Pub Date : 2009-06-03DOI: 10.1109/IVS.2009.5164251
Ludovic Simon, Jean-Philippe Tarel, R. Brémond
This paper proposes an improvement of Advanced Driver Assistance System based on saliency estimation of road signs. After a road sign detection stage, its saliency is estimated using a SVM learning. A model of visual saliency linking the size of an object and a size-independent saliency is proposed. An eye tracking experiment in context close to driving proves that this computational evaluation of the saliency fits well with human perception, and demonstrates the applicability of the proposed estimator for improved ADAS.
{"title":"Alerting the drivers about road signs with poor visual saliency","authors":"Ludovic Simon, Jean-Philippe Tarel, R. Brémond","doi":"10.1109/IVS.2009.5164251","DOIUrl":"https://doi.org/10.1109/IVS.2009.5164251","url":null,"abstract":"This paper proposes an improvement of Advanced Driver Assistance System based on saliency estimation of road signs. After a road sign detection stage, its saliency is estimated using a SVM learning. A model of visual saliency linking the size of an object and a size-independent saliency is proposed. An eye tracking experiment in context close to driving proves that this computational evaluation of the saliency fits well with human perception, and demonstrates the applicability of the proposed estimator for improved ADAS.","PeriodicalId":396749,"journal":{"name":"2009 IEEE Intelligent Vehicles Symposium","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123846221","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 : 2009-06-03DOI: 10.1109/IVS.2009.5164454
Y. Zhao, J. -. Zhang, X. Guan
In-wheel-motor drive electric vehicle (EV) is an innovative configuration, in which each wheel is driven individually by an electric motor. It is possible to use an electronic differential (ED) instead of the heavy mechanical differential because of the fast response time of the motor. A new ED control approach for a two-in-wheel-motor drive EV is devised based on the fuzzy logic control method. The fuzzy logic method employs to estimate the slip rate of each wheel considering the complex and nonlinear of the system. Then, the ED system distributes torque and power to each motor according to requirements. The effectiveness and validation of the proposed control method are evaluated in the Matlab/Simulink environment. Simulation results show that the new ED control system can keep the slip rate within the optimized range, ensuring the stability of the vehicle either in a straight or a curve lane.
{"title":"Modeling and simulation of electronic differential system for an electric vehicle with two-motor-wheel drive","authors":"Y. Zhao, J. -. Zhang, X. Guan","doi":"10.1109/IVS.2009.5164454","DOIUrl":"https://doi.org/10.1109/IVS.2009.5164454","url":null,"abstract":"In-wheel-motor drive electric vehicle (EV) is an innovative configuration, in which each wheel is driven individually by an electric motor. It is possible to use an electronic differential (ED) instead of the heavy mechanical differential because of the fast response time of the motor. A new ED control approach for a two-in-wheel-motor drive EV is devised based on the fuzzy logic control method. The fuzzy logic method employs to estimate the slip rate of each wheel considering the complex and nonlinear of the system. Then, the ED system distributes torque and power to each motor according to requirements. The effectiveness and validation of the proposed control method are evaluated in the Matlab/Simulink environment. Simulation results show that the new ED control system can keep the slip rate within the optimized range, ensuring the stability of the vehicle either in a straight or a curve lane.","PeriodicalId":396749,"journal":{"name":"2009 IEEE Intelligent Vehicles Symposium","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121490176","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 : 2009-06-03DOI: 10.1109/IVS.2009.5164316
Xun Dai, A. Kummert, S. B. Park, D. Neisius
Single Vehicle Road Departure (SVRD) is a main cause of enormous loss of life and property on highways. In total, SVRD accidents amount to around 20 percent of traffic accidents and 40 percent of fatalities in total. Recent developments of Advanced Driver Assistant System (ADAS) such as Lane Departure Warning (LDW) system which perceives road boundaries through optical sensors that trigger a warning when the driver leaves the lane without using their turn signal. However, a robust LDW system can not be realized with only turn signal usage to suppress warnings during an intended lane change. This paper will analyze not only driving position, but also driving tendency and driver state to determine whether an unintended lane departure is detected. The paper will explore how the warning algorithm summarizes information from the environment, vehicle and driver and establishes a model so that real unintended lane departure can be detected and a warning will be triggered accordingly.
