Pub Date : 2015-08-27DOI: 10.1109/IVS.2015.7225732
Mehmet Kilicarslan, J. Zheng, Aied Algarni
Pedestrian detection has been intensively studied based on appearances for driving safety. Only a few works have explored between-frame optical flow as one of features for human classification. In this paper, however, a new point of view is taken to watch a longer period for non-smooth movement. We explore the pedestrian detection purely based on motion, which is common and intrinsic for all pedestrians regardless of their shape, color, background, etc. We found unique motion characteristics of humans different from rigid objects in motion profiles. Based on the explicit analysis of spatial-temporal behaviors of pedestrians, non-smooth motion points are detected at the motion trajectories of limbs and body. This method works for driving video where both pedestrians and background are moving, and it yields good results as it is less influenced from pedestrian variations in shape and environment. The method also has low computational cost and it can be combined with a shape-based method as pre-screening tool for accuracy and speed.
{"title":"Pedestrian detection from non-smooth motion","authors":"Mehmet Kilicarslan, J. Zheng, Aied Algarni","doi":"10.1109/IVS.2015.7225732","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225732","url":null,"abstract":"Pedestrian detection has been intensively studied based on appearances for driving safety. Only a few works have explored between-frame optical flow as one of features for human classification. In this paper, however, a new point of view is taken to watch a longer period for non-smooth movement. We explore the pedestrian detection purely based on motion, which is common and intrinsic for all pedestrians regardless of their shape, color, background, etc. We found unique motion characteristics of humans different from rigid objects in motion profiles. Based on the explicit analysis of spatial-temporal behaviors of pedestrians, non-smooth motion points are detected at the motion trajectories of limbs and body. This method works for driving video where both pedestrians and background are moving, and it yields good results as it is less influenced from pedestrian variations in shape and environment. The method also has low computational cost and it can be combined with a shape-based method as pre-screening tool for accuracy and speed.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132262577","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225722
Xuewei Qi, Guoyuan Wu, K. Boriboonsomsin, M. Barth
The energy management system (EMS) is crucial to a plug-in hybrid electric vehicle (PHEV) in reducing its fuel consumption and pollutant emissions. The EMS determines how energy flows in a hybrid powertrain should be managed in response to a variety of driving conditions. In the development of EMS, the battery state-of-charge (SOC) control strategy plays a critical role. This paper proposes a novel evolutionary algorithm (EA)-based EMS with self-adaptive SOC control strategy for PHEVs, which can achieve the optimal fuel efficiency without trip length (by time) information. Numerical studies show that this proposed system can save up to 13% fuel, compared to other on-line EMS with different SOC control strategies. Further analysis indicates that the proposed system is less sensitive to the errors in predicting propulsion power in real-time, which is favorable for on-line implementation.
{"title":"Evolutionary algorithm based on-line PHEV energy management system with self-adaptive SOC control","authors":"Xuewei Qi, Guoyuan Wu, K. Boriboonsomsin, M. Barth","doi":"10.1109/IVS.2015.7225722","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225722","url":null,"abstract":"The energy management system (EMS) is crucial to a plug-in hybrid electric vehicle (PHEV) in reducing its fuel consumption and pollutant emissions. The EMS determines how energy flows in a hybrid powertrain should be managed in response to a variety of driving conditions. In the development of EMS, the battery state-of-charge (SOC) control strategy plays a critical role. This paper proposes a novel evolutionary algorithm (EA)-based EMS with self-adaptive SOC control strategy for PHEVs, which can achieve the optimal fuel efficiency without trip length (by time) information. Numerical studies show that this proposed system can save up to 13% fuel, compared to other on-line EMS with different SOC control strategies. Further analysis indicates that the proposed system is less sensitive to the errors in predicting propulsion power in real-time, which is favorable for on-line implementation.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132367883","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225727
Chao Wang, Huijing Zhao, Chunzhao Guo, S. Mita, H. Zha
As a key technique in ADAS (Advanced Driving Assistant System) or autonomous driving systems, visual-based on-road vehicle detection has been studied widely, while it faces still great challenges, among which are the complexity, diversity and unpredictable changes of the real-world environments. In the authors' previous work, an algorithm was developed in a probabilistic inference framework with its focus on solving the multi-view and occlusion problems at multi-lane motor way scenes. In this research, we seek to answer the questions: how efficient is the system during a long-term operation across a large area of changed conditions? To this end, a large scale experiment is conducted, where three testing data sets are developed containing the samples of more than 30,000 on Beijing's ring roads, 800 on Nagoya's fast road, and 3,000 on Nagoya's downtown streets, and the performance of visual-based vehicle detection concerning the multi-view and occlusion problems across extensive regions and at transnational environments are studied. We present our preliminary findings in this paper, which leads to a more extensive study in future work.
