This work contributes to vision processing for Advanced Driver Assist Systems (ADAS) and intelligent vehicle applications. We propose a color-only stixel segmentation framework to segment traffic scenes into free, drivable space and obstacles, which has a reduced latency to improve the real-time processing capabilities. Our system learns color appearance models for free-space and obstacle classes in an online and self-supervised fashion. To this end, it applies a disparity-based segmentation, which can run in the background of the critical system path, either with a time delay of several frames or at a frame rate that is only a third of that of the color-based algorithm. In parallel, the most recent video frame is analyzed solely with these learned color appearance models, without an actual disparity estimate and the corresponding latency. This translates into a reduced response time from data acquisition to data analysis, which is a critical property for high-speed ADAS. Our evaluation on two publicly available datasets, one of which we introduce as part of this work, shows that the color-only analysis can achieve similar or even better results in difficult imaging conditions, compared to the disparity-only method. Our system improves the quality of the free-space analysis, while simultaneously lowering the latency and the computational load.
{"title":"Color-Based Free-Space Segmentation Using Online Disparity-Supervised Learning","authors":"Willem P. Sanberg, Gijs Dubbelman, P. D. With","doi":"10.1109/ITSC.2015.152","DOIUrl":"https://doi.org/10.1109/ITSC.2015.152","url":null,"abstract":"This work contributes to vision processing for Advanced Driver Assist Systems (ADAS) and intelligent vehicle applications. We propose a color-only stixel segmentation framework to segment traffic scenes into free, drivable space and obstacles, which has a reduced latency to improve the real-time processing capabilities. Our system learns color appearance models for free-space and obstacle classes in an online and self-supervised fashion. To this end, it applies a disparity-based segmentation, which can run in the background of the critical system path, either with a time delay of several frames or at a frame rate that is only a third of that of the color-based algorithm. In parallel, the most recent video frame is analyzed solely with these learned color appearance models, without an actual disparity estimate and the corresponding latency. This translates into a reduced response time from data acquisition to data analysis, which is a critical property for high-speed ADAS. Our evaluation on two publicly available datasets, one of which we introduce as part of this work, shows that the color-only analysis can achieve similar or even better results in difficult imaging conditions, compared to the disparity-only method. Our system improves the quality of the free-space analysis, while simultaneously lowering the latency and the computational load.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121969666","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}
George Papageorgiou, Athanasios Maimaris, P. Ioannou
The objective of this paper is to present the process of developing a traffic simulation model for evaluating a number of Bus Rapid Transit system components in a highly congested traffic network in Nicosia, Cyprus. The scenarios to be evaluated include the use of dedicated bus lanes and high occupancy vehicle lanes. The assessment is carried out via validated microscopic simulation models of the traffic network under study. As seen from the analysis of the results, a viable long term solution to enhancing the bus transport mode is drawn where significant improvements are achieved regarding a number of measures of effectiveness, such as travel time, delays and speed.
{"title":"Analysis and Evaluation of Intelligent Bus Rapid Transit Systems in Cyprus","authors":"George Papageorgiou, Athanasios Maimaris, P. Ioannou","doi":"10.1109/ITSC.2015.24","DOIUrl":"https://doi.org/10.1109/ITSC.2015.24","url":null,"abstract":"The objective of this paper is to present the process of developing a traffic simulation model for evaluating a number of Bus Rapid Transit system components in a highly congested traffic network in Nicosia, Cyprus. The scenarios to be evaluated include the use of dedicated bus lanes and high occupancy vehicle lanes. The assessment is carried out via validated microscopic simulation models of the traffic network under study. As seen from the analysis of the results, a viable long term solution to enhancing the bus transport mode is drawn where significant improvements are achieved regarding a number of measures of effectiveness, such as travel time, delays and speed.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116850601","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 a novel approach on Model Predictive Control (MPC) using an inhomogeneously discretized preview horizon for the application of urban energy efficient driving. One solution for model predictive energy efficient driving is a direct solution of the underlying speed profile optimization problem using Quadratic Programming (QP), which allows computationally efficient and robust results. Our inhomogeneous horizon discretization allows to have a finer discretization of the typically important near future and a wider discretization of the less decisive far range of an MPC, while keeping a long preview horizon and at the same time limit the number of supporting points, hence limit the problem dimension, computational complexity, and proportional execution time. In extensive simulations of a real-world urban driving scenario, we demonstrate a significantly improved control performance in terms of fuel consumption, trip time, or constraint violation for the same computational complexity.
