CN109143222A - Based on the three dimensional maneuvering object tracking for sampling particle filter of dividing and ruling - Google Patents
Based on the three dimensional maneuvering object tracking for sampling particle filter of dividing and ruling Download PDFInfo
- Publication number
- CN109143222A CN109143222A CN201810841616.XA CN201810841616A CN109143222A CN 109143222 A CN109143222 A CN 109143222A CN 201810841616 A CN201810841616 A CN 201810841616A CN 109143222 A CN109143222 A CN 109143222A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- subspace
- particle
- state
- target
- 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
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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/66—Radar-tracking systems; Analogous systems
- G01S13/72—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar
- G01S13/723—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar by using numerical data
- G01S13/726—Multiple target tracking
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
It is a kind of based on the three dimensional maneuvering object tracking for sampling particle filter of dividing and ruling, comprising: 1, the current time that sensor is measured by measurement information preprocessing module observe data and carry out coordinate conversion, be transformed into cartesian coordinate system from spherical coordinate system；2, sampling of dividing and ruling is carried out to observation data measured by step 1, is mutually independent one-dimensional subspace by three-dimensional motion spatial decomposition, independent sampling particle in each subspace obtains sample set；3, dimension-reduction treatment target maneuver, the sample set in each one-dimensional subspace decomposed in conjunction with observation data to step 2 carry out particle filter, obtain the sub- state of prediction in the subspace；4, merge the sub- state predicted in the obtained each subspace of step 3, obtain the predicted state of subsequent time target, alleviate because in space particle distribution it is sparse caused by algorithm iteration when particle aggravation degenerate, lead to the reduction of sample diversity, algorithm performance decline, not can guarantee the technical problems such as real-time performance of tracking and tracking accuracy.
Description
Technical field
This disclosure relates to maneuvering target tracking field more particularly to a kind of based on the three-dimensional maneuver for sampling particle filter of dividing and ruling
Method for tracking target.
Background technique
Maneuvering target tracking is a basis in many practical applications such as radar tracking, video monitoring, mobile robot
Property and critical tasks, essence be the continuous state that target is estimated using the discrete measuring value of sensor, mainly include target
The modeling of maneuver modeling, motor-driven detection or motor-driven identification and filtering algorithm.Numerous studies all concentrate on two dimension both at home and abroad at present
Plane, when target three-dimensional space all directions all occur intensity it is inconsistent height it is motor-driven, pass through the extension of two dimensional model and algorithm
Can not the movement of accurate description target, therefore three-dimensional space maneuvering target tracking has become one of difficult point of such problem.
Particle filter carries out approximation to probability density function in the random sample that state space is propagated by finding one group, should
Algorithm does not need to do system any a priori assumption, is suitable for strong nonlinearity non-Gaussian filtering, has good algorithm expansible
Property and universality, often by as the filtering algorithm during maneuvering target tracking.But there are sample degeneracies to ask for particle filter itself
Topic and particle degeneracy phenomenon, and algorithm complexity is largely dependent upon number of particles.
To solve this problem, it is typically based on traditional resampling mechanism and improves particle resampling steps, such as layering resampling, certainly
Adapt to resampling, certainty resampling etc.；Another new developing direction is to optimize thought increase sample by introducing colony intelligence
Diversity, such as genetic algorithm, glowworm swarm algorithm, bat algorithm optimize resampling.Above method is by improving particle resampling
Link can increase sample diversity to a certain extent, reduce sample degeneracy degree.But the maneuvering target in processing three-dimensional space
When tracking problem, since maneuver mode and intensity are inconsistent on target different directions, state space will appear the grain of some regions
Son distribution is sparse, it is difficult to which uniform fold causes particle aggravation when algorithm iteration to degenerate, leads to the reduction of sample diversity.With mesh
It marks motion model complexity to increase, algorithm performance decline becomes apparent, and need to often increase number of particles to guarantee coverage area, transport
Evaluation time is longer, not can guarantee real-time performance of tracking and good tracking accuracy.
