WO2017124299A1 - Procédé de suivi multicible et système de suivi basé sur un filtrage séquentiel bayésien - Google Patents

Procédé de suivi multicible et système de suivi basé sur un filtrage séquentiel bayésien Download PDF

Info

Publication number
WO2017124299A1
WO2017124299A1 PCT/CN2016/071347 CN2016071347W WO2017124299A1 WO 2017124299 A1 WO2017124299 A1 WO 2017124299A1 CN 2016071347 W CN2016071347 W CN 2016071347W WO 2017124299 A1 WO2017124299 A1 WO 2017124299A1
Authority
WO
WIPO (PCT)
Prior art keywords
edge distribution
target
probability
edge
current time
Prior art date
Application number
PCT/CN2016/071347
Other languages
English (en)
Chinese (zh)
Inventor
刘宗香
邹燕妮
吴德辉
李良群
Original Assignee
深圳大学
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳大学 filed Critical 深圳大学
Priority to PCT/CN2016/071347 priority Critical patent/WO2017124299A1/fr
Publication of WO2017124299A1 publication Critical patent/WO2017124299A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion

Definitions

  • the invention belongs to the field of multi-sensor information fusion technology, and in particular relates to a multi-target tracking method and a tracking system based on sequential Bayesian filtering.
  • Bayesian filtering technology provides a powerful statistical method tool to assist in the fusion and processing of multi-sensor information with uncertainties in measurement data.
  • the information delay problem caused by the newly received measurement data can not be processed in time and the multi-target tracking problem in the case of the unknown target initial position, we have proposed a solution.
  • No. CN201510284138.3 a patent application for measuring the driving target tracking method and tracking system for transmitting edge distribution.
  • this method can not effectively track the maneuvering target whose motion mode is switched between different models. How to track the maneuvering target that converts the motion mode between different models is a key technology that needs to be explored and solved in the multi-objective Bayesian filtering method. problem.
  • the technical problem to be solved by the present invention is to provide a multi-target tracking method and a tracking system based on sequential Bayesian filtering, aiming at solving the problem of tracking multiple maneuvering targets whose motion modes are switched between different models.
  • the present invention is implemented in this way, a multi-target tracking method based on sequential Bayesian filtering, comprising the following steps:
  • Step A After receiving the new measurement data, calculate a time difference between a time when the new measurement data is received and a time when the previous measurement data is received, to receive the new measurement data. Inscribed as the current time, the time when the previous measurement data is received is the previous time; according to the time difference, the transition probability between each model, and the edge distribution of each target at the previous moment and its existence probability, it is predicted that each target at the current time is Edge distribution under different models and their existence probability;
  • Step B According to the predicted edge current distribution and the existence probability of each target under different models, the Bayes rule is used to sequentially process each measurement data of the current time to obtain the updated edge distribution of each target under different models. And its probability of existence;
  • Step C merging the updated edge distributions and the existence probabilities of the respective targets in the different models at the current moment to form an updated edge distribution and an existence probability of each target at the current moment;
  • Step D using each measurement data of the current moment to generate an edge distribution of the new target, assigning an existence probability and a model label thereto; and simultaneously, respectively, an edge distribution of the new target at the current moment and its existence probability are respectively associated with each target of the current moment Update the edge distribution and its existence probability to merge, and generate the edge distribution of each target at the current moment and its existence probability;
  • Step E The edge distribution with the probability of being less than the first threshold is cut off from the edge distribution of each target at the current moment generated after the merge, and the reduced edge distribution and its existence probability are used as input of recursive filtering at the next moment.
  • the edge distribution with the existence probability greater than the second threshold is extracted from the reduced edge distribution as the output of the current time, and the mean and the variance of the respective output edge distributions are respectively used as the state estimation and the error estimation of the current time target.
  • the invention also provides a multi-target tracking system based on sequential Bayesian filtering, which can also solve the tracking problem of multiple maneuvering targets converted between different models of motion modes, and can ensure the real-time performance of data processing.
  • the multi-target tracking system includes:
  • a prediction module after receiving the new measurement data, calculating a time difference between a time when the new measurement data is received and a time when the previous measurement data is received, to receive the new measurement data as a current time
  • the time at which the previous measurement data is received is the previous time; according to the time difference, the transition probability between each model, and the edge distribution of each target at the previous moment and its existence probability, it is predicted that each target at the current time is under a different model. Edge distribution and its existence probability;