{"title":"Inhomogeneous Model Predictive Control Horizon Discretization for an Urban Truck Energy Efficient Driving Application","authors":"Michael Henzler, M. Buchholz, K. Dietmayer","doi":"10.1109/ITSC.2015.78","DOIUrl":"https://doi.org/10.1109/ITSC.2015.78","url":null,"abstract":"This paper presents a novel approach on Model Predictive Control (MPC) using an inhomogeneously discretized preview horizon for the application of urban energy efficient driving. One solution for model predictive energy efficient driving is a direct solution of the underlying speed profile optimization problem using Quadratic Programming (QP), which allows computationally efficient and robust results. Our inhomogeneous horizon discretization allows to have a finer discretization of the typically important near future and a wider discretization of the less decisive far range of an MPC, while keeping a long preview horizon and at the same time limit the number of supporting points, hence limit the problem dimension, computational complexity, and proportional execution time. In extensive simulations of a real-world urban driving scenario, we demonstrate a significantly improved control performance in terms of fuel consumption, trip time, or constraint violation for the same computational complexity.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117096711","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}
A. Jamshidnejad, H. Hellendoorn, Shu Lin, B. Schutter
Traffic congestion together with emissions has become a big problem in urban areas. Traffic-responsive control systems aim to make the best use of the existing road capacity. Here, we propose a model-predictive controller for urban traffic networks, where the goal of the control is to find a balanced trade-off between reduction of congestion and emissions. The cost function is defined as a weighted combination of the total time spent, TTS, (as a criterion for evaluating the congestion level), the total emissions, TE, and the expected values of the TTS and TE caused by the vehicles that remain in the network at the end of the prediction horizon until they leave the network. We propose a method for estimation of the expected time spent and emissions by the remaining vehicles, where our method is based on a K Shortest path algorithm. For the prediction model of the MPC-based controller, we use a macroscopic integrated flow-emission model that includes the macroscopic flow S-model and the microscopic emission model, VT-micro. Since the S-model includes non-smooth functions, it does not allow us to benefit from efficient gradient-based methods to solve the optimization problem of the MPC-based controller. Therefore, in this paper we also propose smoothing methods for the S-model.
{"title":"Smoothening for Efficient Solution of Model Predictive Control for Urban Traffic Networks Considering Endpoint Penalties","authors":"A. Jamshidnejad, H. Hellendoorn, Shu Lin, B. Schutter","doi":"10.1109/ITSC.2015.456","DOIUrl":"https://doi.org/10.1109/ITSC.2015.456","url":null,"abstract":"Traffic congestion together with emissions has become a big problem in urban areas. Traffic-responsive control systems aim to make the best use of the existing road capacity. Here, we propose a model-predictive controller for urban traffic networks, where the goal of the control is to find a balanced trade-off between reduction of congestion and emissions. The cost function is defined as a weighted combination of the total time spent, TTS, (as a criterion for evaluating the congestion level), the total emissions, TE, and the expected values of the TTS and TE caused by the vehicles that remain in the network at the end of the prediction horizon until they leave the network. We propose a method for estimation of the expected time spent and emissions by the remaining vehicles, where our method is based on a K Shortest path algorithm. For the prediction model of the MPC-based controller, we use a macroscopic integrated flow-emission model that includes the macroscopic flow S-model and the microscopic emission model, VT-micro. Since the S-model includes non-smooth functions, it does not allow us to benefit from efficient gradient-based methods to solve the optimization problem of the MPC-based controller. Therefore, in this paper we also propose smoothing methods for the S-model.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120858595","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}
Stefan Müller, Dennis Hospach, O. Bringmann, J. Gerlach, W. Rosenstiel
In this paper we propose a novel method of robustness evaluation and improvement. The required amount of on-road records used in the design and validation of vision-based advanced driver assistance systems and fully automated driving vehicles is reduced by the use of fitness landscaping. This is realized by guided application of simulated environmental conditions to real video data. To achieve a high test coverage of advanced driver assistance systems many different environmental conditions have to be tested. However, it is by far too time-consuming to build test sets of all environmental combinations by recording real video data. Our approach facilitates the generation of comparable test sets by using largely reduced amounts of real on-road records and subsequent application of computer-generated environmental variations. We demonstrate this method using virtual prototypes of an automotive traffic sign recognition system and a lane detection system. The robustness of these systems is evaluated and improved in a second step.
