CN102706345A - Maneuvering target tracking method based on fading memory sequential detector - Google Patents
Maneuvering target tracking method based on fading memory sequential detector Download PDFInfo
- Publication number
- CN102706345A CN102706345A CN2012101900658A CN201210190065A CN102706345A CN 102706345 A CN102706345 A CN 102706345A CN 2012101900658 A CN2012101900658 A CN 2012101900658A CN 201210190065 A CN201210190065 A CN 201210190065A CN 102706345 A CN102706345 A CN 102706345A
- Authority
- CN
- China
- Prior art keywords
- maneuver
- state
- maneuvering
- target
- memory sequential
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000005562 fading Methods 0.000 title abstract 4
- 238000001914 filtration Methods 0.000 claims abstract description 30
- 239000011159 matrix material Substances 0.000 claims abstract description 14
- 238000001514 detection method Methods 0.000 claims description 27
- 230000008569 process Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 9
- 230000009965 odorless effect Effects 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 5
- 230000009967 tasteless effect Effects 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 2
- 238000012937 correction Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Landscapes
- Feedback Control In General (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a maneuvering target tracking method based on a fading memory sequential detector. Aiming at advantages and disadvantages of a decision-based single-model tracking method and a multi-model tracking method, the invention provides the maneuvering target tracking method based on the fading memory sequential detector. The method comprises the following steps of: performing Kalman filter-unscented Kalman filter (KF-UKF) combined filtration, wherein Kalman filtration based on a uniform model is adopted for a non-maneuvering target; when a maneuvering target is detected, expanding the dimension of a coefficient of variation (CV) model, and performing state estimation by adopting an unscented Kalman filter (UKF); detecting maneuvering by using the fading memory sequential detector; and after the maneuvering is detected, correcting a dimension expanded state vector and a covariance matrix, so that the matched state is matched with the actual moving mode. By the method, the state of the target can be corrected in real time, and matched filters can be selected according to different moving modes, so that the tracking precision is improved.
Description
Technical Field
The invention belongs to the field of maneuvering detection and maneuvering target tracking, and relates to a maneuvering target tracking method based on an attenuation memory sequential detector.
Background
In recent years, maneuvering target tracking is widely applied in civil and military fields such as Air Traffic Control (ATC), ground investigation and monitoring, homing guidance and the like. The difficulty in maneuvering target tracking arises primarily from uncertainty in target motion and state observations. The uncertainty of observation refers to the uncertainty of the target identity, and belongs to the category of multi-target tracking; the uncertainty of the target motion mainly refers to the uncertainty of a target motion model, and mainly comprises the following steps: unknown maneuvering input and process noise statistical characteristics, which cause the mismatch of a tracking model and a target motion mode, cause the reduction of tracking performance, and in severe cases, cause the filtering divergence.
Currently, various maneuvering target tracking researches are developed around uncertainty of target maneuvering, and a decision-based single model method and a multi-model method become two main maneuvering target tracking methods.
Since the maneuvering target motion pattern is usually represented by a model, the target motion pattern decision in the maneuvering target tracking is actually a target motion model decision. Target maneuvering detection is one of the techniques related to model decision in current maneuvering target tracking. In the tracking process, when the target motion mode changes, the filter model and the motion mode are usually mismatched, so that the filter error is increased, and the filter model used must be adjusted in time by a corresponding mode decision process. Maneuver detection is a decision-making technique that detects the occurrence of a maneuver and then adjusts the tracking model to match the corresponding motion pattern.
Although the multi-model approach is favored for its good tracking performance and robustness, its design process is complex and requires significant computational resources to implement. In many resource-constrained situations, decision-based single-model approaches have wider application. Recent research shows that a single model method based on decision can obtain tracking performance similar to a multi-model method by matching with a good maneuvering detection method. Thus, timely and accurate maneuver detection becomes the key to such methods.
Aiming at a decision-based single model tracking method, expert scholars and engineering technicians in the field of target tracking at home and abroad carry out a great deal of research. However, most of the detectors used by them are based on a sliding window detector with a fixed window length, and a common problem with these detectors is the choice of the window length of the motorized detector. Generally, the detection probability increases with the increase of the window length, but the increase of the window length can cause the increase of the maneuver detection delay, and the influence on the target tracking performance is great; the reduction of the window length can reduce the maneuver detection delay, but the false alarm probability is increased, so how to select the window length is a difficulty of this type of detector.
