- Autonomous Vehicle Technology and Safety
- Remote Sensing and LiDAR Applications
- Robotics and Sensor-Based Localization
- Traffic Prediction and Management Techniques
- Infrastructure Maintenance and Monitoring
- Video Surveillance and Tracking Methods
- 3D Surveying and Cultural Heritage
- Advanced Optical Sensing Technologies
- Traffic and Road Safety
- Advanced Vision and Imaging
- Traffic control and management
- Inertial Sensor and Navigation
- Military Defense Systems Analysis
- Advanced SAR Imaging Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Maritime Navigation and Safety
- Vehicle emissions and performance
- Radar Systems and Signal Processing
- Solar Radiation and Photovoltaics
- Microwave Imaging and Scattering Analysis
- Medical Imaging and Pathology Studies
- Safety Warnings and Signage
- Manufacturing Process and Optimization
- Infrared Target Detection Methodologies
- Injection Molding Process and Properties
Shandong Transportation Research Institute
2022-2024
Shandong University
2022-2024
Suzhou Research Institute
2024
China Academy of Transportation Sciences
2021-2024
University of Nevada, Reno
2019-2022
Harbin Engineering University
2010-2022
Ministry of Industry and Information Technology
2022
ORCID
2021
Embry–Riddle Aeronautical University
2019
Shanghai Power Equipment Research Institute
2018
Connected-vehicle system is an important component of smart cities. The complete benefits connected-vehicle technologies need the real-time information all vehicles and other road users. However, existing deployments obtain status connected vehicles, but without knowing unconnected traffic since there are still many pedestrians on roads. Therefore, it urgent to find approach collect high-resolution When difficult for pedestrians, bicyclists broadcast their in near future, enhancing...
Roadside light detection and ranging (LiDAR) is an emerging traffic data collection device has recently been deployed in different transportation areas. The current processing algorithms for roadside LiDAR are usually developed assuming normal weather conditions. Adverse conditions, such as windy snowy could be challenges processing. This paper examines the performance of state-of-the-art under adverse then composed improved background filtering object clustering method order to process...
Abstract In this paper, a novel multi-information fusion methodology is proposed for vehicle pose estimation. The purpose to improve the estimation accuracy during global navigation satellite system (GNSS) outages, mainly from two aspects: (1) extra observations of accurate velocities and angular rates without cumulative errors; (2) adaptive intelligent fusion. Firstly, multidimensional motion perception network (MMPN) designed in order estimate rates. At same time, state also output. inputs...
Tracking trajectories of the unconnected vehicles contributes to improvement traffic efficiency and safety. However, effects occlusions on accuracy reliability tracking results are nonnegligible. To address this issue, a modified multiple objects algorithm was proposed reduce loss caused by occlusions. The based detection results, in which motion states detected were determined. Further, Kalman filter employed predict trajectories, each trajectory uniquely matched object labeled with...
Abstract Metal 3D printing holds great promise for future digitalized manufacturing. However, the intricate interplay between laser and metal powders poses a significant challenge conventional trial-and-error optimization. Meanwhile, ‘optimized’ yet fixed parameters largely limit possible extensions to new designs materials. Herein, we report high throughput design coupled with machine learning (ML) guidance eliminate notorious cracks porosities in improved corrosion resistance overall...
The roadside deployed light detecting and ranging (LiDAR) has been a solution to fill the data gap for transition period from unconnected-vehicles environment connected-vehicles system. For LiDAR system, background filtering is an initial but important step. This paper presented raster-based method with data. proposed contains four major parts: region of interest (ROI) selection, rasterization, area detection, array generation. location points was stored in 3D array. performance tested...
Trajectory data has gained increasing attention in the transportation industry due to its capability of providing valuable spatiotemporal information. Recent advancements have introduced a new type multi-model all-traffic trajectory which provides high-frequency trajectories various road users, including vehicles, pedestrians, and bicyclists. This offers enhanced accuracy, higher frequency, full detection penetration, making it ideal for microscopic traffic analysis. In this study, we...
Tracking road users with high resolution is important for connected vehicles. Due to the complicated environments, tracking objects a single sensor could not meet requirements of high-resolution trajectories due occlusions. How acquire accurate and complete based on multi-source data major challenge researchers engineers. This paper developed novel method fusion roadside LiDAR camera. According relationship between number points distance, adaptive weight coefficient related 3D trajectory...
