Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301676
Shaun Brown, S. Sukkarieh
In many multi-objective missions there are situations when actions based on maximum information gain may not be the best given the overall mission objectives. In addition to properties such as entropy, information also has value which is situationally dependent. This paper presents a derivation of information value that considers both the context of information, via a fused world belief state, and a system mission. A simulated security operation in a structured environment is implemented, with a system of mobile heterogeneous sensors tasked with information gathering. Information value is then used to determine the expected reward for sensor observations of various points in area of operations. A brief comparison is then made to a selection of pure information gain schemes. From simulation results, it has been found that information value often captures elements of the mission and context not apparent using other information entropy metrics
{"title":"The Value of Information in the Multi-Objective Mission","authors":"Shaun Brown, S. Sukkarieh","doi":"10.1109/ICIF.2006.301676","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301676","url":null,"abstract":"In many multi-objective missions there are situations when actions based on maximum information gain may not be the best given the overall mission objectives. In addition to properties such as entropy, information also has value which is situationally dependent. This paper presents a derivation of information value that considers both the context of information, via a fused world belief state, and a system mission. A simulated security operation in a structured environment is implemented, with a system of mobile heterogeneous sensors tasked with information gathering. Information value is then used to determine the expected reward for sensor observations of various points in area of operations. A brief comparison is then made to a selection of pure information gain schemes. From simulation results, it has been found that information value often captures elements of the mission and context not apparent using other information entropy metrics","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132713486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301697
M. Morelande
The problem of tracking multiple targets moving through a network of sensors is considered. It is assumed that the sensors send regular returns to a central node at which all processing is performed. Two approaches to the problem are considered: the unscented Kalman filter and a simple implementation of the auxiliary particle filter. The algorithms are formulated under a general sensor model which does not assume a particular statistical model for the measurements. Monte Carlo simulations are used to assess the performances of the algorithms with both a binary sensor model and a non-thresholded sensor model. The unscented Kalman filter significantly outperforms the particle filter in both cases and has a much lower computational expense
{"title":"Tracking multiple targets with a sensor network","authors":"M. Morelande","doi":"10.1109/ICIF.2006.301697","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301697","url":null,"abstract":"The problem of tracking multiple targets moving through a network of sensors is considered. It is assumed that the sensors send regular returns to a central node at which all processing is performed. Two approaches to the problem are considered: the unscented Kalman filter and a simple implementation of the auxiliary particle filter. The algorithms are formulated under a general sensor model which does not assume a particular statistical model for the measurements. Monte Carlo simulations are used to assess the performances of the algorithms with both a binary sensor model and a non-thresholded sensor model. The unscented Kalman filter significantly outperforms the particle filter in both cases and has a much lower computational expense","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128847793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301736
Andrew L. Bereson, R. Lobbia
This paper reaches beyond the data fusion community to find a novel way to approach the assignment problem in track-to-track (T2T) data fusion. Cluster analysis techniques are explored as a source of assignment algorithms that are practical and efficient. The proposal to apply cluster analysis to the assignment problem is based on a re-examination of the unique requirements of track-to-track fusion. This paper will present the computational argument for a more sophisticated approach to T2T assignment. It will show how the assignment problem may be recast as a clustering problem. Clustering techniques that present promising approaches to T2T assignment are briefly surveyed. A prototype T2T fusion system is described which uses an agglomerative hierarchical clustering assignment algorithm. Experimental results from this system are presented that demonstrate the feasibility, usefulness and efficiency of the proposed approach
