Pub Date : 2018-09-01DOI: 10.1109/ICVES.2018.8519496
Ryo Kurachi, H. Takada, Masato Tanabe, Jun Anzai, Kentaro Takei, Takaaki Iinuma, Manabu Maeda, Hideki Matsushima
In automotive software development, secure coding is required to enhance the security level because the secure coding guidelines state that vulnerability of software must be eliminated. However, secure coding is difficult to incorporate because it provides different assumptions from the coding guidelines of product development for existing automobiles. More specifically, in the automobile industry, MISRA-C is applied to improve the reliability of software. To achieve higher dependability and security level, an original guideline was developed in this study for the AUTOSAR adaptive platform. In this paper, we discuss the secure coding guidelines for strengthening security in classic and adaptive platforms.
{"title":"Improving secure coding rules for automotive software by using a vulnerability database","authors":"Ryo Kurachi, H. Takada, Masato Tanabe, Jun Anzai, Kentaro Takei, Takaaki Iinuma, Manabu Maeda, Hideki Matsushima","doi":"10.1109/ICVES.2018.8519496","DOIUrl":"https://doi.org/10.1109/ICVES.2018.8519496","url":null,"abstract":"In automotive software development, secure coding is required to enhance the security level because the secure coding guidelines state that vulnerability of software must be eliminated. However, secure coding is difficult to incorporate because it provides different assumptions from the coding guidelines of product development for existing automobiles. More specifically, in the automobile industry, MISRA-C is applied to improve the reliability of software. To achieve higher dependability and security level, an original guideline was developed in this study for the AUTOSAR adaptive platform. In this paper, we discuss the secure coding guidelines for strengthening security in classic and adaptive platforms.","PeriodicalId":203807,"journal":{"name":"2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130343903","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 : 2018-09-01DOI: 10.1109/ICVES.2018.8519518
Weimeng Zhu, Jan Siegemund, A. Kummert
Neural networks are widely used in autonomous driving and driver assistance systems tasks. Limited by hardware, these networks are restricted by their capacity and capability. To deal with this limitation, an application dedicated unit which exploits prior knowledge on beneficial steps may reduce the required network complexity. We introduce a neuralnetwork-integrable unit, Dense Spatial Translation Network (DSTN), that compensates for complex intra-class variations in spatial appearance. For example, considering Traffic Sign Recognition (TSR), the design of the same traffic sign in different countries may be different. This efficient unit is explicitly designed for this rectification task and thus replaces the demand to substantially increase the network capacity. It samples input feature maps which are augmented by intra-class variations, and produces output feature maps compensating for these variations. This clearly simplifies the subsequent classification tasks. Also, the DSTN is light-weighted, and is suitable for end-to-end training. It is easily integrated into any existing network structure. We evaluate the performance of the unit based on TSR and number recognition. Results show significant improvement after integrating this unit into a neural network.
{"title":"Dense Spatial Translation Network","authors":"Weimeng Zhu, Jan Siegemund, A. Kummert","doi":"10.1109/ICVES.2018.8519518","DOIUrl":"https://doi.org/10.1109/ICVES.2018.8519518","url":null,"abstract":"Neural networks are widely used in autonomous driving and driver assistance systems tasks. Limited by hardware, these networks are restricted by their capacity and capability. To deal with this limitation, an application dedicated unit which exploits prior knowledge on beneficial steps may reduce the required network complexity. We introduce a neuralnetwork-integrable unit, Dense Spatial Translation Network (DSTN), that compensates for complex intra-class variations in spatial appearance. For example, considering Traffic Sign Recognition (TSR), the design of the same traffic sign in different countries may be different. This efficient unit is explicitly designed for this rectification task and thus replaces the demand to substantially increase the network capacity. It samples input feature maps which are augmented by intra-class variations, and produces output feature maps compensating for these variations. This clearly simplifies the subsequent classification tasks. Also, the DSTN is light-weighted, and is suitable for end-to-end training. It is easily integrated into any existing network structure. We evaluate the performance of the unit based on TSR and number recognition. Results show significant improvement after integrating this unit into a neural network.","PeriodicalId":203807,"journal":{"name":"2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115085205","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 : 2018-09-01DOI: 10.1109/ICVES.2018.8519593
Robert Buecs, Marcel Heistermann, R. Leupers, G. Ascheid
Advanced Driver Assistance Systems (ADAS) matured into comprehensive hardware/software applications with exploding complexity. Various simulation-driven techniques emerged to facilitate their development, e.g., model-based design, driving simulators and virtual platforms. Moreover, multi-domain co-simulation standards arose to join such technologies and achieve fully virtual ADAS prototyping. Built upon these concepts, this paper presents the Static Multi-scale Export Layer Tool (SMELT), a retargetable “one-click” ADAS code generation facility. SMELT accelerates ADAS design space exploration by ensuring continuous refinement from the highest-level model representation down to embedded production code generation. To highlight its advantages, an ADAS library was rapidly prototyped using SMELT. Lastly, algorithmic and system-level analyses are presented, alongside simulation performance evaluation.