  • An update module according to the edge distribution of each target in the prediction module at the current moment and the existence probability of each target under different models, using Bayes rule to sequentially process each measurement data of the current moment to obtain each target under different models Update the edge distribution and its existence probability;
  • the model fusion module integrates the updated edge distribution and the existence probability of each target in the update module under different models at the current moment to form an updated edge distribution and existence probability of each target at the current moment;
  • the edge distribution generation module generates an edge distribution of the new target by using each measurement data at the current moment, and specifies the existence probability and the model label for the current target; meanwhile, the edge distribution of the new target at the current moment and the existence probability thereof are respectively combined with the model fusion module The updated edge distribution of each target in the current moment and its existence probability are combined to generate the edge distribution of each target at the current moment and its existence probability;
  • the edge distribution extraction module removes, from the edge distribution generation module, the edge distribution of each target at the current moment generated by the merge, the edge distribution whose existence probability is less than the first threshold, and the edge distribution after the reduction and the existence thereof Probability is used as the input of recursive filtering at the next moment.
  • the edge distribution with the existence probability greater than the second threshold is extracted from the reduced edge distribution as the output of the current time, and the mean and variance of each output edge distribution are respectively used as the current time target. State estimation and error estimation.
  • the present invention has the beneficial effects that the multi-target tracking method based on sequential Bayesian filtering can sequentially sequence Bayesian by the steps of prediction, update, fusion, edge distribution generation and edge distribution extraction.
  • the combination of different filters and different models not only ensures the real-time performance of data processing, but also effectively solves the problem of multi-maneuvering target tracking between different modules, and has wide practicality.
  • FIG. 1 is a flow chart of a multi-target tracking method for sequential Bayesian filtering of the present invention
  • FIG. 2 is a schematic structural diagram of a multi-target tracking system of sequential Bayesian filtering according to the present invention
  • 3 is a measurement data of a sensor in 50 scan cycles according to an embodiment of the present invention.
  • FIG. 4 is a result of processing a multi-target tracking method according to the present invention and a GM-PHD target tracking method based on a hop Markov system model;
  • FIG. 5 is a result of processing by a multi-target tracking method according to the present invention and a GM-PHD filtering method based on a hop Markov system model;
  • FIG. 6 is a schematic diagram of the average OFPA distance obtained after 100 experiments by the multi-target tracking method according to the present invention and the GM-PHD-JMS filtering method based on the hop Markov system model.
  • the multi-target tracking method based on sequential Bayesian filtering of the present invention solves the maneuvering target tracking for converting between different models by predicting, updating, merging, generating and extracting the edge distribution of each target and its existence probability. The problem and the timely processing of the measurement data received at the current time.
  • the multi-target tracking method based on sequential Bayesian filtering includes the following steps:
  • Step A After receiving new measurement data, calculate a time difference between a time when the new measurement data is received and a time when the previous measurement data is received, so that the time when the new measurement data is received is the current time
  • the time at which the previous measurement data is received is the previous time; according to the time difference, the transition probability between each model, and the edge distribution of each target at the previous moment and its existence probability, it is predicted that each target at the current time is under a different model. Edge distribution and its probability of existence.
  • the model provides a place for the target's motion, and the model is represented as r i,k .
  • the target is the object that needs to be tested and tracked.
  • different models can be transformed into the same model to facilitate the measurement and tracking of motion patterns between different models.
  • the previous moment is represented by k-1, k represents the current time, t k-1 represents the time of the previous moment, t k represents the time of the current moment, and r i,k-1 represents the model of the i-th edge distribution of the previous moment.
  • tag, r i, k denotes the i-th model edge label distributions current time, 1 ⁇ r i, k ⁇ M r, M r represents the total number of models.
  • N denotes a Gaussian distribution
  • x i,k-1 denotes a state vector of the i-th edge distribution at the previous moment
  • m i,k-1 (r i,k-1 ) and P i,k -1 (r i,k-1 ) respectively represent the mean and variance of the i-th edge distribution at the previous moment
  • N k-1 is the total number of targets at the previous moment
  • i is the index number, 1 ⁇ i ⁇ N k-1 .