{"title":"Efficient Track-to-Task Assignment Using Cluster Analysis","authors":"Andrew L. Bereson, R. Lobbia","doi":"10.1109/ICIF.2006.301736","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301736","url":null,"abstract":"This paper reaches beyond the data fusion community to find a novel way to approach the assignment problem in track-to-track (T2T) data fusion. Cluster analysis techniques are explored as a source of assignment algorithms that are practical and efficient. The proposal to apply cluster analysis to the assignment problem is based on a re-examination of the unique requirements of track-to-track fusion. This paper will present the computational argument for a more sophisticated approach to T2T assignment. It will show how the assignment problem may be recast as a clustering problem. Clustering techniques that present promising approaches to T2T assignment are briefly surveyed. A prototype T2T fusion system is described which uses an agglomerative hierarchical clustering assignment algorithm. Experimental results from this system are presented that demonstrate the feasibility, usefulness and efficiency of the proposed approach","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114560646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301798
J. Lancaster, S. Blackman
After giving an overview of the design of the IMM/MHT tracker, this paper discusses a joint tracking and identification approach to the multi-sensor ground target tracking problem. It is widely recognized that the requirements for the continuous tracking of important targets can only be achieved by incorporating feature data and behavioral information. Consequently, a Dempster-Shafer approach has been applied in the integration of multi-sensor classification with the target behavior so that an estimate of target type may included in the data association decision process. The ID information that may be potentially derived from HRR profiles may be combined with conventional IMM/MHT tracking techniques in order to aid the track-observation association process. Issues such as the inevitable loss of track identity due to track switching as well as the presence of confusers must be addressed. Thus, the paper discusses methods to include the effect of confusers and to efficiently reestablish track identity after a track-switch
{"title":"Joint IMM/MHT Tracking and Identification for Multi-Sensor Ground Target Tracking","authors":"J. Lancaster, S. Blackman","doi":"10.1109/ICIF.2006.301798","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301798","url":null,"abstract":"After giving an overview of the design of the IMM/MHT tracker, this paper discusses a joint tracking and identification approach to the multi-sensor ground target tracking problem. It is widely recognized that the requirements for the continuous tracking of important targets can only be achieved by incorporating feature data and behavioral information. Consequently, a Dempster-Shafer approach has been applied in the integration of multi-sensor classification with the target behavior so that an estimate of target type may included in the data association decision process. The ID information that may be potentially derived from HRR profiles may be combined with conventional IMM/MHT tracking techniques in order to aid the track-observation association process. Issues such as the inevitable loss of track identity due to track switching as well as the presence of confusers must be addressed. Thus, the paper discusses methods to include the effect of confusers and to efficiently reestablish track identity after a track-switch","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116914500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301753
R. Grasso, Francesco Spina
This paper describes a system for estimating the local density of small objects on the sea floor by exploiting a robust, non-parametric detector for high resolution images acquired by side scan sonar sensors. Low grazing angle target images are characterised by an area of strong intensity, the high-light, close to an area, the shadow, at the sensor noise level. The detector makes use of mathematical morphology to detect the highlight and the shadow areas within the image, and a fusion scheme to reduce the false alarms due to the sea floor disturbance by declaring a target acquired if an highlight is close to a shadow. Results on data sets collected in the Ligurian and Baltic Sea are reported and discussed
{"title":"Small bottom object density analysis from side scan sonar data by a mathematical morphology detector","authors":"R. Grasso, Francesco Spina","doi":"10.1109/ICIF.2006.301753","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301753","url":null,"abstract":"This paper describes a system for estimating the local density of small objects on the sea floor by exploiting a robust, non-parametric detector for high resolution images acquired by side scan sonar sensors. Low grazing angle target images are characterised by an area of strong intensity, the high-light, close to an area, the shadow, at the sensor noise level. The detector makes use of mathematical morphology to detect the highlight and the shadow areas within the image, and a fusion scheme to reduce the false alarms due to the sea floor disturbance by declaring a target acquired if an highlight is close to a shadow. Results on data sets collected in the Ligurian and Baltic Sea are reported and discussed","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116427840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301808
Huimin Chen, Y. Bar-Shalom
