/CN106597367B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120048355A (en) * | 2010-11-05 | 2012-05-15 | 목포대학교산학협력단 | Knn/pcm hybrid mehod for indoor location determination in waln |
CN102427603A (en) * | 2012-01-13 | 2012-04-25 | 哈尔滨工业大学 | Positioning method of WLAN (Wireless Local Area Network) indoor mobile user based on positioning error estimation |
CN103596267A (en) * | 2013-11-29 | 2014-02-19 | 哈尔滨工业大学 | Fingerprint map matching method based on Euclidean distances |
CN105424030A (en) * | 2015-11-24 | 2016-03-23 | 东南大学 | Fusion navigation device and method based on wireless fingerprints and MEMS sensor |
Non-Patent Citations (2)
Title |
---|
A Testbed of Performance Evaluation for Fingerprint Based WLAN Positioning System;wanlong zhao;《KSII Transactions on Internet and Information Systems》;20160630;第2583-2605页 |
基于K临近法和脊线追踪的指纹匹配算法;于明等;《吉林大学学报(工学版)》;20141130;第44卷(第6期);第1806-1810页 |
Also Published As
Publication number | Publication date |
---|---|
CN106597367A (en) | 2017-04-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109886998A (en) | Multi-object tracking method, device, computer installation and computer storage medium | |
US20140010407A1 (en) | Image-based localization | |
CN109766436A (en) | A kind of matched method and apparatus of data element of the field and knowledge base of tables of data | |
CN105493078B (en) | Colored sketches picture search | |
WO2019080411A1 (en) | Electrical apparatus, facial image clustering search method, and computer readable storage medium | |
JP2016529611A (en) | Method and system for retrieving images | |
Keselman et al. | Many-to-many graph matching via metric embedding | |
CN109325538A (en) | Object detection method, device and computer readable storage medium | |
EP4209959A1 (en) | Target identification method and apparatus, and electronic device | |
CN113344019A (en) | K-means algorithm for improving decision value selection initial clustering center | |
Bastani et al. | Machine-assisted map editing | |
CN105069431A (en) | Method and device for positioning human face | |
CN110796135A (en) | Target positioning method and device, computer equipment and computer storage medium | |
CN111611936B (en) | Automatic identification system for similar vector diagrams in CAD drawings | |
US8495054B2 (en) | Logic diagram search device | |
CN111611935B (en) | Automatic identification method for similar vector diagrams in CAD drawing | |
CN106597367B (en) | The fingerprint image searching method of steepest descending manner in a kind of fingerprint location | |
CN106792509B (en) | A kind of diffusion type fingerprint image searching method in fingerprint location | |
JP7324050B2 (en) | Waveform segmentation device and waveform segmentation method | |
CN106792510B (en) | A kind of prediction type fingerprint image searching method in fingerprint location | |
CN111368674B (en) | Image recognition method and device | |
US11366833B2 (en) | Augmenting project data with searchable metadata for facilitating project queries | |
CN111104922A (en) | Feature matching algorithm based on ordered sampling | |
CN106776505B (en) | Method for comparing standard cell library by calculating characteristic value | |
US20230289617A1 (en) | Method and apparatus for learning graph representation for out-of-distribution generalization, device and storage medium |
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 |