Environment perception is one of the most critical technology of intelligent transportation systems(ITS).Motion interaction between multiple vehicles in ITS makes it important to perform multi-object tracking(MOT).How...Environment perception is one of the most critical technology of intelligent transportation systems(ITS).Motion interaction between multiple vehicles in ITS makes it important to perform multi-object tracking(MOT).However,most existing MOT algorithms follow the tracking-by-detection framework,which separates detection and tracking into two independent segments and limit the global efciency.Recently,a few algorithms have combined feature extraction into one network;however,the tracking portion continues to rely on data association,and requires com‑plex post-processing for life cycle management.Those methods do not combine detection and tracking efciently.This paper presents a novel network to realize joint multi-object detection and tracking in an end-to-end manner for ITS,named as global correlation network(GCNet).Unlike most object detection methods,GCNet introduces a global correlation layer for regression of absolute size and coordinates of bounding boxes,instead of ofsetting predictions.The pipeline of detection and tracking in GCNet is conceptually simple,and does not require compli‑cated tracking strategies such as non-maximum suppression and data association.GCNet was evaluated on a multivehicle tracking dataset,UA-DETRAC,demonstrating promising performance compared to state-of-the-art detectors and trackers.展开更多
In order to investigate the enhancement of data privacy by distributing data packets via multiple paths,this paper formulates a security model and analyzes the privacy problem in multipath scenarios leveraging informa...In order to investigate the enhancement of data privacy by distributing data packets via multiple paths,this paper formulates a security model and analyzes the privacy problem in multipath scenarios leveraging information theoretic concept.Based on proposed model,a privacy function related to the path number is discussed.We heuristically recommend the optimal path number and analyze the tradeoff among the performance,resource consumption and privacy.For reducing the information leakage,the data schedule algorithms are also proposed.The analytical model can provide guidelines for the multipath protocol design.展开更多
Mobile phones equipped with multiple wireless interfaces can increase their goodput performance by making use of concurrent transmissions over multiple paths, enabled by the Multipath TCP(MPTCP). However, utilizing MP...Mobile phones equipped with multiple wireless interfaces can increase their goodput performance by making use of concurrent transmissions over multiple paths, enabled by the Multipath TCP(MPTCP). However, utilizing MPTCP for data delivery may generally result in higher energy consumption, while the battery power of a mobile phone is limited. Thus, how to optimize the energy usage becomes very crucial and urgent. In this paper, we propose MPTCP.QE, a novel quality of experience(Qo E).driven energy.aware multipath content delivery approach for MPTCP.based mobile phones. The main idea of MPTCP.QE is described as follows: it first provides an application rate.aware energy.efficient subflow management strategy to tradeoff throughput performance and energy consumption for mobile phones; then uses an available bandwidth.aware congestion window fast recovery strategy to make a sender avoid unnecessary slow.start and utilize wireless resource quickly; and further introduces a novel receiver.driven energy.efficient SACK strategy to help a receiver possible to detect SACK loss timely and trigger loss recovery in a more energy.efficient way. The simulation results show that with the MPTCP.QE, the energy usage is enhanced while the performance level is maintained compared to existing MPTCP solutions.展开更多
In recent years, we need more bandwidth to enjoy entertainment contents such as video streaming, music and online gaming. To gain enough bandwidth, technologies that combine bandwidth by using multiple interfaces at s...In recent years, we need more bandwidth to enjoy entertainment contents such as video streaming, music and online gaming. To gain enough bandwidth, technologies that combine bandwidth by using multiple interfaces at same time are desired. Multipath transport protocols which combine multiple paths for packet delivery at the transport layer are a promising technology. Such protocols have a mechanism, called “packet scheduler”, to select the interface to send a packet. However, existing studies of the packet scheduler have not explicitly considered the compatibility of mobility with bonding of bandwidth. Therefore, when smartphone users move out of coverage of communication networks such as wireless Local Area Network (LAN) and Long Term Evolution (LTE) by vehicle, packet loss occurs, leading to a decrease of throughput. In this study, we propose a packet scheduler that selects an appropriate communication path so that packets can reach the peer before it moves out of the coverage. Based on routes of a vehicle and the position and communication range of the access point, the time at which a communication path will be lost is predicted. In addition, we employ MPQUIC (Multipath QUIC (Quick UDP Internet Connections)), which is a multipath transport protocol proposed as the extension of QUIC protocol, to reduce the ACK packet loss in multipath communication, and to reduce the time until the starts of retransmission. We evaluated the number of packet losses, the throughput and the time until starts of retransmission using a simulator and show the superiority of proposed method.展开更多
Real-time video transport over wireless Internet faces many challenges due to the heterogeneous environment including wireline and wireless networks. A robust network condition classification algorithm using multiple ...Real-time video transport over wireless Internet faces many challenges due to the heterogeneous environment including wireline and wireless networks. A robust network condition classification algorithm using multiple end-to-end metrics and Support Vector Machine (SVM) is proposed to classify different network events and model the transition pattern of network conditions. End-to-end Quality-of-Service (QoS) mechanisms like congestion control, error control, and power control can benefit from the network condition information and react to different network situations appropriately. The proposed network condition classifica- tion algorithm uses SVM as a classifier to cluster different end-to-end metrics such as end-to-end delay, delay jitter, throughput and packet loss-rate for the UDP traffic with TCP-friendly Rate Control (TFRC), which is used for video transport. The algorithm is also flexible for classifying different numbers of states representing different levels of network events such as wireline congestion and wireless channel loss. Simulation results using network simulator 2 (ns2) showed the effectiveness of the proposed scheme.展开更多
基金Supported by National Key Research and Development Program of China(Grant No.2021YFB1600402)National Natural Science Foundation of China(Grant No.52072212)+1 种基金Dongfeng USharing Technology Co.,Ltd.,China Intelli‑gent and Connected Vehicles(Beijing)Research Institute Co.,Ltd.“Shuimu Tsinghua Scholarship”of Tsinghua University of China.
