AudioSeg is a toolkit dedicated to audio segmentation and classification of audio streams. The toolkit implements standard reference algorithms such as energy-based silence detection, BIC segmentation and clustering as well as GMM/HMM classification
Input: % ima: grey color image % k: Number of classes % Output: % mask: clasification image mask % mu: vector of class means % v: vector of class variances % p: vector of class proportions % % Example: [mask,mu,v,p]=EMSeg(image,3);
An active shape model segmentation scheme is presented that is steered by optimal local features, contrary to normalized first order derivative profiles, as in the original formulation.
Thomas Brox is interested in all aspects of computer vision with special focus on video analysis (optical flow estimation, motion segmentation, learning from videos, detection in videos)