{"title":"Visual-based on-road vehicle detection: A transnational experiment and comparison","authors":"Chao Wang, Huijing Zhao, Chunzhao Guo, S. Mita, H. Zha","doi":"10.1109/IVS.2015.7225727","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225727","url":null,"abstract":"As a key technique in ADAS (Advanced Driving Assistant System) or autonomous driving systems, visual-based on-road vehicle detection has been studied widely, while it faces still great challenges, among which are the complexity, diversity and unpredictable changes of the real-world environments. In the authors' previous work, an algorithm was developed in a probabilistic inference framework with its focus on solving the multi-view and occlusion problems at multi-lane motor way scenes. In this research, we seek to answer the questions: how efficient is the system during a long-term operation across a large area of changed conditions? To this end, a large scale experiment is conducted, where three testing data sets are developed containing the samples of more than 30,000 on Beijing's ring roads, 800 on Nagoya's fast road, and 3,000 on Nagoya's downtown streets, and the performance of visual-based vehicle detection concerning the multi-view and occlusion problems across extensive regions and at transnational environments are studied. We present our preliminary findings in this paper, which leads to a more extensive study in future work.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133425583","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}
Careless driving is a major factor in most traffic accidents. In the last decade, research on estimation of face orientation and tracking of facial features through consequence images have shown very promising results of determining the level of driver's concentration. Image sources could be monochrome camera, stereo camera or depth camera. In this paper, we propose a novel approach of facial features and face orientation detection by using a single uncalibrated depth camera by switching IR depth pattern emitter. With this simple setup, we are able to obtain both depth image and infrared image in a continuously alternating grab mode. Infrared images are employed for facial features detection and tracking while depth information is used for face region detection and face orientation estimation. This system is not utilized only for driver monitoring system, but also other human interface system such as security and avatar systems.
{"title":"Face orientation estimation for driver monitoring with a single depth camera","authors":"Zhencheng Hu, Naoko Uchida, Yanming Wang, Yanchao Dong","doi":"10.1109/IVS.2015.7225808","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225808","url":null,"abstract":"Careless driving is a major factor in most traffic accidents. In the last decade, research on estimation of face orientation and tracking of facial features through consequence images have shown very promising results of determining the level of driver's concentration. Image sources could be monochrome camera, stereo camera or depth camera. In this paper, we propose a novel approach of facial features and face orientation detection by using a single uncalibrated depth camera by switching IR depth pattern emitter. With this simple setup, we are able to obtain both depth image and infrared image in a continuously alternating grab mode. Infrared images are employed for facial features detection and tracking while depth information is used for face region detection and face orientation estimation. This system is not utilized only for driver monitoring system, but also other human interface system such as security and avatar systems.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114622379","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225707
Andreas Møgelmose, M. Trivedi, T. Moeslund
This paper presents a monocular and purely vision based pedestrian trajectory tracking and prediction framework with integrated map-based hazard inference. In Advanced Driver Assistance systems research, a lot of effort has been put into pedestrian detection over the last decade, and several pedestrian detection systems are indeed showing impressive results. Considerably less effort has been put into processing the detections further. We present a tracking system for pedestrians, which based on detection bounding boxes tracks pedestrians and is able to predict their positions in the near future. The tracking system is combined with a module which, based on the car's GPS position acquires a map and uses the road information in the map to know where the car can drive. Then the system warns the driver about pedestrians at risk, by combining the information about hazardous areas for pedestrians with a probabilistic position prediction for all observed pedestrians.
