D. Fernández, I. Parra, M. Sotelo, P. Revenga, S. Alvarez, M. Gavilán
{"title":"3D Candidate Selection Method for Pedestrian Detection on Non-Planar Roads","authors":"D. Fernández, I. Parra, M. Sotelo, P. Revenga, S. Alvarez, M. Gavilán","doi":"10.1109/IVS.2007.4290275","DOIUrl":"https://doi.org/10.1109/IVS.2007.4290275","url":null,"abstract":"This paper describes a stereo-vision-based candidate selection method for pedestrian detection from a moving vehicle. Non-dense 3D maps are computed by using epipolar geometry and a robust correlation process. Non-flat road assumption is used for correcting pitch angle variations. Thus, non obstacle points can be easily removed since they lay on the road. Generic obstacles are selected by using Subtractive Clustering algorithm in a 3D space with an adaptive radius. This clustering technique can be configurable for different types of obstacles. An optimal configuration for pedestrian detection is presented in this work.","PeriodicalId":190903,"journal":{"name":"2007 IEEE Intelligent Vehicles Symposium","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124879767","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}
{"title":"Determining Posterior Probabilities on the Basis of Cascaded Classifiers as used in Pedestrian Detection Systems","authors":"R. Schweiger, H. Hamer, O. Lohlein","doi":"10.1109/IVS.2007.4290295","DOIUrl":"https://doi.org/10.1109/IVS.2007.4290295","url":null,"abstract":"Cascaded classifiers are widely spread in automotive pedestrian detection systems. Since there has been no research on probabilistic information derivable on the basis of a cascade, these systems are limited in the sense that they only exploit the binary classification results. In contrast to that, this paper presents a mathematically founded model regarding the computation of posterior probabilities on the basis of such classifiers. This is highly relevant in respect of the further development of robust and reliable detection systems.","PeriodicalId":190903,"journal":{"name":"2007 IEEE Intelligent Vehicles Symposium","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131529254","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}
{"title":"A Multilevel Traffic Incidents Detection Approach: Identifying Traffic Patterns and Vehicle Behaviours using real-time GPS data","authors":"S. Kamran, O. Haas","doi":"10.1109/IVS.2007.4290233","DOIUrl":"https://doi.org/10.1109/IVS.2007.4290233","url":null,"abstract":"This paper presents a multilevel approach for detecting traffic incidents causing congestion on major roads. It incorporates algorithms to detect unusual traffic patterns and vehicle behaviours on different road segments by utilising the real-time GPS data obtained from vehicles. The incident detection process involves two phases: (1) Identifies of road segments where abnormal traffic pattern is observed and further divides the 'abnormal segments' into smaller segments in order to isolate the potential incident area; (2) Performs a hierarchical analysis of the vehicles' GPS data, using predefined rules to detect any occurrence of abnormal behaviour within the 'abnormal' road section identified in phase 1. The strength of such approach lays in isolating road segments sequentially and then analysing vehicle data specific to the identified road segment. In this way, the processing of vast data is avoided which is an essential requirement for the better performance of such complex systems. The approach is demonstrated using a simulation of motorway segments near Coventry, UK.","PeriodicalId":190903,"journal":{"name":"2007 IEEE Intelligent Vehicles Symposium","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128323844","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}
{"title":"Identification of Aerodynamic Coefficients of Ground Vehicles Using Neural Network","authors":"N. Ramli, S. Mansor, H. Jamaluddin, W. Faris","doi":"10.1109/IVS.2007.4290090","DOIUrl":"https://doi.org/10.1109/IVS.2007.4290090","url":null,"abstract":"The purpose of this paper is to demonstrate the application of a combination of neural network and an oscillating model facility as an approach in identification of aerodynamic coefficients of ground vehicle. In literature study, a method for estimating transient aerodynamic data has been introduced and the aerodynamic coefficients are extracted from the measured time response by means of conventional approach. The potential of neural network as an alternative method is explored. For simplicity, only the damped oscillation considered in this analysis while neglecting any unsteadiness or buffeting load Two feedforward