发布求助
文献互助 智能选刊 最新文献

2019 22th International Conference on Information Fusion (FUSION)最新文献

筛选
英文 中文
A Neutrosophic Set Based Fault Diagnosis Method Based on Power Average Operator (Poster) 基于功率平均算子的中性集故障诊断方法(Poster)
2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011238
Yu Zhong, Xinyang Deng, Wen Jiang
{"title":"A Neutrosophic Set Based Fault Diagnosis Method Based on Power Average Operator (Poster)","authors":"Yu Zhong, Xinyang Deng, Wen Jiang","doi":"10.23919/fusion43075.2019.9011238","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011238","url":null,"abstract":"Fault diagnosis is an extensively applied issue for checking and identifying the faults of objects, which comes from the combination of various theories and technologies. The contributing factors of a fault are complex owing to the uncertainty of the actual environment and the relative importance of fault criteria. Consequently, these causes fails to be considered felicitously in many conventional methods. In this paper, a neutrosophic set based fault diagnosis method based on power average operator is proposed to resolve this matter. The neutrosophic set generated from multi-stage fault sample data would be aggregated via the power average operator, then by using the defuzzification of neutrosophic set, the fault diagnosis results could be obtained. The combination of power average operator and neutrosophic set can be used for handling the relative importance of criteria, and the uncertainty of fault data. Finally, an illustrative example was provided to demonstrate the reasonableness and effectiveness of the proposed method by comparing with the existing methods.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116157980","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}
引用次数: 1
Online Multi-object Visual Tracking using a GM-PHD Filter with Deep Appearance Learning 基于深度外观学习的GM-PHD滤波器在线多目标视觉跟踪
2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011441
Nathanael L. Baisa
{"title":"Online Multi-object Visual Tracking using a GM-PHD Filter with Deep Appearance Learning","authors":"Nathanael L. Baisa","doi":"10.23919/fusion43075.2019.9011441","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011441","url":null,"abstract":"We propose a new online multi-object visual tracker based on a Gaussian mixture Probability Hypothesis Density (GM-PHD) filter in combination with a similarity Convolutional Neural Network (CNN). The GM-PHD filter estimates the states and cardinality of an unknown and time varying number of targets in the scene handling target birth, death, clutter (false alarms) and missing detections in a unified framework, and has a linear complexity with the number of targets. However, it lacks the identity of targets. We combine spatio-temporal and visual similarities obtained from object bounding boxes and deep CNN appearance features, respectively, to alleviate its shortcoming of labelling targets across frames. We apply this developed method for tracking multiple targets in video sequences acquired under varying environmental conditions and targets density using a tracking-by-detection approach. Finally, we carry out extensive experiments on Multiple Object Tracking 2016 (MOTI6) and 2017 (MOTI7) benchmark datasets and find out that our tracker significantly outperforms several state-of-the-art trackers in terms of tracking accuracy and precision.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"303 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116334114","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}
引用次数: 19
Stereo Visual SLAM Based on Unscented Dual Quaternion Filtering 基于Unscented对偶四元数滤波的立体视觉SLAM
2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011391
S. Bultmann, Kailai Li, U. Hanebeck
{"title":"Stereo Visual SLAM Based on Unscented Dual Quaternion Filtering","authors":"S. Bultmann, Kailai Li, U. Hanebeck","doi":"10.23919/fusion43075.2019.9011391","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011391","url":null,"abstract":"We present DQV-SLAM (Dual Quaternion Visual SLAM). This novel feature-based stereo visual SLAM framework uses a stochastic filter based on the unscented transform and a progressive Bayes update, avoiding linearization of the nonlinear spatial transformation group. 6-DoF poses are represented by dual quaternions where rotational and translational components are stochastically modeled by Bingham and Gaussian distributions. Maps represented by point clouds of ORB-features are incrementally built and landmarks are updated with an unscented transform-based method. In order to get reliable measurements during the update, an optical flow-based approach is proposed to remove false feature associations. Drift is corrected by pose graph optimization once loop closure is detected. The KITTI and EuRoC datasets for stereo setup are used for evaluation. The performance of the proposed system is comparable to state-of-the-art optimization-based SLAM systems and better than existing filtering-based approaches.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114743127","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}
引用次数: 41
Multi-Agent System for Threat Assessment and Action Selection under Uncertainty and Ambiguity 不确定性和模糊性下威胁评估与行动选择的多智能体系统
2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011219
G. Rogova, R. Ilin