文摘Environment perception is one of the most critical technology of intelligent transportation systems(ITS).Motion interaction between multiple vehicles in ITS makes it important to perform multi-object tracking(MOT).However,most existing MOT algorithms follow the tracking-by-detection framework,which separates detection and tracking into two independent segments and limit the global efciency.Recently,a few algorithms have combined feature extraction into one network;however,the tracking portion continues to rely on data association,and requires com‑plex post-processing for life cycle management.Those methods do not combine detection and tracking efciently.This paper presents a novel network to realize joint multi-object detection and tracking in an end-to-end manner for ITS,named as global correlation network(GCNet).Unlike most object detection methods,GCNet introduces a global correlation layer for regression of absolute size and coordinates of bounding boxes,instead of ofsetting predictions.The pipeline of detection and tracking in GCNet is conceptually simple,and does not require compli‑cated tracking strategies such as non-maximum suppression and data association.GCNet was evaluated on a multivehicle tracking dataset,UA-DETRAC,demonstrating promising performance compared to state-of-the-art detectors and trackers.
基金This paper was partially supported by the National Basic Re-search Program of China under Grant No. 2007CB307100 the National Natural Science Foundation of China under Crant No 60972010 the Fundamental Research Funds for the Central U- niversities under Grant No. 2011JBM018.
文摘In order to investigate the enhancement of data privacy by distributing data packets via multiple paths,this paper formulates a security model and analyzes the privacy problem in multipath scenarios leveraging information theoretic concept.Based on proposed model,a privacy function related to the path number is discussed.We heuristically recommend the optimal path number and analyze the tradeoff among the performance,resource consumption and privacy.For reducing the information leakage,the data schedule algorithms are also proposed.The analytical model can provide guidelines for the multipath protocol design.
基金supported by the National Natural Science Foundation of China (NSFC) under Grant No. 61562044, 61262014the Natural Science Foundation of Jiangxi Province under Grant No. 20161BAB212046+2 种基金the Project of Soft Science Research Plan of Jiangxi Province under Grant No. 20161BBA10010the Science and Technology Research Project of Jiangxi Provincial Department of Education (GJJ150319)the Higher School Teaching Reform Research Subject of Jiangxi Province(JXJG-15-2-35)
文摘Mobile phones equipped with multiple wireless interfaces can increase their goodput performance by making use of concurrent transmissions over multiple paths, enabled by the Multipath TCP(MPTCP). However, utilizing MPTCP for data delivery may generally result in higher energy consumption, while the battery power of a mobile phone is limited. Thus, how to optimize the energy usage becomes very crucial and urgent. In this paper, we propose MPTCP.QE, a novel quality of experience(Qo E).driven energy.aware multipath content delivery approach for MPTCP.based mobile phones. The main idea of MPTCP.QE is described as follows: it first provides an application rate.aware energy.efficient subflow management strategy to tradeoff throughput performance and energy consumption for mobile phones; then uses an available bandwidth.aware congestion window fast recovery strategy to make a sender avoid unnecessary slow.start and utilize wireless resource quickly; and further introduces a novel receiver.driven energy.efficient SACK strategy to help a receiver possible to detect SACK loss timely and trigger loss recovery in a more energy.efficient way. The simulation results show that with the MPTCP.QE, the energy usage is enhanced while the performance level is maintained compared to existing MPTCP solutions.
文摘In recent years, we need more bandwidth to enjoy entertainment contents such as video streaming, music and online gaming. To gain enough bandwidth, technologies that combine bandwidth by using multiple interfaces at same time are desired. Multipath transport protocols which combine multiple paths for packet delivery at the transport layer are a promising technology. Such protocols have a mechanism, called “packet scheduler”, to select the interface to send a packet. However, existing studies of the packet scheduler have not explicitly considered the compatibility of mobility with bonding of bandwidth. Therefore, when smartphone users move out of coverage of communication networks such as wireless Local Area Network (LAN) and Long Term Evolution (LTE) by vehicle, packet loss occurs, leading to a decrease of throughput. In this study, we propose a packet scheduler that selects an appropriate communication path so that packets can reach the peer before it moves out of the coverage. Based on routes of a vehicle and the position and communication range of the access point, the time at which a communication path will be lost is predicted. In addition, we employ MPQUIC (Multipath QUIC (Quick UDP Internet Connections)), which is a multipath transport protocol proposed as the extension of QUIC protocol, to reduce the ACK packet loss in multipath communication, and to reduce the time until the starts of retransmission. We evaluated the number of packet losses, the throughput and the time until starts of retransmission using a simulator and show the superiority of proposed method.
基金Project supported by the Croucher Foundation Fellowship fromHong Kong, China
文摘Real-time video transport over wireless Internet faces many challenges due to the heterogeneous environment including wireline and wireless networks. A robust network condition classification algorithm using multiple end-to-end metrics and Support Vector Machine (SVM) is proposed to classify different network events and model the transition pattern of network conditions. End-to-end Quality-of-Service (QoS) mechanisms like congestion control, error control, and power control can benefit from the network condition information and react to different network situations appropriately. The proposed network condition classifica- tion algorithm uses SVM as a classifier to cluster different end-to-end metrics such as end-to-end delay, delay jitter, throughput and packet loss-rate for the UDP traffic with TCP-friendly Rate Control (TFRC), which is used for video transport. The algorithm is also flexible for classifying different numbers of states representing different levels of network events such as wireline congestion and wireless channel loss. Simulation results using network simulator 2 (ns2) showed the effectiveness of the proposed scheme.