References of "Frank, Raphaël 50001805"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailWeakly-Supervised Free Space Estimation through Stochastic Co-Teaching
Robinet, François UL; Parera, Claudia UL; Hundt, Christian UL et al

in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2022 (2022, January 04)

Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches train a segmentation model using an annotated dataset. The training data needs to capture ... [more ▼]

Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches train a segmentation model using an annotated dataset. The training data needs to capture the wide variety of environments and weather conditions encountered at runtime, making the annotation cost prohibitively high. In this work, we propose a novel approach for obtaining free space estimates from images taken with a single road-facing camera. We rely on a technique that generates weak free space labels without any supervision, which are then used as ground truth to train a segmentation model for free space estimation. Our work differs from prior attempts by explicitly taking label noise into account through the use of Co-Teaching. Since Co-Teaching has traditionally been investigated in classification tasks, we adapt it for segmentation and examine how its parameters affect performances in our experiments. In addition, we propose Stochastic Co-Teaching, which is a novel method to select clean samples that leads to enhanced results. We achieve an IoU of 82.6%, a Precision of 90.9%, and a Recall of 90.3%. Our best model reaches 87% of the IoU, 93% of the Precision, and 93% of the Recall of the equivalent fully-supervised baseline while using no human annotations. To the best of our knowledge, this work is the first to use Co-Teaching to train a free space segmentation model under explicit label noise. Our implementation and trained models are freely available online. [less ▲]

Detailed reference viewed: 59 (12 UL)
Full Text
Peer Reviewed
See detailRefining Weakly-Supervised Free Space Estimation through Data Augmentation and Recursive Training
Robinet, François UL; Frank, Raphaël UL

in Proceedings of BNAIC/BeneLearn 2021 (2021, November 12)

Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches rely on pixel-wise ground truth annotations to train a segmentation model. To cover the ... [more ▼]

Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches rely on pixel-wise ground truth annotations to train a segmentation model. To cover the wide variety of environments and lighting conditions encountered on roads, training supervised models requires large datasets. This makes the annotation cost prohibitively high. In this work, we propose a novel approach for obtaining free space estimates from images taken with a single road-facing camera. We rely on a technique that generates weak free space labels without any supervision, which are then used as ground truth to train a segmentation model for free space estimation. We study the impact of different data augmentation techniques on the performances of free space predictions, and propose to use a recursive training strategy. Our results are benchmarked using the Cityscapes dataset and improve over comparable published work across all evaluation metrics. Our best model reaches 83.64% IoU (+2.3%), 91:75% Precision (+2.4%) and 91.29% Recall (+0.4%). These results correspond to 88.8% of the IoU, 94.3% of the Precision and 93.1% of the Recall obtained by an equivalent fully-supervised baseline, while using no ground truth annotation. Our code and models are freely available online. [less ▲]

Detailed reference viewed: 96 (27 UL)
Full Text
Peer Reviewed
See detailPoster: Commercial 5G Performance: A V2X Experiment
Frank, Raphaël UL; Hawlader, Faisal UL

in Proceedings of the 13th Vehicular Networking Conference 2021 (2021)

This poster paper presents the results of a 4G/5G measurements campaign conducted in Luxembourg City in August 2021. We test the performance of both network technologies while stationary and on the move ... [more ▼]

This poster paper presents the results of a 4G/5G measurements campaign conducted in Luxembourg City in August 2021. We test the performance of both network technologies while stationary and on the move. We report the results for download and upload throughputs, as well as the Round-trip Time (RTT). We briefly discuss the results in the context of Vehicle-to-Everything (V2X) applications. [less ▲]

Detailed reference viewed: 88 (24 UL)
Full Text
Peer Reviewed
See detailTowards a Framework to Evaluate Cooperative Perception for Connected Vehicles
Hawlader, Faisal UL; Frank, Raphaël UL

in Proceedings of the 13th IEEE Vehicular Networking Conference 2021 (2021)

Over the past few years, Connected and Autonomous Vehicles (CAVs) have gained significant research attention. With the recent deployment of 5G networks in many metropolitan areas, new cooperative driving ... [more ▼]

