Pub Date : 2019-10-01DOI: 10.1109/ITSC.2019.8916843
Rongge Guo, W. Guan, A. Huang, Wen-yi Zhang
Customized bus (CB) is an innovation mode of public transportation (PT) system to alleviate the traffic congestion. As a demand-based transport, CB holds promise to provide personalized service by aggregating travel demand of individuals. However, the data collected through online surveys are limited and unreliable for the CB operation planning. This paper introduces a methodology to investigate the potential travel demands of CB based on smartcard data (SCD). The methodology proposed here consists of three processes: trip chain generation, origin-destination (OD) recognition and travel mode comparison. Drawing on Beijing as the case study, the smartcard dataset is processed for analyzing the spatial-temporal properties of passenger travel behavior and exploring potential travel demand of CB. The results indicate that the data have a workplace-oriented pattern and CB is suitable for passengers with long trip distances (beyond 8 km). These findings advance key points to future CB operation as it is associated with the route design and vehicle arrangement.
{"title":"Exploring Potential Travel Demand of Customized Bus Using Smartcard Data*","authors":"Rongge Guo, W. Guan, A. Huang, Wen-yi Zhang","doi":"10.1109/ITSC.2019.8916843","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8916843","url":null,"abstract":"Customized bus (CB) is an innovation mode of public transportation (PT) system to alleviate the traffic congestion. As a demand-based transport, CB holds promise to provide personalized service by aggregating travel demand of individuals. However, the data collected through online surveys are limited and unreliable for the CB operation planning. This paper introduces a methodology to investigate the potential travel demands of CB based on smartcard data (SCD). The methodology proposed here consists of three processes: trip chain generation, origin-destination (OD) recognition and travel mode comparison. Drawing on Beijing as the case study, the smartcard dataset is processed for analyzing the spatial-temporal properties of passenger travel behavior and exploring potential travel demand of CB. The results indicate that the data have a workplace-oriented pattern and CB is suitable for passengers with long trip distances (beyond 8 km). These findings advance key points to future CB operation as it is associated with the route design and vehicle arrangement.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"195 1","pages":"2645-2650"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72883008","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 : 2019-10-01DOI: 10.1109/ITSC.2019.8917083
Guangmin Wang, Y. Q. Li, Meng Xu
During the morning and evening rush hour in big cities, roads present tide traffic feature, which not only worsens the traffic congestion but also wastes road resources. In this paper, we use the lane reversal to balance the asymmetric traffic flow distribution in the two directions of one road and lane addition to increase road supply. Moreover, we use the tradable credits scheme to manage the mobility. Thus, we integrate the lane reversal, lane addition and tradable credits scheme to alleviate the traffic congestion due to tide traffic, which is modeled into a mix-integer bilevel programming. In this model, the network authority decides the lane reversal scheme, lane addition scheme and credits charging scheme to minimize the total system travel time, while the travelers follow the user equilibrium (UE) to minimize their generalized travel cost. After proposing the algorithm for the model, the Sioux Falls network is adopted to illustrate the numerical experiments, which show that the integration of the management and design can obtain the better performance to alleviate tide traffic and traffic congestion.
{"title":"Integrating the management and design of urban road network to alleviate tide traffic*","authors":"Guangmin Wang, Y. Q. Li, Meng Xu","doi":"10.1109/ITSC.2019.8917083","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917083","url":null,"abstract":"During the morning and evening rush hour in big cities, roads present tide traffic feature, which not only worsens the traffic congestion but also wastes road resources. In this paper, we use the lane reversal to balance the asymmetric traffic flow distribution in the two directions of one road and lane addition to increase road supply. Moreover, we use the tradable credits scheme to manage the mobility. Thus, we integrate the lane reversal, lane addition and tradable credits scheme to alleviate the traffic congestion due to tide traffic, which is modeled into a mix-integer bilevel programming. In this model, the network authority decides the lane reversal scheme, lane addition scheme and credits charging scheme to minimize the total system travel time, while the travelers follow the user equilibrium (UE) to minimize their generalized travel cost. After proposing the algorithm for the model, the Sioux Falls network is adopted to illustrate the numerical experiments, which show that the integration of the management and design can obtain the better performance to alleviate tide traffic and traffic congestion.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"94 1","pages":"708-713"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79854619","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 : 2019-10-01DOI: 10.1109/ITSC.2019.8917505
Dawei Cao, Zhiying Qin, R. Liu, Yang Yang, Dexing Zhong
With the combination of vehicle information and communication technology, there is a new opportunity to solve the problem of rear-end collision in the field of transportation. Based on 802.11p, vehicles equipped with the WAVE (Wireless access in Vehicular Environment) standard can communicate each other in real time. When an accident occurs, vehicles within range can receive warning information quickly through inter-vehicle communication. The drivers will have enough time to calmly brake to stop and also reduce the risk of secondary collision. In order to prevent secondary collisions, we propose an algorithm that includes vehicle accident identification and rear-end collision warning. If it is calculated that the vehicle will collide, the system will notify the driver to take brake. The algorithm is based on the historical path of the vehicle and is primarily used for curved road conditions. The results show that the algorithm has good performance and the false alarm rate does not exceed 1%.
