2020 IEEE 23rd International Conference on Information Fusion (FUSION)最新文献

{"title":"Towards a formal comparison of uncertainty handling","authors":"Cristina Ramos Flores, A. Jousselme, P. Costa","doi":"10.23919/FUSION45008.2020.9190168","DOIUrl":"https://doi.org/10.23919/FUSION45008.2020.9190168","url":null,"abstract":"This paper explores the use of the Uncertainty Representation and Reasoning Evaluation Framework (URREF), a framework intended to change that state of affairs, in evaluating potential uncertainty representation approaches for a maritime Decision Support System. We revisit some comparison aspects discussed along the years and map them to the URREF. We illustrate the comparison on a simple maritime use case involving basic reasoning about threat assessment, with observations from partially reliable sources. The same fusion problem is modeled with the two uncertainty theories of Bayesian probability theory and evidence theory. Within the same framework, we consider two different reasoning schemes, Causal and Evidential, complemented with a source model of partial reliability. Comparison items are mapped to URREF ontology criteria of (Representation) Expressiveness and (Reasoning) Correctness. We highlight the criteria that can be useful in supporting systems developers in their choice of how to represent and manage uncertainty in information fusion processes, and propose some refinement to the URREF to capture handling of inconsistency.","PeriodicalId":419881,"journal":{"name":"2020 IEEE 23rd International Conference on Information Fusion (FUSION)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126444156","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}

{"title":"Simultaneous Estimation of Filtered and Smoothed State Probability Density Functions by Multiple Distribution Estimation","authors":"Masaya Murata, I. Kawano, Koichi Inoue","doi":"10.23919/FUSION45008.2020.9190352","DOIUrl":"https://doi.org/10.23919/FUSION45008.2020.9190352","url":null,"abstract":"This paper shows that for the multiple distribution estimation filter (MDEF)[1] [2], the one-step-behind (OSB) smoothed state probability density function (PDF) used for the estimation of the filtered state PDF is the key factor for the high filtering accuracy of the MDEF. The MDEF calculates the OSB smoothed state PDF prior to the calculation of the filtered state PDF at the current epoch and the filtered state PDF is estimated by the marginalization of the conditional state PDF with respect to this smoothed state PDF. Since the OSB smoothed state PDFs are obtained at every time step prior to the observation update, the MDEF can be regarded as providing the simultaneous estimation of the filtered and OSB smoothed state PDFs. In this paper, we numerically evaluate the estimation accuracy for the OSB smoothed state estimates by the MDEF using the benchmark filtering problems [3]–[5] and compare it with those for the particle and the Gaussian smoothers employed to the MDEF. We confirmed that the smoothing accuracy for the OSB smoothed state estimates was more accurate than that for the Gaussian smoother and almost comparable to that for the particle smoother, while the calculation cost was significantly lowered than that for the particle smoother.","PeriodicalId":419881,"journal":{"name":"2020 IEEE 23rd International Conference on Information Fusion (FUSION)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132495174","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}

{"title":"VADR: Discriminative Multimodal Explanations for Situational Understanding","authors":"Harrison Taylor, Liam Hiley, Jack Furby, A. Preece, Dave Braines","doi":"10.23919/FUSION45008.2020.9190215","DOIUrl":"https://doi.org/10.23919/FUSION45008.2020.9190215","url":null,"abstract":"The focus of this paper is on the generation of multimodal explanations for information fusion tasks performed on multimodal data. We propose that separating modal components in saliency map explanations provides users with a better understanding of how convolutional neural networks process multimodal data. We adapt established state-of-the-art explainability techniques to mid-level fusion networks in order to better understand (a) which modality of the input contributes most to a model's decision and (b) which parts of the input data are most relevant to that decision. Our method separates temporal from non-temporal information to allow a user to focus their attention on salient elements of the scene that are changing in multiple modalities. The work is experimentally tested on an activity recognition task using video and audio data. In view of the fact that explanations need to be tailored to the type of user in a User Fusion context, we focus on meeting explanation requirements for system creators and operators respectively.","PeriodicalId":419881,"journal":{"name":"2020 IEEE 23rd International Conference on Information Fusion (FUSION)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130906610","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}