Disclosure
(1) technical problems to be solved
Present disclose provides a kind of based on the three dimensional maneuvering object tracking for sampling particle filter of dividing and ruling, existing to alleviate
Particle aggravation is degenerated when technology algorithm iteration as caused by particle distribution Sparse Problems in three-dimensional space, leads to sample diversity
It reduces, becoming apparent for algorithm performance decline not can guarantee the technical problems such as real-time performance of tracking and good tracking accuracy.
(2) technical solution
The disclosure provides a kind of based on the three dimensional maneuvering object tracking for sampling particle filter of dividing and ruling, comprising: step 1:
Data are observed to the current time that sensor measures by measurement information preprocessing module and carry out coordinate conversion, are turned from spherical coordinate system
Change to cartesian coordinate system；Step 2: sampling of dividing and ruling being carried out to observation data measured by step 1, by three-dimensional motion spatial decomposition
For mutually independent one-dimensional subspace, independent sampling particle in each subspace obtains sample set；Step 3: dimension-reduction treatment target
Motor-driven, the sample set in each one-dimensional subspace decomposed in conjunction with observation data to step 2 carries out particle filter, is somebody's turn to do
The sub- state of prediction in subspace；And step 4: merge the sub- state predicted in the obtained each subspace of step 3, obtain down
The predicted state of one moment target.
In the embodiments of the present disclosure, in the step 1 current time data measured by sensor be maneuvering target sight
Measured data, including radial distance, azimuth and pitch angle are denoted as Z=[r, b, e]T, Descartes is converted to by ball coordinate system
Coordinate system obtains the observation data in cartesian coordinate system:
Wherein, r is radial distance, and b is azimuth, and e is pitch angle.
In the embodiments of the present disclosure, the noise of the observation data is denoted as [vr, vb, ve]T, covariance matrix R, through sitting
Observation data noise is [v after the conversion of mark systemx, vy, vz]T, covariance matrix Rc=J (Z) RJ (Z), J (Z) are observation data
Jacobian determinant, expression are as follows:
In the embodiments of the present disclosure, the step 2 specifically includes: being mutually independent one-dimensional by three-dimensional motion spatial decomposition
Subspace, for the state vector of target in three-dimensional motion spaceAccording to fortune
Dynamic orthogonal space independence, the sub- state being classified as in three corresponding one-dimensional subspaces, the respectively direction xThe direction yWith the direction zSampling is selected in each subspace
Policy independence sampling particle, generates one-dimensional subspace particle collection according to known prior probability p (X) Wherein, w is the corresponding weighted value of i-th of certain subspace random particles, and N is that certain son is empty
Between in total number of particles, subscript x, y, z indicate subspace direction.
In the embodiments of the present disclosure, the Sampling Strategies selection Gauss of the subspace independent sampling particle is uniformly distributed, by
Known prior probability p (X) obtains sample averageWith variance P, the equally distributed random sample of Gauss is generatedRandn is with quantity of state with the random numbers of Gaussian distribution of dimension.
In the embodiments of the present disclosure, the step 3 includes: more new particle weight；Resampling is carried out to particle collection；And it is pre-
Survey the sub- state of target.
In the embodiments of the present disclosure, the more new particle weight is the observation model in conjunction with newest observation data and target,
The new weight of particle is calculated according to right value update formula, the direction x one-dimensional subspace:
The output of x director state estimation are as follows:
In the embodiments of the present disclosure, described that resampling is carried out to particle collection, according to particle weight from particle collectionAgain N is extractedxA particleAnd it enablesEstablish new particle collection
In the embodiments of the present disclosure, it predicts the sub- state of target, the subsequent time side x is predicted according to the state equation of target movement
To the sub- state of targetWherein the direction y and z direction operation step similarly, respectively obtain sub- state
In the embodiments of the present disclosure, in the step 4, merge the sub- state predicted in each subspace, obtain subsequent time
The predicted state of target obtains overall status estimated value according to the sub- state estimation of each subspace
(3) beneficial effect
It can be seen from the above technical proposal that the disclosure is based on the three dimensional maneuvering object track side for sampling particle filter that divides and rules
Method at least has the advantages that one of them or in which a part:
(1) it can largely increase sample diversity, it is deficient to reduce sample degeneracy problem and particle in particle filter algorithm
Weary phenomenon bring influences.
