Pub Date : 2017-07-10DOI: 10.23919/ICIF.2017.8009768
Dongzhe Wang, K. Mao, G. Ng
With the exponential growth of web meta-data, exploiting multimodal online sources via standard search engine has become a trend in visual recognition as it effectively alleviates the shortage of training data. However, the web meta-data such as text data is usually not as cooperative as expected due to its unstructured nature. To address this problem, this paper investigates the numerical representation of web text data. We firstly adopt convolutional neural network (CNN) for web text modeling on top of word vectors. Combined with CNN for image, we present a multimodal fusion to maximize the discriminative power of visual and textual modality data for decision level and feature level simultaneously. Experimental results show that the proposed framework achieves significant improvement in large-scale image classification on Pascal VOC-2007 and VOC-2012 datasets.
{"title":"Convolutional neural networks and multimodal fusion for text aided image classification","authors":"Dongzhe Wang, K. Mao, G. Ng","doi":"10.23919/ICIF.2017.8009768","DOIUrl":"https://doi.org/10.23919/ICIF.2017.8009768","url":null,"abstract":"With the exponential growth of web meta-data, exploiting multimodal online sources via standard search engine has become a trend in visual recognition as it effectively alleviates the shortage of training data. However, the web meta-data such as text data is usually not as cooperative as expected due to its unstructured nature. To address this problem, this paper investigates the numerical representation of web text data. We firstly adopt convolutional neural network (CNN) for web text modeling on top of word vectors. Combined with CNN for image, we present a multimodal fusion to maximize the discriminative power of visual and textual modality data for decision level and feature level simultaneously. Experimental results show that the proposed framework achieves significant improvement in large-scale image classification on Pascal VOC-2007 and VOC-2012 datasets.","PeriodicalId":148407,"journal":{"name":"2017 20th International Conference on Information Fusion (Fusion)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121148626","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 : 2017-07-10DOI: 10.23919/ICIF.2017.8009783
R. W. Liu, Lin Shi, S. Yu, Defeng Wang
Magnetic resonance imaging (MRI) has been extensively used in clinical practice but suffers from long data acquisition time. Following the success of compressed sensing (CS) theory, many efforts have been made to accurately reconstruct MR images from undersampled k-space measurements and therefore dramatically reduce MRI scan time. To further improve image quality, we formulate undersampled MRI reconstruction as a least-squares optimization problem regularized by shearlet transform and overlapping-group sparsity-promoting total variation (OSTV). Shearlet transform, a directional representation system, is capable of capturing the optimal sparse representation for images with plentiful geometrical information. OSTV performs well in suppressing staircase-like artifacts often arising in traditional TV-based reconstructed images. To guarantee solution stability and efficiency, the resulting optimization problem is solved using an alternating direction methods of multipliers (ADMM)-based numerical algorithm. Extensive experimental results on both phantom and in vivo MRI datasets have demonstrated the superior performance of our proposed method in terms of both quantitative evaluation and visual quality.
{"title":"Hybrid regularization for compressed sensing MRI: Exploiting shearlet transform and group-sparsity total variation","authors":"R. W. Liu, Lin Shi, S. Yu, Defeng Wang","doi":"10.23919/ICIF.2017.8009783","DOIUrl":"https://doi.org/10.23919/ICIF.2017.8009783","url":null,"abstract":"Magnetic resonance imaging (MRI) has been extensively used in clinical practice but suffers from long data acquisition time. Following the success of compressed sensing (CS) theory, many efforts have been made to accurately reconstruct MR images from undersampled k-space measurements and therefore dramatically reduce MRI scan time. To further improve image quality, we formulate undersampled MRI reconstruction as a least-squares optimization problem regularized by shearlet transform and overlapping-group sparsity-promoting total variation (OSTV). Shearlet transform, a directional representation system, is capable of capturing the optimal sparse representation for images with plentiful geometrical information. OSTV performs well in suppressing staircase-like artifacts often arising in traditional TV-based reconstructed images. To guarantee solution stability and efficiency, the resulting optimization problem is solved using an alternating direction methods of multipliers (ADMM)-based numerical algorithm. Extensive experimental results on both phantom and in vivo MRI datasets have demonstrated the superior performance of our proposed method in terms of both quantitative evaluation and visual quality.","PeriodicalId":148407,"journal":{"name":"2017 20th International Conference on Information Fusion (Fusion)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114340415","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 : 2017-07-10DOI: 10.23919/ICIF.2017.8009843
M. E. G. Borges, Dominique Maltese, P. Vanheeghe, E. Duflos
In this paper, we consider the problem of scheduling an agile sensor to perform an optimal control action in the case of the multi-target tracking scenario. Our purpose is to present a random finite set (RFS) approach to the multi-target sensor management problem formulated in the Partially Observed Markov Decision Process (POMDP) framework. The reward function associated with each sensor control (action) is computed via the Expected Risk Reduction between the multi-target predicted and updated densities. The proposed algorithm is implemented via the Probability Hypothesis Density filter (PHD). Numerical studies demonstrate the performance of this particular approach to a radar beam-pointing problem where targets need to be prioritized.
