2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)最新文献_第6页

Classification of Streetsigns Using Gaussian Process Latent Variable Models 使用高斯过程潜变量模型的路牌分类

2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE) Pub Date : 2019-11-01 DOI: 10.1109/ICCVE45908.2019.8964883

Wilfried Wöber, M. Aburaia, C. Olaverri-Monreal

{"title":"Classification of Streetsigns Using Gaussian Process Latent Variable Models","authors":"Wilfried Wöber, M. Aburaia, C. Olaverri-Monreal","doi":"10.1109/ICCVE45908.2019.8964883","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8964883","url":null,"abstract":"Since the rise of deep artificial neuronal nets, object detection and classification became an autonomous procedure, where both, feature extraction and feature processing (e.g.: classification) is done using an architecture based on artificial neurons. The shortcomings of deep neuronal nets are mainly based the black box models and the architecture of the networks, which cannot be estimated. Unknown behavior and over-fitting is still an unsolved problem. Thus, human-made parameters like the number of neurons or the definition of activation functions must be set. This work presents a non-parametric and non-linear approach for image processing using latent variable models. We used Gaussian process latent variable models for street sign feature extraction, where a latent representation is estimated without prior knowledge such as class label. Based on the latent representation, we visualizes the features and use state-of-the-art classifier for street sign classification. Our results proves, that our approach extracts useful features for classification. Our approach has still shortcomings, such as computational time, which are current areas of research.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126887643","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

Improve cybersecurity of C-ITS Road Side Infrastructure Installations: the SerIoT - Secure and Safe IoT approach 提高C-ITS路边基础设施的网络安全:SerIoT -安全的物联网方法

2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE) Pub Date : 2019-11-01 DOI: 10.1109/ICCVE45908.2019.8965056

Alexander Frötscher, Bernhard Monschiebl, A. Drosou, E. Gelenbe, M. Reed, M. Al-Naday

引用次数: 7

3D LiDAR Extrinsic Calibration Method using Ground Plane Model Estimation 基于地平面模型估计的三维激光雷达外部定标方法

2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE) Pub Date : 2019-11-01 DOI: 10.1109/ICCVE45908.2019.8964949

Mohammad Ali Zaiter, R. Lherbier, G. Faour, O. Bazzi, J. Noyer

引用次数: 7

A Path Tracking Approach for Autonomous Driving on Slippery Surfaces 光滑路面自动驾驶的路径跟踪方法

2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE) Pub Date : 2019-11-01 DOI: 10.1109/ICCVE45908.2019.8965231

Enrico Regolin, Massimo Zambelli, M. Vanzulli, A. Ferrara

引用次数: 1

Interference Tests of ITS-G5 Vehicle-to-Vehicle Communication Networks with Virtual Drive Tests 基于虚拟驾驶测试的ITS-G5车对车通信网络干扰测试

2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE) Pub Date : 2019-11-01 DOI: 10.1109/ICCVE45908.2019.8965140

B. Altinel, Frank Wollenschläger, M. Hein

{"title":"Interference Tests of ITS-G5 Vehicle-to-Vehicle Communication Networks with Virtual Drive Tests","authors":"B. Altinel, Frank Wollenschläger, M. Hein","doi":"10.1109/ICCVE45908.2019.8965140","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8965140","url":null,"abstract":"Automotive communication systems have become a hot topic in the research field, especially with a focus towards connected vehicles. The potential of connected and automated driving promises an enormous increase of road safety and traffic efficiency. With this purpose, dedicated short range communication standards (e.g. ITS-G5) have been developed. These standards share spectral resources among all communication partners, which necessitates an evaluation of in-band interference. As one potentially powerful evaluation approach, the road and radio environment can be emulated instead of being accessed through field-operational tests, with major advantages like repeatability and convenience aspects. This paper describes a testing framework that employs a virtual-drive test approach for the evaluation of the performance of ITS-G5 equipment. According to the concept of virtual-drive testing, the road and radio environments have been emulated with regards to a realworld drive track. Packet loss measurements are presented for the evaluation of interference effects present in the communication. The results indicate that the virtual-drive test approach is suitable for testing automotive communication systems.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132736716","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: 7

A longitudinal driver model for long horizon speed prediction in powertrain applications 一种用于动力系统长视界速度预测的纵向驾驶员模型

2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE) Pub Date : 2019-11-01 DOI: 10.1109/ICCVE45908.2019.8965215

F. Morlock, O. Sawodny

引用次数: 0

A Novel Testbench for Development, Calibration and Functional Testing of ADAS/AD Functions 一种用于ADAS/AD功能开发、校准和功能测试的新型测试台

2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE) Pub Date : 2019-11-01 DOI: 10.1109/ICCVE45908.2019.8965225

Selim Solmaz, F. Holzinger

引用次数: 12

Multi-actuated ground vehicle tyre force estimation through a coupled 1D simulation-estimation framework 基于耦合一维仿真估计框架的多驱动地面车辆轮胎力估计

2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE) Pub Date : 2019-11-01 DOI: 10.1109/ICCVE45908.2019.8965229

Marco Viehweger, S. V. Aalst, F. Naets, W. Desmet

引用次数: 1

Safety & Security in the Context of Autonomous Driving 自动驾驶环境下的安全与保障

2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE) Pub Date : 2019-11-01 DOI: 10.1109/ICCVE45908.2019.8965092

Manuel Koschuch, Walter Sebron, Z. Szalay, Á. Török, Hans Tschürtz, I. Wahl

引用次数: 16

GAN Based Method for Labeled Image Augmentation in Autonomous Driving 基于GAN的自动驾驶标记图像增强方法

2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE) Pub Date : 2019-11-01 DOI: 10.1109/ICCVE45908.2019.8964902

Wenbo Yu, Yong Sun, Ruilin Zhou, Xingjian Liu

{"title":"GAN Based Method for Labeled Image Augmentation in Autonomous Driving","authors":"Wenbo Yu, Yong Sun, Ruilin Zhou, Xingjian Liu","doi":"10.1109/ICCVE45908.2019.8964902","DOIUrl":"https://doi.org/10.1109/ICCVE45908.2019.8964902","url":null,"abstract":"Deep learning models in Autonomous Driving perception tasks commonly use supervised learning methods and thus highly depend on labeled data. Training with more labeled data tends to bring better results, which highlights the meaning of data augmentation. Currently there are two difficulties when doing data augmentation. Firstly, it is time consuming to manually label the collected raw data. The second issue is that the diversity of a dataset is limited by the collection environment and time. In this paper, we proposed to use the current state of the art Multimodal Unsupervised Image-to-Image Translation (MUNIT) to generate synthesized images from labeled data. One of the benefits is that the generated data are automated labeled since they share the same ground truth with the raw data. Then we used the augmentation dataset to do different tasks including drivable area detection and object detection to prove that the data could be used to improve the performance of convolution neural networks (CNNs). We also designed an auto labelling tool that people could do labelling with the help of the improved CNN. The whole process is like a close loop that finishes labelling tasks while making progresses by itself. Generally speaking, our approach introduces an auto labelling pipeline based on unsupervised image-to-image translation to increase the amount and diversity of labeled data.","PeriodicalId":384049,"journal":{"name":"2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE)","volume":"238 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121871151","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