Pub Date : 2006-07-10DOI: 10.1109/ICIF.2006.301784
M. Sodhi, P. Swaszek, E. Bovio
Unmanned underwater vehicles (UUVs) are increasingly being used in a diverse range of applications. In one particular application, we analyze UUV operations for location, detection and classification of mines. The mission objective is to search the area of interest, using underwater imaging sensors such as side scan sonars, until either the first mine is located, or it is verified that none can be found. Communication constraints require that the vehicle be connected with physically for downloads. In such as scenario, the search area can be considered as a line, and prior probabilities of finding a mine on the line can be related to external considerations such as the bottom characteristics, etc. The optimization problem is the determination of a sequence of points on the line where the UUV should be configured to return for a data download, so as to minimize the expected mission time. Operational models are defined and analytical expressions and numerical results describe the optimal strategies for searching with several distributions and return point specifications
{"title":"Stochastic Line Search Using UUVs","authors":"M. Sodhi, P. Swaszek, E. Bovio","doi":"10.1109/ICIF.2006.301784","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301784","url":null,"abstract":"Unmanned underwater vehicles (UUVs) are increasingly being used in a diverse range of applications. In one particular application, we analyze UUV operations for location, detection and classification of mines. The mission objective is to search the area of interest, using underwater imaging sensors such as side scan sonars, until either the first mine is located, or it is verified that none can be found. Communication constraints require that the vehicle be connected with physically for downloads. In such as scenario, the search area can be considered as a line, and prior probabilities of finding a mine on the line can be related to external considerations such as the bottom characteristics, etc. The optimization problem is the determination of a sequence of points on the line where the UUV should be configured to return for a data download, so as to minimize the expected mission time. Operational models are defined and analytical expressions and numerical results describe the optimal strategies for searching with several distributions and return point specifications","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"41 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":"134394517","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.2006.301684
F. Sawo, D. Brunn, U. Hanebeck
In this paper we attempt to lay the foundation for a novel filtering technique for the fusion of two random vectors with imprecisely known stochastic dependency. This problem mainly occurs in decentralized estimation, e.g., of a distributed phenomenon, where the stochastic dependencies between the individual states are not stored. Thus, we derive parameterized joint densities with both Gaussian marginals and Gaussian mixture marginals. These parameterized joint densities contain all information about the stochastic dependencies between their marginal densities in terms of a parameter vector xi, which can be regarded as a generalized correlation parameter. Unlike the classical correlation coefficient, this parameter is a sufficient measure for the stochastic dependency even characterized by more complex density functions such as Gaussian mixtures. Once this structure and the bounds of these parameters are known, bounding densities containing all possible density functions could be found
{"title":"Parameterized Joint Densities with Gaussian and Gaussian Mixture Marginals","authors":"F. Sawo, D. Brunn, U. Hanebeck","doi":"10.1109/ICIF.2006.301684","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301684","url":null,"abstract":"In this paper we attempt to lay the foundation for a novel filtering technique for the fusion of two random vectors with imprecisely known stochastic dependency. This problem mainly occurs in decentralized estimation, e.g., of a distributed phenomenon, where the stochastic dependencies between the individual states are not stored. Thus, we derive parameterized joint densities with both Gaussian marginals and Gaussian mixture marginals. These parameterized joint densities contain all information about the stochastic dependencies between their marginal densities in terms of a parameter vector xi, which can be regarded as a generalized correlation parameter. Unlike the classical correlation coefficient, this parameter is a sufficient measure for the stochastic dependency even characterized by more complex density functions such as Gaussian mixtures. Once this structure and the bounds of these parameters are known, bounding densities containing all possible density functions could be found","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"18 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":"132077866","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.2006.301568
F. Souvannavong, B. Huet
In this paper we introduce a new method for fusing classifier outputs. It is inspired from the behavior knowledge space model with the extra ability to work on continuous input values. This property allows to deal with heterogeneous classifiers and in particular it does not require to make any decision at the classifier level. We propose to build a set of units, defining a knowledge space, with respect to classifier output spaces. A new sample is then classified with respect to the unit it belongs to and some statistics computed on each unit. Several methods to create cells and make the final decision are proposed and compared to k-nearest neighbor and decision tree schemas. The evaluation is conducted on the task of video content retrieval which will reveal the efficiency of our approach