{"title":"Robustness Evaluation and Improvement for Vision-Based Advanced Driver Assistance Systems","authors":"Stefan Müller, Dennis Hospach, O. Bringmann, J. Gerlach, W. Rosenstiel","doi":"10.1109/ITSC.2015.427","DOIUrl":"https://doi.org/10.1109/ITSC.2015.427","url":null,"abstract":"In this paper we propose a novel method of robustness evaluation and improvement. The required amount of on-road records used in the design and validation of vision-based advanced driver assistance systems and fully automated driving vehicles is reduced by the use of fitness landscaping. This is realized by guided application of simulated environmental conditions to real video data. To achieve a high test coverage of advanced driver assistance systems many different environmental conditions have to be tested. However, it is by far too time-consuming to build test sets of all environmental combinations by recording real video data. Our approach facilitates the generation of comparable test sets by using largely reduced amounts of real on-road records and subsequent application of computer-generated environmental variations. We demonstrate this method using virtual prototypes of an automotive traffic sign recognition system and a lane detection system. The robustness of these systems is evaluated and improved in a second step.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"610 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123946560","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}
Anastasios Kouvelas, M. Saeedmanesh, N. Geroliminis
A control scheme for heterogeneous transportation networks is presented. The methodology is based on the concept of the Macroscopic Fundamental Diagram (MFD) integrated with an adaptive optimization technique. The heterogeneous transportation network is first partitioned into a number of regions with homogeneous traffic conditions and well-defined MFDs. A macroscopic MFD-based model is used to describe the traffic dynamics of the resulting multi-region transportation system. A multivariable proportional integral (PI) feedback regulator is implemented to control the nonlinear system in real-time. The control variables consist of the inter-transferring flows between neighbourhood regions and the actuators correspond to the traffic lights of these areas (e.g. boundaries between regions). The recently proposed Adaptive Fine-Tuning (AFT) algorithm is used to optimize the gain matrices as well as the vector with the set-points of the PI controller. AFT is an iterative adaptive algorithm that optimizes the values of the tuneable parameters of the controller (e.g. gains and set-points) based on measurements of a performance index (e.g. total delay) for different perturbations of the parameters. The overall control scheme is tested in simulation and different performance criteria are studied. The performance of a fixed-time policy is compared to the final controller that is obtained after the convergence of AFT.
