My currently research interests is in Computer Vision and Machine Learning. I am doing researches in the following sub-areas:
1) Low-level Image feature analysis and fusion.
2) Multi-view panorama stitching.
3) Fast human pose estimations for immersive telepresence applications using stereo and hand-face tracking.
Publications
Wei Xu and Jane Mulligan. Performance Evaluation of Color Correction Approaches for Automatic Multi-view Image and Video Stitching. Accepted by CVPR 2010.(project webpage)
Wei Xu and Jane Mulligan. A Fast Multi-Channel Edge Detection Algorithm for Vision-based Autonomous Spacecraft Docking. In Proc. 2009 IEEE Workshop on Applications of Computer Vision (WACV¡¯09), December 2009. (pdf)
Wei Xu and Jane Mulligan. Augmenting Exercise Systems with Virtual Exercise Environment. In Proc. 5th International Symposium on Visual Computing (ISVC¡¯09), November 2009.
Wei Xu and Jane Mulligan. Feature Matching under Region-based Constraints for Robust Epipolar Geometry Estimation.In Proc. 5th International Symposium on Visual Computing (ISVC¡¯09), November 2009.
Wei Xu and Jane Mulligan. Robust Relative Pose Estimation with Integrated Cheirality Constraint, In Proc. 19th International Conference on Pattern Recognition (ICPR¡¯08), December 2008.
Wei Xu