{"title":"Multi-Scale Code Generation for Simulation-Driven Rapid ADAS Prototyping: the SMELT Approach","authors":"Robert Buecs, Marcel Heistermann, R. Leupers, G. Ascheid","doi":"10.1109/ICVES.2018.8519593","DOIUrl":"https://doi.org/10.1109/ICVES.2018.8519593","url":null,"abstract":"Advanced Driver Assistance Systems (ADAS) matured into comprehensive hardware/software applications with exploding complexity. Various simulation-driven techniques emerged to facilitate their development, e.g., model-based design, driving simulators and virtual platforms. Moreover, multi-domain co-simulation standards arose to join such technologies and achieve fully virtual ADAS prototyping. Built upon these concepts, this paper presents the Static Multi-scale Export Layer Tool (SMELT), a retargetable “one-click” ADAS code generation facility. SMELT accelerates ADAS design space exploration by ensuring continuous refinement from the highest-level model representation down to embedded production code generation. To highlight its advantages, an ADAS library was rapidly prototyped using SMELT. Lastly, algorithmic and system-level analyses are presented, alongside simulation performance evaluation.","PeriodicalId":203807,"journal":{"name":"2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116081632","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 : 2018-09-01DOI: 10.1109/ICVES.2018.8519595
Bindu Verma, Ayesha Choudhary
In this paper, we propose a novel, real-time driver emotion monitoring system “in the wild” based on face detection and racial expression analysis. A camera is placed inside the vehicle that continuously looks at the driver's face and monitors the driver's emotional state at regular time intervals. Camera based monitoring of the driver's attentiveness based on the driver's emotional state in naturalistic driving environments is a non-intrusive approach and an important part of an automated driver assistance system (ADAS). Our work employs a face detection model based on mixture of trees with shared pool of parts to robustly detect the drivers face in varied environmental conditions. We also extract racial landmark points, and use them to enhance our emotion recognition system. In our proposed work, we use convolution neural networks. In the first, we use VGG16 to extract appearance features from the detected face image and in the second VGG16 network, to extract geometrical features from the racial landmark points. We then combine these two features using an integration method to accurately recognize the emotions. Based on the recognized emotional state of the driver, the driver can be made aware of his emotional state in case necessary. Experimental results on publicly available driver and face expression datasets show that our system is robust and accurate for driver emotion detection.