Disclosure of Invention
The invention aims to design an attenuation memory sequential detector aiming at the defects of the existing detector. The detector is fused with a target tracking algorithm, and a maneuvering target tracking method based on an attenuation memory sequential detector is provided for the field of maneuvering detection and target tracking research.
A maneuvering target tracking method based on an attenuation memory sequential detector comprises the following steps:
step 1, initial setting of state covariance and Kalman filtering: when the target moves linearly at a constant speed, a two-dimensional Kalman filter is adopted by the moving target, a CV model is adopted by the system model, and Kalman filtering is performed according to a state equation and a measurement equation.
Step 2, designing a detector: and designing a decaying memory sequential detector based on the generalized likelihood ratio according to the defined likelihood ratio function, wherein the decaying memory sequential detector is realized by a decaying memory sequential detection algorithm.
Step 3, input estimation and state compensation: the time at which the maneuver occurred is detected using a decaying memory sequential detector, after which the magnitude of the maneuver is estimated. And correcting innovation and covariance according to the estimated maneuvering amplitude.
Step 4, expanding dimension and correcting state in real time: when inkWhen the maneuver is detected at any time, the pair of the [ mu ] m [ mu ]n,k]And compensating the state in the time interval, then expanding the dimension of the state vector and the covariance matrix, and correcting the CV model in real time according to the estimated magnitude of the maneuver amplitude.
Step 5, exiting the maneuver judgment: if the discriminant is true at a given level of significance, the generation of acceleration is considered not to be caused by maneuvering of the target, i.e., the target is considered to be in a non-maneuverable state.
Step 6, tasteless Kalman filtering estimation: when the target is maneuvered, an odorless Kalman filter is adopted to filter the state of the target, unscented transformation is firstly carried out in the odorless Kalman filtering process, and then the state variable after transformation is used for filtering.
The invention has the beneficial effects that: the invention provides the attenuation sequential detector based on the generalized likelihood ratio by utilizing the condition that the observation data are sequentially obtained, and the advantage of attenuation memory is to utilize the theory that the data at different moments have different influences on maneuver judgment, so that the influence of the data at the moment close to the moment on the maneuver judgment is larger, the influence of the data at the moment far away from the moment on the maneuver judgment is smaller, the precision of the detector can be improved, and the maneuver detection delay can be shortened. Meanwhile, the designed maneuvering detector is integrated into a tracking system, a maneuvering target tracking method based on an attenuation memory sequential detector is designed, meanwhile, a Kalman filter and an odorless Kalman filter are used for filtering in a combined filtering mode, the Kalman filter is used when the target is in a non-maneuvering state, and the odorless Kalman filter is used for filtering when the target is in a maneuvering state, so that the filtering precision is improved. The method has good tracking performance for processing the maneuvering target tracking problem, particularly for maneuvering and non-maneuvering alternate motion modes, and reduces the calculated amount and improves the practicability of the method compared with a maneuvering target tracking method based on multiple models. The invention has stronger maneuvering detection performance and practicability.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, the present invention comprises the steps of:
step 1, initial setting of state covariance and Kalman filtering: when the target moves linearly at a constant speed, a two-dimensional Kalman filter is adopted by the moving target, a CV model is adopted by the system model, and Kalman filtering is performed according to a state equation and a measurement equation.
Step 2, designing a detector: a generalized likelihood ratio based attenuated memory sequential detector is designed based on a defined likelihood ratio function. The attenuation memory sequential detector is realized by an attenuation memory sequential detection algorithm. In target maneuvering detection, observation data are often obtained sequentially, so that compared with a batch-processed sliding window type detector, sequential detection is more suitable for application and maneuvering detection, and the length of a detection window does not need to be preset in the sequential detection, so that an important problem in the sliding window type detection is avoided.
Step 3, input estimation and state compensation: the time at which the maneuver occurred is detected using a decaying memory sequential detector, after which the magnitude of the maneuver is estimated. And correcting innovation and covariance according to the estimated maneuvering amplitude.
Step 4, expanding dimension and correcting state in real time: when a maneuver is detected at time k, the pairn,k]Compensating for states in time intervals, and then expanding the state vector and covariance matrixAnd (4) dimension and correcting the CV model in real time according to the estimated magnitude of the maneuver amplitude.