{"title":"Explainability in threat assessment with evidential networks and sensitivity spaces","authors":"P. Kowalski, Maximilian Zocholl, A. Jousselme","doi":"10.23919/FUSION45008.2020.9190475","DOIUrl":"https://doi.org/10.23919/FUSION45008.2020.9190475","url":null,"abstract":"One of the main threats to the underwater communication cables identified in the recent years is possible tampering or damage by malicious actors. This paper proposes a solution with explanation abilities to detect and investigate this kind of threat within the evidence theory framework. The reasoning scheme implements the traditional “opportunity-capability-intent” threat model to assess a degree to which a given vessel may pose a threat. The scenario discussed considers a variety of possible pieces of information available from different sources. A source quality model is used to reason with the partially reliable sources and the impact of this meta-information on the overall assessment is illustrated. Examples of uncertain relationships between the relevant variables are modelled and the constructed model is used to investigate the probability of threat of four vessels of different types. One of these cases is discussed in more detail to demonstrate the explanation abilities. Explanations about inference are provided thanks to sensitivity spaces in which the impact of the different pieces of information on the reasoning are compared.","PeriodicalId":419881,"journal":{"name":"2020 IEEE 23rd International Conference on Information Fusion (FUSION)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121911567","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}

{"title":"An Explainable Statistical Learning Algorithm to Support Data Fusion","authors":"K. Dayman, J. Hite, Adam Drescher, B. Ade","doi":"10.23919/FUSION45008.2020.9190238","DOIUrl":"https://doi.org/10.23919/FUSION45008.2020.9190238","url":null,"abstract":"This paper presents a statistical learning algorithm called the relevance vector machine that is currently under development to support data fusion applications. The algorithm is applicable to classification and regression problems and has been shown to be capable of learning complex, explainable behaviors in real engineering problems. This article summarizes construction of the learning algorithm and provides an example application to demonstrate some of the capabilities of the relevance vector machine with feature fusion. Finally, the possibilities are presented for using the relevance vector machine to support multi-modal data fusion by exploiting the statistically consistent outputs given by the model to extend binary label fusion to continuous label fusion.","PeriodicalId":419881,"journal":{"name":"2020 IEEE 23rd International Conference on Information Fusion (FUSION)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125981158","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}

{"title":"Towards Cognitive Vehicles: GNSS-free Localization using Visual Anchors","authors":"Abdessattar Hayouni, B. Debaque, N. Duclos-Hindié, M. Florea","doi":"10.23919/FUSION45008.2020.9190496","DOIUrl":"https://doi.org/10.23919/FUSION45008.2020.9190496","url":null,"abstract":"Cognitive vehicles (CV) differ from smart vehicles (SV) in a way that they don't just rely on the sensors' readings and follow rigorously the patterns and functions already preprogrammed externally. CVs utilize the different sensors as a source of information, which needs to be processed and turned into intelligence and perception. CVs learn at a scale, make assumptions, predict outcomes, and learn from experience rather than being explicitly programmed. In this work, we attempt to present a model that duplicates the cognitive process through which humans can self-localize. We present an innovative GNSS-free solution for vehicle self-localization based on detection pattern recognition of visual anchors. The proposed cognitive approach is successfully tested in different routes taken from a real urban environment. The system location estimates are compared with the GPS reported locations and show promising performances.","PeriodicalId":419881,"journal":{"name":"2020 IEEE 23rd International Conference on Information Fusion (FUSION)","volume":"72 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129670449","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}

{"title":"An Improved Algorithm for Universal Sensor Registration","authors":"Daniel Sigalov, Aharon Gal, B. Vigdor","doi":"10.23919/FUSION45008.2020.9190399","DOIUrl":"https://doi.org/10.23919/FUSION45008.2020.9190399","url":null,"abstract":"We revise the ideas presented in a previous paper and propose an improved method for absolute sensor registration in target tracking applications. The approach uses targets of opportunity and, without making assumptions on their dynamical models, allows simultaneous calibration of multiple three- and two-dimensional sensors. The idea is representing the sensor angular misalignments as rotations of the actual position vectors by some rotation matrices. We formulate the registration task as a Maximum Likelihood (ML) estimation problem where the parameters to be estimated as the unknown rotation matrices as well as the unknown ground truth positions. Whereas for two-sensor scenarios only relative registration is possible, in practical cases with three or more sensors unambiguous absolute calibration may be achieved. The derived algorithm, as opposed to its previous version, is ensured to converge for three-dimensional scenarios. The derived algorithms are straightforward to implement and do not require tuning of parameters. The performance of the algorithms is tested in a numerical study.","PeriodicalId":419881,"journal":{"name":"2020 IEEE 23rd International Conference on Information Fusion (FUSION)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131940460","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}