{"title":"A risk-based sensor management using random finite sets and POMDP","authors":"M. E. G. Borges, Dominique Maltese, P. Vanheeghe, E. Duflos","doi":"10.23919/ICIF.2017.8009843","DOIUrl":"https://doi.org/10.23919/ICIF.2017.8009843","url":null,"abstract":"In this paper, we consider the problem of scheduling an agile sensor to perform an optimal control action in the case of the multi-target tracking scenario. Our purpose is to present a random finite set (RFS) approach to the multi-target sensor management problem formulated in the Partially Observed Markov Decision Process (POMDP) framework. The reward function associated with each sensor control (action) is computed via the Expected Risk Reduction between the multi-target predicted and updated densities. The proposed algorithm is implemented via the Probability Hypothesis Density filter (PHD). Numerical studies demonstrate the performance of this particular approach to a radar beam-pointing problem where targets need to be prioritized.","PeriodicalId":148407,"journal":{"name":"2017 20th International Conference on Information Fusion (Fusion)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114793066","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 : 2017-07-10DOI: 10.23919/ICIF.2017.8009619
Wenbo Wang, P. Mandal
Particle Filter (PF) is a popular sequential Monte Carlo method to deal with non-linear non-Gaussian filtering problems. However, it suffers from the so-called curse of dimensionality in the sense that the required number of particle (needed for a reasonable performance) grows exponentially with the dimension of the system. One of the techniques found in the literature to tackle this is to split the high-dimensional state in to several lower dimensional (sub)spaces and run a particle filter on each subspace, the so-called multiple particle filter (MPF). It is also well-known from the literature that a good proposal density can help to improve the performance of a particle filter. In this article, we propose a new particle filter consisting of two stages. The first stage derives a suitable proposal density that incorporates the information from the measurements. In the second stage a PF is employed with the proposal density obtained in the first stage. Through a simulated example we show that in high-dimensional systems, the proposed two-stage particle filter performs better than the MPF with much fewer number of particles.
{"title":"A two-stage particle filter in high dimension","authors":"Wenbo Wang, P. Mandal","doi":"10.23919/ICIF.2017.8009619","DOIUrl":"https://doi.org/10.23919/ICIF.2017.8009619","url":null,"abstract":"Particle Filter (PF) is a popular sequential Monte Carlo method to deal with non-linear non-Gaussian filtering problems. However, it suffers from the so-called curse of dimensionality in the sense that the required number of particle (needed for a reasonable performance) grows exponentially with the dimension of the system. One of the techniques found in the literature to tackle this is to split the high-dimensional state in to several lower dimensional (sub)spaces and run a particle filter on each subspace, the so-called multiple particle filter (MPF). It is also well-known from the literature that a good proposal density can help to improve the performance of a particle filter. In this article, we propose a new particle filter consisting of two stages. The first stage derives a suitable proposal density that incorporates the information from the measurements. In the second stage a PF is employed with the proposal density obtained in the first stage. Through a simulated example we show that in high-dimensional systems, the proposed two-stage particle filter performs better than the MPF with much fewer number of particles.","PeriodicalId":148407,"journal":{"name":"2017 20th International Conference on Information Fusion (Fusion)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114984567","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 : 2017-07-10DOI: 10.23919/ICIF.2017.8009761
E. J. Clark, E. Griffith, S. Maskell, J. Ralph
This paper compares the tracking performance that can be achieved when using a nonlinear drag model for a helicopter, a constant drag motion model, and a baseline constant acceleration model. A particle filter is used for state estimation to address problems associated with nonlinear drag and nonlinear measurements of helicopter pose. We demonstrate that the inclusion of this nonlinear kinematic effect provides improved tracking performance for a manoeuvring target.