Step 5, exiting the maneuver judgment: if the discriminant is true at a given level of significance, the generation of acceleration is considered not to be caused by maneuvering of the target, i.e., the target is considered to be in a non-maneuverable state.
Step 6, tasteless Kalman filtering estimation: when the target is maneuvered, an odorless Kalman filter is adopted to filter the state of the target, unscented transformation is firstly carried out in the odorless Kalman filtering process, and then the state variable after transformation is used for filtering.
The specific steps of state covariance initialization and Kalman filtering in step 1 are as follows:
when the target moves linearly at a constant speed, a two-dimensional Kalman filter is adopted by the moving target, and a CV model is adopted by a system model. And performing Kalman filtering according to the state equation and the measurement equation.
The initial covariance is:
(1)
in the formula,
in order to measure the variance of the noise,
is the sampling period. Because of the fact thatIs the covariance of the position component, with a magnitude equal to the covariance of the metrology noise.
、
Which is the covariance of the velocity components, can be derived from the mathematical relationship between velocity and position,
==。
is the covariance of the acceleration component, obtained from the mathematical relationship of position and acceleration
=
In the same way, the method can obtain, 
. At this point, an initial covariance matrix is obtained.
The specific steps of the detector design in step 2 are as follows:
assuming the target maneuver state equation is:
(2)
wherein c is an input control matrix,
is the magnitude of the maneuver amplitude at time k,
is process noise.
And
all have gaussian characteristics.
First, a binary assumption is made:
wherein it is assumed thatIndicates no maneuver, assume
It is indicated that a maneuver is present,
indicating the magnitude of the maneuver.
Defining a likelihood ratio function
Wherein,
is novel, has the characteristic of Gaussian white noise,
a joint probability density function of the innovation is assumed for the maneuver.
The recursive form of the decaying memory sequential detection algorithm is as follows:
wherein,
in order to be able to use the attenuation factor,the value of (a) can be obtained empirically.
According to the relation between the equation (5) and 0, the detection threshold can be set to 0, the probability density function follows gaussian distribution, and the maneuver identification rule is as follows:
(1) if it isThen receive
Suppose, that there is a maneuver, then the maneuver start time is:
then carrying out state compensation;
(2) if it is
The checking process is continued
。
The specific steps of input estimation and state compensation in step 3 are as follows:
detecting the time of occurrence of the maneuver by using an attenuation memory sequential detector, and then estimating the maneuver amplitude, wherein if the maneuver occurs at the time n and the maneuver occurs at the time k, the estimation of the maneuver amplitude is as follows:
wherein,
a state transition matrix for time k,
Is a matrix of the errors covariance for the maneuver,
is new.
The state estimation and covariance estimation for one sampling period using kalman filter filtering is:
wherein,
，
in order to be the gain of the filter,
the covariance matrix is predicted for the state one step,
is an innovation covariance matrix.
Therefore, inn,k]The state within the time interval is modified as follows:
(8)
in the formula (8), inn,k]The correction of the state in the time interval already comprises the analytic relation between the time interval and the maneuvering amplitude, because the target state is six-dimensional and comprises components such as position, speed, acceleration and the like, and the maneuvering amplitude is the acceleration. The maneuver amplitude and the time interval thus satisfy the analytical relationship of equation (8).
And (3) innovation correction:
and (3) covariance correction:
wherein
Is the error covariance matrix of maneuver magnitudes.
，
、
Is andn…k]a matrix of coefficients related to the states of (a) and (b).
The specific steps of the dimension expansion and the real-time state correction in the step 4 are as follows:
when the maneuver is detected at time k, andn,k]and after the state in the time interval is compensated, finally, the state vector and the covariance matrix are subjected to dimension expansion, and the model is corrected in real time according to the estimated maneuvering amplitude.
(12)
Wherein,
is an estimate of the maneuver amplitude.
The specific steps for exiting the maneuver determination in the step 5 are as follows:
normalized square of the input amplitude is
In [ 2 ]n,k]The normalized sum of squares of the amplitudes over the time interval being
(14)
The discriminant:
at a given level of significance
If the above formula is satisfied, the acceleration is not generated by the maneuver of the target, and in this case, the non-maneuver processing is performed, so that the target is considered to be in the non-maneuver state.