{"title":"A Rear-end Collision Warning Algorithm based on Vehicular Communication*","authors":"Dawei Cao, Zhiying Qin, R. Liu, Yang Yang, Dexing Zhong","doi":"10.1109/ITSC.2019.8917505","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917505","url":null,"abstract":"With the combination of vehicle information and communication technology, there is a new opportunity to solve the problem of rear-end collision in the field of transportation. Based on 802.11p, vehicles equipped with the WAVE (Wireless access in Vehicular Environment) standard can communicate each other in real time. When an accident occurs, vehicles within range can receive warning information quickly through inter-vehicle communication. The drivers will have enough time to calmly brake to stop and also reduce the risk of secondary collision. In order to prevent secondary collisions, we propose an algorithm that includes vehicle accident identification and rear-end collision warning. If it is calculated that the vehicle will collide, the system will notify the driver to take brake. The algorithm is based on the historical path of the vehicle and is primarily used for curved road conditions. The results show that the algorithm has good performance and the false alarm rate does not exceed 1%.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"179 1","pages":"3367-3372"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80094714","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 : 2019-10-01DOI: 10.1109/ITSC.2019.8917321
Yue Cao, W. Shangguan, Xinhang Shang, Weizhi Qiu, Yu Du
Aiming at the difficulty in hub airport field test, a multi-objects operational method was proposed. To meet the immersion needs, models were designed by 3DMax modeling tool while scenes were rendered by Unity3D multiplatform development engine. In terms of interaction, 5DT virtual glove and VM-I attitude sensor were used to achieve basic control of the simulated train status by the operator. Using macroscopic physical analysis and interval control of the train, this paper put forward a time-speed control method. To verify the theory, a large hub airport APM System virtual simulation platform was built, with the Beijing Capital International Airport as an example. The test results of train control, human-computer interaction and scenarios performance prove the reliability of the platform , which is of great practical application value.
{"title":"Dynamical Interaction based Multi-objects Operation Simulation for Hub Airport APM System","authors":"Yue Cao, W. Shangguan, Xinhang Shang, Weizhi Qiu, Yu Du","doi":"10.1109/ITSC.2019.8917321","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917321","url":null,"abstract":"Aiming at the difficulty in hub airport field test, a multi-objects operational method was proposed. To meet the immersion needs, models were designed by 3DMax modeling tool while scenes were rendered by Unity3D multiplatform development engine. In terms of interaction, 5DT virtual glove and VM-I attitude sensor were used to achieve basic control of the simulated train status by the operator. Using macroscopic physical analysis and interval control of the train, this paper put forward a time-speed control method. To verify the theory, a large hub airport APM System virtual simulation platform was built, with the Beijing Capital International Airport as an example. The test results of train control, human-computer interaction and scenarios performance prove the reliability of the platform , which is of great practical application value.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"14 1","pages":"900-905"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80111492","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 : 2019-10-01DOI: 10.1109/ITSC.2019.8917438
Moad Kissai, B. Monsuez, X. Mouton, D. Martinez, A. Tapus
Several systems are integrated in passenger cars. Some of them are just redundant systems due to safety requirements. Others, are completely different and can interact with each other as long as they are operating inside the same vehicle. Control allocation methods have been successfully implemented in advanced aircrafts to avoid conflicts, especially in the context of redundant systems. In this paper, we will rather focus on coordinating non-redundant advanced chassis systems with different dynamics. This difference in dynamics can be especially problematic when systems exhibit different communication delays. Model Predictive Control Allocation (MPCA) methods are therefore investigated in order to activate the right system at the right moment. Results show that particularly when the most effective system is saturated, another system with a different time delay can be activated few steps before saturation to instantly take over the maneuver. With good knowledge of actuator dynamics and higher computation power, MPCA methods are able to solve complex problems in severe situations.
