To be able to automatically capture, process, analyze, and use image and video contents are getting more and more important these days, thanks to the improving computing power, the growing number of cameras, and the fast-increasing use of mobile devices. Our focus is to make computers more intelligent such that they can automatically analyze and learn from image data, recognize objects, and understand image contents automatically. We expect these technologies will greatly make our life more rich, safe, and convenient.
Our research field covers a wide array of topics related to images. Image processing includes the enhancement, restoration, segmentation, compression, and watermarking techniques. A more advanced example is adaptive image scaling that intelligently provides good-quality viewing for various display devices. Computer vision covers all kinds of analysis of visual contents, e.g., camera calibration, three-dimensional modeling, automatic localization and environment learning in stereo vision, the detection and recognition of persons, objects, and events in surveillance systems, as well as video content analysis and many other techniques. Pattern recognition is concerned with the techniques for automatic classification and clustering of data, which have many applications in computer vision.
- Video Surveillance
- Object Tracking and Recognition
- Camera Calibration
- Image Enhancement and Restoration
- Image Segmentation
- 3D Modeling and Reconstruction
- Autonomous Navigation and Environment Understanding,
- Video Analysis
- Image and Video Indexing
- Image and Video Compression
- Computational Photography
- Information Hiding and Digital Watermarking
- Remote-sensing and Seismic Data Analysis
- Clustering Algorithms