Pub Date : 2007-07-09DOI: 10.1109/ICIF.2007.4408077
G. Ng, K. Ng, K. H. Tan, Chong Hock K. Goh
In this paper, we present two novel methods to handle the fusion of multiple Bayesian Network knowledge fragments which we termed N-Combinator and N-Clone. In DSO National Laboratories, we have developed a cognition based dynamic reasoning machine called D'Brain capable of performing high level data fusion. Knowledge is encapsulated in D'Brain as Bayesian Networks knowledge fragments. D'Brain is dynamic in its reasoning mechanism that resembles human reasoning, where the knowledge structure is ever evolving with the different sources of observable inputs. N-Combinator and N-Clone are the methods used in the dynamic reasoning mechanism. Experiments have shown the good performance of these two methods.
{"title":"Novel methods for fusing Bayesian network knowledge fragments in d’brain","authors":"G. Ng, K. Ng, K. H. Tan, Chong Hock K. Goh","doi":"10.1109/ICIF.2007.4408077","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408077","url":null,"abstract":"In this paper, we present two novel methods to handle the fusion of multiple Bayesian Network knowledge fragments which we termed N-Combinator and N-Clone. In DSO National Laboratories, we have developed a cognition based dynamic reasoning machine called D'Brain capable of performing high level data fusion. Knowledge is encapsulated in D'Brain as Bayesian Networks knowledge fragments. D'Brain is dynamic in its reasoning mechanism that resembles human reasoning, where the knowledge structure is ever evolving with the different sources of observable inputs. N-Combinator and N-Clone are the methods used in the dynamic reasoning mechanism. Experiments have shown the good performance of these two methods.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126778951","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408177
Ya-Dong Wang, Jian-Kang Wu, Weimin Huang, A. Kassim
This paper presents our work which involves the application of a recursive Bayesian filter, the Gaussian mixture probability hypothesis density (GMPHD) filter, to a visual tracking problem. Foreground objects are detected using statistical background modeling to obtain measurements which are input into the filter. The GMPHD filter explicitly models the birth, survival and death of objects by managing the number of Gaussian components and jointly estimates the time-varying number of objects and their states. A scene-driven method is proposed to initialize the GMPHD filter and model the birth of new objects. The results shows when a person or a group appeared, merged, split, and disappeared in the field of view, the GMPHD filter can track the number and positions at the most time. The scene-driven GMPHD filter can track the birth of new objects faster than the particle PHD filter.
{"title":"Gaussian mixture probability hypothesis density for visual people racking","authors":"Ya-Dong Wang, Jian-Kang Wu, Weimin Huang, A. Kassim","doi":"10.1109/ICIF.2007.4408177","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408177","url":null,"abstract":"This paper presents our work which involves the application of a recursive Bayesian filter, the Gaussian mixture probability hypothesis density (GMPHD) filter, to a visual tracking problem. Foreground objects are detected using statistical background modeling to obtain measurements which are input into the filter. The GMPHD filter explicitly models the birth, survival and death of objects by managing the number of Gaussian components and jointly estimates the time-varying number of objects and their states. A scene-driven method is proposed to initialize the GMPHD filter and model the birth of new objects. The results shows when a person or a group appeared, merged, split, and disappeared in the field of view, the GMPHD filter can track the number and positions at the most time. The scene-driven GMPHD filter can track the birth of new objects faster than the particle PHD filter.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121152825","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408174
F. Fletcher, B. Ristic, D. Musicki
This paper considers the recursive estimation of emitter location using time difference of arrival measurements formed by the correlation of signals received by two unmanned aerial vehicles. The time difference of arrival measurement defines an hyperbola of possible emitter locations. This hyperbola is used as a measurement in a nonlinear Alter. The performance of two such filters, an extended Kalman filter (EKF) and an unscented Kalman filter (UKF), is analysed for a stationary and moving emitter and compared with the Cramer-Rao lower bound. The UKF performs generally better than the EKF, but both algorithms suffer from diverged tracks.
{"title":"Recursive estimation of emitter location using TDOA measurements from two UAVs","authors":"F. Fletcher, B. Ristic, D. Musicki","doi":"10.1109/ICIF.2007.4408174","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408174","url":null,"abstract":"This paper considers the recursive estimation of emitter location using time difference of arrival measurements formed by the correlation of signals received by two unmanned aerial vehicles. The time difference of arrival measurement defines an hyperbola of possible emitter locations. This hyperbola is used as a measurement in a nonlinear Alter. The performance of two such filters, an extended Kalman filter (EKF) and an unscented Kalman filter (UKF), is analysed for a stationary and moving emitter and compared with the Cramer-Rao lower bound. The UKF performs generally better than the EKF, but both algorithms suffer from diverged tracks.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125023446","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408109
Zhenhua Li, H. Leung
This paper presents a contour-based multisensor image registration algorithm. The characteristic of this approach is that the registration parameters are calculated according to the centroids and the long axes of matched contour pairs in the images to be registered It overcomes the difficulties of control point detection and correspondence in feature- based registration techniques. The geometrical deformation between the reference and sensed images is assumed to follow a rigid transformation. Salient contours are extracted from the reference and sensed images, respectively. After contour matching, open contour matches are changed to closed contour matches by linking the two endpoints of each open contour together with a line section. Registration parameters are then estimated according to the centroids and the angles of long axes of closed contour matches. Experiments using real data show that the proposed algorithm works well in multisensor image registration.
