We present a novel statistical and variational approach to image segmentation based on a new algorithm named region competition. This algorithm is derived by minimizing a generalized Bayes/MDL criterion using the variational principle. The algorithm is guaranteed to converge to a local minimum

, gyroscope measurements to deal with fast motions, measurements of gravity and magnetic field to avoid drift, and a back store of reference frames with online frame selection to re-initialise automatically after dynamic occlusions or failures. A novel edge-based tracker dispenses with the conventional edge

tracking, where the flow of input data may be at a rate of 10 or 20 Mbytes per second. The tracker described here extracts edges in a frame of an image sequence and attempts to find corresponding edges in the next (and subsequent) frame(s) of the sequence. Using computationally cheap versions

irregular motions as well as shot boundaries. Additionally, dense trajectories cover the mo-tion information in videos well. We, also, investigate how to design descriptors to encode the trajectory information. We introduce a novel descriptor based on motion boundary histograms, which is robust to camera

Network tomography is a process for inferring “internal” link-level delay and loss performance information based on end-to-end (edge) network measurements. These methods require knowledge of the network topology; therefore a first crucial step in the tomography process is topology identification

. The proposed solutions together form a new foundation for quality-of-service communication via a scalable edge-based architecture where the novel functionality is added strictly at either edge routers or end hosts. In particular, this thesis proposes techniques for multi-class service inference, active probing

the classifier and can cause further drift. In this paper we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems, and can therefore lead to a more robust tracker with fewer parameter tweaks. We present a novel online MIL algorithm for object tracking

, each of which captures a different feature channel. Our features include the distribution of edges, dense and sparse visual words, and feature descriptors at different levels of spatial organization. Such a powerful classifier cannot be tested on all image sub-windows in a reasonable amount of time

This paper proposes and evaluates a novel, edge-based approach, which we call the kset

of support vectors, with negligible loss in classification accuracy on various tasks. This approximation also applies to 1 − χ2 and other kernels of similar form. We also introduce novel features based on a multi-level histograms of oriented edge energy and present experiments on various detection datasets