A5101516023- Optical measurement and interference techniques
- Infrastructure Maintenance and Monitoring
- Industrial Technology and Control Systems
- Concrete Corrosion and Durability
- 3D Surveying and Cultural Heritage
- Industrial Vision Systems and Defect Detection
- Advanced Algorithms and Applications
- Structural Health Monitoring Techniques
- Advanced Vision and Imaging
- Non-Destructive Testing Techniques
- Construction Engineering and Safety
- Innovations in Concrete and Construction Materials
- Advanced Optical Sensing Technologies
- Bamboo properties and applications
- Advanced X-ray Imaging Techniques
- Water Quality Monitoring and Analysis
- Mineral Processing and Grinding
- Image and Object Detection Techniques
- Advanced Sensor and Energy Harvesting Materials
- Extraction and Separation Processes
- Adaptive optics and wavefront sensing
- Optical Systems and Laser Technology
- Environmental remediation with nanomaterials
- Advanced Neural Network Applications
- Chromatography in Natural Products
Peng Cheng Laboratory
2022-2025
Beijing Institute of Technology
2024
East China University of Science and Technology
2022
Hong Kong University of Science and Technology
2018-2021
University of Hong Kong
2018-2021
Hohai University
2013
Chinese Center For Disease Control and Prevention
2008
Sichuan University
2004
Abstract Early and timely detection of surface damages is important for maintaining the functionality, reliability, safety concrete bridges. Recent advancement in convolution neural network has enabled development deep learning‐based visual inspection techniques detecting multiple structural damages. However, most are built on two‐stage, proposal‐driven detectors using less complex image data, which could be restricted practical applications possible integration within intelligent autonomous...
Accurate prediction of reaction temperature in rotary kiln is essential to realize its advanced process control and operational optimizations. However, the complexity physical chemical reactions makes it difficult for traditional mechanism model characterize dynamic process. In this study, a deep learning-based proposed accurately track changes during production kiln. The integrates temporal convolutional network (TCN) with long short-term memory (LSTM) network. former enables be aware local...
Deep learning techniques have attracted significant attention in the field of visual inspection civil infrastructure systems recently. Currently, most deep learning-based utilize a convolutional neural network to recognize surface defects either by detecting bounding box each defect or classifying all pixels on an image without distinguishing between different instances. These outputs cannot be directly used for acquiring geometric properties individual image, thus hindering development...
The timely and accurate measurement of temperature field is great significance for the low-carbon high-efficiency operation zinc oxide rotary volatile kiln (ZORVK). Due to large axial length, closed internal space complex reaction mechanism, it difficult measure complete data. In this study, a novel prediction model based on fusion thermodynamics infrared images proposed first time. First, thermodynamic involving chemical heat established. Then, an industrial thermal imager developed. order...
With the success of Transformers in natural language processing, object detection with (DETR) has attracted widespread attentions. In previous Transformer-based 2D detectors, queries are a set learning embeddings. However, it is very hard to apply these detectors 3D domain due lack explicit physical meanings and position priors learned queries. this paper, we introduce concept anchors propose novel query design based on anchor points. our design, use foreground points as encode Consequently,...
Fringe projection profilometry (FPP) is an extensively used active three-dimensional (3D) measurement technique. However, it faces challenges in achieving synchronous improvement of range, speed, accuracy and shadow issues. To meet the demand for rapid 3D reconstruction two views only using a single-shot phase-shifting grating, we initially propose fast large-scale system based on deep learning with dual-projector single-camera configuration, named DL_DPSL. The key feature that entire...
Detecting concrete surface damages is a vital task for maintaining the structural health and reliability of highway bridges. Currently, most these tasks are conducted manually which could be cumbersome time-consuming. Recent rapid advancement in convolution neural network has enabled development deep learning-based visual inspection techniques detecting multiple damages. However, built on two-stage, proposal-driven detectors using less complex image data, not promising to promote practical...
Concrete cracks are one of the most apparent indicators for possible structural deterioration and need to be periodically inspected. However, current image-based automated crack inspection techniques, accurate detailed quantification assessment remain a challenging task. Most these techniques require high-quality input images, which may difficult ensure in practice. Besides, simply merging detections from multiple images generate large map result an inaccurate outcome severity assessment. In...
The intelligent goal of process manufacturing is to achieve high efficiency and greening the entire production. Whereas information system it used functionally independent, resulting knowledge gaps between each level. Decision-making still requires lots workers making manually. industrial metaverse a necessary means bridge by sharing collaborative decision-making. Considering safety stability requirements manufacturing, this article conducts thorough survey on intelligence empowered...
The three-frequency heterodyne phase shift profilometry is widely used in high-precision 3D reconstruction. However, the high accuracy comes at cost of requiring many projected frames, which increases measurement time and decreases efficiency. To address this challenge, we propose a rapid, absolute acquisition method called X+1+1, fully integrates advantages multi-frequency n-step phase-shifting speed Modified Fourier transform (MFTP). highest frequency gratings use standard X-step to...
The demand for accurate and real-time indoor localization human sensing is rising with the development of smart environments, applications in security homes. Effective systems enhance safety, energy efficiency, user experience by leveraging existing infrastructure, reducing deployment costs, integrating seamlessly. Traditional methods rely on dedicated hardware, while communication or lighting infrastructure can provide dual-purpose solutions. This research focuses Visible Light...