{"title":"Multi-Agent System for Threat Assessment and Action Selection under Uncertainty and Ambiguity","authors":"G. Rogova, R. Ilin","doi":"10.23919/fusion43075.2019.9011219","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011219","url":null,"abstract":"This paper describes an approach to designing a multi-agent decision support system, which monitors uncertain and ambiguous dynamic environments to produce probable explanations of the current situation and identify asymmetric threat as well as selects actions to prevent catastrophic consequences or mitigate their impact while acting under resource and time constraints. The proposed system incorporates decision makers' attitude toward risk and uncertainty in situations involving regular and high consequence rare events. An example scenario showing potentials of the described approach is also presented.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126362195","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}
引用次数: 1
Novel Adaptive Dwell Scheduling Algorithm for Digital Array Radar based on Pulse Interleaving 基于脉冲交错的数字阵列雷达自适应驻留调度算法
2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011216
Xiaoying Lu, T. Cheng, Han Peng, Zishu He, Huiyong Li
{"title":"Novel Adaptive Dwell Scheduling Algorithm for Digital Array Radar based on Pulse Interleaving","authors":"Xiaoying Lu, T. Cheng, Han Peng, Zishu He, Huiyong Li","doi":"10.23919/fusion43075.2019.9011216","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011216","url":null,"abstract":"In order to make full use of the digital array radar (DAR), effective dwell scheduling must be implemented. According to the signal processing characteristics of DAR, an adaptive dwell scheduling algorithm is proposed. In this algorithm, time and energy vectors are introduced to implement pulse interleaving and the scheduling analysis, which breaks the limitations of strict interleaving conditions, and reduces the complexity of scheduling analysis compared with existing algorithms based on pulse interleaving technique. Meanwhile, the synthetic priority of the task and the validity of scheduling it are considered comprehensively. Simulation results demonstrate that the proposed algorithm can effectively improve the scheduling performance for DAR.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126435997","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}
引用次数: 0
Information Fusion and Image Processing Based Arc Detection and Localization in Pantograph-Catenary Systems 基于信息融合和图像处理的受电弓接触网系统电弧检测与定位
2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011333
P. Lu, Changfan Huo, Wangwang Duan, Jianyong Ai, Haifeng Jin, Lijun Jin
{"title":"Information Fusion and Image Processing Based Arc Detection and Localization in Pantograph-Catenary Systems","authors":"P. Lu, Changfan Huo, Wangwang Duan, Jianyong Ai, Haifeng Jin, Lijun Jin","doi":"10.23919/fusion43075.2019.9011333","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011333","url":null,"abstract":"Rail transit system represented by high-speed railway supplies power to locomotive electric equipment by connecting pantograph and catenary. The off-line phenomenon often occurs during the operation of pantograph-catenary system and generates off-line arc. Off-line arc spark causes drastic change of locomotive current and aggravates wear of pantograph slide plate and catenary, which seriously endangers the safe operation of rail transit. The automatic analysis and synthesis of dynamic image information, speed information acquired in time sequence and static track information in map database by computer simulation technology to complete the detection and geographic localization of pantograph-catenary arc defects are researched in this paper. Useful information needed is obtained by fusion of sensor information and human-derived prior information: according to the fusion of prior knowledge and image processing, a pantograph location method based on connected region and arc recognition method based on regional color feature are proposed. The degree of arc defect and catenary wear is obtained by fusion of image detection results and speed information, the severity of defect is determined quickly, and the state of arc is monitored in real time. Through the fusion analysis of arc monitoring results and highspeed rail speed and track information, the localization of arc defects in pantograph-catenary is determined, and the region of serious wear of catenary is obtained, which provides a reference for overhaul and maintenance of catenary. This method runs fast and has strong real-time performance, which meets the requirements of real-time detection and localization of pantograph-catenary arc.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130445341","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}
引用次数: 6
Combining Deep Learning and Model-Based Methods for Robust Real-Time Semantic Landmark Detection 结合深度学习和基于模型的鲁棒实时语义地标检测方法
2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011403
Benjamin Naujoks, P. Burger, Hans-Joachim Wünsche
{"title":"Combining Deep Learning and Model-Based Methods for Robust Real-Time Semantic Landmark Detection","authors":"Benjamin Naujoks, P. Burger, Hans-Joachim Wünsche","doi":"10.23919/fusion43075.2019.9011403","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011403","url":null,"abstract":"Compared to abstract features, significant objects, so-called landmarks, are a more natural means for vehicle localization and navigation, especially in challenging unstructured environments. The major challenge is to recognize landmarks in various lighting conditions and changing environment (growing vegetation) while only having few training samples available. We propose a new method which leverages Deep Learning as well as model-based methods to overcome the need of a large data set. Using RGB images and light detection and ranging (LiDAR) point clouds, our approach combines state-of-the-art classification results of Convolutional Neural Networks (CNN), with robust model-based methods by taking prior knowledge of previous time steps into account. Evaluations on a challenging real-wold scenario, with trees and bushes as landmarks, show promising results over pure learning-based state-of-the-art 3D detectors, while being significant faster.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"325 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133876461","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}