{"title":"Nonlinear kinematics for improved helicopter tracking","authors":"E. J. Clark, E. Griffith, S. Maskell, J. Ralph","doi":"10.23919/ICIF.2017.8009761","DOIUrl":"https://doi.org/10.23919/ICIF.2017.8009761","url":null,"abstract":"This paper compares the tracking performance that can be achieved when using a nonlinear drag model for a helicopter, a constant drag motion model, and a baseline constant acceleration model. A particle filter is used for state estimation to address problems associated with nonlinear drag and nonlinear measurements of helicopter pose. We demonstrate that the inclusion of this nonlinear kinematic effect provides improved tracking performance for a manoeuvring target.","PeriodicalId":148407,"journal":{"name":"2017 20th International Conference on Information Fusion (Fusion)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121432444","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 : 2017-07-10DOI: 10.23919/ICIF.2017.8009870
K. Chang, Z. Tian, Jiayang Yu
Dynamic construction of optimal portfolio is investigated. Multiple assets are allocated and rebalanced periodically based on different principles. We develop several dynamic allocation strategies to maximize long-term portfolio value based on Kelly's approach related to mutual information. We show that the resulting asset allocation strategy outperforms the traditional approaches and produces an excellent trade-off between risk and return. Out of sample simulation results are also provided to demonstrate the performance.
{"title":"Dynamic asset allocation — Chasing a moving target","authors":"K. Chang, Z. Tian, Jiayang Yu","doi":"10.23919/ICIF.2017.8009870","DOIUrl":"https://doi.org/10.23919/ICIF.2017.8009870","url":null,"abstract":"Dynamic construction of optimal portfolio is investigated. Multiple assets are allocated and rebalanced periodically based on different principles. We develop several dynamic allocation strategies to maximize long-term portfolio value based on Kelly's approach related to mutual information. We show that the resulting asset allocation strategy outperforms the traditional approaches and produces an excellent trade-off between risk and return. Out of sample simulation results are also provided to demonstrate the performance.","PeriodicalId":148407,"journal":{"name":"2017 20th International Conference on Information Fusion (Fusion)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123907560","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 : 2017-07-10DOI: 10.23919/ICIF.2017.8009743
Xiaomei Qu
This paper investigates the passive localization of a mobile source based on time difference of arrival (TDOA) measurements when the sensor positions suffer from random uncertainties. In the formulation of the dynamic system, the nonlinear measurement function contains random parameters, so the classical high-degree cubature Kalman filtering (CKF) method is unrealizable. We develop an augmented high-degree CKF method to deal with the random parameters, where the system is augmented by incorporating the random sensor positions into the state vector and the number of cubature points is enlarged. Although the proposed augmented high-degree CKF method requires more computational complexity, its estimation accuracy is improved in comparison with that of the classical high-degree CKF method which ignores the sensor position uncertainties. Monte Carlo simulations are used to illustrate the good performance of the proposed method.
{"title":"Mobile localization via high-degree cubature Kalman filter with sensor position uncertainties","authors":"Xiaomei Qu","doi":"10.23919/ICIF.2017.8009743","DOIUrl":"https://doi.org/10.23919/ICIF.2017.8009743","url":null,"abstract":"This paper investigates the passive localization of a mobile source based on time difference of arrival (TDOA) measurements when the sensor positions suffer from random uncertainties. In the formulation of the dynamic system, the nonlinear measurement function contains random parameters, so the classical high-degree cubature Kalman filtering (CKF) method is unrealizable. We develop an augmented high-degree CKF method to deal with the random parameters, where the system is augmented by incorporating the random sensor positions into the state vector and the number of cubature points is enlarged. Although the proposed augmented high-degree CKF method requires more computational complexity, its estimation accuracy is improved in comparison with that of the classical high-degree CKF method which ignores the sensor position uncertainties. Monte Carlo simulations are used to illustrate the good performance of the proposed method.","PeriodicalId":148407,"journal":{"name":"2017 20th International Conference on Information Fusion (Fusion)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129287239","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 : 2017-07-10DOI: 10.23919/ICIF.2017.8009803
Hongwei Wang, Hongbin Li, Wei Zhang, Heping Wang
In this paper, we attack the estimation problem in Kalman filtering when the measurements are contaminated by outliers. We employ the Laplace distribution to model the underlying non-Gaussian measurement process. The maximum posterior estimation is solved by the majorization minimization (MM) approach. This yields an MM based robust filter, where the intractable ℓ1 norm problem is converted into an ℓ2 norm format. Furthermore, we implement the MM based robust filter in the Kalman filtering framework and develop a Laplace ℓ1 robust Kalman filter. The proposed algorithm is tested by numerical simulations. The robustness of our algorithm has been borne out when compared with other robust filters, especially in scenarios of heavy outliers.