Over the past few years, Connected and Autonomous Vehicles (CAVs) have gained significant research attention. With the recent deployment of 5G networks in many metropolitan areas, new cooperative driving concepts are emerging. One of those is cooperative perception, where vehicles exchange sensory information via a V2X network to maximize their awareness horizon without the need for additional and potentially expensive sensors. The idea is to distribute the processing of the sensor information to find the best trade-off between data transmission and processing time. To experimentally evaluate the performance of cooperative perception schemes is time-consuming and costly due to the expensive hardware it involves. To the best of our knowledge there is to date no open- source simulation framework that allows to transfer realistic sensor data between multiple simulated vehicles via a V2X network. In this work-in-progress paper, we address this issue by proposing an extension of the well-known CARLA open- source simulator for automated driving research. We implement a basic communication channel on top of the existing client-server architecture of CARLA and show how sensor information can be exchanged. Transferring realistic sensor information between multiple vehicles opens up a wide range of experiments to test and evaluate novel approaches to collaborative driving in simulation. [less ▲]

Detailed reference viewed: 107 (44 UL)
Full Text
Peer Reviewed
See detailRoboBus: A Diverse and Cross-Border Public Transport Dataset
Varisteas, Georgios; Frank, Raphaël UL; Robinet, François UL

in Proceedings of the 19th International Conference on Pervasive Computing and Communications (PerCom 2021) (2021, March 22)

Detailed reference viewed: 146 (28 UL)
Full Text
Peer Reviewed
See detailTowards Privacy Preserving Data Centric Super App
Carvalho Ota, Fernando Kaway UL; Meira, Jorge Augusto UL; Frank, Raphaël UL et al

in Carvalho Ota, Fernando Kaway; Meira, Jorge Augusto; Frank, Raphaël (Eds.) et al 2020 Mediterranean Communication and Computer Networking Conference, Arona 17-19 June 2020 (2020, September 10)

The number of smartphone users recently surpassed the numbers of desktop users on Internet, and opened up countless development challenges and business opportunities. Not only the fact that the majority ... [more ▼]

The number of smartphone users recently surpassed the numbers of desktop users on Internet, and opened up countless development challenges and business opportunities. Not only the fact that the majority of users are connected using their smartphones, but the number of Internet users in general has popularized the massive use of data-driven applications. In this context, the concept of super apps seems to be the next game-changer for the mobile apps industry, and the challenges related to security and privacy are key aspects for keeping user data safe. Thus, by combining different components for provisioning, authentication, membership and others, we propose a novel framework that enables the creation of a super app using privacy by design principles. [less ▲]

Detailed reference viewed: 114 (8 UL)
Full Text
Peer Reviewed
See detailLeveraging Privileged Information to Limit Distraction in End-to-End Lane Following
Robinet, François UL; Demeules, Antoine; Frank, Raphaël UL et al

in 2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) (2020)

Convolutional Neural Networks have been successfully used to steer vehicles using only road-facing cameras. In this work, we investigate the use of Privileged Information for training an end-to-end lane ... [more ▼]

Convolutional Neural Networks have been successfully used to steer vehicles using only road-facing cameras. In this work, we investigate the use of Privileged Information for training an end-to-end lane following model. Starting from the prior assumption that such a model should spend a sizeable fraction of its focus on lane markings, we take advantage of lane geometry information available at training time to improve its performance. To this end, we constrain the class of learnable functions by imposing a prior stemming from a lane segmentation task. For each input frame, we compute the set of pixels that most contribute to the prediction of the model using the VisualBackProp method. These pixel-relevance heatmaps are then compared with ground truth lane segmentation masks. A Distraction Loss term is added to the objective to regularize the training process. We learn from real-world data collected using our experimental vehicle and compare the results to those obtained using the simple Mean Squared Error objective. We show that the presence of our regularizer benefits both the performance and the stability of the model across a variety of evaluation metrics. We use a pretrained lane segmentation model without fine-tuning to extract lane marking masks and show that valuable learning signals can be extracted even from imperfect privileged knowledge. This method can be implemented easily and very efficiently on top of an existing architecture, without requiring the addition of any trainable parameter. [less ▲]