  • the edge distribution predicted by each target under different models at the current moment is N(x i,k ;m i ,k
  • k-1 (r i,k )),i 1,2,...,N k-1 ,1 ⁇ r i,k ⁇ M r ;
  • the existence probability of each predicted edge distribution at the current time is ⁇ i,k
  • k-1 (r i,k ) p S,k (t k -t k-1 )t k
  • r i,k-1 ) ⁇ i,k-1 (r i,k-1 ),i 1,2,...,N k-1 ,1 ⁇ r i,k ⁇ M r
  • k-1 (r i,k ) F k-1 (r i,k )
  • Step B According to the predicted edge current distribution and the existence probability of each target under different models, the Bayes rule is used to sequentially process each measurement data of the current time to obtain the updated edge distribution of each target under different models. And its probability of existence.
  • Bayesian rule (Bayes theorem) is a mathematical formula expressed in a mathematical language: the more events that support an attribute occur, the greater the likelihood that the attribute will be established. In layman's terms, when the nature of a thing cannot be accurately known, the probability of its essential attribute can be judged by the number of events associated with the specific nature of the thing. Bayesian rules are conditional probabilities for random events A and B And the probability of the edge. Corresponding term explanation: Pr(A) is the prior probability or edge probability of A, which is called a priori because it does not consider any B factor; Pr(A
  • the probability is also called the posterior probability of A because it knows the value of B; Pr(B
  • Step C merging the updated edge distribution and the existence probability of each target in different models at the current moment to form an updated edge distribution and existence probability of each target at the current moment.
  • Step D using each measurement data of the current moment to generate an edge distribution of the new target, which is referred to The existence probability and the model label are determined; at the same time, the edge distribution of the new target at the current moment and the existence probability thereof are respectively combined with the updated edge distribution of each target at the current moment and the existence probability thereof, and the edge distribution of each target at the current moment is generated and Its probability of existence.
  • Step E The edge distribution with the probability of being less than the first threshold is cut off from the edge distribution of each target at the current moment generated after the merge, and the reduced edge distribution and its existence probability are used as inputs of the next time recursive filtering.
  • the edge distribution with the existence probability greater than the second threshold is extracted from the reduced edge distribution as the output of the current time, and the mean and the variance of the respective output edge distributions are respectively used as the state estimation and the error estimation of the current time target.
  • the edge distribution with the probability less than the first threshold is cut off from the edge distribution of the current time generated after the combination, and the edge distribution after clipping and its existence probability are used as the recursive input of the filter at the next moment, and the probability of existence is greater than
  • the edge distribution of the two thresholds is taken as the output of the current time.
  • the first threshold is also referred to as a reduction threshold, and the value ranges from greater than 0 to less than the specified new target existence probability; the second threshold is also referred to as a reduction threshold, and the value ranges from greater than 0 to less than 1.
  • a multi-target tracking system based on sequential Bayesian filtering includes: a prediction module 201, an update module 202, a model fusion module 203, an edge distribution generation module 204, and an edge distribution extraction module 205.
  • the prediction module 201 calculates the time difference between the time when the new measurement data is received and the time when the previous measurement data is received, so that the time when the new measurement data is received is the current time, and the received time is received.
  • the time of the previous measurement data is the previous time; according to the time difference, the transition probability between the models, and the edge distribution of each target at the previous moment and the existence probability thereof, the edge distribution of each target under different models at the current time is predicted and Probability of existence.
  • the update module 202 sequentially processes each measurement data of the current time according to the edge distribution of each target under different models predicted by the prediction module 201 at the current time, and obtains the update of each target under different models by using the Bayes rule. Edge distribution and its probability of existence.
  • the model fusion module 203 is configured to combine the updated edge distributions and the existence probabilities of the respective targets in the update module 202 at different moments in the different models to form an updated edge distribution and an existence probability of each target at the current moment.
  • the edge distribution generation module 204 generates an edge distribution of the new target by using each measurement data of the current time, and specifies the existence probability and the model label for the current target; meanwhile, the edge distribution of the new target at the current moment and the existence probability thereof are respectively combined with the model fusion module.
  • the updated edge distribution of each target in the current moment and its existence probability are combined to generate the edge distribution of each target at the current moment and its existence probability.