(2) the sample coverage rate in state space is promoted, algorithm complexity is reduced.
(3) operation time is saved while improving tracking accuracy, guarantees the real-time and accuracy of target following.
Detailed description of the invention
Fig. 1 is the embodiment of the present disclosure based on the three dimensional maneuvering object tracking process signal for sampling particle filter of dividing and ruling
Figure.
Fig. 2 is that the embodiment of the present disclosure is shown based on the three dimensional maneuvering object tracking process frame for sampling particle filter of dividing and ruling
It is intended to.
Specific embodiment
Present disclose provides a kind of based on the three dimensional maneuvering object tracking for sampling particle filter of dividing and ruling, the three-dimensional machine
Tracking of maneuvering target method replaces general sampling with sampling of dividing and ruling, and can largely increase sample diversity, reduces particle filter
Sample degeneracy problem and particle degeneracy phenomenon bring influence in algorithm, promote the sample coverage rate in state space, reduce and calculate
Method complexity saves operation time while improving tracking accuracy, guarantees the real-time and accuracy of target following.
For the purposes, technical schemes and advantages of the disclosure are more clearly understood, below in conjunction with specific embodiment, and reference
The disclosure is further described in attached drawing.
Fig. 1 be it is described based on the three dimensional maneuvering object tracking flow diagram for sampling particle filter of dividing and ruling, Fig. 2 is
The embodiment of the present disclosure is based on the three dimensional maneuvering object tracking process block schematic illustration for sampling particle filter of dividing and ruling.In conjunction with Fig. 1
With shown in Fig. 2, it is described based on the three dimensional maneuvering object tracking flow diagram for sampling particle filter of dividing and ruling including as follows
Step:
Step 1: coordinate conversion being carried out to the current time data that sensor measures, Descartes is transformed into from spherical coordinate system and sits
Mark system；
Step 2, sampling of dividing and ruling is carried out to sample point, is mutually independent one-dimensional subspace by three-dimensional motion spatial decomposition,
Independent sampling particle in each subspace obtains sample set；
Step 3, dimension-reduction treatment target maneuver, in each one-dimensional subspace decomposed in conjunction with measurement information to step 2
Sample set carries out particle filter, obtains the sub- state of prediction in the subspace；
Step 4, merge the sub- state predicted in the obtained each subspace of step 3, obtain the prediction of subsequent time target
State.
In the step 1, increase measurement information preprocessing module before being filtered tracking operation, this is because practical application
In, the metric data of maneuvering target is obtained by sensor measurements such as radars, and obtained metric data is based on spherical coordinates more, including
Radial distance r, azimuth b and pitch angle e etc., the observation data based on spherical coordinates have it is very strong non-linear, for convenient for subsequent
Divide and rule sampling and dimension-reduction treatment operation, be converted into based on cartesian coordinate system, i.e. the observation data of rectangular coordinate system.
