A5100627569- Manufacturing Process and Optimization
- Product Development and Customization
- Welding Techniques and Residual Stresses
- Technology Assessment and Management
- Digital Transformation in Industry
- Industrial Vision Systems and Defect Detection
- Infrared Target Detection Methodologies
- Advanced Image Fusion Techniques
- Additive Manufacturing Materials and Processes
- Image Processing Techniques and Applications
- Extenics and Innovation Methods
- Tribology and Lubrication Engineering
- Advanced Vision and Imaging
- High Entropy Alloys Studies
- Image Enhancement Techniques
- Advanced Measurement and Metrology Techniques
- Remote-Sensing Image Classification
- Optical measurement and interference techniques
- Random lasers and scattering media
- CCD and CMOS Imaging Sensors
- Image and Object Detection Techniques
- Design Education and Practice
- Thermography and Photoacoustic Techniques
- Color Science and Applications
- Quality Function Deployment in Product Design
Zhejiang University of Technology
2012-2024
Zhejiang University
2013-2023
Nanjing University of Aeronautics and Astronautics
2023
Zhongyuan University of Technology
2017-2021
Umbo Computer Vision (United Kingdom)
2019
Zhejiang Institute of Mechanical and Electrical Engineering
2009
Zhejiang Energy Research Institute
2008
Daewoo Pharma (South Korea)
2007
Fixed-pattern noise (FPN), which is caused by the nonuniform opto-electronic responses of microbolometer focal-plane-array (FPA) optoelectronics, imposes a challenging problem in infrared imaging systems. In this paper, we successfully demonstrate that better single-image-based non-uniformity correction (NUC) operator can be directly learned from large number simulated training images instead being handcrafted as before. Our proposed scheme, based on convolutional neural networks (CNNs) and...
This paper presents the first challenge on demosaicing of natural spectral images for snapshot hyperspectral imaging systems (HIS) which utilize a multi-spectral filer array (MSFA), i.e., recovery whole-scene information from spatially sub-sampled information. expands "ARAD_1K" data set to first-of-its-kind large-scale multispectral filter scenes containing 1,000 images. Challenge participants were required recover synthetically generated MSFA simulating capture by known calibrated mosaic...
Multidisciplinary complex mechatronic systems span disciplines such as mechanics, electronics, control and software. Increasing complexity makes the implementation of automated design for mechatronics highly challenging. An effective method decomposing an overall function to obtain structure principle solution is needed efficient creative design. A hybrid approach proposed automate process functional decomposition which contains three main steps. First, decomposed several effects...
Recent research has demonstrated that the fusion of complementary information captured by multi-modal sensors (visible and infrared cameras) enables robust pedestrian detection under various surveillance situations (e.g., daytime nighttime). In this paper, we investigate a number architectures in an attempt to identify optimal way incorporating multispectral for joint semantic segmentation detection. We made two important findings: (1) sum strategy, which computes feature maps at same...
In this paper we present a novel non-uniformity correction (NUC) method to remove column fixed-pattern noise (FPN), which is introduced by of on-chip column-parallel readout circuit in uncooled infrared focal plane array. We first define new image statistic measurement, named as 1D horizontal differential statistics, differentiate FPN from structural edges, and further propose filtering scheme adaptively compute terms structure non-structure regions applying different models. The proposed...
The performance indicator system based on balanced scorecard (BSC) is the vertical breakdown proceeding from strategy, it neglects considering collaborative relationship between upstream and downstream departments. This paper proposes a design method of company integrated strategic BSC 'suppliers-input-process-output-customers' model (SIPOC). First, strategy map are adopted to develop company-level key indicators (KPIs), which gradually broken down different departments forming department...
The objectives of this study are to optimize the key process parameters laser cladding remanufacturing parts, improve sealing quality hemispherical valve and prolong its service life reliability. A high-power fiber-coupled semiconductor was used fabricate a single Co-based alloy layer on pump material ZG45 plate. power, scanning speed powder feeding rate in taken as optimization variables, coating width, height, depth, aspect ratio dilution response indexes. Based surface analysis method,...
This article proposes a scheme for functional specification in accordance with the new generation of geometrical product specification. The is to decompose requirement on complex mechanism into geometric specifications defined key parts. assembly analyzed by graph theory. general and decomposed if necessary, tolerances specified ending Then variation model built according invariant degree freedom both datum reference system tolerance zone, which subsequently used validate sufficiency frame...
To assure feasibility and economy of mechanical product design, tolerance design should be incorporated into conceptual structure phase. The completion the evolving procedures from functional requirement to scheme resolution in early stage, greatly promotes selection optimization cost. paper provides a concurrent methodology for using principle decomposition reconstitution growth based on surfaces. A is given, including design-supported structure-tolerance process, assembly information model...
Non-line-of-sight (NLOS) imaging of hidden objects is a challenging yet vital task, facilitating important applications such as rescue operations, medical imaging, and autonomous driving. In this paper, we attempt to develop computational steady-state NLOS localization framework that works accurately robustly under various illumination conditions. For purpose, build physical image acquisition hardware system corresponding virtual setup obtain real-captured simulated images different ambient...
A local and temporal separated manufacturing becomes possible, which can enhance the economic efficiency of production. Complex products such as spacecraft, large CNC Machine, compressor face challenges in their development process. The cloud is based on computing Internet Things system makes collaborative process complex customized product become rapid intelligent efficient low-energy consumption. Cloud Manufacturing a new pattern organizes resource to provide customers with all kinds...
A datum selection strategy based on statistical learning is proposed. The an important part of tolerance specification which the base geometric and principle selection. problem to deduce reference frame (DRF) geometrical, contact, positioning characteristics. Currently, heuristic rules are used for DRF selection, leading suboptimal choice in many cases. proposed formulates normalized vectors computed from geometric, characteristics surfaces. surfaces different parts can be compared by their...