A5101518904- Video Surveillance and Tracking Methods
- Robotics and Sensor-Based Localization
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Advanced Vision and Imaging
- Software-Defined Networks and 5G
- Remote Sensing and LiDAR Applications
- Scheduling and Optimization Algorithms
- Advanced Image Processing Techniques
- Collaboration in agile enterprises
- Image and Signal Denoising Methods
- Interactive and Immersive Displays
- Business Strategy and Innovation
- Technology Adoption and User Behaviour
- Impact of AI and Big Data on Business and Society
- Business Process Modeling and Analysis
- Cloud Computing and Resource Management
- 3D Shape Modeling and Analysis
- Water Quality Monitoring Technologies
- Blockchain Technology Applications and Security
- Advanced Image Fusion Techniques
Chang'an University
2024
Southwestern University of Finance and Economics
2018-2023
The University of Texas Southwestern Medical Center
2009
Southwestern Medical Center
2009
We have developed a learning-based image transformation framework and successfully applied it to three common operations: downscaling, decolorization, high dynamic range tone mapping. use convolutional neural network (CNN) as non-linear mapping function transform an input desired output. A separate CNN trained for very large classification task is used feature extractor construct the training loss of CNN. Unlike similar applications in related literature such super-resolution, none problems...
Given a new 6DoF camera pose in an indoor environment, we study the challenging problem of predicting view from that based on set reference RGBD views. Existing explicit or implicit 3D geometry construction methods are computationally expensive while those learning have predominantly focused isolated views object categories with regular geometric structure. Differing traditional render-inpaint approach to synthesis real propose conditional generative adversarial neural network (P2I-NET)...
Precisely relating pixels in the projector image to camera plays a significant role many projector-camera systems. In this paper, we present novel method of finding correspondence simple and efficient manner. Our registration approach uses binary coding scheme, only need capture few pictures does not give any assumption system. experimental results demonstrate advantage using our methods.