2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF)最新文献

Neural Network Aided Potential Field Approach For Pedestrian Prediction 神经网络辅助电位场法行人预测

2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF) Pub Date : 2019-10-01 DOI: 10.1109/SDF.2019.8916659

F. Particke, Jiaren Zhou, M. Hiller, Christian Hofmann, J. Thielecke

{"title":"Neural Network Aided Potential Field Approach For Pedestrian Prediction","authors":"F. Particke, Jiaren Zhou, M. Hiller, Christian Hofmann, J. Thielecke","doi":"10.1109/SDF.2019.8916659","DOIUrl":"https://doi.org/10.1109/SDF.2019.8916659","url":null,"abstract":"Autonomous driving is one of the key challenges in recent time. As pedestrians are the most vulnerable traffic participants, collisions with pedestrians have to be avoided under all circumstances. Hence, prediction of pedestrian trajectories is of high interest for automated vehicles. For this purpose, a plethora of algorithms has been proposed to model the pedestrian in the last decades, reaching from simple kinematic models to advanced microscopic models. In addition, the machine learning community started to learn the behavior of pedestrians and showed major improvements in complex scenarios or unexpected situations. However, as most of the machine learning algorithms are treated as black boxes, the safeguarding of the software is one key challenge which has to be solved. This contribution proposes to combine classic modeling of pedestrians with machine learning algorithms by learning the model errors between a simple physical model and real data. In particular, it is proposed to combine a physical model based on potential fields with a neural network to predict the future behavior of pedestrians. It is shown that the combined approach outperforms the physical model in learnable areas, whereas the physical model without the neural network is more robust in areas where almost no training data is available. In addition, different structures of neural networks are analyzed.","PeriodicalId":186196,"journal":{"name":"2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116463091","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: 2

ACTIVE - Autonomous Car to Infrastructure Communication Mastering Adverse Environments 主动-自动驾驶汽车与基础设施的通信控制不利环境

2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF) Pub Date : 2019-10-01 DOI: 10.1109/SDF.2019.8916631

Josef Steinbaeck, H. Fuereder, C. Steger, E. Brenner, C. Schwarzl, N. Druml, T. Herndl, Stefan Loigge, Nadja Marko, Markus Postl, Georg Kail, Reinhard Hladik, Gerhard Hechenberger

{"title":"ACTIVE - Autonomous Car to Infrastructure Communication Mastering Adverse Environments","authors":"Josef Steinbaeck, H. Fuereder, C. Steger, E. Brenner, C. Schwarzl, N. Druml, T. Herndl, Stefan Loigge, Nadja Marko, Markus Postl, Georg Kail, Reinhard Hladik, Gerhard Hechenberger","doi":"10.1109/SDF.2019.8916631","DOIUrl":"https://doi.org/10.1109/SDF.2019.8916631","url":null,"abstract":"Precise localization is crucial for autonomous navigation, especially for autonomous driving. GNSS localization is prone to a number of errors and is not sufficient to provide reliable positional data in all situations. Most existing approaches for fine-grained positioning are not working reliably in difficult weather conditions. In this paper we present a method to tackle that problem by performing precise localization by exploiting the angle-of-arrival of V2X communications. During a 30-months project, we built an unmanned vehicle capable of determining its precise location via V2X communication. In order to safely navigate in the environment and detect obstacles in its path, the robot is also equipped with environmental perception sensors (time-of-flight and radar). We evaluated the proposed localization method during a test-drive on a precisely mapped parking lot. The resulting localization precision was improved by over 60 percent compared to the standard GPS localization.","PeriodicalId":186196,"journal":{"name":"2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114830096","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

Stochastic Partitioning for Extended Object Probability Hypothesis Density Filters 扩展目标概率假设密度滤波器的随机划分

2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF) Pub Date : 2019-10-01 DOI: 10.1109/SDF.2019.8916656

Julian Böhler, Tim Baur, S. Wirtensohn, J. Reuter

引用次数: 3

Data fusion strategy to improve the realiability of machine learning based classifications 提高机器学习分类可靠性的数据融合策略

2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF) Pub Date : 2019-10-01 DOI: 10.1109/SDF.2019.8916636

Karsten Schwalbe, Alexander Groh, Frank Hertwig, U. Scheunert

{"title":"Data fusion strategy to improve the realiability of machine learning based classifications","authors":"Karsten Schwalbe, Alexander Groh, Frank Hertwig, U. Scheunert","doi":"10.1109/SDF.2019.8916636","DOIUrl":"https://doi.org/10.1109/SDF.2019.8916636","url":null,"abstract":"Automatic object recognition plays a major role in many industrial applications. This task is mostly performed by using optical sensors and image processing methods. Degeneration processes, such as surface wear, however, can pose quite some challenges when it comes to high-quality optical recognition. In this article we present our solution to optical character recognition of strongly degenerated numbers, characterized by a varying embossing depth and texture intensity, imprinted on metal surfaces. Under these conditions Machine Learning (ML) based recognition models seem to perform better than conventional ones. Typically, ML models have a black box character in the sense that the algorithm steps have no direct interpretable meaning and are kind of arbitrary. Consequently, the results of such models are difficult to interpret with respect to their trustworthiness. In order to receive more reliable recognition results, we have developed a rule-based fusion strategy that combines the output of several different AI models. This approach not only leads to a higher rate of correctly recognized objects, it also indicates when the recognition result is uncertain. As a result, our method increases the process safety and makes object recognition in industrial applications more flexible and robust.","PeriodicalId":186196,"journal":{"name":"2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125447574","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

A Generic Anomaly Detection Approach Applied to Mixture-of-unigrams and Maritime Surveillance Data 一种用于混合图和海事监测数据的通用异常检测方法

2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF) Pub Date : 2019-10-01 DOI: 10.1109/SDF.2019.8916633

Yifan Zhou, James Wright, S. Maskell

引用次数: 2

Randomized Evolution Model for Multi Hypothesis Kalman Filter 多假设卡尔曼滤波的随机进化模型

2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF) Pub Date : 2019-10-01 DOI: 10.1109/SDF.2019.8916630

S. Handke, Joshua Gehlen

引用次数: 0

Track-Oriented MHT with Unresolved Measurements 带未解析测量的轨迹导向MHT

2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF) Pub Date : 2019-10-01 DOI: 10.1109/SDF.2019.8916657

S. Coraluppi, C. Carthel

引用次数: 1

Shooter Localization with a Microphone Array Based on a Linearly Modeled Bullet Speed 基于线性模型子弹速度的传声器阵列射击定位

2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF) Pub Date : 2019-10-01 DOI: 10.1109/SDF.2019.8916651

Luisa Still, M. Varela, W. Wirth, M. Oispuu

引用次数: 3

Extended Object Tracking assisted Adaptive Clustering for Radar in Autonomous Driving Applications 扩展目标跟踪辅助雷达自适应聚类在自动驾驶中的应用

2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF) Pub Date : 2019-10-01 DOI: 10.1109/SDF.2019.8916658

Stefan Haag, B. Duraisamy, F. Govaers, W. Koch, M. Fritzsche, J. Dickmann

引用次数: 8

Joint stereo camera calibration and multi-target tracking using the linear-complexity factorial cumulant filter 基于线性复杂度因子累积滤波器的联合立体摄像机标定与多目标跟踪

2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF) Pub Date : 2019-10-01 DOI: 10.1109/SDF.2019.8916653

M. Campbell, Daniel E. Clark

引用次数: 1