{"title":"Deep Learning Based Real-Time Driver Emotion Monitoring","authors":"Bindu Verma, Ayesha Choudhary","doi":"10.1109/ICVES.2018.8519595","DOIUrl":"https://doi.org/10.1109/ICVES.2018.8519595","url":null,"abstract":"In this paper, we propose a novel, real-time driver emotion monitoring system “in the wild” based on face detection and racial expression analysis. A camera is placed inside the vehicle that continuously looks at the driver's face and monitors the driver's emotional state at regular time intervals. Camera based monitoring of the driver's attentiveness based on the driver's emotional state in naturalistic driving environments is a non-intrusive approach and an important part of an automated driver assistance system (ADAS). Our work employs a face detection model based on mixture of trees with shared pool of parts to robustly detect the drivers face in varied environmental conditions. We also extract racial landmark points, and use them to enhance our emotion recognition system. In our proposed work, we use convolution neural networks. In the first, we use VGG16 to extract appearance features from the detected face image and in the second VGG16 network, to extract geometrical features from the racial landmark points. We then combine these two features using an integration method to accurately recognize the emotions. Based on the recognized emotional state of the driver, the driver can be made aware of his emotional state in case necessary. Experimental results on publicly available driver and face expression datasets show that our system is robust and accurate for driver emotion detection.","PeriodicalId":203807,"journal":{"name":"2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123545411","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 : 2018-09-01DOI: 10.1109/ICVES.2018.8519487
Kaddour Mahmoud, Makkawi Khoder, Ait-Tmazirte Nourdine, E. N. Maan, M. Nazih
this paper presents an integrity monitoring method in order to provide a precise Global Navigation Satellite System (GNSS) positioning. The originality of the proposed method consists on robustly select the non-faulty observations subset from GNSS observation by detecting and excluding erroneous measurements. A part of classical Fault Detection and Exclusion (FDE) literature is based on residual using prediction step of a recursive Bayesian filter like Kalman filter. The confidence granted to the prediction in such methods is critical in the phase of error detection. In GNSS standalone positioning, classical used prediction models are very approximate by inducing bad decisions, which increases the false alarm probability (PFA) and missed detection probability (PMD), leading a diminution in the integrity of GNSS positioning.In order to improve prediction step accuracy, in this paper, we propose a procedure of prediction optimization using a parametric model in the framework of a RAIM (Receiver Autonomous Integrity Monitoring) residual method used for erroneous measurements detection. Real GNSS data in experimental studies are used to test the proposed method. The results show that prediction optimization method improves RAIM residual sensitivity. In addition, the developed isolation step reduces considerably computational time.
{"title":"Prediction optimization method for multi-fault detection enhancement: application to GNSS positioning","authors":"Kaddour Mahmoud, Makkawi Khoder, Ait-Tmazirte Nourdine, E. N. Maan, M. Nazih","doi":"10.1109/ICVES.2018.8519487","DOIUrl":"https://doi.org/10.1109/ICVES.2018.8519487","url":null,"abstract":"this paper presents an integrity monitoring method in order to provide a precise Global Navigation Satellite System (GNSS) positioning. The originality of the proposed method consists on robustly select the non-faulty observations subset from GNSS observation by detecting and excluding erroneous measurements. A part of classical Fault Detection and Exclusion (FDE) literature is based on residual using prediction step of a recursive Bayesian filter like Kalman filter. The confidence granted to the prediction in such methods is critical in the phase of error detection. In GNSS standalone positioning, classical used prediction models are very approximate by inducing bad decisions, which increases the false alarm probability (PFA) and missed detection probability (PMD), leading a diminution in the integrity of GNSS positioning.In order to improve prediction step accuracy, in this paper, we propose a procedure of prediction optimization using a parametric model in the framework of a RAIM (Receiver Autonomous Integrity Monitoring) residual method used for erroneous measurements detection. Real GNSS data in experimental studies are used to test the proposed method. The results show that prediction optimization method improves RAIM residual sensitivity. In addition, the developed isolation step reduces considerably computational time.","PeriodicalId":203807,"journal":{"name":"2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"355 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121709187","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 : 2018-09-01DOI: 10.1109/ICVES.2018.8519587
Lei Yuan, Yuan Yang, lvaro Hernandez Alonso, Shuyu Li
As a solid medium of sound propagation, rails provide perfect acoustic features. In this way, rail breakage detection systems based on ultrasonic guided waves (UGW) have been recently developed. In outdoor applications of these systems, different types of interference are usually added to the received signal, which makes UGW signals difficult to distinguish and analyze, even leading to false alarms and affecting the system efficiency. In order to recover UGW signals in these systems, the application of a variational mode decomposition (VMD) algorithm to denoise and reconstruct UGW signals is proposed in this work. This algorithm can decompose the received signal into different intrinsic mode functions (IMF), which some are useful signals and the others are interference. Removing the interference part and the UGW signals can be reconstructed. By comparing the amplitude of reconstructed UGW signal with a predefined threshold, the rail status can be determined easier than before. Furthermore, by calculating the deviation between the reconstructed signal after the VMD algorithm and the original one, the effectiveness and suitability of the proposal is verified through some simulation results.