{"title":"Trajectory analysis and prediction for improved pedestrian safety: Integrated framework and evaluations","authors":"Andreas Møgelmose, M. Trivedi, T. Moeslund","doi":"10.1109/IVS.2015.7225707","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225707","url":null,"abstract":"This paper presents a monocular and purely vision based pedestrian trajectory tracking and prediction framework with integrated map-based hazard inference. In Advanced Driver Assistance systems research, a lot of effort has been put into pedestrian detection over the last decade, and several pedestrian detection systems are indeed showing impressive results. Considerably less effort has been put into processing the detections further. We present a tracking system for pedestrians, which based on detection bounding boxes tracks pedestrians and is able to predict their positions in the near future. The tracking system is combined with a module which, based on the car's GPS position acquires a map and uses the road information in the map to know where the car can drive. Then the system warns the driver about pedestrians at risk, by combining the information about hazardous areas for pedestrians with a probabilistic position prediction for all observed pedestrians.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131834221","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225690
Hiroshi Fukui, Takayoshi Yamashita, Yuji Yamauchi, H. Fujiyoshi, H. Murase
Pedestrian detection is an active research topic for driving assistance systems. To install pedestrian detection in a regular vehicle, however, there is a need to reduce its cost and ensure high accuracy. Although many approaches have been developed, vision-based methods of pedestrian detection are best suited to these requirements. In this paper, we propose the methods based on Convolutional Neural Networks (CNN) that achieves high accuracy in various fields. To achieve such generalization, our CNN-based method introduces Random Dropout and Ensemble Inference Network (EIN) to the training and classification processes, respectively. Random Dropout selects units that have a flexible rate, instead of the fixed rate in conventional Dropout. EIN constructs multiple networks that have different structures in fully connected layers. The proposed methods achieves comparable performance to state-of-the-art methods, even though the structure of the proposed methods are considerably simpler.
{"title":"Pedestrian detection based on deep convolutional neural network with ensemble inference network","authors":"Hiroshi Fukui, Takayoshi Yamashita, Yuji Yamauchi, H. Fujiyoshi, H. Murase","doi":"10.1109/IVS.2015.7225690","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225690","url":null,"abstract":"Pedestrian detection is an active research topic for driving assistance systems. To install pedestrian detection in a regular vehicle, however, there is a need to reduce its cost and ensure high accuracy. Although many approaches have been developed, vision-based methods of pedestrian detection are best suited to these requirements. In this paper, we propose the methods based on Convolutional Neural Networks (CNN) that achieves high accuracy in various fields. To achieve such generalization, our CNN-based method introduces Random Dropout and Ensemble Inference Network (EIN) to the training and classification processes, respectively. Random Dropout selects units that have a flexible rate, instead of the fixed rate in conventional Dropout. EIN constructs multiple networks that have different structures in fully connected layers. The proposed methods achieves comparable performance to state-of-the-art methods, even though the structure of the proposed methods are considerably simpler.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116176043","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225761
Felix Kunz, Dominik Nuss, J. Wiest, H. Deusch, Stephan Reuter, Franz Gritschneder, A. Scheel, M. Stuebler, Martin Bach, Patrick Hatzelmann, Cornelius Wild, K. Dietmayer
The project “Autonomous Driving” at Ulm University aims at advancing highly-automated driving with close-to-market sensors while ensuring easy exchangeability of the particular components. In this contribution, the experimental vehicle that was realized during the project is presented along with its software modules. To achieve the mentioned goals, a sophisticated fusion approach for robust environment perception is essential. Apart from the necessary motion planning algorithms, this paper thus focuses on the sensor-independent fusion scheme. It allows for an efficient sensor replacement and realizes redundancy by using probabilistic and generic interfaces. Redundancy is ensured by utilizing multiple sensors of different types in crucial modules like grid mapping, localization and tracking. Furthermore, the combination of the module outputs to a consistent environment model is achieved by employing their probabilistic representation. The performance of the vehicle is discussed using the experience from numerous autonomous driving tests on public roads.