Detailed reference viewed: 182 (41 UL)
Full Text
Peer Reviewed
See detailIntrusion detection on robot cameras using spatio-temporal autoencoders: A self-driving car application
Amrouche, Faouzi UL; Lagraa, Sofiane UL; Frank, Raphaël UL et al

in 91st IEEE Vehicular Technology Conference, VTC Spring 2020, Antwerp, Belgium, May 25-28, 2020 (2020)

Robot Operating System (ROS) is becoming more and more important and is used widely by developers and researchers in various domains. One of the most important fields where it is being used is the self ... [more ▼]

Robot Operating System (ROS) is becoming more and more important and is used widely by developers and researchers in various domains. One of the most important fields where it is being used is the self-driving cars industry. However, this framework is far from being totally secure, and the existing security breaches do not have robust solutions. In this paper we focus on the camera vulnerabilities, as it is often the most important source for the environment discovery and the decision-making process. We propose an unsupervised anomaly detection tool for detecting suspicious frames incoming from camera flows. Our solution is based on spatio-temporal autoencoders used to truthfully reconstruct the camera frames and detect abnormal ones by measuring the difference with the input. We test our approach on a real-word dataset, i.e. flows coming from embedded cameras of self-driving cars. Our solution outperforms the existing works on different scenarios. [less ▲]

Detailed reference viewed: 174 (18 UL)
Full Text
Peer Reviewed
See detailHow Road and Mobile Networks Correlate: Estimating Urban Traffic Using Handovers
Derrmann, Thierry; Frank, Raphaël UL; Viti, Francesco UL et al

in IEEE Transactions on Intelligent Transportation Systems (2019)

We propose a novel way of linking mobile network signaling data to the state of the underlying urban road network. We show how a predictive model of traffic flows can be created from mobile network ... [more ▼]

We propose a novel way of linking mobile network signaling data to the state of the underlying urban road network. We show how a predictive model of traffic flows can be created from mobile network signaling data. To achieve this, we estimate the vehicular density inside specific areas using a polynomial function of the inner and exiting mobile phone handovers performed by the base stations covering those areas. We can then use the aggregated handovers as flow proxies alongside the density proxy to directly estimate an average velocity within an area. We evaluate the model in a simulation study of Luxembourg city and generalize our findings using a real-world data set extracted from the LTE network of a Luxembourg operator. By predicting the real traffic states as measured through floating car data, we achieve a mean absolute percentage error of 11.12%. Furthermore, in our study case, the approximations of the network macroscopic fundamental diagrams (MFD) of road network partitions can be generated. The analyzed data exhibit low variance with respect to a quadratic concave flow-density function, which is inline with the previous theoretical results on MFDs and are similar when estimated from simulation and real data. These results indicate that mobile signaling data can potentially be used to approximate MFDs of the underlying road network and contribute to better estimate road traffic states in urban congested networks. [less ▲]

Detailed reference viewed: 226 (16 UL)
Full Text
Peer Reviewed
See detailEvaluation of End-To-End Learning for Autonomous Driving: The Good, the Bad and the Ugly
Varisteas, Georgios UL; Frank, Raphaël UL; Sajadi Alamdari, Seyed Amin UL et al

in 2nd International Conference on Intelligent Autonomous Systems, Singapore, Feb. 28 to Mar. 2, 2019 (2019, March 01)

Detailed reference viewed: 302 (49 UL)
Full Text
Peer Reviewed
See detailJUNIOR, A Research Platform for Connected and Automated Driving
Varisteas, Georgios UL; Frank, Raphaël UL

in Proceedings of 2019 IEEE Vehicular Networking Conference (2019)

This poster paper presents a platform to conduct connected and automated driving experiments. We describe a low cost and easy to implement hardware and software platform suitable for universities and ... [more ▼]

This poster paper presents a platform to conduct connected and automated driving experiments. We describe a low cost and easy to implement hardware and software platform suitable for universities and companies. We first motivate the choice of the vehicle and the various hardware components, followed by the description of the open-source software stack. We will conclude by providing an overview of use cases and ongoing projects. [less ▲]

