A5078812150- Traffic and Road Safety
- Traffic control and management
- Autonomous Vehicle Technology and Safety
- Traffic Prediction and Management Techniques
- Infrastructure Maintenance and Monitoring
- Vehicle emissions and performance
- Video Surveillance and Tracking Methods
- Transportation Systems and Logistics
- Safety Warnings and Signage
- Anomaly Detection Techniques and Applications
- Occupational Health and Safety Research
- Simulation and Modeling Applications
- Technology and Security Systems
- Risk and Safety Analysis
- Imbalanced Data Classification Techniques
- Advanced Decision-Making Techniques
- Remote Sensing and LiDAR Applications
- BIM and Construction Integration
- Text and Document Classification Technologies
- 3D Modeling in Geospatial Applications
Chang'an University
2020-2025
Ministry of Education
2025
Nanyang Technological University
2022-2025
Xi'an Technological University
2022-2023
To mitigate the prevalence of highway accidents in Southwest China during adverse weather conditions, this study introduces a novel method for identifying accident-prone sections complex meteorological circumstances. The technique, anchored data mining’s support index, pioneers concept responsiveness, which includes elucidation its mechanisms and development computational methodologies. Historical accident records from mountainous highways were meticulously analyzed to quantify spectrum...
Due to the widespread use of unmanned aerial vehicles (UAVs) in remote sensing, there are fully developed techniques for extracting vehicle speed and trajectory data from video, using either a traditional method based on optical features or deep learning method; however, few papers that discuss how solve issue video shaking, existing rarely linked lane lines. To address deficiencies current research, this study, we formulated more reliable real traffic acquisition outperforms methods terms...
A digital twin is a mapping of real world objects in virtual space. For the study traffic safety issues, twins have great potential to facilitate more accurate and detailed risk analysis. In this study, method for highway driving analysis proposed, which consists three parts: Extracting vehicle motion information world, constructing scenes analyzing risks. Firstly, aerial video captured by drone, while microscopic trajectories are extracted from using machine vision algorithms. Secondly,...
Aiming at the traffic risks entrances and exits of expressways, drones are used to obtain aerial video, machine vision methods extract flow micro-data including driving trajectories vehicle speeds, segmented integrated according Prescan is build roads trajectories. Model, based on simulation interface, trajectory realized in Vissim, which as a digital twin system microscopic entrance exit sections expressway realize equivalent mapping sections. On this basis, conflict technology further...
In the expressway reconstruction and expansion engineering, form of rightward zone is increasingly adopted, its complicated traffic conditions can easily cause accidents. order to quickly effectively grasp risk right diversion section, this study employs average speed, coefficient variation, equivalent minimum safety distance, deceleration as evaluation indexes driving risk, then analyses influence rules volume, proportion large vehicles, length transition section on each index by using...
Road infrastructure has significant effects on road traffic safety and needs further examination. In terms of crash prediction, recent studies have started to develop deep learning classification algorithms. However, given the uncertainty crashes, predicting risk potential different sections remains a challenge. To bridge this knowledge gap, study investigated real-world expressway collected its data between 2013 2020. Then, according time-spatial density ratio (Pts), were assigned into...
Understanding the sideslip risks of various trajectory patterns, as well impact rainfall on them, is critical for improving road safety. However, lack precise classification indicators hampers systematic analysis variations in vehicle patterns. To address this, this study proposes a parameterized method trajectories curved segments, employing radius and offset primary features dividing into nine These patterns represent from smaller to larger radii inside outside lane offsets, reflecting...
Research on the standardization of interchange BIM components is required to encourage use technology in and quicken development improvement relevant standards specifications. The depth level model, classification, coding components, design administration component library are main topics this work. First, concept research content were proposed. Second, common forms summarized. basic interchanges include through lanes, ramps, connections, overpass bridges, traffic safety facilities, can be...
Due to the different driving characteristics of vehicle models, inappropriate mandatory lane changes (MLCs) by heavy vehicles at interchanges often lead serious traffic accidents. Therefore, this paper focuses on impact road geometric design MLC duration trucks using full time-domain trajectory data. Specifically, we use generalized additive time-varying Cox model establish interchanges, then analyze combined influence elements. The results show that consistency index is 0.9, indicating it...
With the aim of enhancing level safety management during operation phase highways, application digital twin technology platform is employed. Following principles intelligent perception information, risk assessment, and decision-making, a set assessment control methods for highway traffic established based on integration static dynamic infrastructure information. Firstly, IoT (Internet Things) utilized to achieve information such as environment foundation data. Multiple-source fusion cloud...
The traditional method of designing freeway geometric characteristics may not well consider traffic safety and evaluation problems associated with vehicle, driver, road, environmental features. This paper looks into accident-prone compound curves puts forward a that can comprehensively assess various influencing factors. integrates driving simulation Virtual Reality (VR) technology. Methodically, this first used three-dimensional (3D) design software to build the digital model spatial scene...