{"title":"Continuous Behaviour Knowledge Space For Semantic Indexing of Video Content","authors":"F. Souvannavong, B. Huet","doi":"10.1109/ICIF.2006.301568","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301568","url":null,"abstract":"In this paper we introduce a new method for fusing classifier outputs. It is inspired from the behavior knowledge space model with the extra ability to work on continuous input values. This property allows to deal with heterogeneous classifiers and in particular it does not require to make any decision at the classifier level. We propose to build a set of units, defining a knowledge space, with respect to classifier output spaces. A new sample is then classified with respect to the unit it belongs to and some statistics computed on each unit. Several methods to create cells and make the final decision are proposed and compared to k-nearest neighbor and decision tree schemas. The evaluation is conducted on the task of video content retrieval which will reveal the efficiency of our approach","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":"133683225","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.2006.301670
Genshe Chen, Dan Shen, C. Kwan, J. B. Cruz, M. Kruger, E. Blasch
The strategy of data fusion has been applied in threat prediction and situation awareness and the terminology has been standardized by the Joint Directors of Laboratories (JDL) in the form of a so-called JDL data fusion model, which currently called DFIG model. Higher levels of the DFIG model call for prediction of future development and awareness of the development of a situation. It is known that Bayesian network is an insightful approach to determine optimal strategies against asymmetric adversarial opponent. However, it lacks the essential adversarial decision processes perspective. In this paper, a highly innovative data-fusion framework for asymmetric-threat detection and prediction based on advanced knowledge infrastructure and stochastic (Markov) game theory is proposed. In particular, asymmetric and adaptive threats are detected and grouped by intelligent agent and hierarchical entity aggregation in level 2 and their intents are predicted by a decentralized Markov (stochastic) game model with deception in level 3. We have verified that our proposed algorithms are scalable, stable, and perform satisfactorily according to the situation awareness performance metric
{"title":"Game Theoretic Approach to Threat Prediction and Situation Awareness","authors":"Genshe Chen, Dan Shen, C. Kwan, J. B. Cruz, M. Kruger, E. Blasch","doi":"10.1109/ICIF.2006.301670","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301670","url":null,"abstract":"The strategy of data fusion has been applied in threat prediction and situation awareness and the terminology has been standardized by the Joint Directors of Laboratories (JDL) in the form of a so-called JDL data fusion model, which currently called DFIG model. Higher levels of the DFIG model call for prediction of future development and awareness of the development of a situation. It is known that Bayesian network is an insightful approach to determine optimal strategies against asymmetric adversarial opponent. However, it lacks the essential adversarial decision processes perspective. In this paper, a highly innovative data-fusion framework for asymmetric-threat detection and prediction based on advanced knowledge infrastructure and stochastic (Markov) game theory is proposed. In particular, asymmetric and adaptive threats are detected and grouped by intelligent agent and hierarchical entity aggregation in level 2 and their intents are predicted by a decentralized Markov (stochastic) game model with deception in level 3. We have verified that our proposed algorithms are scalable, stable, and perform satisfactorily according to the situation awareness performance metric","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"55 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":"133694816","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.2006.301619
A. D. Mastio, V. Cappellini
In the last few years, the cultural heritage field has posed its attention over image processing techniques, in particular for the diagnostic of art works. Many different images of the same painting are taken, in different parts of the light spectrum; these different images have to be fused together, to get an augmented image showing much more details and information which are only visible in some sub-parts of the spectrum singularly. In this paper, we pose the attention over the compulsory step accomplished just before the "fusion" of such images, i.e. the registration step; in particular, we present an automatic registration technique, based on the computation of mutual information. By means of the registration, it is possible to exactly align the different images, which is the preliminary step to obtain a useful and correct augmented image. These techniques can be also applied to other areas, and in particular to remote sensing images
{"title":"Registration of Digital Images","authors":"A. D. Mastio, V. Cappellini","doi":"10.1109/ICIF.2006.301619","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301619","url":null,"abstract":"In the last few years, the cultural heritage field has posed its attention over image processing techniques, in particular for the diagnostic of art works. Many different images of the same painting are taken, in different parts of the light spectrum; these different images have to be fused together, to get an augmented image showing much more details and information which are only visible in some sub-parts of the spectrum singularly. In this paper, we pose the attention over the compulsory step accomplished just before the \"fusion\" of such images, i.e. the registration step; in particular, we present an automatic registration technique, based on the computation of mutual information. By means of the registration, it is possible to exactly align the different images, which is the preliminary step to obtain a useful and correct augmented image. These techniques can be also applied to other areas, and in particular to remote sensing images","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"1 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121016007","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.2006.301626