{"title":"Feedback Perimeter Control for Heterogeneous Urban Networks Using Adaptive Optimization","authors":"Anastasios Kouvelas, M. Saeedmanesh, N. Geroliminis","doi":"10.1109/ITSC.2015.148","DOIUrl":"https://doi.org/10.1109/ITSC.2015.148","url":null,"abstract":"A control scheme for heterogeneous transportation networks is presented. The methodology is based on the concept of the Macroscopic Fundamental Diagram (MFD) integrated with an adaptive optimization technique. The heterogeneous transportation network is first partitioned into a number of regions with homogeneous traffic conditions and well-defined MFDs. A macroscopic MFD-based model is used to describe the traffic dynamics of the resulting multi-region transportation system. A multivariable proportional integral (PI) feedback regulator is implemented to control the nonlinear system in real-time. The control variables consist of the inter-transferring flows between neighbourhood regions and the actuators correspond to the traffic lights of these areas (e.g. boundaries between regions). The recently proposed Adaptive Fine-Tuning (AFT) algorithm is used to optimize the gain matrices as well as the vector with the set-points of the PI controller. AFT is an iterative adaptive algorithm that optimizes the values of the tuneable parameters of the controller (e.g. gains and set-points) based on measurements of a performance index (e.g. total delay) for different perturbations of the parameters. The overall control scheme is tested in simulation and different performance criteria are studied. The performance of a fixed-time policy is compared to the final controller that is obtained after the convergence of AFT.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125766861","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}
Qi Wang, C. S. Wieghardt, Yan Jiang, Jian-wei Gong, Bernardo Wagner
A new generalized path corridor-based local planner for a nonholonomic mobile robot is proposed to avoid dynamic obstacles while following the lead of a global path. Rather than applying the global path directly, the proposed local planner will transform the global path into a normative path. Then, a generalized path corridor (GPC) is constructed based on the normative path. GPC defines the maximum free space along the normative path for local path planning. This avoids the local planner searching the entire space but still provides enough flexibility to deal with the dynamic obstacles. Additionally, a new type of heuristic cost is also proposed, which is measured based on the distance from the current location to the goal along the normative path. The integration of the normative path-based heuristic makes the local path planning more goal-oriented and helps the robot to navigate through the GPC and reach the goal more effectively.
{"title":"Generalized Path Corridor-based Local Path Planning for Nonholonomic Mobile Robot","authors":"Qi Wang, C. S. Wieghardt, Yan Jiang, Jian-wei Gong, Bernardo Wagner","doi":"10.1109/ITSC.2015.311","DOIUrl":"https://doi.org/10.1109/ITSC.2015.311","url":null,"abstract":"A new generalized path corridor-based local planner for a nonholonomic mobile robot is proposed to avoid dynamic obstacles while following the lead of a global path. Rather than applying the global path directly, the proposed local planner will transform the global path into a normative path. Then, a generalized path corridor (GPC) is constructed based on the normative path. GPC defines the maximum free space along the normative path for local path planning. This avoids the local planner searching the entire space but still provides enough flexibility to deal with the dynamic obstacles. Additionally, a new type of heuristic cost is also proposed, which is measured based on the distance from the current location to the goal along the normative path. The integration of the normative path-based heuristic makes the local path planning more goal-oriented and helps the robot to navigate through the GPC and reach the goal more effectively.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124803860","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 reports on a simulation-based test of two new single intersection control algorithms and the methods to be used to get the needed input data for the two new methods. It also demonstrates, that the new methods have the promise of improving the currently used conventional method by 15% -- 28% on average. Although the results so far are based on a microscopic simulation, efforts have been made to be as close as possible to reality. In a future step the two new methods will be tested in the field at a real intersection.
{"title":"VITAL: A Simulation-Based Assessment of New Traffic Light Controls","authors":"J. Erdmann, R. Oertel, P. Wagner","doi":"10.1109/ITSC.2015.12","DOIUrl":"https://doi.org/10.1109/ITSC.2015.12","url":null,"abstract":"This paper reports on a simulation-based test of two new single intersection control algorithms and the methods to be used to get the needed input data for the two new methods. It also demonstrates, that the new methods have the promise of improving the currently used conventional method by 15% -- 28% on average. Although the results so far are based on a microscopic simulation, efforts have been made to be as close as possible to reality. In a future step the two new methods will be tested in the field at a real intersection.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128563822","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}
The rapid growth of urban population and numbers of private cars in this modern era, results in increasingly urgent transportation problem in cities throughout the world. Road traffic congestion is an omnipresent problem, which leads to delays, time loss, human stress, energy consumption, environmental pollution e.c.t. In order to decrease traffic congestion, there is a need for simulating and optimizing traffic control and improving traffic management. There are different ways for traffic congestion monitoring and analysis such as using video monitoring and surveillance systems, or static and dynamic sensors which allow traffic management in real time. There are also other methods using non real time analysis where traf?c congestion can be extracted from historical patterns of traf?c congestion. The historical patterns can be gained from the stored travel time and speed data. The goal of enhancing driver convenience is achieved by providing applications based on road traffic condition that mainly identifies congestion status. This paper presents a web application which uses live traffic congestion data from Google Maps traffic layer for real time congestion calculation. A technique utilized for estimating the level of congestion is image processing. The main objective is to provide an automated and yet interactive visualization tool for congestion analysis in real time. The aim is reducing the traffic congestion on roads which will lead to decrease in the number of accidents. It can provide important data which can help road traffic management. Thus, it is mainly dedicated to traffic managers, operators and analysts. Nevertheless it can be implemented also by road users. Unlike most sensor based applications, it makes quantified congestion data available even in regions with limited traffic data information.