{"title":"Contour-based multisensor image registration with rigid transformation","authors":"Zhenhua Li, H. Leung","doi":"10.1109/ICIF.2007.4408109","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408109","url":null,"abstract":"This paper presents a contour-based multisensor image registration algorithm. The characteristic of this approach is that the registration parameters are calculated according to the centroids and the long axes of matched contour pairs in the images to be registered It overcomes the difficulties of control point detection and correspondence in feature- based registration techniques. The geometrical deformation between the reference and sensed images is assumed to follow a rigid transformation. Salient contours are extracted from the reference and sensed images, respectively. After contour matching, open contour matches are changed to closed contour matches by linking the two endpoints of each open contour together with a line section. Registration parameters are then estimated according to the centroids and the angles of long axes of closed contour matches. Experiments using real data show that the proposed algorithm works well in multisensor image registration.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122475275","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408119
F. Sawo, Marco F. Huber, U. Hanebeck
This paper addresses the problem of model-based reconstruction and parameter identification of distributed phenomena characterized by partial differential equations. The novelty of the proposed method is the systematic approach and the integrated treatment of uncertainties, which naturally occur in the physical system and arise from noisy measurements. The main challenge of accurate reconstruction is that model parameters, i.e., diffusion coefficients, of the physical model are not known in advance and usually need to be identified. Generally, the problem of parameter identification leads to a nonlinear estimation problem. Hence, a novel efficient recursive procedure is employed. Unlike other estimators, the so-called Hybrid Density Filter not only assures accurate estimation results for nonlinear systems, but also offers an efficient processing. By this means it is possible to reconstruct and identify distributed phenomena monitored by autonomous wireless sensor networks. The performance of the proposed estimation method is demonstrated by means of simulations.
{"title":"Parameter identification and reconstruction for distributed phenomena based on hybrid density filter","authors":"F. Sawo, Marco F. Huber, U. Hanebeck","doi":"10.1109/ICIF.2007.4408119","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408119","url":null,"abstract":"This paper addresses the problem of model-based reconstruction and parameter identification of distributed phenomena characterized by partial differential equations. The novelty of the proposed method is the systematic approach and the integrated treatment of uncertainties, which naturally occur in the physical system and arise from noisy measurements. The main challenge of accurate reconstruction is that model parameters, i.e., diffusion coefficients, of the physical model are not known in advance and usually need to be identified. Generally, the problem of parameter identification leads to a nonlinear estimation problem. Hence, a novel efficient recursive procedure is employed. Unlike other estimators, the so-called Hybrid Density Filter not only assures accurate estimation results for nonlinear systems, but also offers an efficient processing. By this means it is possible to reconstruct and identify distributed phenomena monitored by autonomous wireless sensor networks. The performance of the proposed estimation method is demonstrated by means of simulations.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122489914","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408214
J. Biermann
A very short overview is given on experience gained in the area of high level information fusion (JDL level 2 and 3) since 1988. The main characteristics of the referenced projects and experimental systems for the support of intelligence officers in land battle missions will be outlined. The different approaches to analyse and model military intelligence processing and the development of concepts and methods are described. Lessons learned from these projects are used to give a personal perception of the actual situation in level 2/3 fusion activities for intelligence and to suggest possible ways ahead for further research.
{"title":"Some experiences with experimental high level fusion systems","authors":"J. Biermann","doi":"10.1109/ICIF.2007.4408214","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408214","url":null,"abstract":"A very short overview is given on experience gained in the area of high level information fusion (JDL level 2 and 3) since 1988. The main characteristics of the referenced projects and experimental systems for the support of intelligence officers in land battle missions will be outlined. The different approaches to analyse and model military intelligence processing and the development of concepts and methods are described. Lessons learned from these projects are used to give a personal perception of the actual situation in level 2/3 fusion activities for intelligence and to suggest possible ways ahead for further research.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133437010","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408032
J. Roy
Uncertainty makes the analysis of even simple situations difficult. It forces situation analysts to formulate and manage hypotheses during the construction of the explicit representations of the real world situations. Because of human cognitive limitations, this may quickly become overwhelming, even for the most experienced and capable analysts. In an attempt to provide better support systems, this position paper revisits the main concepts behind Multiple Hypothesis Tracking (MHT) in order to highlight how these ideas could be reused to deal with uncertainty in situation analysis. The development of a prototype reusing components of a prior MHT implementation is briefly presented. Finally, a number of challenging R&D issues and questions that have not yet been addressed are identified.