The problem of track-to-track association and track fusion has been considered in the literature where the fusion center has access to multiple track estimates and the associated estimation error covariances from local sensors, as well as their cross covariances. Due primarily to the communication constraints in real systems, some legacy trackers may only provide the local track estimates to the fusion center without any covariance information. In some cases, the local (sensor-level) trackers operate with fixed filter gain and do not have any self assessment of their estimation errors. In other cases, the network conveys a coarsely quantized root mean square (RMS) estimation error of each local tracker. Thus the fusion center needs to solve the track association and fusion problem with incomplete data from legacy local trackers. In this paper a robust track-to-track association and fusion algorithm is described for a distributed tracking system, which accounts for the cross correlation of the estimation error between local tracks in a practical way. Its applicability to real-time and different rate data sources is also discussed by generalizing the algorithms from the existing literature to the case of asynchronous sensors. The problem of track fusion with legacy track sources which lack covariance information is handled by approximating this information through a modified Lyapunov equation. The situation when a coarsely quantized RMS estimation error is available is also discussed. A two-sensor tracking example is used to illustrate the effectiveness of the proposed distributed track fusion algorithm and compared with a centralized interacting multiple model estimator
{"title":"Track Fusion with Legacy Track Sources","authors":"Huimin Chen, Y. Bar-Shalom","doi":"10.1109/ICIF.2006.301808","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301808","url":null,"abstract":"The problem of track-to-track association and track fusion has been considered in the literature where the fusion center has access to multiple track estimates and the associated estimation error covariances from local sensors, as well as their cross covariances. Due primarily to the communication constraints in real systems, some legacy trackers may only provide the local track estimates to the fusion center without any covariance information. In some cases, the local (sensor-level) trackers operate with fixed filter gain and do not have any self assessment of their estimation errors. In other cases, the network conveys a coarsely quantized root mean square (RMS) estimation error of each local tracker. Thus the fusion center needs to solve the track association and fusion problem with incomplete data from legacy local trackers. In this paper a robust track-to-track association and fusion algorithm is described for a distributed tracking system, which accounts for the cross correlation of the estimation error between local tracks in a practical way. Its applicability to real-time and different rate data sources is also discussed by generalizing the algorithms from the existing literature to the case of asynchronous sensors. The problem of track fusion with legacy track sources which lack covariance information is handled by approximating this information through a modified Lyapunov equation. The situation when a coarsely quantized RMS estimation error is available is also discussed. A two-sensor tracking example is used to illustrate the effectiveness of the proposed distributed track fusion algorithm and compared with a centralized interacting multiple model estimator","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124732899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301628
A. Kräußling, D. Schulz
Tracking extended targets is of central interest in mobile robotics as it is a prerequisite for interaction with the environment. There are significant differences between tracking punctiform targets and tracking extended targets. Most of the existing algorithms assume the targets to be punctiform, which is not always suitable. In recent years, two advanced algorithms for tracking extended targets have been developed by the authors-a switching algorithm and the SJPDAF. The switching algorithm uses the Kalman filter and an adapted version of the Viterbi algorithm, which includes certain geometrical characteristics of the problem. The SJPDAF combines the idea of particle filtering with the JPDAF. In this paper we present these two algorithms and compare them with respect to accuracy, speed and robustness in case of crossing targets. We show, that the more recently developed switching algorithm outperforms the SJPDAF regarding these criterions
{"title":"Tracking Extended Targets - A Switching Algorithm Versus The SJPDAF","authors":"A. Kräußling, D. Schulz","doi":"10.1109/ICIF.2006.301628","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301628","url":null,"abstract":"Tracking extended targets is of central interest in mobile robotics as it is a prerequisite for interaction with the environment. There are significant differences between tracking punctiform targets and tracking extended targets. Most of the existing algorithms assume the targets to be punctiform, which is not always suitable. In recent years, two advanced algorithms for tracking extended targets have been developed by the authors-a switching algorithm and the SJPDAF. The switching algorithm uses the Kalman filter and an adapted version of the Viterbi algorithm, which includes certain geometrical characteristics of the problem. The SJPDAF combines the idea of particle filtering with the JPDAF. In this paper we present these two algorithms and compare them with respect to accuracy, speed and robustness in case of crossing targets. We show, that the more recently developed switching algorithm outperforms the SJPDAF regarding these criterions","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"595 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127517356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301572
