Teck Khim Ng

Learn More
In this thesis, we describe a statistical method for 3D object detection. In this method, we decompose the 3D geometry of each object into a small number of viewpoints. For each viewpoint , we construct a decision rule that determines if the object is present at that specific orientation. Each decision rule uses the statistics of both object appearance and(More)
Removal of rain streaks in video is a challenging problem due to the random spatial distribution and fast motion of rain. This paper presents a new rain removal algorithm that incorporates both temporal and chromatic properties of rain in video. The temporal property states that an image pixel is never always covered by rain throughout the entire video. The(More)
This paper introduces a human body contour registration method for static pedestrian images with unconstrained background. By using a statistical compound model to impose structural and textural constraints on valid pedestrian appearances, the matching process is robust to image clutter. Experimental results show that the proposed method register pedestrian(More)
Parameter indeterminacies are inherent in 3D computer vision. We show in this thesis that how they are treated can have significant impact on the accuracy of the estimated 3D structure. However, there has not been a general and convenient method available for representing and analyzing the indeterminacies and their effects on accuracy. Consequently , up to(More)
Acknowledgements It is a privilege to have had the opportunity t o w ork with my advisor, Dr. Takeo Kanade. I w ould like to thank him for his guidance and patience throughout the course of this project. His perseverance in research and his ability to look at things from a global perspective while attending to critical details will continue to have positive(More)
In this paper, we present a robust face tracking system for video indexing and retrieval. Our face tracker is designed based on the condensation algorithm. The strength of our face tracking system is in the incorporation of Lucas-Kanade feature tracker in the measurement stage of condensation. Skin color and facial feature points are used for tracking. The(More)
  • 1