Target observation data, including radial distance r, azimuth b and pitch angle e are measured by sensor, be denoted as Z=[r, b,
e]T.Assuming that there are coordinate transforms between Two coordinate systemWherein h=[hr, hb, he]T, when the value of known system observation data
It is denoted as Z=[r, b, e]T, it can be deduced that the value of the observation data in cartesian coordinate system:
Former observation noise [vr, vb, ve]T, covariance matrix R, observation noise is [v after coordinate system is convertedx, vy, vz]T,
Covariance matrix Rc=J (Z) RJ (Z), J (Z) are the Jacobian determinant of observed quantity, expression are as follows:
In the step 2, the spatial coverage to guarantee sample point is wide enough, using the method for sampling of dividing and ruling, this method master
Wanting thought is that system mode three-dimensional motion space is divided into several independent one-dimensional subspaces, and every sub-spaces are used respectively best
Policy independence sample particle, concrete operations are as follows:
It is mutually independent one-dimensional subspace by three-dimensional motion spatial decomposition, for the state of target in three-dimensional motion space
VectorAccording to space Orthogonal independence, it is one-dimensional to be classified as three correspondences
Sub- state in subspace, the respectively direction xThe direction yWith the direction z
Sampling policy independent sampling particle is selected in each subspace, and one-dimensional subspace is generated according to known prior probability p (X)
Particle collection
Wherein, w is the corresponding weighted value of i-th of certain subspace random particles, and N is the total number of particles in certain subspace, under
Marking x, y, z indicates subspace direction；
When k=0, subspace is decomposed according to state space independence, by prior probability p (X0) generate one-dimensional subspace particle
Collection
The Sampling Strategies selection Gauss of the subspace independent sampling particle is uniformly distributed, and is obtained by known prior probability p (X)
To sample averageWith variance P, the equally distributed random sample of Gauss is generatedRandn is with quantity of state with the random numbers of Gaussian distribution of dimension.
In the step 3, dimension-reduction treatment target maneuver, in conjunction with measurement information to the sample set in each one-dimensional subspace
Particle filter is carried out, the sub- state of prediction in the subspace is obtained, specifically includes:
More new particle weight is calculated in conjunction with the observation model of newest observed data value and target according to right value update formula
The new weight of particle, by taking the one-dimensional subspace of the direction x as an example:
The output of x director state estimation:
Resampling, the preferably big particle of weight are carried out to particle collection, retain a part of small weight particle.According to particle weight
From particle collectionAgain N is extractedxA particleAnd it enablesEstablish new particle collection
The sub- state of target is predicted, according to the sub- state of target in the state equation prediction direction subsequent time x of target movement
The direction y and z direction operation step similarly, execute step 3 respectively and obtain sub- state
In the step 4, merge the sub- state predicted in each subspace, obtain the predicted state of subsequent time target, has
Gymnastics conduct: overall status estimated value is obtained according to each sub- state estimation
After executing the step 4, moment k=k+1 returns again to step 1, carries out subsequent cycle.
So far, attached drawing is had been combined the embodiment of the present disclosure is described in detail.It should be noted that in attached drawing or saying
In bright book text, the implementation for not being painted or describing is form known to a person of ordinary skill in the art in technical field, and
It is not described in detail.In addition, the above-mentioned definition to each element and method be not limited in mentioning in embodiment it is various specific
Structure, shape or mode, those of ordinary skill in the art simply can be changed or be replaced to it, such as:
(1) metric data can be replaced observation data.
According to above description, those skilled in the art should be to the disclosure based on the three-dimensional maneuver for sampling particle filter of dividing and ruling
Method for tracking target has clear understanding.
In conclusion present disclose provides a kind of based on the three dimensional maneuvering object tracking for sampling particle filter of dividing and ruling,
The three dimensional maneuvering object tracking replaces general sampling with sampling of dividing and ruling, and can largely increase sample diversity, drops
Sample degeneracy problem and particle degeneracy phenomenon bring influence in low particle filter algorithm, promote the sample covering in state space
Rate, reduce algorithm complexity, save operation time while improving tracking accuracy, guarantee target following real-time and accurately
Property.
It should also be noted that, the direction term mentioned in embodiment, for example, "upper", "lower", "front", "rear", " left side ",
" right side " etc. is only the direction with reference to attached drawing, not is used to limit the protection scope of the disclosure.Through attached drawing, identical element by
Same or similar appended drawing reference indicates.When may cause understanding of this disclosure and cause to obscure, conventional structure will be omitted
Or construction.
And the shape and size of each component do not reflect actual size and ratio in figure, and only illustrate the embodiment of the present disclosure
Content.In addition, in the claims, any reference symbol between parentheses should not be configured to the limit to claim
System.