Detailed reference viewed: 142 (28 UL)
Full Text
Peer Reviewed
See detailVisualizing the Learning Progress of Self-Driving Cars
Mund, Sandro; Frank, Raphaël UL; Varisteas, Georgios UL et al

in 21st International Conference on Intelligent Transportation Systems (2018, November 02)

Using Deep Learning to predict lateral and longitudinal vehicle control, i.e. steering, acceleration and braking, is becoming increasingly popular. However, it remains widely unknown why those models ... [more ▼]

Using Deep Learning to predict lateral and longitudinal vehicle control, i.e. steering, acceleration and braking, is becoming increasingly popular. However, it remains widely unknown why those models perform so well. In order for them to become a commercially viable solution, it first needs to be understood why a certain behavior is triggered and how and what those networks learn from human-generated driving data to ensure safety. One research direction is to visualize what the network sees by highlighting regions of an image that influence the outcome of the model. In this vein, we propose a generic visualization method using Attention Heatmaps (AHs) to highlight what a given Convolutional Neural Network (CNN) learns over time. To do so, we rely on a novel occlusion technique to mask different regions of an input image to observe the effect on a predicted steering signal. We then gradually increase the amount of training data and study the effect on the resulting Attention Heatmaps, both in terms of visual focus and temporal behavior. [less ▲]

Detailed reference viewed: 240 (16 UL)
Full Text
Peer Reviewed
See detailUsing mobile phone data for urban network state estimation
Derrmann, Thierry; Frank, Raphaël UL; Engel, Thomas UL et al

Scientific Conference (2018, June)

Detailed reference viewed: 107 (4 UL)
Full Text
Peer Reviewed
See detailEstimating Urban Road Traffic States Using Mobile Network Signaling Data
Derrmann, Thierry UL; Frank, Raphaël UL; Viti, Francesco UL et al

in Abstract book of the 20th International Conference on Intelligent Transportation Systems (2017, October)

It is intuitive that there is a causal relationship between human mobility and signaling events in mobile phone networks. Among these events, not only the initiation of calls and data sessions can be used ... [more ▼]

It is intuitive that there is a causal relationship between human mobility and signaling events in mobile phone networks. Among these events, not only the initiation of calls and data sessions can be used in analyses, but also handovers between different locations that reflect mobility. In this work, we investigate if handovers can be used as a proxy metric for flows in the underlying road network, especially in urban environments. More precisely, we show that characteristic profiles of handovers within and between clusters of mobile network cells exist. We base these profiles on models from road traffic flow theory, and show that they can be used for traffic state estimation using floating-car data as ground truth. The presented model can be beneficial in areas with good mobile network coverage but low road traffic counting infrastructure, e.g. in developing countries, but also serve as an additional predictor for existing traffic state monitoring systems. [less ▲]

Detailed reference viewed: 314 (19 UL)
Peer Reviewed
See detailCharacterizing Driving Environments Through Bluetooth Discovery
Bronzi, Walter UL; Faye, Sébastien UL; Frank, Raphaël UL et al

Scientific Conference (2017, October)

Within the world of wireless technologies, Bluetooth has recently been at the forefront of innovation. It is becoming increasingly relevant for vehicles to become aware of their surroundings. Therefore ... [more ▼]

Within the world of wireless technologies, Bluetooth has recently been at the forefront of innovation. It is becoming increasingly relevant for vehicles to become aware of their surroundings. Therefore, having knowledge of nearby Bluetooth devices, both inside and outside other vehicles, can provide the listening vehicles with enough data to learn about their environment. In this paper, we collect and analyze a dataset of Bluetooth Classic (BC) and Low Energy (BLE) discoveries. We evaluate their respective characteristics and ability to provide context-aware information from a vehicular perspective. By taking a look at data about the encountered devices, such as GPS location, quantity, quality of signal and device class information, we infer distinctive behaviors between BC and BLE relative to context and application. For this purpose, we propose a set a features to train a classifier for the recognition of different driving environments (i.e. road classes) from Bluetooth discovery data alone. Comparing the performance of our classifier with different sampling parameters, the presented results indicate that, with our feature selection, we are able to predict with reasonable confidence up to three classes (Highway, City, Extra-Urban) by using only discovery data and no geographical information. This outcome gives promising results targeted at low energy and privacy-friendly applications and can open up a wide range of research directions. [less ▲]