neural networks are constructed to estimate the damping ratio and natural frequency, respectively, from the measured time response recorded during the dynamic wind tunnel test. These two parameters are used to calculate the aerodynamic coefficients of the ground vehicle model. To validate the network approach, the resulted coefficients are compared with the ones retrieved conventionally. By simulating the system's transfer function, the response generated from neural network results were found to be closer to the measured time response compared to the response generated using the conventionally estimated coefficients.","PeriodicalId":190903,"journal":{"name":"2007 IEEE Intelligent Vehicles Symposium","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121344788","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}
{"title":"Gain Scheduled Active Steering Control Based on a Parametric Bicycle Model","authors":"S. C. Baslamisli, I. Polat, I. E. Kose","doi":"10.1109/IVS.2007.4290276","DOIUrl":"https://doi.org/10.1109/IVS.2007.4290276","url":null,"abstract":"This paper presents a gain scheduled active steering control design method to preserve vehicle stability in extreme handling situations. It is shown that instead of the classical linear tire model based on expressing cornering force proportional to tire sideslip angle, a simple rational model with validity extending beyond the linear regime of the tire may be considered. This results in a new formulation of the bicycle model in which tire sideslip angles and vehicle forward speed appear as time-varying parameters. Such a model happens to be useful in the design of controllers scheduled by tire sideslip angles: after having expressed the parametric bicycle model in the parametric descriptor form, a gain scheduled active steering controller is designed in this study to improve vehicle handling at \"large\" driver commanded steering angles. Simulations reveal the efficiency of the selected modeling and controller design methodology in enhancing vehicle handling capacity during cornering on roads with high and low adhesion coefficient.","PeriodicalId":190903,"journal":{"name":"2007 IEEE Intelligent Vehicles Symposium","volume":"47 2-3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120928772","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}
{"title":"Navigation of Autonomous Vehicles in Unknown Environments using Reinforcement Learning","authors":"T. Martínez-Marín, Rafael Rodríguez","doi":"10.1109/IVS.2007.4290226","DOIUrl":"https://doi.org/10.1109/IVS.2007.4290226","url":null,"abstract":"In this paper we propose a generic approach for navigation of nonholonomic vehicles in unknown environments. The vehicle model is also unknown, so the path planner uses reinforcement learning to acquire the optimal behaviour together with the model, which is estimated by a reduced set of transitions. After the training phase, the vehicle is able to explore the environment through a wall-following behaviour. In order to guide the navigation and to build a map of the environment the planner employs virtual walls. The learning time to acquire a good approximation of the wall-following behaviour was only a few minutes. Both simulation and experimental results are reported to show the satisfactory performance of the method.","PeriodicalId":190903,"journal":{"name":"2007 IEEE Intelligent Vehicles Symposium","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129577246","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}
S. Oncu, S. Karaman, Levent Guvenc, S. Ersolmaz, E. Serdar Ozturk, E. Çetin, M. Sinal
{"title":"Robust Yaw Stability Controller Design for a Light Commercial Vehicle Using a Hardware in the Loop Steering Test Rig","authors":"S. Oncu, S. Karaman, Levent Guvenc, S. Ersolmaz, E. Serdar Ozturk, E. Çetin, M. Sinal","doi":"10.1109/IVS.2007.4290223","DOIUrl":"https://doi.org/10.1109/IVS.2007.4290223","url":null,"abstract":"This paper is on designing a multi-objective, robust parameter space steering controller for yaw stability improvement of a light commercial vehicle and its testing on a hardware-in-the-loop steering test rig. A linear single track model of the light commercial vehicle is used for controller design while its nonlinear version is used during hardware-in-the-loop simulations. The multi-objective design method used here maps D-stability, mixed sensitivity and phase margin bounds into the parameter space of chosen disturbance observer based steering controller filter parameters. The resulting controller design is tested using offline and hardware-in-the-loop simulations. A hardware-in-the-loop simulation