  • the edge distribution extraction module 205 cuts off the edge distribution of the edge distribution of each target at the current moment generated by the merged edge generated by the merged edge, and reduces the edge distribution and the existence of the edge distribution Probability is used as the input of recursive filtering at the next moment.
  • the edge distribution with the existence probability greater than the second threshold is extracted from the reduced edge distribution as the output of the current time, and the mean and variance of each output edge distribution are respectively used as the current time target. State estimate With error estimates.
  • the previous time is represented by k-1, k represents the current time, t k-1 represents the time of the previous time, t k represents the time of the current time, and r i,k-1 represents the i-th time of the previous time.
  • label edges distribution model, r i, k represents the current moment of the i-th label edge distribution model, 1 ⁇ r i, k ⁇ M r, M r represents the total number of models.
  • N denotes a Gaussian distribution
  • x i,k-1 denotes a state vector of the i-th edge distribution at the previous moment
  • m i,k-1 (r i,k-1 ) and P i,k -1 (r i,k-1 ) respectively represent the mean and variance of the i-th edge distribution at the previous moment
  • N k-1 is the total number of targets at the previous moment
  • i is the index number, 1 ⁇ i ⁇ N k-1 .
  • the edge distribution predicted by each target under different models at the current moment is N(x i,k ;m i ,k
  • k-1 (r i,k )),i 1,2,...,N k-1 ,1 ⁇ r i,k ⁇ M r ;
  • the existence probability of each predicted edge distribution at the current time is ⁇ i,k
  • k-1 (r i,k ) p S,k (t k -t k-1 )t k
  • r i,k-1 ) ⁇ i,k-1 (r i,k-1 ),i 1,2,...,N k-1 ,1 ⁇ r i,k ⁇ M r
  • k-1 (r i,k ) F k-1 (r i,k )
  • the sequential processing of the measurement data received at the current time specifically includes:
  • the processing unit sequentially processes the first to M measurement data by using a Bayes rule:
  • the edge distribution of the target i under the model r i,k before processing the jth measurement data The existence probability of the edge distribution of the target i under the model r i,k for the jth measurement data, where 1 ⁇ j ⁇ M; with The probability of existence when the jth measurement data is updated is Mean vector Covariance matrix Filter gain
  • H k (r i,k ) is the observation matrix of the model r i,k
  • R k (r i,k ) is the observed noise variance matrix of the model r i,k
  • p D,k is the detection probability of the target
  • ⁇ c,k is the clutter density
  • I represents the unit matrix
  • y j,k is the jth measurement data received at the current time
  • the superscript T is represented as the transpose of the matrix or vector
  • r i,k 1,..., M r .
  • the edge distribution of the new target at the current time is generated by using the M measurement data at the current time.
  • the edge distribution extraction module 205 cuts the edge distribution whose existence probability is less than the first threshold from the edge distribution of the current time generated after the combination, and reduces the edge distribution and the existence probability as the recursive input of the next time filter, and The edge distribution whose existence probability is greater than the second threshold is selected as the output of the current time.
  • the state of the target is composed of position and velocity, expressed as Where x and y represent positional components, respectively.
  • the superscript T represents the transpose of the vector
  • the state transition matrix is
  • the process noise variance matrix is
  • ⁇ v is the standard deviation of the process noise
  • the Markov transition probability matrix between different motion models is Observation matrix Observed noise variance matrix ⁇ w is the standard deviation of
  • the simulated observation data of the sensor in 50 scan cycles in one experiment is shown in Fig. 3.
  • the relevant parameters of the present invention and the Gaussian Mixture probability hypothesis density filter for jump Markov system models (GM-PHD-JMS filter) are set to p.
  • the first threshold is 10 -3
  • the multi-target tracking method of the present invention is processed with the existing GM-PHD-JMS filter for the simulation data of FIG.
  • the existing GM-PHD filtering based on the hopping Markov model is more accurate in tracking the maneuvering target in the case of correlation uncertainty, detection uncertainty and clutter. Accurate and reliable target state estimation, its OFAC distance is smaller than the existing OSPA distance obtained by this method.
  • the multi-target tracking method based on sequential Bayesian filtering and the multi-target tracking system of the present invention combine different models with sequential Bayesian filters, and use Markov chain to control the conversion between models, through the current moment Sequential processing of measurement data to obtain the edge distribution and its existence probability of each target updated under different models at the current time, and synthesize multiple edge distributions into one edge distribution by merging the edge distribution of the target under different models, which makes
  • the target tracking method can not only timely process the measurement data received at the current time, thereby avoiding the delay of information processing, ensuring the real-time performance of the data processing, and at the same time, maneuvering the target with the motion pattern jumping between different models. Effective tracking, which has expanded Practicality.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Image Analysis (AREA)