This study addresses the complex challenges associated with road traffic flow prediction and congestion management through enhancement of attention-based spatiotemporal graph convolutional network (ASTGCN) algorithm. Leveraging toll data real-time information from Orange County, California, algorithm undergoes refinement to adeptly capture abrupt changes in dynamics identify instances acute congestion. The optimization structure is approached both macro micro perspectives, incorporating key...
Light detection and ranging (LiDAR) is a crucial roadside intelligent perception device in cooperative vehicle infrastructure systems, which can generate large amount of disordered 3-D point cloud data. Point clustering serves as prerequisite for road target identification, trajectory tracking, traffic conflict prediction. However, due to limitations data collection methods algorithms, pronounced delay exists. In this work, real-time algorithm LiDAR (RTPCC-RL) proposed, primarily comprises...
Patching is a common technology used in repairing asphalt-pavement potholes. Due to the differences material properties between patched- and unpatched-asphalt mixtures, significant strain stress concentrations could be induced; thus, further cracks interfacial debonding distress caused. As remedy, can alleviated by utilizing optimum patching shapes. Therefore, this paper employed finite element methods (FEM) deeply analyze mechanical performance of patched-asphalt pavements embedded with...
The attributes of diversity and concealment pose formidable challenges in the accurate detection efficacious management distresses within subgrade structures. onset may precipitate structural degradation, thereby amplifying frequency traffic incidents instigating economic ramifications. Accurate timely is essential for maintaining repairing road sections with existing distresses. This helps to prolong service life infrastructure reduce financial burden. In recent years, advent numerous novel...
Repeater deception jamming is an effective SAR technique. It has been the hot spot of Synthetic Aperture Radar (SAR) Electronic Counter Measures (ECM) research for its ability to generate false targets with low power, which reduces difficulty hardware realization jammer. Linear format modulated (LFM) signal most commonly used radar signal. However it poor anti-jamming performance simple form and high recognition. A new hybrid signal-LFM-PC signal, using phase coded modulates LFM proposed....
The roadside Light Detection and Ranging (LiDAR) sensor can provide the high-resolution micro traffic data (HRMTD) of all road users by collecting real-time point clouds in three-dimensional (3D) space. HRMTD collected LiDAR provides a solution to fill gap under mixed situation (both connected vehicles unconnected exist on roads) for vehicle technologies. Lane identification is important information HRMTD. current lane algorithms are mainly developed autonomous vehicles, which could not be...
Real-time queue length information is an important input for many traffic applications. This paper presents a novel method real-time detection with roadside LiDAR data. Vehicles on the road were continuously tracked data processing procedures (including background filtering, point clustering, object classification, lane identification and association). A detailed to identify vehicle at end of considering occlusion issue package loss was documented in this study. The proposed can provide...
In transportation, LiDAR sensors have been primarily used in surveying and autonomous driving as a major onboard sensing device to detect field objects. Recently, with reduced price increased demand from real-time trajectory-level traffic detection, technology sees great potential for becoming mainstream means of infrastructure-based detection other than only being onboard. addition its many advanced features, is much less impacted by illumination conditions compared video significant data...
The increasing conflicts between skateboarders and pedestrians on the campuses have caused safety concerns. Although traffic planners campus usually did not consider skateboarding into planning due to lack of historical data. traditional data collection method such as manual counting or video detection took a lot effort could only provide macrolevel Therefore, this research presented new approach for skateboarder using roadside LiDAR sensor. A two-stage classification was developed...
Abstract Vehicle tracking technology is a prerequisite for the connected-vehicle (CV) system. However, mixture of CV and unconnected vehicles will be under normal conditions on roads in near future. How to obtain real-time traffic status remains challenge engineers. The roadside Light Detection Ranging (LiDAR) sensor provides solution collecting high-resolution micro data all road users (CV vehicles). This article developed systematic procedure vehicle using LiDAR sensors. can divided into...
In recent years, with the continuous development of unmanned ground vehicles (UGVs), performance requirements vehicle positioning system are also gradually improved. Existing need to use a variety sensors provide measurement information, and available information is dynamically combined in results calculated. this paper, multi-source fusion established based on factor graph model. order solve problem that algorithm difficult identify exclude abnormal observations autonomously, paper combines...
Light detection and ranging (LiDAR) technology is a key component of an autonomous vehicle's sensing system. It also has the potential to be used at roadside as major infrastructure-based for connected traffic infrastructure systems, well general purpose data collection performance evaluation. Lane movement-based volume basic function systems. The accuracy mainly impacted by occlusion most advanced technologies, such LiDAR, video, radar. This paper presents research results quantify...