{"title":"Model Predictive Control Allocation of Systems with Different Dynamics","authors":"Moad Kissai, B. Monsuez, X. Mouton, D. Martinez, A. Tapus","doi":"10.1109/ITSC.2019.8917438","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917438","url":null,"abstract":"Several systems are integrated in passenger cars. Some of them are just redundant systems due to safety requirements. Others, are completely different and can interact with each other as long as they are operating inside the same vehicle. Control allocation methods have been successfully implemented in advanced aircrafts to avoid conflicts, especially in the context of redundant systems. In this paper, we will rather focus on coordinating non-redundant advanced chassis systems with different dynamics. This difference in dynamics can be especially problematic when systems exhibit different communication delays. Model Predictive Control Allocation (MPCA) methods are therefore investigated in order to activate the right system at the right moment. Results show that particularly when the most effective system is saturated, another system with a different time delay can be activated few steps before saturation to instantly take over the maneuver. With good knowledge of actuator dynamics and higher computation power, MPCA methods are able to solve complex problems in severe situations.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"22 1","pages":"4170-4177"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82387729","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 evaluates the feasibility of upgrading the static traffic light control to a local adaptive traffic light control, for a road network carrying less-lane-disciplined, heterogeneous traffic. We analyze the performance of a few deep learning based object detection algorithms (e.g., SSD, RCNN), with respect to the computation requirements, and accuracy for computing the Passenger Car Unit (PCU) count, under heterogeneous traffic condition. We propose an algorithm for a local adaptive TLC, leveraging the existing infrastructure. This algorithm efficiently computes the phase duration, based on round-robin scheduling, considering real-time traffic information. Simulations are carried out to analyze the effect of varying error rates in PCU count on the performance of adaptive TLCs. Further, the performance of the proposed TLC is compared with the conventional static TLC and the recently proposed micro auction based adaptive TLC algorithms. The simulation results suggest that the proposed TLC algorithm can tolerate 20% error in the PCU count without degrading the performance. Also, this work demonstrates that the traffic information with the required accuracy can be processed in real time using the available platforms (e.g., Raspberry Pi). The proposed work establishes the feasibility of upgrading the existing static TLC to a local adaptive TLC with minimal infrastructure requirement.
{"title":"A Feasibility Study on Upgrading the Static TLC Infrastructure to Adaptive TLC","authors":"Abhyudai Bisht, Khilan Ravani, Manish Chaturvedi, Naveen Kumar","doi":"10.1109/ITSC.2019.8916836","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8916836","url":null,"abstract":"This paper evaluates the feasibility of upgrading the static traffic light control to a local adaptive traffic light control, for a road network carrying less-lane-disciplined, heterogeneous traffic. We analyze the performance of a few deep learning based object detection algorithms (e.g., SSD, RCNN), with respect to the computation requirements, and accuracy for computing the Passenger Car Unit (PCU) count, under heterogeneous traffic condition. We propose an algorithm for a local adaptive TLC, leveraging the existing infrastructure. This algorithm efficiently computes the phase duration, based on round-robin scheduling, considering real-time traffic information. Simulations are carried out to analyze the effect of varying error rates in PCU count on the performance of adaptive TLCs. Further, the performance of the proposed TLC is compared with the conventional static TLC and the recently proposed micro auction based adaptive TLC algorithms. The simulation results suggest that the proposed TLC algorithm can tolerate 20% error in the PCU count without degrading the performance. Also, this work demonstrates that the traffic information with the required accuracy can be processed in real time using the available platforms (e.g., Raspberry Pi). The proposed work establishes the feasibility of upgrading the existing static TLC to a local adaptive TLC with minimal infrastructure requirement.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"43 1","pages":"2563-2568"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82528704","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}
Probabilistic trajectory prediction for other vehicles can be an effective way to improve the understanding of dynamic and stochastic traffic environment for automated vehicles. One challenge is how to predict the vehicle trajectory accurately both in the short-term and long-term horizon. In this paper, we propose an integrated approach combining the driver characteristic and intention estimation (DCIE) model with the Gaussian process (GP) model. Our proposed method makes use of both vehicle low-level and high-level information and inquires parameters by learning from public naturalistic driving dataset. Our method is applied and analyzed in the highway lane change scenarios. Compared with other traditional methods, the advantages of this proposed method are demonstrated by more accurate prediction and more reasonable uncertainty description during the whole prediction horizon.