{"title":"Application of VMD Algorithm in UGW-based Rail Breakage Detection System","authors":"Lei Yuan, Yuan Yang, lvaro Hernandez Alonso, Shuyu Li","doi":"10.1109/ICVES.2018.8519587","DOIUrl":"https://doi.org/10.1109/ICVES.2018.8519587","url":null,"abstract":"As a solid medium of sound propagation, rails provide perfect acoustic features. In this way, rail breakage detection systems based on ultrasonic guided waves (UGW) have been recently developed. In outdoor applications of these systems, different types of interference are usually added to the received signal, which makes UGW signals difficult to distinguish and analyze, even leading to false alarms and affecting the system efficiency. In order to recover UGW signals in these systems, the application of a variational mode decomposition (VMD) algorithm to denoise and reconstruct UGW signals is proposed in this work. This algorithm can decompose the received signal into different intrinsic mode functions (IMF), which some are useful signals and the others are interference. Removing the interference part and the UGW signals can be reconstructed. By comparing the amplitude of reconstructed UGW signal with a predefined threshold, the rail status can be determined easier than before. Furthermore, by calculating the deviation between the reconstructed signal after the VMD algorithm and the original one, the effectiveness and suitability of the proposal is verified through some simulation results.","PeriodicalId":203807,"journal":{"name":"2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124292716","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 : 2018-09-01DOI: 10.1109/ICVES.2018.8519522
A. Hussein, F. García, C. Olaverri-Monreal
Intelligent vehicles simulations are utilized as the initial step of experiments before the deployment on the roads. Nowadays there are several frameworks that can be used to control vehicles, and Robot Operating System (ROS) is the most common one. Moreover, there are several powerful visualization tools that can be used for simulations, and Unity Game Engine is on the top of the list. Accordingly, this paper introduces a methodology to connect both systems, ROS and Unity, thus linking the performance in simulations and real-life for better analogy. Additionally, a comparative study between GAZEBO simulator and Unity simulator, in terms of functionalities and capabilities is shown. Last but not least, two use cases are presented for validation of the proposed methodology. Therefore, the main contribution of this paper is to introduce a methodology to connect both systems, ROS and Unity, to achieve the best possible approximation to vehicle behavior in the real world.
