A5059659160- Advanced Vision and Imaging
- Sleep and Work-Related Fatigue
- Data Management and Algorithms
- Optical measurement and interference techniques
- Advanced Image and Video Retrieval Techniques
- Robotics and Sensor-Based Localization
- Color perception and design
- Gaze Tracking and Assistive Technology
- Advanced Graph Neural Networks
- Graph Theory and Algorithms
- Video Surveillance and Tracking Methods
- Ergonomics and Musculoskeletal Disorders
- Image and Video Stabilization
Hunan University
2023
National Taiwan University
2009-2014
In this paper, a video stabilization technique is presented. There are four steps in the proposed approach. We begin with extracting feature points from input image using Lowe SIFT (scale invariant transform) point detection technique. This set of then matched against detected previous Wyk et al. RKHS (reproducing kernel Hilbert space) graph matching can calculate camera motion between two images aid 3D model. Expected and unexpected components separated taxonomy method. Finally, full-frame...
In this paper, a vision system for monitoring driver's vigilance is presented. The level of determined by integrating number facial parameters. order to estimate these parameters, the features eyes, mouth and head are first located in input video sequence. then tracked over subsequent images. Facial parameters estimated during feature tracking. parametric values collected analyzed every fixed time interval provide real-time driver. A series experiments on real sequences were demonstrated...
In this paper, a vision system for monitoring driver's facial features is presented. To begin, the face first located in input video sequence. It then tracked over subsequent images. The of eyes, mouth and head are kept detecting course tracking. Feature detection tracking performed parall so that precise can be improved. A number sequences with drivers different ages genders under various illumination road conditions were employed to demonstrate performance proposed system. Future work on...