The specific steps of the unscented kalman filter estimation in step 6 are as follows:
the UKF filter in the invention is an odorless Kalman filter.
The UKF first performs a flat transform (UT) in processing the state equations and then performs a filtering estimation using the flat transformed state variables to reduce estimation errors.
Calculate 2n +1
Dot
I =1,2, …, 2n, where n is the state vector dimension.
In the formula
，
Determine (a)
The degree of dot spread, usually taking a small positive value, such as 0.01,
usually 0 is taken.
Computing
Dot
I =1,2, …, 2n, propagation through the equation of state:
in the formula
。
Computing
Dot
，
Propagation through the metrology equation:
(18)
one step advance prediction of the computational output:
at new quantity measurement
And (3) carrying out filtering updating after arrival:
wherein
Is the filter gain matrix.
The method of the invention comprises the following main processes: assuming that the target initially moves at a constant speed, firstly, setting initial values of a state vector and a covariance matrix according to measured values, estimating the state by adopting a two-dimensional Kalman filter based on a CV model, and simultaneously, carrying out maneuvering detection by utilizing an attenuation memory sequential detector. If no maneuver exists, returning to continue to carry out the state estimation of the next period; if a maneuver is detected, the magnitude of the maneuver and the time at which the maneuver occurred are estimated. The filter state and covariance are compensated for taking into account the delay in maneuver detection. And finally, carrying out dimension expansion on the CV model according to the corrected state and the maneuvering amplitude to obtain a real-time corrected model, and then carrying out UKF filtering according to the real-time corrected model. And repeating the maneuver detection process, if the maneuver is detected again, performing input estimation and state compensation, simultaneously updating the model in real time, if the maneuver is not detected, performing maneuver exiting judgment, if the maneuver amplitude is greater than the threshold, indicating that the maneuver is not exited, repeating UKF filtering, and if the maneuver amplitude is less than the threshold, considering that the target is in a non-maneuver state, and at the moment, adopting two-dimensional Kalman filtering, repeating the processes, thereby forming the maneuver target tracking method based on the attenuation memory sequential detector.
Claims (2)
1. A maneuvering target tracking method based on an attenuation memory sequential detector is characterized by comprising the following steps:
step 1, initial setting of state covariance and Kalman filtering: when the target moves linearly at a constant speed, a two-dimensional Kalman filter is adopted by the moving target, a CV model is adopted by a system model, and Kalman filtering is carried out according to a state equation and a measurement equation;
step 2, designing a detector: designing an attenuation memory sequential detector based on the generalized likelihood ratio according to a defined likelihood ratio function, wherein the attenuation memory sequential detector is realized by an attenuation memory sequential detection algorithm;
step 3, input estimation and state compensation: detecting the time of occurrence of the maneuver by using an attenuation memory sequential detector, and then estimating the amplitude of the maneuver; correcting innovation and covariance according to the estimated maneuvering amplitude;
step 4, expanding dimension and correcting state in real time: when inkWhen the maneuver is detected at any time, the pair of the [ mu ] m [ mu ]n,k]Compensating the state in the time interval, then expanding the dimension of the state vector and the covariance matrix, and correcting the CV model in real time according to the estimated maneuvering amplitude;
step 5, exiting the maneuver judgment: under a given significance level, if the discriminant is established, the generation of the acceleration is not generated by the maneuvering of the target, namely the target is considered to be in a non-maneuvering state;
step 6, tasteless Kalman filtering estimation: when the target is maneuvered, an odorless Kalman filter is adopted to filter the state of the target, unscented transformation is firstly carried out in the odorless Kalman filtering process, and then the state variable after transformation is used for filtering.