It unless there are known entitled phase otherwise anticipates, the numerical parameter in this specification and appended claims is approximation, energy
Enough bases pass through the resulting required characteristic changing of content of this disclosure.Specifically, all be used in specification and claim
The middle content for indicating composition, the number of reaction condition etc., it is thus understood that repaired by the term of " about " in all situations
Decorations.Under normal circumstances, the meaning expressed refers to include by specific quantity ± 10% variation in some embodiments, some
± 5% variation in embodiment, ± 1% variation in some embodiments, in some embodiments ± 0.5% variation.
Furthermore word "comprising" does not exclude the presence of element or step not listed in the claims.It is located in front of the element
Word "a" or "an" does not exclude the presence of multiple such elements.
The word of ordinal number such as " first ", " second ", " third " etc. used in specification and claim, with modification
Corresponding element, itself is not meant to that the element has any ordinal number, does not also represent the suitable of a certain element and another element
Sequence in sequence or manufacturing method, the use of those ordinal numbers are only used to enable an element and another tool with certain name
Clear differentiation can be made by having the element of identical name.
In addition, unless specifically described or the step of must sequentially occur, there is no restriction in the above institute for the sequence of above-mentioned steps
Column, and can change or rearrange according to required design.And above-described embodiment can be based on the considerations of design and reliability, that
This mix and match is used using or with other embodiments mix and match, i.e., the technical characteristic in different embodiments can be freely combined
Form more embodiments.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.Also, in the unit claims listing several devices, several in these devices can be by same hard
Part item embodies.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of each open aspect,
Above in the description of the exemplary embodiment of the disclosure, each feature of the disclosure is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
The disclosure of shield requires features more more than feature expressly recited in each claim.More precisely, as following
Claims reflect as, open aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as the separate embodiments of the disclosure.
Particular embodiments described above has carried out further in detail the purpose of the disclosure, technical scheme and beneficial effects
Describe in detail it is bright, it is all it should be understood that be not limited to the disclosure the foregoing is merely the specific embodiment of the disclosure
Within the spirit and principle of the disclosure, any modification, equivalent substitution, improvement and etc. done should be included in the guarantor of the disclosure
Within the scope of shield.
Claims (10)
1. a kind of based on the three dimensional maneuvering object tracking for sampling particle filter of dividing and ruling, comprising:
Step 1: data are observed to the current time that sensor measures by measurement information preprocessing module and carry out coordinate conversion, from
Spherical coordinate system is transformed into cartesian coordinate system；
Step 2: sampling of dividing and ruling being carried out to observation data measured by step 1, is mutually independent by three-dimensional motion spatial decomposition
One-dimensional subspace, independent sampling particle in each subspace obtain sample set；
Step 3: dimension-reduction treatment target maneuver, the sample in each one-dimensional subspace that step 2 is decomposed in conjunction with observation data
Subset carries out particle filter, obtains the sub- state of prediction in the subspace；And
Step 4: merging the sub- state predicted in the obtained each subspace of step 3, obtain the predicted state of subsequent time target.
2. three dimensional maneuvering object tracking according to claim 1, wherein current measured by sensor in step 1
Time data is the observation data of maneuvering target, including radial distance, azimuth and pitch angle, is denoted as Z=[r, b, e]T,
Cartesian coordinate system is converted to by ball coordinate system, obtains the observation data in cartesian coordinate system:
Wherein, r is radial distance, and b is azimuth, and e is pitch angle.