{"title":"Multi-Task Sensor Resource Balancing Using Lagrangian Relaxation and Policy Rollout","authors":"M. Schöpe, H. Driessen, A. Yarovoy","doi":"10.23919/FUSION45008.2020.9190546","DOIUrl":"https://doi.org/10.23919/FUSION45008.2020.9190546","url":null,"abstract":"The sensor resource management problem in a multi-object tracking scenario is considered. In order to solve it, a dynamic budget balancing algorithm is proposed which models the different sensor tasks as partially observable Markov decision processes. Those are being solved by applying a combination of Lagrangian relaxation and policy rollout. The algorithm converges to a solution which is close to the optimal steady-state solution. This is shown through simulations of a two-dimensional tracking scenario. Moreover, it is demonstrated how the algorithm allocates the sensor time budgets dynamically to a changing environment and takes predictions of the future situation into account.","PeriodicalId":419881,"journal":{"name":"2020 IEEE 23rd International Conference on Information Fusion (FUSION)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127848846","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}

{"title":"Accuracy Study on Shooter Localization Using Incomplete Acoustic Measurements","authors":"Luisa Still, M. Oispuu, W. Koch","doi":"10.23919/FUSION45008.2020.9190429","DOIUrl":"https://doi.org/10.23919/FUSION45008.2020.9190429","url":null,"abstract":"This paper deals with data fusion of acoustic measurements of multiple sensors for the purpose of shooter localization. Muzzle blast and shock wave are the two impulsive sounds that occur due to supersonic gunfire. Depending on its position, a microphone array can measure a complete measurement data set, composed of two bearing angles and the TDOA between both sound waves, or an incomplete subset. In this paper a framework is created to fuse all measurements, whether complete or incomplete. For this problem, a shooter state estimator is proposed and the associated Cramér-Rao bound is derived. The estimation results are studied in Monte Carlo simulations and evaluated in comparison with the Cramér-Rao bound.","PeriodicalId":419881,"journal":{"name":"2020 IEEE 23rd International Conference on Information Fusion (FUSION)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128798468","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}

{"title":"Comparison of early and late fusion techniques for movie trailer genre labelling","authors":"J. H. Mervitz, J. D. Villiers, J. P. Jacobs, M. H. O. Kloppers","doi":"10.23919/FUSION45008.2020.9190344","DOIUrl":"https://doi.org/10.23919/FUSION45008.2020.9190344","url":null,"abstract":"In this paper we explore automatic genre labelling of motion picture previews using audio-visual features present in movie trailers and the focus is on fusion techniques (early fusion and late fusion) and the resultant improvement on classification accuracy. This paper proposes a novel combination of deep learned features (from a pretrained VGG-16 model) obtained using a state-of-the-art shot detector and hand-crafted audio features. This combination of features and an associated comparison of early and late fusion with these features has not been attempted in the literature before. Furthermore, two popular fusion techniques and three distinct classification algorithms are investigated to determine the optimal fusion technique and classifier combination. The study uses a subset of the LMTD-9 movie trailer dataset with selected genres (action, comedy, drama and horror). The best performing low-level audio features are comprised of timbre features extracted using the MIRtoolbox followed by standalone mel-frequency cepstral coefficients. The best performing high-level audio feature is tonality. Audio features are augmented by visual features extracted using a pre-trained convolutional neural network (VGG-16). Feature fusion (early and late fusion) methods are investigated together with classification methods such as extreme gradient boosting, support vector machine and a neural network. Evaluation metrics such as precision, recall, confusion matrices and F1 score are used to measure classification accuracy. Early fusion methods outperform late fusion methods with a classification performance gain of approximately 10% for a four class classification problem. The best classification performance for early fusion obtained with a support vector machine is (73.12% accuracy), followed by the extreme gradient boosting classifier (69.37% accuracy) and neural network classifier (67.50% accuracy), whereas chance is 25%. It is shown that superior classification performance can be achieved by employing early feature fusion of low-level audio descriptors, high-level audio descriptors and high-level visual feature descriptors together with suitable classifiers.","PeriodicalId":419881,"journal":{"name":"2020 IEEE 23rd International Conference on Information Fusion (FUSION)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128816310","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}