2. The maneuvering target tracking method based on the attenuation memory sequential detector is characterized by comprising the following steps of: the step 2 is specifically as follows:
first, a binary assumption is made:
： 
wherein it is assumed that
Indicates no maneuver, assume
It is indicated that a maneuver is present,
the magnitude of the maneuver is indicated by the magnitude of the maneuver,
represents a time of day;
defining a likelihood ratio function
Wherein,is novel, has the characteristic of Gaussian white noise,
a joint probability density function of the innovation for the maneuver hypothesis;
the recursive form of the decaying memory sequential detection algorithm is as follows:
wherein,
in order to be able to use the attenuation factor,
according to the relation between the equation (3) and 0, the detection threshold is set to be 0, the probability density function follows Gaussian distribution, and the maneuver identification rule is as follows:
(1) if it is
Then receive
Suppose, that there is a maneuver, then the maneuver start time is:then carrying out state compensation;
(2) if it is
The checking process is continued。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210190065.8A CN102706345B (en) | 2012-06-11 | 2012-06-11 | Maneuvering target tracking method based on fading memory sequential detector |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210190065.8A CN102706345B (en) | 2012-06-11 | 2012-06-11 | Maneuvering target tracking method based on fading memory sequential detector |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102706345A true CN102706345A (en) | 2012-10-03 |
| CN102706345B CN102706345B (en) | 2015-01-28 |
Family
ID=46899297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210190065.8A Active CN102706345B (en) | 2012-06-11 | 2012-06-11 | Maneuvering target tracking method based on fading memory sequential detector |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102706345B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744058A (en) * | 2013-12-24 | 2014-04-23 | 河海大学 | Ballistic trajectory formation method based on exponential weighting attenuated memory filtering |
| CN103901426A (en) * | 2012-12-28 | 2014-07-02 | 重庆凯泽科技有限公司 | Single-maneuvering target tracking system |
| CN104180801A (en) * | 2014-08-20 | 2014-12-03 | 广州海格通信集团股份有限公司 | Method and system for predicting track points based on ADS-B system |
| CN106772351A (en) * | 2016-11-16 | 2017-05-31 | 西安电子科技大学 | Kalman filter method based on the memory of limited step |
| CN106910211A (en) * | 2015-12-21 | 2017-06-30 | 中国石油天然气股份有限公司 | Multi-maneuvering-target tracking method under complex environment |
| CN108332939A (en) * | 2017-12-31 | 2018-07-27 | 中国科学院声学研究所 | A method of across medium time-varying fluid parameter On-line Estimation |
| CN108629935A (en) * | 2018-05-17 | 2018-10-09 | 山东深图智能科技有限公司 | A kind of method and system for climbing building pivot frame larceny based on video monitoring detection |
| CN113155122A (en) * | 2021-04-01 | 2021-07-23 | 广州大学 | Maneuvering target tracking method based on adaptive filtering |
| CN113484839A (en) * | 2021-07-02 | 2021-10-08 | 中国船舶重工集团公司第七二四研究所 | Radar target track automatic detection sequential processing method based on significance test |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2128644A1 (en) * | 2007-03-22 | 2009-12-02 | Furuno Electric Co., Ltd. | Gps composite navigation apparatus |
| US20090322590A1 (en) * | 2007-04-18 | 2009-12-31 | Schoettl Alfred | Method with a system for ascertaining and predicting a motion of a target object |
| CN102043906A (en) * | 2010-12-15 | 2011-05-04 | 北京航空航天大学 | Diagonal-form fusion method for maneuvering target tracking |
-
2012
- 2012-06-11 CN CN201210190065.8A patent/CN102706345B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2128644A1 (en) * | 2007-03-22 | 2009-12-02 | Furuno Electric Co., Ltd. | Gps composite navigation apparatus |
| US20090322590A1 (en) * | 2007-04-18 | 2009-12-31 | Schoettl Alfred | Method with a system for ascertaining and predicting a motion of a target object |
| CN102043906A (en) * | 2010-12-15 | 2011-05-04 | 北京航空航天大学 | Diagonal-form fusion method for maneuvering target tracking |
Non-Patent Citations (2)
| Title |
|---|
| JIFENG RU: "Sequential Detection of Target Maneuvers", 《2005 7TH INTERNATIONAL CONFERENCE ON INFORMATION FUSION(FUSION)》 * |
| 盛琥等: "基于新息序列修正的输入估计算法", 《系统工程与电子技术》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103901426A (en) * | 2012-12-28 | 2014-07-02 | 重庆凯泽科技有限公司 | Single-maneuvering target tracking system |