Detailed reference viewed: 281 (23 UL)
Full Text
Peer Reviewed
See detailHow Mobile Phone Handovers reflect Urban Mobility: A Simulation Study
Derrmann, Thierry UL; Frank, Raphaël UL; Engel, Thomas UL et al

in Proceedings of the 5th IEEE Conference on Models and Technologies for Intelligent Transportation Systems. (2017, June 26)

Detailed reference viewed: 256 (22 UL)
Full Text
Peer Reviewed
See detailSmartphone-based Adaptive Driving Maneuver Detection: A large-scale Evaluation Study
Castignani, German UL; Derrmann, Thierry UL; Frank, Raphaël UL et al

in IEEE Transactions on Intelligent Transportation Systems (2017)

The proliferation of connected mobile devices together with advances in their sensing capacity has enabled a new distributed telematics platform. In particular, smartphones can be used as driving sensors ... [more ▼]

The proliferation of connected mobile devices together with advances in their sensing capacity has enabled a new distributed telematics platform. In particular, smartphones can be used as driving sensors to identify individual driver behavior and risky maneuvers. However, in order to estimate driver behavior with smartphones, the system must deal with different vehicle characteristics. This is the main limitation of existing sensing platforms, which are principally based on fixed thresholds for different sensing parameters. In this paper, we propose an adaptive driving maneuver detection mechanism that iteratively builds a statistical model of the driver, vehicle, and smartphone combination using a multivariate normal model. By means of experimentation over a test track and public roads, we first explore the capacity of different sensor input combinations to detect risky driving maneuvers, and we propose a training mechanism that adapts the profiling model to the vehicle, driver, and road topology. A large-scale evaluation study is conducted, showing that the model for maneuver detection and scoring is able to adapt to different drivers, vehicles, and road conditions. [less ▲]

Detailed reference viewed: 337 (9 UL)
Peer Reviewed
See detailPoster: LuST-LTE: A Simulation Package for Pervasive Vehicular Connectivity
Derrmann, Thierry UL; Faye, Sébastien UL; Frank, Raphaël UL et al

Poster (2016, December 08)

Recent technological advances in communication technology have provided new ways to understand human mobility. Connected vehicles with their rising market penetration are particularly representative of ... [more ▼]

Recent technological advances in communication technology have provided new ways to understand human mobility. Connected vehicles with their rising market penetration are particularly representative of this trend. They become increasingly interesting, not only as sensors, but also as participants in Intelligent Transportation System (ITS) applications. More specifically, their pervasive connectivity to cellular networks enables them as passive and active sensing units. In this paper, we introduce LuST-LTE, a package of open-source simulation tools that allows the simulation of vehicular traffic along with pervasive LTE connectivity. [less ▲]

Detailed reference viewed: 257 (22 UL)
Full Text
Peer Reviewed
See detailTowards Privacy-Neutral Travel Time Estimation from Mobile Phone Signalling Data
Derrmann, Thierry UL; Frank, Raphaël UL; Faye, Sébastien UL et al

in Proceedings of the 2016 IEEE International Smart Cities Conference (ISC2) (2016, September)

Today’s mobile penetration rates enable cellular signaling data to be useful in diverse fields such as transportation planning, the social sciences and epidemiology. Of particular interest for these ... [more ▼]

Today’s mobile penetration rates enable cellular signaling data to be useful in diverse fields such as transportation planning, the social sciences and epidemiology. Of particular interest for these applications are mobile subscriber dwell times. They express how long users stay in the service range of a base station. In this paper, we want to evaluate whether dwell time distributions can serve as predictors for road travel times. To this end, we transform floating car data into synthetic dwell times that we use as weights in a graph-based model. The model predictions are evaluated using the floating car ground truth data. Additionally, we show a potential link between handover density and travel times. We conclude that dwell times are a promising predictor for travel times, and can serve as a valuable input for intelligent transportation systems. [less ▲]

Detailed reference viewed: 358 (20 UL)