S. Giompapa, A. Farina, F. Gini, A. Graziano, R. D. Stefano
This work presents a deterministic approach to the problem of modelling the human behaviour in a command and control radar system and it considers the fusion of information between the operator and the system. The implementation and the results of a case study are presented where a human operator performs a tracking operation of multiple targets in a sea region. The mission performed by the operator is the surveillance of a coast area and the selection of a system action against possible threat targets, in order to check their identity. An analytical model of human memory has been investigated where the human decision maker is represented as a subsystem involved with two operational blocks, corresponding to the situation assessment process and the response selection process that he performs. The operator performance is evaluated by mean of his error probability in these two processes
{"title":"A Model for a Human Decision-Maker in a Command and Control Radar System: Surveillance Tracking of Multiple Targets","authors":"S. Giompapa, A. Farina, F. Gini, A. Graziano, R. D. Stefano","doi":"10.1109/ICIF.2006.301626","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301626","url":null,"abstract":"This work presents a deterministic approach to the problem of modelling the human behaviour in a command and control radar system and it considers the fusion of information between the operator and the system. The implementation and the results of a case study are presented where a human operator performs a tracking operation of multiple targets in a sea region. The mission performed by the operator is the surveillance of a coast area and the selection of a system action against possible threat targets, in order to check their identity. An analytical model of human memory has been investigated where the human decision maker is represented as a subsystem involved with two operational blocks, corresponding to the situation assessment process and the response selection process that he performs. The operator performance is evaluated by mean of his error probability in these two processes","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"10 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":"114928659","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.2006.301658
L. Snidaro, C. Piciarelli, G. Foresti
In this paper, we address the problem of identifying anomalous events in the context of a multi sensor surveillance system. Targets' trajectories are analyzed and compared to common patterns of activity represented as clusters of trajectories. Here we extend our previous work to cater for observations provided by multiple cameras observing the same scene. Data fusion is performed within the Dempster-Shafer theory of evidence framework. The proposed approach is validated through experimental results performed in the context of an automatic road traffic monitoring application
{"title":"Fusion of trajectory clusters for situation assessment","authors":"L. Snidaro, C. Piciarelli, G. Foresti","doi":"10.1109/ICIF.2006.301658","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301658","url":null,"abstract":"In this paper, we address the problem of identifying anomalous events in the context of a multi sensor surveillance system. Targets' trajectories are analyzed and compared to common patterns of activity represented as clusters of trajectories. Here we extend our previous work to cater for observations provided by multiple cameras observing the same scene. Data fusion is performed within the Dempster-Shafer theory of evidence framework. The proposed approach is validated through experimental results performed in the context of an automatic road traffic monitoring application","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":"116948141","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.2006.301570
T. D. Dixon, Jian Li, J. Noyes, T. Troscianko, S. G. Nikolov, J. Lewis, E. Canga, D. Bull, C. N. Canagarajah
Image fusion is the process of combining images of differing modalities, such as visible and infrared (IR) images. Significant work has recently been carried out comparing methods of fused image assessment, with findings strongly suggesting that a task-centred approach would be beneficial to the assessment process. The current paper reports a pilot study analysing eye movements of participants involved in four tasks. The first and second tasks involved tracking a human figure wearing camouflage clothing walking through thick undergrowth at light and dark luminance levels, whilst the third and fourth task required tracking an individual in a crowd, again at two luminance levels. Participants were shown the original visible and IR images individually, pixel-averaged, contrast pyramid, and dual-tree complex wavelet fused video sequences. They viewed each display and sequence three times to compare inter-subject scanpath variability. This paper describes the initial analysis of the eye-tracking data gathered from the pilot study. These were also compared with computational metric assessment of the image sequences