T. Denoeux
Dempster's rule plays a central role in the theory of belief functions. However, it assumes the items of evidence combined to be distinct, an assumption which is not always verified in practice. In this paper, a new operator, the cautious rule of combination, is introduced. This operator is commutative, associative and idempotent. This latter property makes it suitable to combine non distinct items of evidence. Extensions based on triangular norms (some of which allow to define operators whose behavior is intermediate between the Dempster's rule and the cautious rule) are also introduced
{"title":"The cautious rule of combination for belief functions and some extensions","authors":"T. Denoeux","doi":"10.1109/ICIF.2006.301572","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301572","url":null,"abstract":"Dempster's rule plays a central role in the theory of belief functions. However, it assumes the items of evidence combined to be distinct, an assumption which is not always verified in practice. In this paper, a new operator, the cautious rule of combination, is introduced. This operator is commutative, associative and idempotent. This latter property makes it suitable to combine non distinct items of evidence. Extensions based on triangular norms (some of which allow to define operators whose behavior is intermediate between the Dempster's rule and the cautious rule) are also introduced","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130098425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301552
D. Lambert
A state transition data fusion model is introduced as an extension of the dominant sensor fusion paradigm to provide a unification of both sensor and higher-level fusion
引入状态转换数据融合模型作为主流传感器融合范式的扩展，以提供传感器和高级融合的统一
{"title":"A Unification of Sensor and Higher-Level Fusion","authors":"D. Lambert","doi":"10.1109/ICIF.2006.301552","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301552","url":null,"abstract":"A state transition data fusion model is introduced as an extension of the dominant sensor fusion paradigm to provide a unification of both sensor and higher-level fusion","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132773548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301783
J. J. Sudano, Lockheed Martin
In information fusion situations, it is vital to manage uncertainty and the incomplete information set for time critical decisions. The Dempster-Shafer evidential theory is a very elegant method of mathematically representing this knowledge. The evidential theory knowledge is represented by a frame of discernment with a power-set number of basic belief assignment (BBA) components. For real time implementation this may be a bit of a conundrum especially when supporting many hypotheses in real time systems. A multi/dual probability delineation of Dempster-Shafer evidential theory is presented to overcome the power-set problem for real time implementations. The set of BBAs are mapped via pignistic probability transforms to many sets of probabilities that support the incomplete information set. These sets of probabilities are ordered via the probability information content equation for further processing (fusing, decision making). The problem has been transformed from addressing a power-set of components 2Omega to a multiple number of probability components N Omega greatly simplifying real time implementations. A fusion process demonstrating dispersion in decision space is also presented
{"title":"Yet Another Paradigm Illustrating Evidence Fusion (YAPIEF)","authors":"J. J. Sudano, Lockheed Martin","doi":"10.1109/ICIF.2006.301783","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301783","url":null,"abstract":"In information fusion situations, it is vital to manage uncertainty and the incomplete information set for time critical decisions. The Dempster-Shafer evidential theory is a very elegant method of mathematically representing this knowledge. The evidential theory knowledge is represented by a frame of discernment with a power-set number of basic belief assignment (BBA) components. For real time implementation this may be a bit of a conundrum especially when supporting many hypotheses in real time systems. A multi/dual probability delineation of Dempster-Shafer evidential theory is presented to overcome the power-set problem for real time implementations. The set of BBAs are mapped via pignistic probability transforms to many sets of probabilities that support the incomplete information set. These sets of probabilities are ordered via the probability information content equation for further processing (fusing, decision making). The problem has been transformed from addressing a power-set of components 2Omega to a multiple number of probability components N Omega greatly simplifying real time implementations. A fusion process demonstrating dispersion in decision space is also presented","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131972323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：