Abstract

La présente invention concerne un procédé de suivi multicible et un système de suivi basé sur un filtrage séquentiel Bayésien, appartenant au domaine technique de la fusion d'information de capteur multiple. Le procédé consiste : à prédire les distribution de bord d'une variété de cibles dans différents modèles ainsi que les probabilités d'existence associées au moment actuel ; conformément aux distributions de bords prédites et aux probabilités d'existence associées, à utiliser une règle Bayésienne pour le traitement de manière à obtenir les distributions de bord mises à jour et les probabilités d'existence associées ; à fusionner les distributions de bord mises à jour et les probabilités d'existence associées de manière à former la distribution de bord mise à jour et une probabilité d'existence associée au moment actuel ; à combiner une distribution de bord et une probabilité d'existence associée d'une nouvelle cible avec une distribution de bord mise à jour et la probabilité d'existence respectivement associée de manière à générer une distribution de bord et une probabilité d'existence associée au moment actuel ; et à couper une distribution de bord ayant une probabilité d'existence inférieure à une première valeur seuil, et à extraire et fournir une distribution de bord ayant une probabilité d'existence supérieure à une seconde valeur seuil. Le procédé de suivi multicible garantit l'efficacité en temps réel du traitement de données et permet également de résoudre de manière efficace les problèmes de suivi pour un objet de manœuvre multiple avec des modes de déplacement étant commutés entre différents modèles.
PCT/CN2016/071347 2016-01-19 2016-01-19 Procédé de suivi multicible et système de suivi basé sur un filtrage séquentiel bayésien WO2017124299A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/071347 WO2017124299A1 (fr) 2016-01-19 2016-01-19 Procédé de suivi multicible et système de suivi basé sur un filtrage séquentiel bayésien

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/071347 WO2017124299A1 (fr) 2016-01-19 2016-01-19 Procédé de suivi multicible et système de suivi basé sur un filtrage séquentiel bayésien

Publications (1)

Publication Number Publication Date
WO2017124299A1 true WO2017124299A1 (fr) 2017-07-27

Family

ID=59361100

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/071347 WO2017124299A1 (fr) 2016-01-19 2016-01-19 Procédé de suivi multicible et système de suivi basé sur un filtrage séquentiel bayésien

Country Status (1)

Country Link
WO (1) WO2017124299A1 (fr)

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110320512A (zh) * 2019-07-09 2019-10-11 大连海事大学 一种基于带标签的gm-phd平滑滤波多目标跟踪方法
CN111127523A (zh) * 2019-12-04 2020-05-08 杭州电子科技大学 基于量测迭代更新的多传感器gmphd自适应融合方法
CN111352104A (zh) * 2020-03-18 2020-06-30 清华大学 一种基于信息积累的弱目标检测前跟踪方法
CN111488552A (zh) * 2020-04-24 2020-08-04 商丘师范学院 基于高斯混合概率假设密度的紧邻多目标跟踪方法
CN112614163A (zh) * 2020-12-31 2021-04-06 华中光电技术研究所（中国船舶重工集团公司第七一七研究所） 一种融合贝叶斯轨迹推理的目标跟踪方法及系统
CN112816973A (zh) * 2020-12-31 2021-05-18 清华大学 一种跟踪信息辅助的目标检测方法
CN114626307A (zh) * 2022-03-29 2022-06-14 电子科技大学 一种基于变分贝叶斯的分布式一致性目标状态估计方法
US11386346B2 (en) 2018-07-10 2022-07-12 D-Wave Systems Inc. Systems and methods for quantum bayesian networks
US11410067B2 (en) 2015-08-19 2022-08-09 D-Wave Systems Inc. Systems and methods for machine learning using adiabatic quantum computers
US11461644B2 (en) 2018-11-15 2022-10-04 D-Wave Systems Inc. Systems and methods for semantic segmentation
US11468293B2 (en) 2018-12-14 2022-10-11 D-Wave Systems Inc. Simulating and post-processing using a generative adversarial network
US11481669B2 (en) 2016-09-26 2022-10-25 D-Wave Systems Inc. Systems, methods and apparatus for sampling from a sampling server
US11501195B2 (en) 2013-06-28 2022-11-15 D-Wave Systems Inc. Systems and methods for quantum processing of data using a sparse coded dictionary learned from unlabeled data and supervised learning using encoded labeled data elements
US11531852B2 (en) * 2016-11-28 2022-12-20 D-Wave Systems Inc. Machine learning systems and methods for training with noisy labels
US11586915B2 (en) 2017-12-14 2023-02-21 D-Wave Systems Inc. Systems and methods for collaborative filtering with variational autoencoders
US11625612B2 (en) 2019-02-12 2023-04-11 D-Wave Systems Inc. Systems and methods for domain adaptation
US11900264B2 (en) 2019-02-08 2024-02-13 D-Wave Systems Inc. Systems and methods for hybrid quantum-classical computing

