被引排行
Status quo characteristics and trend analysis of national expressway traffic demand
TIAN Shimo;LI Tanfeng;YUAN Chunyi;WANG Mingzhi;TIAN He;ZHANG Shuo;Building an expressway network that matches the economic and social development scientifically has always been one of the difficulties and focuses of traffic planning. The analysis of traffic demand is an important prerequisite for it. Based on the analysis of the national expressway traffic volume,congestion and other data in the past ten years,combined with the development of the expressway network mileage scale,focusing on the difference between supply and demand,the development trends of traffic demand and expressway network load are studied. And relevant suggestions are put forward to provide a reference for formulating road network development plans and carrying out preliminary work of road construction projects in the future.
Research advances on millimeter wave radar and vision fusion in traffic object detection
WANG Wenbo;ZHU Shihao;CHEN Zeyu;ZHANG Weibin;Object detection is one of the basic research contents of traffic perception. In recent years, with the development of sensor technology and machine learning, object detection based on multisensor fusion has received extensive attention. This paper gives a comprehensive overview of object detection methods based on the fusion of millimeter wave radar and vision. The evaluation indicators and common public datasets of object detection are introduced. The calibration of millimeter wave radar and visual sensor are briefly described, and then the relevant data fusion methods are compared from the perspective of front fusion, post fusion and feature fusion. Combined with the current research and difficult problems, the future research directions are prospected. The research shows that the fusion detection scheme of millimeter wave radar and visual sensor can break through the inherent defects of single sensor detection, exhibit better detection performance and robustness in complex scenes, and is a feasible way to realize high-level intelligent transportation in the future. The existing methods are limited by factors such as computational power, dataset quality, number of sensors and so on, and most methods remain in the theoretical and experimental stage. Subsequent research should focus on the real complex scenes and integrate more sensors to make them closer to reality in terms of detection accuracy, detection speed, robustness and so on, so as to better serve the engineering practice.
Research and implementation of the coordinated development of smart city infrastructure and intelligent networked vehicles
SI Shengying;LIU Ziwei;SUN Enze;In order to promote the coordinated development of national smart city infrastructure and intelligent networked vehicles, this paper focus on the research and practice of road construction, network construction, cloud platform construction, and application scenarios. The interconnection of smart city infrastructure and intelligent networked vehicles in different regions are explored from the aspects of infrastructure construction, industry standard formulation, platform capability construction, and legal and regulatory guarantee suggestions. On this basis, application scenario construction and operation mode mining are studied so as to solve the practical livelihood problems in the pilot areas, form the generalizability and replicability, and radiate the useful experience to other cities.