引用次数: 5
Simulated Evaluation of Ubiquitous Sensed Situational Awareness Systems 泛在感知态势感知系统的仿真评估
2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011412
Brooks P. Saunders, Varun K. Garg, T. Wickramarathne
{"title":"Simulated Evaluation of Ubiquitous Sensed Situational Awareness Systems","authors":"Brooks P. Saunders, Varun K. Garg, T. Wickramarathne","doi":"10.23919/fusion43075.2019.9011412","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011412","url":null,"abstract":"Developing technical capability that enables the utilization of ubiquitous sensing for situational awareness will likely catalyze a paradigm shift in data fusion, especially in light of recent advances in computing and data-driven techniques. Via the use of appropriate models, the well-entrenched data fusion methods can be utilized to mitigate some of the current challenges that are hindering the progress in this direction. However, due to the inherent challenges associated with ubiquitous sensing and randomness of data acquisition, adequate evaluation of advanced detection and sensor fusion systems remains a major challenge that hampers the progress in this direction. In this paper, a simulation approach for generating a synthetic dataset for comprehensive evaluation of Situational Awareness Systems (SASs) that utilize ubiquitous sensing for data acquisition is presented. With a particular emphasis on recording and organizing spatio-temporal observations, the steps towards construction of a comprehensive dataset that takes into account various spatiotemporal parameters corresponding to location, hazards and detectors is presented. The presented approach is then utilized to illustrate a simplified evaluation of an efficient data storage and inference system designed for asynchronous detections that are characteristic of ubiquitous sensed SASs.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133912013","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}
引用次数: 1
Distributed Estimation using Square Root Decompositions of Dependent Information 基于相关信息平方根分解的分布式估计
2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011162
Susanne Radtke, B. Noack, U. Hanebeck
{"title":"Distributed Estimation using Square Root Decompositions of Dependent Information","authors":"Susanne Radtke, B. Noack, U. Hanebeck","doi":"10.23919/fusion43075.2019.9011162","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011162","url":null,"abstract":"Sensor networks allow robust and precise estimation by fusing estimates from several distributed sensor nodes. Because of the often limited communication resources, a trade-off between the amount of information communicated and the quality of the fusion result has to be made. On the one hand, obtaining the optimal fusion result often needs an infeasible amount of additional information, but on the other hand, conservative methods usually lead to more pessimistic results in comparison. This paper proposes a square root decomposition of the incorporated noise terms to reconstruct the cross-covariance matrices between sensor nodes. To save communication bandwidth, a residual is defined that allows bounding of the cross-covariance matrix with a reduced number of noise terms. The consistency of the proposed method is demonstrated by two simulation examples featuring a linear and a nonlinear setup and is compared with other state-of -the-art fusion methods.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133988084","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}
引用次数: 4
On Malicious Agents in Non-Bayesian Social Learning with Uncertain Models 不确定模型下非贝叶斯社会学习中的恶意代理研究
2019 22th International Conference on Information Fusion (FUSION) Pub Date : 2019-07-01 DOI: 10.23919/fusion43075.2019.9011362
J. Z. Hare, César A. Uribe, Lance M. Kaplan, A. Jadbabaie
{"title":"On Malicious Agents in Non-Bayesian Social Learning with Uncertain Models","authors":"J. Z. Hare, César A. Uribe, Lance M. Kaplan, A. Jadbabaie","doi":"10.23919/fusion43075.2019.9011362","DOIUrl":"https://doi.org/10.23919/fusion43075.2019.9011362","url":null,"abstract":"Social Learning is the process of cooperatively aggregating information between agents in order to collectively estimate or learn an unknown value. Most all research in social learning assume that the likelihoods of the private observations given the possible hypotheses are known with absolute certainty. However, these likelihoods must be machine learned before the social learning process. Recent work has extended social learning for uncertain likelihoods. Such likelihoods are only known within Dirichlet distributions due to limited training samples available to learn them. This paper investigates the effects of malicious agents when both the good and malicious agents are uncertain about their likelihoods. Such malicious agents are trying to drive the consensus to accept an incorrect hypothesis and reject the correct hypothesis. This paper also presents and evaluates a method to identify and remediate against the effects of the malicious agents.","PeriodicalId":348881,"journal":{"name":"2019 22th International Conference on Information Fusion (FUSION)","volume":"33 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134382365","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}
引用次数: 12
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信