{"title":"A warning algorithm for Lane Departure Warning system","authors":"Xun Dai, A. Kummert, S. B. Park, D. Neisius","doi":"10.1109/IVS.2009.5164316","DOIUrl":"https://doi.org/10.1109/IVS.2009.5164316","url":null,"abstract":"Single Vehicle Road Departure (SVRD) is a main cause of enormous loss of life and property on highways. In total, SVRD accidents amount to around 20 percent of traffic accidents and 40 percent of fatalities in total. Recent developments of Advanced Driver Assistant System (ADAS) such as Lane Departure Warning (LDW) system which perceives road boundaries through optical sensors that trigger a warning when the driver leaves the lane without using their turn signal. However, a robust LDW system can not be realized with only turn signal usage to suppress warnings during an intended lane change. This paper will analyze not only driving position, but also driving tendency and driver state to determine whether an unintended lane departure is detected. The paper will explore how the warning algorithm summarizes information from the environment, vehicle and driver and establishes a model so that real unintended lane departure can be detected and a warning will be triggered accordingly.","PeriodicalId":396749,"journal":{"name":"2009 IEEE Intelligent Vehicles Symposium","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128982713","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 : 2009-06-03DOI: 10.1109/IVS.2009.5164351
S. Kraus, M. Althoff, B. Heissing, M. Buss
In order to increase the acceptance of vehicles that drive (partly) autonomously, it seems advantageous that the driving style of autonomous cars is human-like. Furthermore, the acceptance of autonomous cars is believed to be increased when their actions and current state becomes more transparent to the passengers. These aspects can be tackled by implementing emotions to an autonomous car which allows a situation specific adaption of driving functions and vehicle dynamics. In this work, the emotions are modeled by the cognitive appraisal model as described by Ortony, Clore and Collins. The approach is presented for a traffic scene where two lanes are merged into one.
{"title":"Cognition and emotion in autonomous cars","authors":"S. Kraus, M. Althoff, B. Heissing, M. Buss","doi":"10.1109/IVS.2009.5164351","DOIUrl":"https://doi.org/10.1109/IVS.2009.5164351","url":null,"abstract":"In order to increase the acceptance of vehicles that drive (partly) autonomously, it seems advantageous that the driving style of autonomous cars is human-like. Furthermore, the acceptance of autonomous cars is believed to be increased when their actions and current state becomes more transparent to the passengers. These aspects can be tackled by implementing emotions to an autonomous car which allows a situation specific adaption of driving functions and vehicle dynamics. In this work, the emotions are modeled by the cognitive appraisal model as described by Ortony, Clore and Collins. The approach is presented for a traffic scene where two lanes are merged into one.","PeriodicalId":396749,"journal":{"name":"2009 IEEE Intelligent Vehicles Symposium","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122444769","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 : 2009-06-03DOI: 10.1109/IVS.2009.5164470
Sihong Zhu, Baozhan Lu
Based on the investigation of vibration characteristics of certain vehicle without suspension, a new type of damping- adjustable hydro-pneumatic suspension was put forward. Based on the analysis of working principle, the nonlinear mathematical and output force characteristic models of suspension were set up. Using MATLAB/Simulink, through adjusting initialization pressure and volume of accumulator, the diameter and number of orifice valve, the diameter of adjustable throttle and the amplitude and frequency of excitation, the influences of these parameters to output force characteristics were put forward. Simulation results show that initialization pressure of accumulator doesn't influence the curve shape of displacement and velocity characteristics of output force and doesn't influence the damping force of suspension, and orifice valve, adjustable throttle and excitation influence greatly to output force characteristics, especially to revert phase.
