A5039406844- Traffic control and management
- Transportation Planning and Optimization
- Traffic Prediction and Management Techniques
- Autonomous Vehicle Technology and Safety
- Organic Electronics and Photovoltaics
- Traffic and Road Safety
- Organic Light-Emitting Diodes Research
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Robotic Path Planning Algorithms
- Vehicle emissions and performance
- Electric Vehicles and Infrastructure
- Robotics and Sensor-Based Localization
- Transportation and Mobility Innovations
- Conducting polymers and applications
- Luminescence and Fluorescent Materials
- Advanced Sensor and Energy Harvesting Materials
- Advanced Image and Video Retrieval Techniques
- Vehicular Ad Hoc Networks (VANETs)
- Vehicle License Plate Recognition
- Remote Sensing and LiDAR Applications
- Thermography and Photoacoustic Techniques
- Molecular Junctions and Nanostructures
- Photoacoustic and Ultrasonic Imaging
- Indoor and Outdoor Localization Technologies
Hefei University of Technology
2025
Beihang University
2015-2024
University of Copenhagen
2024
Chengdu University of Technology
2022-2023
Southeast University
2021-2023
Jiangsu University
2023
Hebei Agricultural University
2022
Shanghai Jiao Tong University
2013-2021
Ministry of Industry and Information Technology
2021
Beijing Advanced Sciences and Innovation Center
2019-2021
Electrification of passenger vehicles has been viewed by many as a way to significantly reduce carbon emissions, operate more efficiently, and oil dependence. Due the potential benefits electric vehicle (EV), federal local governments have allocated considerable funding taken number legislative regulatory steps promote EV deployment adoption. With this momentum, it is not difficult see that in near future, EVs could gain significant market penetration, particularly densely populated urban...
UAV based traffic monitoring holds distinct advantages over traditional sensors, such as loop detectors, UAVs have higher mobility, wider field of view, and less impact on the observed traffic. For from images, essential but challenging task is vehicle detection. This paper extends framework Faster R-CNN for car detection low-altitude imagery captured signalized intersections. Experimental results show that can achieve promising compared with other methods. Our tests further demonstrate...
Subway short-term ridership forecasting plays an important role in intelligent transportation systems. However, limited efforts have been made to forecast the subway ridership, accounting for dynamic volatility. The traditional methods can only provide point values that are unable offer enough information on volatility/uncertainty of results. To fill this gap, aim paper is incorporate volatility into process not generates expected value but also obtains prediction interval. Four kinds...
A new hybrid vehicle detection scheme which integrates the Viola-Jones (V-J) and linear SVM classifier with HOG feature (HOG + SVM) methods is proposed for from low-altitude unmanned aerial (UAV) images. As both V-J are sensitive to on-road vehicles’ in-plane rotation, first adopts a roadway orientation adjustment method, rotates each UAV image align roads horizontal direction so original or method can be directly applied achieve fast high accuracy. To address issue of descending speed SVM,...
This research develops an advanced vehicle detection method, which improves the original Viola-Jones (V-J) object scheme for better detections from lowaltitude unmanned aerial (UAV) imagery. The V-J method is sensitive to objects' in-plane rotation, and therefore has difficulties in detecting vehicles with unknown orientations UAV images. To address this issue, proposes a road orientation adjustment rotates each image once so that roads on-road on rotated images will be aligned horizontal...
Driven by the prominent thermal signature of humans and following growing availability unmanned aerial vehicles (UAVs), more research efforts have been focusing on detection tracking pedestrians using infrared images recorded from UAVs. However, pedestrian obtained UAVs pose many challenges due to low-resolution imagery, platform motion, image instability relatively small size objects. This tackles these proposing a system. A two-stage blob-based approach is first developed for detection....
This research explores the inherent vulnerability of nonlinear vehicle platoons characterized by oscillatory behavior triggered external perturbations. The perturbation exerted on platoon is regarded as an force object. Following mechanical vibration analysis in mechanics, this proposes a vibration-theoretic approach that advances our understanding from two aspects. First, proposed introduces damping intensity to characterize vehicular vulnerability, which divides oscillations into types,...
We have successfully obtained a highly transparent and conductive film by doping poly(3,4-ethylenedioxythiophene):poly(styrene sulfonate) (PEDOT:PSS) with graphene oxide (GO) sodium dodecyl benzene sulfonate (SDBS).
Object detection on railway tracks, which is crucial for train operational safety, face numerous challenges such as multiple types of objects and the complexity running environment. In this study, a multi-sensor framework proposed to fuse camera LiDAR data track including small obstacles forward trains. The involves two-stage process: region interest extraction object detection. first stage, multi-scale prediction network designed achieve pixel level segmentation via image. second used...