{"title":"An Integrated Approach to Probabilistic Vehicle Trajectory Prediction via Driver Characteristic and Intention Estimation","authors":"Jinxin Liu, Yugong Luo, Hui Xiong, Tinghan Wang, Heye Huang, Zhihua Zhong","doi":"10.1109/ITSC.2019.8917039","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917039","url":null,"abstract":"Probabilistic trajectory prediction for other vehicles can be an effective way to improve the understanding of dynamic and stochastic traffic environment for automated vehicles. One challenge is how to predict the vehicle trajectory accurately both in the short-term and long-term horizon. In this paper, we propose an integrated approach combining the driver characteristic and intention estimation (DCIE) model with the Gaussian process (GP) model. Our proposed method makes use of both vehicle low-level and high-level information and inquires parameters by learning from public naturalistic driving dataset. Our method is applied and analyzed in the highway lane change scenarios. Compared with other traditional methods, the advantages of this proposed method are demonstrated by more accurate prediction and more reasonable uncertainty description during the whole prediction horizon.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"27 1","pages":"3526-3532"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82316809","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 : 2019-10-01DOI: 10.1109/ITSC.2019.8917056
Qichao Wang, M. Abbas
In this work, we compared two adaptive control systems: (1) a National Electrical Manufacturing Association (NEMA) based virtual phase-link macroscopic model and (2) a Max Pressure controller based model. The control variables of these models are the green splits. We contrasted the performance of these two models in controlling traffic signal systems in an experimental Vissim framework, and compared them with two other control strategies. It was found that the virtual phaselink method outperformed two control strategies and performed close, by not as good as, the Max Pressure control strategy. We found that the disadvantage of the virtual phase-link method stemmed from that fact that the cycle time was not fully used for some of the intersections. It was also found that the platoon created by the cyclic control schemes might slow down to allow vehicles to switch lanes. Compared to the Max Pressure control strategy, the virtual phase-link method can be implemented by any traffic controller that follows the NEMA standards. The real-time requirement of the virtual phase-link method is not as strict as the Max Pressure control strategy.
{"title":"Comparing and Contrasting NEMA-based Virtual Phase-Link control with Max Pressure Control in Arterial Signal Systems","authors":"Qichao Wang, M. Abbas","doi":"10.1109/ITSC.2019.8917056","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917056","url":null,"abstract":"In this work, we compared two adaptive control systems: (1) a National Electrical Manufacturing Association (NEMA) based virtual phase-link macroscopic model and (2) a Max Pressure controller based model. The control variables of these models are the green splits. We contrasted the performance of these two models in controlling traffic signal systems in an experimental Vissim framework, and compared them with two other control strategies. It was found that the virtual phaselink method outperformed two control strategies and performed close, by not as good as, the Max Pressure control strategy. We found that the disadvantage of the virtual phase-link method stemmed from that fact that the cycle time was not fully used for some of the intersections. It was also found that the platoon created by the cyclic control schemes might slow down to allow vehicles to switch lanes. Compared to the Max Pressure control strategy, the virtual phase-link method can be implemented by any traffic controller that follows the NEMA standards. The real-time requirement of the virtual phase-link method is not as strict as the Max Pressure control strategy.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"299 1","pages":"1361-1366"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87532995","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 : 2019-10-01DOI: 10.1109/ITSC.2019.8917187
Yuki Mori, Hiroshi Fukui, Tsubasa Hirakawa, Jo Nishiyama, Takayoshi Yamashita, H. Fujiyoshi
Driving has various risk factors, including the possibility of traffic accidents involving pedestrians and/or oncoming vehicles. A driver assistance system that can prevent traffic accidents must be able to get the driver ' s attention. A practical solution for attention attraction should involve caption generation from in-vehicle images. Although a number of approaches for caption generation with deep neural networks have been proposed, they are inadequate for the specific risk factors while driving. The reason is that conventional captioning methods focus on not these factors but the entirety of an image. To tackle this problem, we first created a dataset to attract attention, one that considers risk factors during driving. Furthermore, we propose an image captioning method for the assistance system. Our method is based on neural baby talk and introduces an attention mask focusing on risk factors in an image. The mask enables our model to generate captions on each factor. Experimental results with our created dataset show that our method can generate captions for ideal attention attraction.
