This paper presents a system to analyze the reachability of the human body. The inverse kinematics technique is employed to find which regions of space are reachable using a certa...
We propose a key frame extraction mechanism to aid the Structure from Motion (SfM) problem when dealing with image sequences from video cameras. Due to high frame rates (15 frames...
Vector Quantization is useful for data compression. Competitive Learning which minimizes reconstruction error is an appropriate algorithm for vector quantization of unlabelled dat...
Feature selection is an important problem for pattern classification systems. Mutual information is a good indicator of relevance between variables, and has been used as a measure...
RANSAC (Random Sample Consensus) is a popular and effective technique for estimating model parameters in the presence of outliers. Efficient algorithms are necessary for both fram...
Paul McIlroy, Edward Rosten, Simon Taylor, Tom Dru...