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007007138A1 (fr) * 2005-07-14 2007-01-18 Telefonaktiebolaget Lm Ericsson (Publ) Adaptation d'ensemble de modeles par diffusion de masse de probabilite
CN102110296A (zh) * 2011-02-24 2011-06-29 上海大学 一种复杂场景下的运动目标跟踪方法
CN102147468A (zh) * 2011-01-07 2011-08-10 西安电子科技大学 基于贝叶斯理论的多传感器检测跟踪联合处理方法
CN102811343A (zh) * 2011-06-03 2012-12-05 南京理工大学 一种基于行为识别的智能视频监控系统
US20130006576A1 (en) * 2010-03-15 2013-01-03 Bae Systems Plc Target tracking
US20140324339A1 (en) * 2013-04-30 2014-10-30 BASELABS GmbH Method and apparatus for the tracking of multiple objects
CN104794735A (zh) * 2015-04-02 2015-07-22 西安电子科技大学 基于变分贝叶斯期望最大化的扩展目标跟踪方法
CN104867163A (zh) * 2015-05-28 2015-08-26 深圳大学 一种传递边缘分布的测量驱动目标跟踪方法与跟踪系统
CN105719312A (zh) * 2016-01-19 2016-06-29 深圳大学 基于序贯贝叶斯滤波的多目标跟踪方法及跟踪系统

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007007138A1 (fr) * 2005-07-14 2007-01-18 Telefonaktiebolaget Lm Ericsson (Publ) Adaptation d'ensemble de modeles par diffusion de masse de probabilite
US20130006576A1 (en) * 2010-03-15 2013-01-03 Bae Systems Plc Target tracking
CN102147468A (zh) * 2011-01-07 2011-08-10 西安电子科技大学 基于贝叶斯理论的多传感器检测跟踪联合处理方法
CN102110296A (zh) * 2011-02-24 2011-06-29 上海大学 一种复杂场景下的运动目标跟踪方法
CN102811343A (zh) * 2011-06-03 2012-12-05 南京理工大学 一种基于行为识别的智能视频监控系统
US20140324339A1 (en) * 2013-04-30 2014-10-30 BASELABS GmbH Method and apparatus for the tracking of multiple objects
CN104794735A (zh) * 2015-04-02 2015-07-22 西安电子科技大学 基于变分贝叶斯期望最大化的扩展目标跟踪方法
CN104867163A (zh) * 2015-05-28 2015-08-26 深圳大学 一种传递边缘分布的测量驱动目标跟踪方法与跟踪系统
CN105719312A (zh) * 2016-01-19 2016-06-29 深圳大学 基于序贯贝叶斯滤波的多目标跟踪方法及跟踪系统