{"title":"Towards multiple hypothesis situation analysis","authors":"J. Roy","doi":"10.1109/ICIF.2007.4408032","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408032","url":null,"abstract":"Uncertainty makes the analysis of even simple situations difficult. It forces situation analysts to formulate and manage hypotheses during the construction of the explicit representations of the real world situations. Because of human cognitive limitations, this may quickly become overwhelming, even for the most experienced and capable analysts. In an attempt to provide better support systems, this position paper revisits the main concepts behind Multiple Hypothesis Tracking (MHT) in order to highlight how these ideas could be reused to deal with uncertainty in situation analysis. The development of a prototype reusing components of a prior MHT implementation is briefly presented. Finally, a number of challenging R&D issues and questions that have not yet been addressed are identified.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131890692","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408147
D. Danu, A. Sinha, T. Kirubarajan, M. Farooq, D. Brookes
Over-the-horizon (OTH) radar and automatic identification system (AIS) are commonly used in the surveillance of maritime areas. This paper presents a method, which includes tracking and association algorithms, for fusing the information from these two types of systems into an overall maritime picture. Data to be fused consists of asynchronous track estimates from the OTH system and measurements obtained from AIS. The data available at the fusion center, as output of real world systems, contained incomplete information, compared to theoretical tracking and fusion algorithms. A method to estimate the missing information in the input data is described. Results obtained using real data as well as simulated data are presented. This type of fusion provides overall pictures of maritime areas, with benefits for surveillance against military threats, as well as threats to exclusive economic zones.
{"title":"Fusion of over-the-horizon radar and automatic identification systems for overall maritime picture","authors":"D. Danu, A. Sinha, T. Kirubarajan, M. Farooq, D. Brookes","doi":"10.1109/ICIF.2007.4408147","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408147","url":null,"abstract":"Over-the-horizon (OTH) radar and automatic identification system (AIS) are commonly used in the surveillance of maritime areas. This paper presents a method, which includes tracking and association algorithms, for fusing the information from these two types of systems into an overall maritime picture. Data to be fused consists of asynchronous track estimates from the OTH system and measurements obtained from AIS. The data available at the fusion center, as output of real world systems, contained incomplete information, compared to theoretical tracking and fusion algorithms. A method to estimate the missing information in the input data is described. Results obtained using real data as well as simulated data are presented. This type of fusion provides overall pictures of maritime areas, with benefits for surveillance against military threats, as well as threats to exclusive economic zones.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134216333","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408024
Henrik Boström
Two strategies for fusing information from multiple sources when generating predictive models in the domain of pesticide classification are investigated: i) fusing different sets of features (molecular descriptors) before building a model and ii) fusing the classifiers built from the individual descriptor sets. An empirical investigation demonstrates that the choice of strategy can have a significant impact on the predictive performance. Furthermore, the experiment shows that the best strategy is dependent on the type of predictive model considered. When generating a decision tree for pesticide classification, a statistically significant difference in accuracy is observed in favor of combining predictions from the individual models compared to generating a single model from the fused set of molecular descriptors. On the other hand, when the model consists of an ensemble of decision trees, a statistically significant difference in accuracy is observed in favor of building the model from the fused set of descriptors compared to fusing ensemble models built from the individual sources.
{"title":"Feature vs. classifier fusion for predictive data mining a case study in pesticide classification","authors":"Henrik Boström","doi":"10.1109/ICIF.2007.4408024","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408024","url":null,"abstract":"Two strategies for fusing information from multiple sources when generating predictive models in the domain of pesticide classification are investigated: i) fusing different sets of features (molecular descriptors) before building a model and ii) fusing the classifiers built from the individual descriptor sets. An empirical investigation demonstrates that the choice of strategy can have a significant impact on the predictive performance. Furthermore, the experiment shows that the best strategy is dependent on the type of predictive model considered. When generating a decision tree for pesticide classification, a statistically significant difference in accuracy is observed in favor of combining predictions from the individual models compared to generating a single model from the fused set of molecular descriptors. On the other hand, when the model consists of an ensemble of decision trees, a statistically significant difference in accuracy is observed in favor of building the model from the fused set of descriptors compared to fusing ensemble models built from the individual sources.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"14 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134290195","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 : 2007-07-09DOI: 10.1109/ICIF.2007.4408055
D. Lambert
The state transition data fusion (STDF) model is an extension of the dominant sensor fusion paradigm to provide a unification of both sensor and higher-level fusion. Maritime domain awareness (MDA) is the problem of situation awareness in the maritime domain. This paper outlines an application of the STDF model to perform automated situation assessments for an aspect of MDA.
{"title":"STDF model based maritime situation assessments","authors":"D. Lambert","doi":"10.1109/ICIF.2007.4408055","DOIUrl":"https://doi.org/10.1109/ICIF.2007.4408055","url":null,"abstract":"The state transition data fusion (STDF) model is an extension of the dominant sensor fusion paradigm to provide a unification of both sensor and higher-level fusion. Maritime domain awareness (MDA) is the problem of situation awareness in the maritime domain. This paper outlines an application of the STDF model to perform automated situation assessments for an aspect of MDA.","PeriodicalId":298941,"journal":{"name":"2007 10th International Conference on Information Fusion","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114430345","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：