{"title":"Autonomous driving at Ulm University: A modular, robust, and sensor-independent fusion approach","authors":"Felix Kunz, Dominik Nuss, J. Wiest, H. Deusch, Stephan Reuter, Franz Gritschneder, A. Scheel, M. Stuebler, Martin Bach, Patrick Hatzelmann, Cornelius Wild, K. Dietmayer","doi":"10.1109/IVS.2015.7225761","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225761","url":null,"abstract":"The project “Autonomous Driving” at Ulm University aims at advancing highly-automated driving with close-to-market sensors while ensuring easy exchangeability of the particular components. In this contribution, the experimental vehicle that was realized during the project is presented along with its software modules. To achieve the mentioned goals, a sophisticated fusion approach for robust environment perception is essential. Apart from the necessary motion planning algorithms, this paper thus focuses on the sensor-independent fusion scheme. It allows for an efficient sensor replacement and realizes redundancy by using probabilistic and generic interfaces. Redundancy is ensured by utilizing multiple sensors of different types in crucial modules like grid mapping, localization and tracking. Furthermore, the combination of the module outputs to a consistent environment model is achieved by employing their probabilistic representation. The performance of the vehicle is discussed using the experience from numerous autonomous driving tests on public roads.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130087852","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225823
Yingnan Guang, Min Yang, Xuedan Zhang
With the taxi playing an increasingly important role in the lives of people, we need further develop the understanding of taxi behavior to analyze the movement pattern of population and improve various intelligent transportation systems. Our work focus on building a new model for the vacant taxi movement pattern in town center of Beijing and we make contribution in three ways. Firstly, through studying foraging behavior of wild animals, we establish the model combined with Lévy flight and exponential distribution. The simulation result is approximate to actual data we collected. Secondly, unlike previous models, we add the time dimension into our model and show the time function of all parameters. Finally, we explain the physical significance and conversion relation of parameters in our model. With these relationship, we can calculate parameters by some small items of data, not the whole database.
{"title":"A new model for the movement pattern of vacant taxi","authors":"Yingnan Guang, Min Yang, Xuedan Zhang","doi":"10.1109/IVS.2015.7225823","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225823","url":null,"abstract":"With the taxi playing an increasingly important role in the lives of people, we need further develop the understanding of taxi behavior to analyze the movement pattern of population and improve various intelligent transportation systems. Our work focus on building a new model for the vacant taxi movement pattern in town center of Beijing and we make contribution in three ways. Firstly, through studying foraging behavior of wild animals, we establish the model combined with Lévy flight and exponential distribution. The simulation result is approximate to actual data we collected. Secondly, unlike previous models, we add the time dimension into our model and show the time function of all parameters. Finally, we explain the physical significance and conversion relation of parameters in our model. With these relationship, we can calculate parameters by some small items of data, not the whole database.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127525201","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225830
Jason Kong, Mark Pfeiffer, Georg Schildbach, F. Borrelli
We study the use of kinematic and dynamic vehicle models for model-based control design used in autonomous driving. In particular, we analyze the statistics of the forecast error of these two models by using experimental data. In addition, we study the effect of discretization on forecast error. We use the results of the first part to motivate the design of a controller for an autonomous vehicle using model predictive control (MPC) and a simple kinematic bicycle model. The proposed approach is less computationally expensive than existing methods which use vehicle tire models. Moreover it can be implemented at low vehicle speeds where tire models become singular. Experimental results show the effectiveness of the proposed approach at various speeds on windy roads.