3. three dimensional maneuvering object tracking according to claim 1, wherein the noise of the observation data is denoted as [vr,
vb, ve]T, covariance matrix R, it is [v that data noise is observed after coordinate system is convertedx, vy, vz]T, covariance matrix Rc=J
(Z) RJ (Z), J (Z) are the Jacobian determinant for observing data, expression are as follows:
4. three dimensional maneuvering object tracking according to claim 1, wherein the step 2 specifically includes:
It is mutually independent one-dimensional subspace by three-dimensional motion spatial decomposition, for the state vector of target in three-dimensional motion spaceAccording to space Orthogonal independence, it is classified as three one-dimensional sons of correspondence
Sub- state in space, the respectively direction xThe direction yWith the direction zSampling policy independent sampling particle is selected in each subspace, generates one according to known prior probability p (X)
N-dimensional subspace n particle collection Wherein, w is certain subspace i-th at random
The corresponding weighted value of particle, N are the total number of particles in certain subspace, and subscript x, y, z indicates subspace direction.
5. three dimensional maneuvering object tracking according to claim 4, the Sampling Strategies of the subspace independent sampling particle
Selection Gauss is uniformly distributed, and obtains sample average by known prior probability p (X)With variance P, generate Gauss it is equally distributed with
Press proof sheetRandn be with quantity of state with dimension Gaussian Profile with
Machine number.
6. three dimensional maneuvering object tracking according to claim 1, wherein the step 3 includes: more new particle power
Value；Resampling is carried out to particle collection；And the prediction sub- state of target.
7. three dimensional maneuvering object tracking according to claim 6, wherein the more new particle weight is to combine most
The observation model of new observation data and target calculates the new weight of particle according to right value update formula, the direction x one-dimensional subspace:
The output of x director state estimation are as follows:
8. three dimensional maneuvering object tracking according to claim 6, wherein described to carry out resampling, root to particle collection
According to particle weight from particle collectionAgain N is extractedxA particleAnd it enablesIt establishes
New particle collection
9. three dimensional maneuvering object tracking according to claim 6, wherein the sub- state of the prediction target, according to mesh
The sub- state of target in the state equation prediction direction subsequent time x of mark movementWherein the direction y and z direction operation step are same
Reason, respectively obtains sub- state
10. three dimensional maneuvering object tracking according to claim 1, wherein in the step 4, merge each subspace
The sub- state of middle prediction, obtains the predicted state of subsequent time target, obtains totality according to the sub- state estimation of each subspace
State estimation
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810841616.XA CN109143222B (en) | 2018-07-27 | 2018-07-27 | Three-dimensional maneuvering target tracking method based on divide-and-conquer sampling particle filtering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810841616.XA CN109143222B (en) | 2018-07-27 | 2018-07-27 | Three-dimensional maneuvering target tracking method based on divide-and-conquer sampling particle filtering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109143222A true CN109143222A (en) | 2019-01-04 |
| CN109143222B CN109143222B (en) | 2023-04-25 |
Family
ID=64798198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810841616.XA Active CN109143222B (en) | 2018-07-27 | 2018-07-27 | Three-dimensional maneuvering target tracking method based on divide-and-conquer sampling particle filtering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109143222B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115496924A (en) * | 2022-09-29 | 2022-12-20 | 北京瑞莱智慧科技有限公司 | Data processing method, related equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101055563A (en) * | 2007-05-21 | 2007-10-17 | 北京理工大学 | Particle filter method based on multiple advice distribution |
| WO2008008046A1 (en) * | 2006-07-11 | 2008-01-17 | Agency For Science, Technology And Research | Method and system for multi-object tracking |
| CN101701826A (en) * | 2009-11-20 | 2010-05-05 | 西安电子科技大学 | Target tracking method of passive multi-sensor based on layered particle filtering |