| CN103744058A (en) * | 2013-12-24 | 2014-04-23 | 河海大学 | Ballistic trajectory formation method based on exponential weighting attenuated memory filtering |
| CN104180801A (en) * | 2014-08-20 | 2014-12-03 | 广州海格通信集团股份有限公司 | Method and system for predicting track points based on ADS-B system |
| CN104180801B (en) * | 2014-08-20 | 2017-06-06 | 广州海格通信集团股份有限公司 | Forecasting Methodology and system based on ADS B system track points |
| CN106910211A (en) * | 2015-12-21 | 2017-06-30 | 中国石油天然气股份有限公司 | Multi-maneuvering-target tracking method under complex environment |
| CN106772351A (en) * | 2016-11-16 | 2017-05-31 | 西安电子科技大学 | Kalman filter method based on the memory of limited step |
| CN108332939A (en) * | 2017-12-31 | 2018-07-27 | 中国科学院声学研究所 | A method of across medium time-varying fluid parameter On-line Estimation |
| CN108332939B (en) * | 2017-12-31 | 2020-04-07 | 中国科学院声学研究所 | Cross-medium time-varying fluid parameter online estimation method |
| CN108629935A (en) * | 2018-05-17 | 2018-10-09 | 山东深图智能科技有限公司 | A kind of method and system for climbing building pivot frame larceny based on video monitoring detection |
| CN113155122A (en) * | 2021-04-01 | 2021-07-23 | 广州大学 | Maneuvering target tracking method based on adaptive filtering |
| CN113484839A (en) * | 2021-07-02 | 2021-10-08 | 中国船舶重工集团公司第七二四研究所 | Radar target track automatic detection sequential processing method based on significance test |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102706345B (en) | 2015-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102706345A (en) | Maneuvering target tracking method based on fading memory sequential detector | |
| CN107045125B (en) | Interactive multi-model radar target tracking method based on predicted value measurement conversion | |
| CN101221238B (en) | Dynamic deviation estimation method based on gauss average value mobile registration | |
| CN102568004A (en) | Tracking algorithm for high maneuvering targets | |
| CN108682023A (en) | Close coupling Unscented kalman tracking filter algorithm based on Elman neural networks | |
| CN102721951B (en) | Method for tracking high maneuvering target | |
| CN104809326A (en) | Asynchronous sensor space alignment algorithm | |
| CN104504728B (en) | Multiple maneuver target tracking methods, system and broad sense JPDA device thereof | |
| CN110209180B (en) | Unmanned underwater vehicle target tracking method based on HuberM-Cubasic Kalman filtering | |
| CN107633256A (en) | Joint objective positioning and sensor registration method under a kind of multi-source ranging | |
| CN110231620B (en) | Noise-related system tracking filtering method | |
| CN107169478A (en) | A kind of adaptive online filtering method | |
| CN104066179A (en) | Improved method for positioning WSN nodes through adaptive iterative UKF | |
| CN108319570A (en) | Deviation Combined estimator and compensation method and device when a kind of asynchronous multiple sensors sky | |
| Zhang et al. | Low-cost adaptive square-root cubature Kalman filter for systems with process model uncertainty | |
| CN110889862A (en) | Combined measurement method for multi-target tracking in network transmission attack environment | |
| Choi et al. | State estimation with delayed measurements considering uncertainty of time delay | |
| CN110989341A (en) | Constraint auxiliary particle filtering method and target tracking method | |
| CN105701292B (en) | A kind of parsing discrimination method of maneuvering target turning rate | |
| CN110532517A (en) | Gas pipeline method for parameter estimation based on improved ARUKF | |
| CN107330468B (en) | Multi-sensor distributed data fusion method based on Cherenov fusion criterion | |
| CN105549003A (en) | Automobile radar target tracking method | |
| Li et al. | Tracking an underwater maneuvering target using an adaptive Kalman filter | |
| CN108872973B (en) | EKF filtering method for trajectory guided missile target orbit determination | |
| CN104868876B (en) | A kind of Kalman filter method being directed under process noise covariance matrix Q unknown situations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20121003 Assignee: HANGZHOU DAZHI ELECTROMECHANICAL Co.,Ltd. Assignor: HANGZHOU DIANZI University Contract record no.: X2020330000073 Denomination of invention: A maneuvering target tracking method based on attenuated memory sequential detector Granted publication date: 20150128 License type: Common License Record date: 20201010 |
|
| EE01 | Entry into force of recordation of patent licensing contract |