A5060296003- Infrastructure Maintenance and Monitoring
- Railway Engineering and Dynamics
- Video Surveillance and Tracking Methods
- Advanced Neural Network Applications
- Advanced Algorithms and Applications
- Vehicle License Plate Recognition
- 3D Shape Modeling and Analysis
- Advanced Measurement and Detection Methods
- Mobile and Web Applications
- Surface Roughness and Optical Measurements
- Reliability and Maintenance Optimization
- Image Processing Techniques and Applications
- Cardiac electrophysiology and arrhythmias
- Transport and Economic Policies
- Receptor Mechanisms and Signaling
- Industrial Vision Systems and Defect Detection
- Simulation and Modeling Applications
- Computer Graphics and Visualization Techniques
- Electrochemical Analysis and Applications
- Advanced Numerical Analysis Techniques
Shenzhen Urban Transport Planning Center Co.
2024
Beijing Jiaotong University
2018-2023
Wuhan University of Technology
2017
La Roche College
2008
Computer vision systems have attracted much attention in recent years for use detecting surface defects on rails; however, accurate and efficient recognition of possible remains challenging due to the variations shown by also noise. This paper proposes a coarse-to-fine model (CTFM) identify at different scales. The works three scales from coarse fine: subimage level, region pixel level. At background subtraction exploits row consistency longitudinal direction, strongly filters defect-free...
Predicting the tamping cycles of railway track sections based on geometry deterioration rules is necessary to reasonably allocate limited maintenance resources. Existing research modeling for cycle prediction lacks simultaneous consideration characteristics including heterogeneity, uncertainty, and historical dependence, thereby limiting accuracy results. Thus, this study considers a 200 m segment as basic object uses power-time-transformed Wiener process develop model longitudinal level...
Vehicles carrying hazardous material (hazmat) are severe threats to the safety of highway transportation, and a model that can automatically recognize hazmat markers installed or attached on vehicles is essential for intelligent management systems. However, there still no public dataset benchmarking task marker detection. To this end, paper releases large-scale vehicle named VisInt-VHM, which includes 10,000 images with total 20,023 captured under different environmental conditions from...
<p indent=0mm>The traditional image threshold is not effective for detecting conductive particles in a thin-film transistor liquid crystal display (TFT-LCD) circuit due to uneven illumination, micro size, and the large number of involved. To improve accuracy speed TFT-LCD particles, novel method based on gradient proposed. Given variable brightness an image, pseudo-illuminant-direction-detection estimation presented. The directly addresses issue that illuminant model cannot be adapted...
Vehicles transporting hazardous material (HAZMAT) pose a severe threat to highway safety, especially in road tunnels. Vehicle reidentification is essential for identifying and warning abnormal states of HAZMAT vehicles However, there still no public dataset benchmarking this task. To end, work releases real-world tunnel vehicle dataset, VisInt-THV-ReID, including 10,048 images with 865 their spatiotemporal information. A method based on multimodal information fusion proposed realize by...
Inland waterway vessel video has a very important role in the automated management of inland waterways. However, there is currently no open platform for implementing processing vessels. According to characteristics large and formats vessel, paper proposes build standard library establish vessels based on Hadoop, which adopts B/S architecture, with Html, CSS JavaScript as front desk technology, JSP, Servlet JavaBean background realizes function online video. Compared traditional stand-alone...