{"title":"Simulation on output force characteristics of damping-adjustable hydro-pneumatic suspension","authors":"Sihong Zhu, Baozhan Lu","doi":"10.1109/IVS.2009.5164470","DOIUrl":"https://doi.org/10.1109/IVS.2009.5164470","url":null,"abstract":"Based on the investigation of vibration characteristics of certain vehicle without suspension, a new type of damping- adjustable hydro-pneumatic suspension was put forward. Based on the analysis of working principle, the nonlinear mathematical and output force characteristic models of suspension were set up. Using MATLAB/Simulink, through adjusting initialization pressure and volume of accumulator, the diameter and number of orifice valve, the diameter of adjustable throttle and the amplitude and frequency of excitation, the influences of these parameters to output force characteristics were put forward. Simulation results show that initialization pressure of accumulator doesn't influence the curve shape of displacement and velocity characteristics of output force and doesn't influence the damping force of suspension, and orifice valve, adjustable throttle and excitation influence greatly to output force characteristics, especially to revert phase.","PeriodicalId":396749,"journal":{"name":"2009 IEEE Intelligent Vehicles Symposium","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121985640","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}
This paper presents an central difference Kalman filter (CDKF) based Simultaneous Localization and Mapping (SLAM) algorithm, which is an alternative to the classical extended Kalman filter based SLAM solution (EKF-SLAM). EKF-SLAM suffers from two important problems, which are the calculation of Jacobians and the linear approximations to the nonlinear models. They can lead the filter to be inconsistent. To overcome the serious drawbacks of the previous frameworks, Sterling's polynomial interpolation method is employed to approximate nonlinear models. Combined with the Kanlman filter framework, CDKF is proposed to solve the probabilistic state-space SLAM problem. The proposed approach improves the filter consistency and state estimation accuracy. Both simulated experiments and bench mark data set are used to demonstrating the superiority of the proposed algorithm.
{"title":"A SLAM algorithm based on the central difference Kalman filter","authors":"Jihua Zhu, Nanning Zheng, Zejian Yuan, Qiang Zhang, Xuetao Zhang, Yongjian He","doi":"10.1109/IVS.2009.5164264","DOIUrl":"https://doi.org/10.1109/IVS.2009.5164264","url":null,"abstract":"This paper presents an central difference Kalman filter (CDKF) based Simultaneous Localization and Mapping (SLAM) algorithm, which is an alternative to the classical extended Kalman filter based SLAM solution (EKF-SLAM). EKF-SLAM suffers from two important problems, which are the calculation of Jacobians and the linear approximations to the nonlinear models. They can lead the filter to be inconsistent. To overcome the serious drawbacks of the previous frameworks, Sterling's polynomial interpolation method is employed to approximate nonlinear models. Combined with the Kanlman filter framework, CDKF is proposed to solve the probabilistic state-space SLAM problem. The proposed approach improves the filter consistency and state estimation accuracy. Both simulated experiments and bench mark data set are used to demonstrating the superiority of the proposed algorithm.","PeriodicalId":396749,"journal":{"name":"2009 IEEE Intelligent Vehicles Symposium","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126359589","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 : 2009-06-03DOI: 10.1109/IVS.2009.5164355
J. Andreasson
This paper describes how dynamic optimization can be used to evaluate the potential of different actuator combinations for extended vehicle controllability. The paper illustrates the methodology by comparing performance of rear axle steering with wheel torque distribution. The evaluated maneuver is a rapid sideways motion, aiming at avoiding a suddenly appearing obstacle on the road.
{"title":"Enhancing active safety by extending controllability - How much can be gained?","authors":"J. Andreasson","doi":"10.1109/IVS.2009.5164355","DOIUrl":"https://doi.org/10.1109/IVS.2009.5164355","url":null,"abstract":"This paper describes how dynamic optimization can be used to evaluate the potential of different actuator combinations for extended vehicle controllability. The paper illustrates the methodology by comparing performance of rear axle steering with wheel torque distribution. The evaluated maneuver is a rapid sideways motion, aiming at avoiding a suddenly appearing obstacle on the road.","PeriodicalId":396749,"journal":{"name":"2009 IEEE Intelligent Vehicles Symposium","volume":"11 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129167451","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 : 2009-06-03DOI: 10.1109/IVS.2009.5164485
L. Lirong, Jin Xiaoxiong, Jin Chang
In addition to the function of fresh air intake and filtering, automotive intake system is usually also required a good acoustic characteristics and the effective control of the engine intake noise. The impact of different structure parameters to the flow field of the intake system is analyzed in the paper, the one-dimensional porous jump model is applied to model the filter paper. Meanwhile, silencing component is added to the intake system to degrade the noise peak value and improve silencing performance at low-frequency. The comparison of the simulation and testing results shows good agreement. It is proved that the acoustic performance of the intake system has been greatly improved after adding the silencing component.