test rig with the actual rack and pinion mechanism of the light commercial vehicle under study was built for this purpose. The steering control actuator is placed on the second pinion of the double pinion steering test system used. The hardware and geometry of the steering test rig are identical to the implementation of the steering system in the test vehicle. Unnecessary and expensive road testing is avoided with this approach as most problems are identified and solved in the hardware-in-the-loop simulation phase conducted in the laboratory where the steering subsystem and its controller exist as hardware and the rest of the vehicle being implemented exists as real time capable software. Hardware-in-the-loop simulation results show the effectiveness of the controller design proposed in this paper in tracking desired steering dynamics and in rejecting yaw disturbance moments.","PeriodicalId":190903,"journal":{"name":"2007 IEEE Intelligent Vehicles Symposium","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134582089","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}
{"title":"Human Driver Model and Driver Decision Making for Intersection Driving","authors":"Yiting Liu, U. Ozguner","doi":"10.1109/IVS.2007.4290188","DOIUrl":"https://doi.org/10.1109/IVS.2007.4290188","url":null,"abstract":"In this paper, a general architecture of human driver model at intersections is proposed. One of the key modules in the architecture, driver decision making module, is discussed in details under various traffic scenarios. Process flow diagrams that are built in the decision making module for various decision making processes at both unsignalized and signalized intersections are also presented. This human driver model can be used not only for simulating human driver response, but also for autonomous vehicle's decision making in the intersection area. A left-turning scenario at an unsignalized intersection was simulated by applying the proposed driver decision process flow diagram. Driver's behavior was mimicked and safe vehicle operations were demonstrated.","PeriodicalId":190903,"journal":{"name":"2007 IEEE Intelligent Vehicles Symposium","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131113629","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}
B. Alefs, G. Eschemann, H. Ramoser, Csaba Beleznai
{"title":"Road Sign Detection from Edge Orientation Histograms","authors":"B. Alefs, G. Eschemann, H. Ramoser, Csaba Beleznai","doi":"10.1109/IVS.2007.4290246","DOIUrl":"https://doi.org/10.1109/IVS.2007.4290246","url":null,"abstract":"This paper presents a system for road sign detection based on edge orientation histograms. Edge orientation histograms are reliable, scale and contrast invariant features that can be extracted efficiently using integral images. A learning method is introduced that selects features based on the implicit transmission function of the designer's template to the object's appearance in the image. The system is able to detect 85% of the objects on from 12 pixels width and 95% for objects on from 24 pixels width at a low false alarm rate.","PeriodicalId":190903,"journal":{"name":"2007 IEEE Intelligent Vehicles Symposium","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133688518","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}
{"title":"Assessing the maneuverability of tractor trailer systems in heavy goods transport","authors":"E. Balcerak, T. Weidenfeller, D. Zobel","doi":"10.1109/IVS.2007.4290166","DOIUrl":"https://doi.org/10.1109/IVS.2007.4290166","url":null,"abstract":"In recent years strong efforts have been made for assistance and automation of heavy goods vehicles. The major efforts focus on driver and driving assistance systems for a broad scope of use cases. Minor efforts have been spent for autonomous driving of heavy goods vehicles. Here the scope of application is limited to non-public traffic, e.g. logistics centers and factory grounds. Also the degree of autonomy is limited, typically to the same level as for AGV's following predefined trajectories. However, extending autonomous driving to logistics centers and factory grounds comes along with a variety of new challenges. An important one is discussed here and regards the maneuverability of vehicles with a high degree of nonholonomy on narrow grounds. In doing this a quantifiable measure of maneuverability has to be defined and applied to comparable heavy goods vehicles.","PeriodicalId":190903,"journal":{"name":"2007 IEEE Intelligent Vehicles Symposium","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133710065","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}