| CN104035083A (en) * | 2014-06-20 | 2014-09-10 | 电子科技大学 | Radar target tracking method based on measurement conversion |
| US20160316325A1 (en) * | 2015-04-24 | 2016-10-27 | Mojix, Inc. | Location Based Services for RFID and Sensor Networks |
| CN107609451A (en) * | 2017-09-14 | 2018-01-19 | 斯坦德机器人（深圳）有限公司 | A kind of high-precision vision localization method and system based on Quick Response Code |
-
2018
- 2018-07-27 CN CN201810841616.XA patent/CN109143222B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008008046A1 (en) * | 2006-07-11 | 2008-01-17 | Agency For Science, Technology And Research | Method and system for multi-object tracking |
| CN101055563A (en) * | 2007-05-21 | 2007-10-17 | 北京理工大学 | Particle filter method based on multiple advice distribution |
| CN101701826A (en) * | 2009-11-20 | 2010-05-05 | 西安电子科技大学 | Target tracking method of passive multi-sensor based on layered particle filtering |
| CN104035083A (en) * | 2014-06-20 | 2014-09-10 | 电子科技大学 | Radar target tracking method based on measurement conversion |
| US20160316325A1 (en) * | 2015-04-24 | 2016-10-27 | Mojix, Inc. | Location Based Services for RFID and Sensor Networks |
| CN107609451A (en) * | 2017-09-14 | 2018-01-19 | 斯坦德机器人（深圳）有限公司 | A kind of high-precision vision localization method and system based on Quick Response Code |
Non-Patent Citations (3)
| Title |
|---|
| STEFAN DUFFNER 等: "Dynamic Partitioned Sampling For Tracking", 《PROCEEDING OF THE BRITISH MACHINE VISON CONFERENCE》 * |
| 刘晨光: "基于单目视频无标记点的三维人体姿态估计的研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
| 苗彬 等: "蚁群优化粒子滤波视觉跟踪算法", 《烟台大学学报(自然科学与工程版)》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115496924A (en) * | 2022-09-29 | 2022-12-20 | 北京瑞莱智慧科技有限公司 | Data processing method, related equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109143222B (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110497373B (en) | Joint calibration method between three-dimensional laser radar and mechanical arm of mobile robot | |
| Shareef et al. | Localization using neural networks in wireless sensor networks | |
| CN104299247B (en) | A kind of video target tracking method based on adaptive measuring matrix | |
| CN107576949B (en) | SVDD radar target one-dimensional range profile identification method based on density weight and mixed kernel function | |
| CN106125087A (en) | Dancing Robot indoor based on laser radar pedestrian tracting method | |
| CN105652255B (en) | The spatial registration method of Radar Network System | |
| CN108254727A (en) | A kind of radar plot condensing method based on Contour extraction | |
| CN110309010B (en) | Partial discharge network training method and device for phase resolution of power equipment | |
| CN116050136B (en) | Method, device and equipment for generating intelligent ship test scene library | |
| CN108225332B (en) | Indoor positioning fingerprint map dimension reduction method based on supervision | |
| CN109799535A (en) | A kind of filtering method of full tensor magnetic gradient detection and localization data | |
| CN109540040B (en) | Active vision detection system and method based on unconstrained concentric beam family automobile morphology | |
| CN109143222A (en) | Based on the three dimensional maneuvering object tracking for sampling particle filter of dividing and ruling | |
| Chen et al. | An intelligent vision recognition method based on deep learning for pointer meters | |
| CN112612275A (en) | Complex path planning system and method for database machine room | |
| CN114092545A (en) | Self-adaptive grid searching method suitable for spherical target fitting | |
| Zhuang et al. | Lyrn (lyapunov reaching network): A real-time closed loop approach from monocular vision | |
| Hanlon et al. | Active Visual Localization for Multi-Agent Collaboration: A Data-Driven Approach | |
| CN109579828B (en) | Positioning system based on arc magnetic field sensor array and use method thereof | |
| Kong et al. | Research on the Bolt Positioning System Based on Multieye Vision Industrial Robots | |
| Tsyganov et al. | Adaptive eetimation of a moving object trajectory using sequential hypothesis testing | |
| CN113177969A (en) | Point cloud single-target tracking method of candidate seeds based on motion direction change | |
| CN112465874B (en) | Crane lifting appliance guiding and positioning method and system based on image sensing | |
| Hou et al. | Frontier-based exploration on continuous radial basis function neural network map | |
| Huang et al. | Minimum zone sphericity evaluation based on a modified cuckoo search algorithm with fuzzy logic |
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 |