Traffic Information Analysis Research Articles

Research on Practical Teaching of Traffic Information Analysis and Application Course under the Background of New Engineering

Research on Practical Teaching of Traffic Information Analysis and Application Course under the Background of New Engineering

YOLOv7-3D: A Monocular 3D Traffic Object Detection Method from a Roadside Perspective

Current autonomous driving systems predominantly focus on 3D object perception from the vehicle’s perspective. However, the single-camera 3D object detection algorithm in the roadside monitoring scenario provides stereo perception of traffic objects, offering more accurate collection and analysis of traffic information to ensure reliable support for urban traffic safety. In this paper, we propose the YOLOv7-3D algorithm specifically designed for single-camera 3D object detection from a roadside viewpoint. Our approach utilizes various information, including 2D bounding boxes, projected corner keypoints, and offset vectors relative to the center of the 2D bounding boxes, to enhance the accuracy of 3D object bounding box detection. Additionally, we introduce a 5-layer feature pyramid network (FPN) structure and a multi-scale spatial attention mechanism to improve feature saliency for objects of different scales, thereby enhancing the detection accuracy of the network. Experimental results demonstrate that our YOLOv7-3D network achieved significantly higher detection accuracy on the Rope3D dataset while reducing computational complexity by 60%.

Train a central traffic prediction model using local data: A spatio-temporal network based on federated learning

With the growing complexity of onboard sensors and the widespread deployment of road sensors, deep learning enables fine-grained traffic prediction using massive amounts of raw traffic data, which facilitates accurate analysis of traffic information in the Internet of Vehicles (IoV). However, most existing studies focus on using all the local data to jointly build a prediction model, facing severe challenges of data security and privacy concerns as well as substantial communication overhead. To address these challenges, in this paper, we propose the Spatial-Temporal Traffic Prediction Network based on federated learning (F-STTP-Net), which only updates the model parameters to the centralized server without any private data. Firstly, we design a sub-area division method, which divides the road network into sub-areas with different macroscopic fundamental diagram properties. Then, we propose a local training model for each sub-area, which uses the graph attention network (GAT) and the long short-term memory (LSTM) to capture the spatio-temporal dependence of the road network. The model uses the branch structure to predict the traffic volume of each intersection in the sub-area. Finally, the local models are aggregated based on federated learning to form a powerful central model, which bridges the constraints on global data sharing and privacy guarantee. We conduct experiments on the real-life dataset in Xuchang Lotus Lake 5G automated vehicles demonstration area to demonstrate that F-STTP-Net can achieve excellent prediction performance without the interaction of sub-area raw data. In addition, the proposed model has a strong generalization ability and can be quickly transferred to a new sub-area.

Investigation of the Fatigue Vehicle Load for a Long-span Steel Bridge Based on Nine Years of Measured Traffic Data

ABSTRACT This study conducts a rational investigation of nine years of traffic monitoring information concerning the Jiangyin Yangtze River Bridge within which the traffic flow, vehicle composition, vehicle load and axle-weight features are analyzed and discussed. Based on the annual analysis of traffic information, it is observed that compact cars weighing less than 30 kN account for 61% of the total traffic volume. According to the number of axles, wheelbase and axle groups, the vehicles in the traffic flow are classified into 11 representative types. Among them, two-axle vehicles form the major category, accounting for 80% of the total traffic flow. Statistical analysis of the gross vehicle weight and axle weight indicates that the gross vehicle weight follows a bimodal normal distribution, whereas the axle weight follows diverse distributions, including a normal distribution and an extreme distribution. In addition, by using equivalent damage theory, five equivalent vehicle models are established according to measurements of the axle weight and wheelbase. Finally, a six-axle fatigue-loaded vehicle model is proposed and discussed.

Integrated approach to information analysis for planning the transport of sensitive cargo