{"title":"Laplace ℓ1 robust Kalman filter based on majorization minimization","authors":"Hongwei Wang, Hongbin Li, Wei Zhang, Heping Wang","doi":"10.23919/ICIF.2017.8009803","DOIUrl":"https://doi.org/10.23919/ICIF.2017.8009803","url":null,"abstract":"In this paper, we attack the estimation problem in Kalman filtering when the measurements are contaminated by outliers. We employ the Laplace distribution to model the underlying non-Gaussian measurement process. The maximum posterior estimation is solved by the majorization minimization (MM) approach. This yields an MM based robust filter, where the intractable ℓ1 norm problem is converted into an ℓ2 norm format. Furthermore, we implement the MM based robust filter in the Kalman filtering framework and develop a Laplace ℓ1 robust Kalman filter. The proposed algorithm is tested by numerical simulations. The robustness of our algorithm has been borne out when compared with other robust filters, especially in scenarios of heavy outliers.","PeriodicalId":148407,"journal":{"name":"2017 20th International Conference on Information Fusion (Fusion)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121503391","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 : 2017-07-10DOI: 10.23919/ICIF.2017.8009679
Mingjie Wang, H. Ji, Xiaolong Hu, Yongquan Zhang
The probability hypothesis density (PHD) filter is a promising filter for multi-target tracking which propagates the posterior intensity of the multi-target state. In this paper, a Gaussian mixture particle flow PHD (GMPF-PHD) filter is proposed which uses a bank of particles to represent the Gaussian components in the Gaussian mixture PHD (GM-PHD) filter. Then a particle flow is implemented to migrate the particles to a more appropriate region in order to obtain a more accurate approximation of the posterior intensity. To verify the effectiveness of the algorithm, both linear and nonlinear multi-target tracking problem are designed, and the performance are compared with the classical approaches such as the GM-PHD filter, the Gaussian mixture particle PHD (GMP-PHD) filter, and the particle PHD filter. Simulation results show that the proposed filter can achieve a good performance with a reasonable computational cost.
{"title":"Gaussian mixture particle flow probability hypothesis density filter","authors":"Mingjie Wang, H. Ji, Xiaolong Hu, Yongquan Zhang","doi":"10.23919/ICIF.2017.8009679","DOIUrl":"https://doi.org/10.23919/ICIF.2017.8009679","url":null,"abstract":"The probability hypothesis density (PHD) filter is a promising filter for multi-target tracking which propagates the posterior intensity of the multi-target state. In this paper, a Gaussian mixture particle flow PHD (GMPF-PHD) filter is proposed which uses a bank of particles to represent the Gaussian components in the Gaussian mixture PHD (GM-PHD) filter. Then a particle flow is implemented to migrate the particles to a more appropriate region in order to obtain a more accurate approximation of the posterior intensity. To verify the effectiveness of the algorithm, both linear and nonlinear multi-target tracking problem are designed, and the performance are compared with the classical approaches such as the GM-PHD filter, the Gaussian mixture particle PHD (GMP-PHD) filter, and the particle PHD filter. Simulation results show that the proposed filter can achieve a good performance with a reasonable computational cost.","PeriodicalId":148407,"journal":{"name":"2017 20th International Conference on Information Fusion (Fusion)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132613613","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 : 2017-07-10DOI: 10.23919/ICIF.2017.8009880
C. Laudy, Fabio Ruini, A. Zanasi, Marcin Przybyszewski, A. Stachowicz
The development of mobile devices as well as social media platforms recently lead to the necessity of monitoring the latter during crisis and emergency situations. Paradoxically, the huge amount of information available through these new sources may lead to information gaps, within the Public Safety Organization operators' awareness. We describe some specific types of information gaps due first to imprecise or unreliable information and second to information overload. We then propose a set of tools aiming at reducing these information gaps and supporting the human operators in the social media generated information during crisis and emergency management. The first tool aims at geolocalising tweets relying on the content of the messages. The second tool provides sentiment analysis and clustering of multi-lingual messages and the third tool provides means for semantic information fusion and hypothesis evaluation relying on the contents and metadata of the tweets reporting about an event.
{"title":"Using social media in crisis management: SOTERIA fusion center for managing information gaps","authors":"C. Laudy, Fabio Ruini, A. Zanasi, Marcin Przybyszewski, A. Stachowicz","doi":"10.23919/ICIF.2017.8009880","DOIUrl":"https://doi.org/10.23919/ICIF.2017.8009880","url":null,"abstract":"The development of mobile devices as well as social media platforms recently lead to the necessity of monitoring the latter during crisis and emergency situations. Paradoxically, the huge amount of information available through these new sources may lead to information gaps, within the Public Safety Organization operators' awareness. We describe some specific types of information gaps due first to imprecise or unreliable information and second to information overload. We then propose a set of tools aiming at reducing these information gaps and supporting the human operators in the social media generated information during crisis and emergency management. The first tool aims at geolocalising tweets relying on the content of the messages. The second tool provides sentiment analysis and clustering of multi-lingual messages and the third tool provides means for semantic information fusion and hypothesis evaluation relying on the contents and metadata of the tweets reporting about an event.","PeriodicalId":148407,"journal":{"name":"2017 20th International Conference on Information Fusion (Fusion)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116665570","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：