{"title":"Scanpath Analysis of Fused Multi-Sensor Images with Luminance Change: A Pilot Study","authors":"T. D. Dixon, Jian Li, J. Noyes, T. Troscianko, S. G. Nikolov, J. Lewis, E. Canga, D. Bull, C. N. Canagarajah","doi":"10.1109/ICIF.2006.301570","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301570","url":null,"abstract":"Image fusion is the process of combining images of differing modalities, such as visible and infrared (IR) images. Significant work has recently been carried out comparing methods of fused image assessment, with findings strongly suggesting that a task-centred approach would be beneficial to the assessment process. The current paper reports a pilot study analysing eye movements of participants involved in four tasks. The first and second tasks involved tracking a human figure wearing camouflage clothing walking through thick undergrowth at light and dark luminance levels, whilst the third and fourth task required tracking an individual in a crowd, again at two luminance levels. Participants were shown the original visible and IR images individually, pixel-averaged, contrast pyramid, and dual-tree complex wavelet fused video sequences. They viewed each display and sequence three times to compare inter-subject scanpath variability. This paper describes the initial analysis of the eye-tracking data gathered from the pilot study. These were also compared with computational metric assessment of the image sequences","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"62 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":"114912001","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.2006.301720
G. Mellema
Passive sonar depends on signals of opportunity to detect, track and localize targets. These signals are typically detected and then tracked using Kalman filter-type signal followers. Target motion analysis (TMA) is then used to estimate the target's range and, from this, its position, course and speed. The accuracy of TMA is strongly dependent on the duration of the available track. Initiating a second tracker in reverse time at the time of detection can reduce or eliminate the delay between target detection and localization. A detection and tracking system for a passive sonar using a towed array receiver is described and an example of reverse-time tracking using real data is provided. Reverse-time tracking is able to significantly increase the amount of track data that can be extracted from already available data, highlighting the need for improved data fusion. Potential improvements to this enhanced system through track association are discussed
{"title":"Reverse-Time Tracking to Enhance Passive Sonar","authors":"G. Mellema","doi":"10.1109/ICIF.2006.301720","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301720","url":null,"abstract":"Passive sonar depends on signals of opportunity to detect, track and localize targets. These signals are typically detected and then tracked using Kalman filter-type signal followers. Target motion analysis (TMA) is then used to estimate the target's range and, from this, its position, course and speed. The accuracy of TMA is strongly dependent on the duration of the available track. Initiating a second tracker in reverse time at the time of detection can reduce or eliminate the delay between target detection and localization. A detection and tracking system for a passive sonar using a towed array receiver is described and an example of reverse-time tracking using real data is provided. Reverse-time tracking is able to significantly increase the amount of track data that can be extracted from already available data, highlighting the need for improved data fusion. Potential improvements to this enhanced system through track association are discussed","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"9 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":"115542142","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.2006.301754
R. Grasso, S. Giannecchini
Tactical decision aid systems support the military or civilian operation planning process providing the decisional authorities with a simplified view of the environmental conditions over a theatre of operations. Methods for multi-source data fusion and support for disseminating and managing geospatial data are key factors for a successful system implementation. This paper describes a tactical decision aid system based on fuzzy logic reasoning for data fusion and on current open geospatial consortium specifications for interoperability, data dissemination and geo-spatial services support. Results from system implementation tests during live exercises are reported and discussed showing the flexibility and reliability of the proposed architecture. Future directions are provided and discussed as well, including web processing services, context fuzzy reasoning and group decision making
{"title":"Geo-spatial Tactical Decision Aid systems: fuzzy logic for supporting decision making","authors":"R. Grasso, S. Giannecchini","doi":"10.1109/ICIF.2006.301754","DOIUrl":"https://doi.org/10.1109/ICIF.2006.301754","url":null,"abstract":"Tactical decision aid systems support the military or civilian operation planning process providing the decisional authorities with a simplified view of the environmental conditions over a theatre of operations. Methods for multi-source data fusion and support for disseminating and managing geospatial data are key factors for a successful system implementation. This paper describes a tactical decision aid system based on fuzzy logic reasoning for data fusion and on current open geospatial consortium specifications for interoperability, data dissemination and geo-spatial services support. Results from system implementation tests during live exercises are reported and discussed showing the flexibility and reliability of the proposed architecture. Future directions are provided and discussed as well, including web processing services, context fuzzy reasoning and group decision making","PeriodicalId":248061,"journal":{"name":"2006 9th International Conference on Information Fusion","volume":"133 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":"121356176","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：