智能车辆仿真是智能车辆上路部署前的初始实验步骤。目前有几种框架可以用于控制车辆，机器人操作系统(ROS)是最常用的一种。此外，还有一些强大的可视化工具可以用于模拟，Unity Game Engine是其中的首选工具。因此，本文介绍了一种方法来连接两个系统，ROS和Unity，从而将模拟和现实生活中的性能联系起来，以便更好地进行类比。此外，GAZEBO模拟器和Unity模拟器在功能和性能方面进行了比较研究。最后但并非最不重要的是，提出了两个用例来验证所建议的方法。因此，本文的主要贡献是引入一种方法来连接两个系统，ROS和Unity，以实现对现实世界中车辆行为的最佳逼近。
{"title":"ROS and Unity Based Framework for Intelligent Vehicles Control and Simulation","authors":"A. Hussein, F. García, C. Olaverri-Monreal","doi":"10.1109/ICVES.2018.8519522","DOIUrl":"https://doi.org/10.1109/ICVES.2018.8519522","url":null,"abstract":"Intelligent vehicles simulations are utilized as the initial step of experiments before the deployment on the roads. Nowadays there are several frameworks that can be used to control vehicles, and Robot Operating System (ROS) is the most common one. Moreover, there are several powerful visualization tools that can be used for simulations, and Unity Game Engine is on the top of the list. Accordingly, this paper introduces a methodology to connect both systems, ROS and Unity, thus linking the performance in simulations and real-life for better analogy. Additionally, a comparative study between GAZEBO simulator and Unity simulator, in terms of functionalities and capabilities is shown. Last but not least, two use cases are presented for validation of the proposed methodology. Therefore, the main contribution of this paper is to introduce a methodology to connect both systems, ROS and Unity, to achieve the best possible approximation to vehicle behavior in the real world.","PeriodicalId":203807,"journal":{"name":"2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122253163","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 : 2018-09-01DOI: 10.1109/ICVES.2018.8519591
Mingkang Li, Fabian Straub, M. Kunert, R. Henze, F. Küçükay
Nowadays, the automotive advanced driver assistance systems have the ability to detect surrounding objects, predict impending collisions and initiate automatic emergency braking. However, by a late detection of objects at higher speeds, the collision is hardly avoidable by braking only, hence an evasive steering maneuver shall be performed simultaneously to cure this deficiency. This paper presents a novel approach that utilizes a dedicated cost function to make the appropriate maneuver decision in an imminent collision avoidance situation. By taking into account the host vehicle and the collision target motions as well as other moving or stationary objects in the near vicinity, diverse aspects and criteria are analyzed and discussed to evaluate possible maneuver candidates. After that, the cost functions of different maneuvers are calculated by summarizing the results of all the evaluation criteria and aspects. In both simulated and measured critical situations, the cost function is validated and the maneuver with the best (i.e., lowest) cost is selected to avoid the impending collision and the endangerment of any other road users aside.
{"title":"A Novel Cost Function for Decision-Making Strategies in Automotive Collision Avoidance Systems","authors":"Mingkang Li, Fabian Straub, M. Kunert, R. Henze, F. Küçükay","doi":"10.1109/ICVES.2018.8519591","DOIUrl":"https://doi.org/10.1109/ICVES.2018.8519591","url":null,"abstract":"Nowadays, the automotive advanced driver assistance systems have the ability to detect surrounding objects, predict impending collisions and initiate automatic emergency braking. However, by a late detection of objects at higher speeds, the collision is hardly avoidable by braking only, hence an evasive steering maneuver shall be performed simultaneously to cure this deficiency. This paper presents a novel approach that utilizes a dedicated cost function to make the appropriate maneuver decision in an imminent collision avoidance situation. By taking into account the host vehicle and the collision target motions as well as other moving or stationary objects in the near vicinity, diverse aspects and criteria are analyzed and discussed to evaluate possible maneuver candidates. After that, the cost functions of different maneuvers are calculated by summarizing the results of all the evaluation criteria and aspects. In both simulated and measured critical situations, the cost function is validated and the maneuver with the best (i.e., lowest) cost is selected to avoid the impending collision and the endangerment of any other road users aside.","PeriodicalId":203807,"journal":{"name":"2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127826318","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 : 2018-09-01DOI: 10.1109/ICVES.2018.8519588
Sasan Jafarnejad, G. Castignani, T. Engel
The increasing penetration of connected vehicles nowadays has enabled driving data collection at a very large scale. Many telematics applications have been also enabled from the analysis of those datasets and the usage of Machine Learning techniques, including driving behavior analysis, predictive maintenance of vehicles, modeling of vehicle health and vehicle component usage, among others. In particular, being able to identify the individual behind the steering wheel has many application fields. In the insurance or car-rental market, the fact that more than one driver make use of the vehicle generally triggers extra fees for the contract holder. Moreover being able to identify different drivers enables the automation of comfort settings or personalization of advanced driver assistance (ADAS) technologies. In this paper, we propose a driver identification algorithm based on Gaussian Mixture Models (GMM). We show that only using features extracted from the gas pedal position and steering wheel angle signals we are able to achieve near 100% accuracy in scenarios with up to 67 drivers. In comparison to the state-of-the-art, our proposed methodology has lower complexity, superior accuracy and offers scalability to a larger number of drivers.