{"title":"Attention Neural Baby Talk: Captioning of Risk Factors while Driving","authors":"Yuki Mori, Hiroshi Fukui, Tsubasa Hirakawa, Jo Nishiyama, Takayoshi Yamashita, H. Fujiyoshi","doi":"10.1109/ITSC.2019.8917187","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917187","url":null,"abstract":"Driving has various risk factors, including the possibility of traffic accidents involving pedestrians and/or oncoming vehicles. A driver assistance system that can prevent traffic accidents must be able to get the driver ' s attention. A practical solution for attention attraction should involve caption generation from in-vehicle images. Although a number of approaches for caption generation with deep neural networks have been proposed, they are inadequate for the specific risk factors while driving. The reason is that conventional captioning methods focus on not these factors but the entirety of an image. To tackle this problem, we first created a dataset to attract attention, one that considers risk factors during driving. Furthermore, we propose an image captioning method for the assistance system. Our method is based on neural baby talk and introduces an attention mask focusing on risk factors in an image. The mask enables our model to generate captions on each factor. Experimental results with our created dataset show that our method can generate captions for ideal attention attraction.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"2 1","pages":"4317-4322"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87571896","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 : 2019-10-01DOI: 10.1109/ITSC.2019.8917139
Patrick Weyers, David Schiebener, A. Kummert
Knowing what the driver is doing inside a vehicle is essential information for all stages of vehicle automation. For example it can be used for adaptive warning strategies in combination with an advanced driver assistance systems system, for predicting the response time to take back the control of a partially automated vehicle, or ensuring the driver is ready to manually drive a highly automated vehicle in the future. We present a system for driver activity recognition based on image sequences of an in-cabin time-of-flight camera. Our dataset includes actions such as entering and leaving a car or driver object interactions such as using a phone or drinking. In the first stage, we localize body key points of the driver. In the second stage, we extract image regions around the localized hands. These regions and the determined 3D body key points are used as the input to a recurrent neural network for driver activity recognition. With a mean average precision of 0.85 we reach better classification rates than approaches relying only on body key points or images.
{"title":"Action and Object Interaction Recognition for Driver Activity Classification","authors":"Patrick Weyers, David Schiebener, A. Kummert","doi":"10.1109/ITSC.2019.8917139","DOIUrl":"https://doi.org/10.1109/ITSC.2019.8917139","url":null,"abstract":"Knowing what the driver is doing inside a vehicle is essential information for all stages of vehicle automation. For example it can be used for adaptive warning strategies in combination with an advanced driver assistance systems system, for predicting the response time to take back the control of a partially automated vehicle, or ensuring the driver is ready to manually drive a highly automated vehicle in the future. We present a system for driver activity recognition based on image sequences of an in-cabin time-of-flight camera. Our dataset includes actions such as entering and leaving a car or driver object interactions such as using a phone or drinking. In the first stage, we localize body key points of the driver. In the second stage, we extract image regions around the localized hands. These regions and the determined 3D body key points are used as the input to a recurrent neural network for driver activity recognition. With a mean average precision of 0.85 we reach better classification rates than approaches relying only on body key points or images.","PeriodicalId":6717,"journal":{"name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","volume":"56 1","pages":"4336-4341"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88007237","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：