{"title":"Flow field simulation analysis and acoustic performance improvement of automotive intake system","authors":"L. Lirong, Jin Xiaoxiong, Jin Chang","doi":"10.1109/IVS.2009.5164485","DOIUrl":"https://doi.org/10.1109/IVS.2009.5164485","url":null,"abstract":"In addition to the function of fresh air intake and filtering, automotive intake system is usually also required a good acoustic characteristics and the effective control of the engine intake noise. The impact of different structure parameters to the flow field of the intake system is analyzed in the paper, the one-dimensional porous jump model is applied to model the filter paper. Meanwhile, silencing component is added to the intake system to degrade the noise peak value and improve silencing performance at low-frequency. The comparison of the simulation and testing results shows good agreement. It is proved that the acoustic performance of the intake system has been greatly improved after adding the silencing component.","PeriodicalId":396749,"journal":{"name":"2009 IEEE Intelligent Vehicles Symposium","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131807748","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 : 2009-06-03DOI: 10.1109/IVS.2009.5164404
A. Sebastian, Maolin Tang, Yanming Feng, M. Looi
Cooperative collision warning system for road vehicles, enabled by recent advances in positioning systems and wireless communication technologies, can potentially reduce traffic accident significantly. To improve the system, we propose a graph model to represent interactions between multiple road vehicles in a specific region and at a specific time. Given a list of vehicles in vicinity, we can generate the interaction graph using several rules that consider vehicle's properties such as position, speed, heading, etc. Safety applications can use the model to improve emergency warning accuracy and optimize wireless channel usage. The model allows us to develop some congestion control strategies for an efficient multi-hop broadcast protocol.
{"title":"Multi-vehicles interaction graph model for cooperative collision warning system","authors":"A. Sebastian, Maolin Tang, Yanming Feng, M. Looi","doi":"10.1109/IVS.2009.5164404","DOIUrl":"https://doi.org/10.1109/IVS.2009.5164404","url":null,"abstract":"Cooperative collision warning system for road vehicles, enabled by recent advances in positioning systems and wireless communication technologies, can potentially reduce traffic accident significantly. To improve the system, we propose a graph model to represent interactions between multiple road vehicles in a specific region and at a specific time. Given a list of vehicles in vicinity, we can generate the interaction graph using several rules that consider vehicle's properties such as position, speed, heading, etc. Safety applications can use the model to improve emergency warning accuracy and optimize wireless channel usage. The model allows us to develop some congestion control strategies for an efficient multi-hop broadcast protocol.","PeriodicalId":396749,"journal":{"name":"2009 IEEE Intelligent Vehicles Symposium","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121198290","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 : 2009-06-03DOI: 10.1109/IVS.2009.5164450
Christopher Claus, A. Laika, Lei Jia, W. Stechele
Emerging camera systems in a rising number of cars increase the demand for real-time capable low cost image processing systems. The capability of such a system is demonstrated by an algorithm for the computation of Optical Flow. In this paper it is shown how the algorithm has to be (re-)designed in order to benefit from platform (FPGA or CPU) specific features. In addition a hardware implementation is presented meeting the real-time requirements and outperforms general purpose CPUs in terms of execution time and power consumption. Timing measurements as well as an analysis on the quality of the resulting Optical Flow are presented. Although the clock frequency of the FPGA-based solution is nearly 18 times lower, compared to a 1.86 GHz Core2 CPU, results are computed almost twice as fast.
{"title":"High performance FPGA based optical flow calculation using the census transformation","authors":"Christopher Claus, A. Laika, Lei Jia, W. Stechele","doi":"10.1109/IVS.2009.5164450","DOIUrl":"https://doi.org/10.1109/IVS.2009.5164450","url":null,"abstract":"Emerging camera systems in a rising number of cars increase the demand for real-time capable low cost image processing systems. The capability of such a system is demonstrated by an algorithm for the computation of Optical Flow. In this paper it is shown how the algorithm has to be (re-)designed in order to benefit from platform (FPGA or CPU) specific features. In addition a hardware implementation is presented meeting the real-time requirements and outperforms general purpose CPUs in terms of execution time and power consumption. Timing measurements as well as an analysis on the quality of the resulting Optical Flow are presented. Although the clock frequency of the FPGA-based solution is nearly 18 times lower, compared to a 1.86 GHz Core2 CPU, results are computed almost twice as fast.","PeriodicalId":396749,"journal":{"name":"2009 IEEE Intelligent Vehicles Symposium","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121357190","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：