This article presents the methodology of information analysis, required for planning safe road transport of sensitive cargoes. Based on the literature studies we found that the traditional approaches applied to analyze traffic information are insufficient to ensure safe transport of sensitive loads as they fail to take into account several threatening factors. In addition, the need was noted to develop the procedures that may allow to choose a transport route considering appearance of so-called high-risk zones within road infrastructure, analyze the interdependence of such zones with errors made during the design or operation of road infrastructure and investigate the impact of road traffic on the frequency of road accidents involving Heavy Goods Vehicle. Therefore, article aims to present an integrated approach to traffic information analysis. Thus a multiple stage data ordering procedures were proposed, based on grouping information on accident rates and inclusion of audit results of selected route sections. Considering that transport infrastructure plays an important role in transport safety, the proposed methodology includes the analysis of errors in infrastructure and a merger in the sections the detected risk zones within the road infrastructure in any location. Application of this methodology can improve the planning of road transport of sensitive cargoes. Its verification was carried out on the example of a selected route running through Poland. During the audit of the route, it was found that a number of incorrect design solutions were applied on its separate sections, which may lead to high values of the severity factor for potential collisions and indicator of possible post-accidental losses. As a result of the research, the areas of the route were identified, where high-risk zones are located that threaten the safety of road traffic of vehicles, including those carrying sensitive loads. Research results may be of interest for those, who are involved in planning and organization of sensitive cargo transport, both in domestic and in international relations.

Intelligent Traffic Decision Analysis System Based on Big Data Mining

The urban intelligent traffic decision analysis system is a system designed to solve urban road traffic problems, improve traffic safety and comfort, and improve the level of traffic services. The application of big data mining technology can improve the ability of various types of road traffic information analysis and processing, expand the scope of application, and provide decision-making reference for the application of intelligent transportation systems, so as to ensure the smoothness and safety of roads. This article will introduce the concept of big data mining technology and intelligent transportation system, and analyze the architecture of urban traffic intelligent system based on big data technology and the design and implementation of mining system.

An assessment of adding value of traffic information and other attributes as part of its classifiers in a data mining tool set for predicting surface ozone levels

This study seeks to examine to what extent traffic information can improve the prediction of surface ozone levels from mobile sources when coupled with a state of the art air quality monitoring system and the application of data mining tools. For the purpose of the experiment an open-path Deferential Optical Absorption Spectroscopy (DOAS) instrument is used and 10min video samples obtained from Sohar's main highway (SHW) (Sultanate of Oman). This traffic information is collated to recognize, classify, and count three types of vehicles passenger car; light duty vehicle; and heavy duty vehicle. The DOAS is deployed to measure the following gases; ambient nitrogen dioxide (NO2); ozone (O3); sulfur dioxide (SO2); and BTX (benzene, toluene, xylene) across SHW. The ambient concentrations of these gases are measured in situ at time resolutions that vary from 30s to 1min along with simultaneous measurements of meteorological parameters. The Waikato Environment for Knowledge Analysis (WEKA) (Witten and Frank, 2005) software was used for the data mining part of the study. To identify which classifiers in WEKA would be the most suitable in predicting surface O3 levels the following five indexes were used: correlation coefficient (CC); mean absolute error (MAE); root mean square error (RMSE); relative absolute error (RAE); and root relative squared error (RRSE). It was found that the Bagging and M5P classifiers were the most robust when compared to others within the software when measured against the fives indexes. It was identified that with the additions of time and day of the week as well as changing of the parameters as part of the classifiers in WEKA the robustness of the predictions was not enhanced significantly. However, the findings did illustrate that the analysis of traffic information does improve the robustness of the prediction of surface O3 levels.

PEMANFAATAN ALGORITMA K-MEANS UNTUK PEMETAAN HASIL KLASTERISASI DATA KECELAKAAN LALU LINTAS

It is a vital importance to analyze road traffic accidents in order to improve traffic security management. Currently, most of the traffic information analysis is limited to general statistical analysis, which is hard to explore the rules hiding in its dataset and also difficult to find the spatial distribution characteristics. This paper aims to analyze the road traffic accidents dataset based on data mining method of K-Means clustering and visualize the result as a map. Firstly, data are extracted for clustering road segments based on similar characteristics that lies on the dataset, i.e. the number of accidents, the number vehicles involved, and the number accidents’ victims. Secondly, the result of clustering are presented as a map that aims to assist the police officer in identifying and evaluating some black spot areas (accident prone areas) in a monthly period, hence monitoring the safety of highways users can be anticipated earlier.

Based on Data Fusion Intelligent Traffic Information Analysis and Optimization

In this paper, we propose an analysis refine scheme based on data fusion towards some existing problems in data analysis of intelligent transportation systems .This method constructed the data into a plurality of time-series according to the characteristics of each attribute data. Providing an objective scientific basis for dynamic traffic management through intelligent analysis of traffic information based on the gray advantage analysis among data and system model of Intelligent Traffic Information decision support and auxiliary decision analysis.