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11501195B2 (en) 2013-06-28 2022-11-15 D-Wave Systems Inc. Systems and methods for quantum processing of data using a sparse coded dictionary learned from unlabeled data and supervised learning using encoded labeled data elements
US11410067B2 (en) 2015-08-19 2022-08-09 D-Wave Systems Inc. Systems and methods for machine learning using adiabatic quantum computers
US11481669B2 (en) 2016-09-26 2022-10-25 D-Wave Systems Inc. Systems, methods and apparatus for sampling from a sampling server
US11531852B2 (en) * 2016-11-28 2022-12-20 D-Wave Systems Inc. Machine learning systems and methods for training with noisy labels
US11586915B2 (en) 2017-12-14 2023-02-21 D-Wave Systems Inc. Systems and methods for collaborative filtering with variational autoencoders
US11386346B2 (en) 2018-07-10 2022-07-12 D-Wave Systems Inc. Systems and methods for quantum bayesian networks
US11461644B2 (en) 2018-11-15 2022-10-04 D-Wave Systems Inc. Systems and methods for semantic segmentation
US11468293B2 (en) 2018-12-14 2022-10-11 D-Wave Systems Inc. Simulating and post-processing using a generative adversarial network
US11900264B2 (en) 2019-02-08 2024-02-13 D-Wave Systems Inc. Systems and methods for hybrid quantum-classical computing
US11625612B2 (en) 2019-02-12 2023-04-11 D-Wave Systems Inc. Systems and methods for domain adaptation
CN110320512A (zh) * 2019-07-09 2019-10-11 大连海事大学 一种基于带标签的gm-phd平滑滤波多目标跟踪方法
CN111127523B (zh) * 2019-12-04 2023-03-24 杭州电子科技大学 基于量测迭代更新的多传感器gmphd自适应融合方法
CN111127523A (zh) * 2019-12-04 2020-05-08 杭州电子科技大学 基于量测迭代更新的多传感器gmphd自适应融合方法
CN111352104A (zh) * 2020-03-18 2020-06-30 清华大学 一种基于信息积累的弱目标检测前跟踪方法
CN111488552B (zh) * 2020-04-24 2023-03-21 商丘师范学院 基于高斯混合概率假设密度的紧邻多目标跟踪方法
CN111488552A (zh) * 2020-04-24 2020-08-04 商丘师范学院 基于高斯混合概率假设密度的紧邻多目标跟踪方法
CN112816973A (zh) * 2020-12-31 2021-05-18 清华大学 一种跟踪信息辅助的目标检测方法
CN112614163A (zh) * 2020-12-31 2021-04-06 华中光电技术研究所（中国船舶重工集团公司第七一七研究所） 一种融合贝叶斯轨迹推理的目标跟踪方法及系统
CN112816973B (zh) * 2020-12-31 2024-05-10 清华大学 一种跟踪信息辅助的目标检测方法
CN114626307A (zh) * 2022-03-29 2022-06-14 电子科技大学 一种基于变分贝叶斯的分布式一致性目标状态估计方法

Similar Documents

Publication Publication Date Title
WO2017124299A1 (fr) Procédé de suivi multicible et système de suivi basé sur un filtrage séquentiel bayésien
CN105719312B (zh) 基于序贯贝叶斯滤波的多目标跟踪方法及跟踪系统
CN107462882B (zh) 一种适用于闪烁噪声的多机动目标跟踪方法及系统
WO2018098926A1 (fr) Procédé de poursuite multi-cibles et système applicable à un bruit de papillotement
CN112154481B (zh) 基于多个测量假设的目标追踪
WO2018010099A1 (fr) Procédé de suivi de cible pour manoeuvre de virage et système associé
Dong et al. Student-t mixture labeled multi-Bernoulli filter for multi-target tracking with heavy-tailed noise
US10935653B2 (en) Multi-target tracking method and tracking system applicable to clutter environment
Beard et al. A generalised labelled multi-Bernoulli filter for extended multi-target tracking
Wang et al. Variational Bayesian IMM-filter for JMSs with unknown noise covariances
Punchihewa et al. A generalized labeled multi-Bernoulli filter for maneuvering targets
CN104867163A (zh) 一种传递边缘分布的测量驱动目标跟踪方法与跟踪系统
Li et al. State estimation for jump Markov linear systems by variational Bayesian approximation
Vo et al. An implementation of the multi-sensor generalized labeled multi-Bernoulli filter via Gibbs sampling
Vo et al. Multi-Bernoulli filtering with unknown clutter intensity and sensor field-of-view
CN106168943A (zh) 一种用于跟踪转弯机动目标的方法及其系统
Chen et al. Multitarget multisensor tracking
Lindenmaier et al. GM-PHD filter based sensor data fusion for automotive frontal perception system
Faber et al. A randomized sampling based approach to multi-object tracking
Liu et al. Multi-target Bayesian filter for propagating marginal distribution
Yang et al. Interacting multiple model unscented Gauss-Helmert filter for bearings-only tracking with state-dependent propagation delay
Wan et al. Variational Bayesian learning for robust AR modeling with the presence of sparse impulse noise
Su et al. A variational Bayesian approach for partly resolvable group tracking
Yun et al. Variational Bayesian based adaptive PDA filter in scenarios with unknown detection probability and heavy-tailed process noise
Papi et al. Multitarget tracking via joint PHD filtering and multiscan association

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16885572

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16885572

Country of ref document: EP

Kind code of ref document: A1