{"title":"Revisiting Gaussian Mixture Models for Driver Identification","authors":"Sasan Jafarnejad, G. Castignani, T. Engel","doi":"10.1109/ICVES.2018.8519588","DOIUrl":"https://doi.org/10.1109/ICVES.2018.8519588","url":null,"abstract":"The increasing penetration of connected vehicles nowadays has enabled driving data collection at a very large scale. Many telematics applications have been also enabled from the analysis of those datasets and the usage of Machine Learning techniques, including driving behavior analysis, predictive maintenance of vehicles, modeling of vehicle health and vehicle component usage, among others. In particular, being able to identify the individual behind the steering wheel has many application fields. In the insurance or car-rental market, the fact that more than one driver make use of the vehicle generally triggers extra fees for the contract holder. Moreover being able to identify different drivers enables the automation of comfort settings or personalization of advanced driver assistance (ADAS) technologies. In this paper, we propose a driver identification algorithm based on Gaussian Mixture Models (GMM). We show that only using features extracted from the gas pedal position and steering wheel angle signals we are able to achieve near 100% accuracy in scenarios with up to 67 drivers. In comparison to the state-of-the-art, our proposed methodology has lower complexity, superior accuracy and offers scalability to a larger number of drivers.","PeriodicalId":203807,"journal":{"name":"2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114942438","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 : 2018-09-01DOI: 10.1109/ICVES.2018.8519494
David Augustin, Marius Hofmann, U. Konigorski
Intelligent automated driving functions require a deep understanding about the current traffic situation and its likely evolution. For highly automated driving on highways, predicting trajectories of traffic participants is a crucial task for collision-free trajectory planning and risk-aware maneuver choice. For a prediction horizon of a few seconds the execution of those trajectories is fuzzy and highly dependent on the maneuver choice of the driver. This paper presents a new online-capable statistical approach for maneuver detection and uncertainty-aware trajectory prediction in highway scenarios based on detecting and clustering typical motion patterns in real highway footage and deriving prototypical trajectories for each cluster. The cluster prototypes are utilized for maneuver detection by evaluating their proximities to incomplete tra- jectory records while identifying for each prototype its most similar section. The remaining segment of the best fit is used as an estimate for the future motion of the traffic participant. Quantitative evaluation results demonstrate the potential of the proposed concept for maneuver detection and maneuver-based trajectory prediction.
{"title":"Motion Pattern Recognition for Maneuver Detection and Trajectory Prediction on Highways","authors":"David Augustin, Marius Hofmann, U. Konigorski","doi":"10.1109/ICVES.2018.8519494","DOIUrl":"https://doi.org/10.1109/ICVES.2018.8519494","url":null,"abstract":"Intelligent automated driving functions require a deep understanding about the current traffic situation and its likely evolution. For highly automated driving on highways, predicting trajectories of traffic participants is a crucial task for collision-free trajectory planning and risk-aware maneuver choice. For a prediction horizon of a few seconds the execution of those trajectories is fuzzy and highly dependent on the maneuver choice of the driver. This paper presents a new online-capable statistical approach for maneuver detection and uncertainty-aware trajectory prediction in highway scenarios based on detecting and clustering typical motion patterns in real highway footage and deriving prototypical trajectories for each cluster. The cluster prototypes are utilized for maneuver detection by evaluating their proximities to incomplete tra- jectory records while identifying for each prototype its most similar section. The remaining segment of the best fit is used as an estimate for the future motion of the traffic participant. Quantitative evaluation results demonstrate the potential of the proposed concept for maneuver detection and maneuver-based trajectory prediction.","PeriodicalId":203807,"journal":{"name":"2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127013286","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：