{"title":"Traffic Congestion Analysis Visualisation Tool","authors":"N. Petrovska, A. Stevanovic","doi":"10.1109/ITSC.2015.243","DOIUrl":"https://doi.org/10.1109/ITSC.2015.243","url":null,"abstract":"The rapid growth of urban population and numbers of private cars in this modern era, results in increasingly urgent transportation problem in cities throughout the world. Road traffic congestion is an omnipresent problem, which leads to delays, time loss, human stress, energy consumption, environmental pollution e.c.t. In order to decrease traffic congestion, there is a need for simulating and optimizing traffic control and improving traffic management. There are different ways for traffic congestion monitoring and analysis such as using video monitoring and surveillance systems, or static and dynamic sensors which allow traffic management in real time. There are also other methods using non real time analysis where traf?c congestion can be extracted from historical patterns of traf?c congestion. The historical patterns can be gained from the stored travel time and speed data. The goal of enhancing driver convenience is achieved by providing applications based on road traffic condition that mainly identifies congestion status. This paper presents a web application which uses live traffic congestion data from Google Maps traffic layer for real time congestion calculation. A technique utilized for estimating the level of congestion is image processing. The main objective is to provide an automated and yet interactive visualization tool for congestion analysis in real time. The aim is reducing the traffic congestion on roads which will lead to decrease in the number of accidents. It can provide important data which can help road traffic management. Thus, it is mainly dedicated to traffic managers, operators and analysts. Nevertheless it can be implemented also by road users. Unlike most sensor based applications, it makes quantified congestion data available even in regions with limited traffic data information.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129341482","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}
We present a system for efficient dynamic hand gesture recognition based on a single time-of-flight sensor. As opposed to other approaches, we simply rely on depth data to interpret user movement with the hand in mid-air. We set up a large database to train multilayer perceptrons (MLPs) which are subsequently used for classification of static hand poses that define the targeted dynamic gestures. In order to remain robust against noise and to balance the low sensor resolution, PCA is used for data cropping and highly descriptive features, obtainable in real-time, are presented. Our simple yet efficient definition of a dynamic hand gesture shows how strong results are achievable in an automotive environment allowing for interesting and sophisticated applications to be realized.
{"title":"A Real-Time Applicable Dynamic Hand Gesture Recognition Framework","authors":"Thomas Kopinski, A. Gepperth, U. Handmann","doi":"10.1109/ITSC.2015.381","DOIUrl":"https://doi.org/10.1109/ITSC.2015.381","url":null,"abstract":"We present a system for efficient dynamic hand gesture recognition based on a single time-of-flight sensor. As opposed to other approaches, we simply rely on depth data to interpret user movement with the hand in mid-air. We set up a large database to train multilayer perceptrons (MLPs) which are subsequently used for classification of static hand poses that define the targeted dynamic gestures. In order to remain robust against noise and to balance the low sensor resolution, PCA is used for data cropping and highly descriptive features, obtainable in real-time, are presented. Our simple yet efficient definition of a dynamic hand gesture shows how strong results are achievable in an automotive environment allowing for interesting and sophisticated applications to be realized.","PeriodicalId":124818,"journal":{"name":"2015 IEEE 18th International Conference on Intelligent Transportation Systems","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127433777","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：