{"title":"Kinematic and dynamic vehicle models for autonomous driving control design","authors":"Jason Kong, Mark Pfeiffer, Georg Schildbach, F. Borrelli","doi":"10.1109/IVS.2015.7225830","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225830","url":null,"abstract":"We study the use of kinematic and dynamic vehicle models for model-based control design used in autonomous driving. In particular, we analyze the statistics of the forecast error of these two models by using experimental data. In addition, we study the effect of discretization on forecast error. We use the results of the first part to motivate the design of a controller for an autonomous vehicle using model predictive control (MPC) and a simple kinematic bicycle model. The proposed approach is less computationally expensive than existing methods which use vehicle tire models. Moreover it can be implemented at low vehicle speeds where tire models become singular. Experimental results show the effectiveness of the proposed approach at various speeds on windy roads.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128855333","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 : 2015-08-27DOI: 10.1109/IVS.2015.7225857
S. Amsalu, A. Homaifar, F. Afghah, S. Ramyar, A. Kurt
The capability to estimate driver's intention leads to the development of advanced driver assistance systems that can assist the drivers in complex situations. Developing precise driver behavior models near intersections can considerably reduce the number of accidents at road intersections. In this study, the problem of driver behavior modeling near a road intersection is investigated using support vector machines (SVMs) based on the hybrid-state system (HSS) framework. In the HSS framework, the decisions of the driver are represented as a discrete-state system and the vehicle dynamics are represented as a continuous-state system. The proposed modeling technique utilizes the continuous observations from the vehicle and estimates the driver's intention at each time step using a multi-class SVM approach. Statistical methods are used to extract features from continuous observations. This allows for the use of history in estimating the current state. The developed algorithm is trained and tested successfully using naturalistic driving data collected from a sensor-equipped vehicle operated in the streets of Columbus, OH and provided by the Ohio State University. The proposed framework shows a promising accuracy of above 97% in estimating the driver's intention when approaching an intersection.
估计驾驶员意图的能力导致了先进驾驶员辅助系统的发展，可以在复杂情况下帮助驾驶员。在十字路口建立精确的驾驶员行为模型可以大大减少十字路口的事故数量。本文采用基于混合状态系统(HSS)框架的支持向量机(svm)对路口附近驾驶员行为建模问题进行了研究。在HSS框架中，驾驶员的决策被表示为离散状态系统，车辆动力学被表示为连续状态系统。所提出的建模技术利用车辆的连续观测，并使用多类支持向量机方法估计驾驶员在每个时间步的意图。使用统计方法从连续观测中提取特征。这允许在估计当前状态时使用历史记录。所开发的算法经过训练，并通过俄亥俄州立大学(Ohio State University)提供的一辆在俄亥俄州哥伦布市(Columbus)街道上行驶的配备传感器的车辆收集的自然驾驶数据，成功地进行了测试。所提出的框架显示，在接近十字路口时，估计驾驶员意图的准确率超过97%。
{"title":"Driver behavior modeling near intersections using support vector machines based on statistical feature extraction","authors":"S. Amsalu, A. Homaifar, F. Afghah, S. Ramyar, A. Kurt","doi":"10.1109/IVS.2015.7225857","DOIUrl":"https://doi.org/10.1109/IVS.2015.7225857","url":null,"abstract":"The capability to estimate driver's intention leads to the development of advanced driver assistance systems that can assist the drivers in complex situations. Developing precise driver behavior models near intersections can considerably reduce the number of accidents at road intersections. In this study, the problem of driver behavior modeling near a road intersection is investigated using support vector machines (SVMs) based on the hybrid-state system (HSS) framework. In the HSS framework, the decisions of the driver are represented as a discrete-state system and the vehicle dynamics are represented as a continuous-state system. The proposed modeling technique utilizes the continuous observations from the vehicle and estimates the driver's intention at each time step using a multi-class SVM approach. Statistical methods are used to extract features from continuous observations. This allows for the use of history in estimating the current state. The developed algorithm is trained and tested successfully using naturalistic driving data collected from a sensor-equipped vehicle operated in the streets of Columbus, OH and provided by the Ohio State University. The proposed framework shows a promising accuracy of above 97% in estimating the driver's intention when approaching an intersection.","PeriodicalId":294701,"journal":{"name":"2015 IEEE Intelligent Vehicles Symposium (IV)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128056737","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：