In this paper, a motion field scheme for video compression is presented. A split-andmerge segmentation technique and weighted linear regression are used to segment the field and an affine motion model is used to describe the movements of the regions. In the regression, individual motion vectors are weighted according to the relative sensitivity of the reconstruction to inaccurate motion at that...

Introduction Myocardial Delayed Enhancement (MDE) MR imaging has been used for visualization of myocardial scar tissue created due to radio-frequency ablation (RFA) of the left atrium for the treatment of atrial fibrillation [1,2]. After administration of gadolinium-DTPA contrast, ECG-gated 3D-MDE is performed with an inversion-recovery preparatory pulse, followed by a segmented k-space gradien...

The lumbar spine, although often described as a single functional unit, is composed of 5 vertebrae forming what are called "motion segments" connected in series.5 Each motion segment consists of 2 adjacent vertebral bodies and the connecting ligaments.6 Spinal motion segments represent the smallest segments of the spine exhibiting biomechanical characteristics similar to those of the entire spi...

We extend our previous work [1] of the general framework for video data mining to further address the issue such as how to mine video data, in other words, how to extract previously unknown knowledge and detect interesting patterns. In our previous work, we have developed how to segment the incoming raw video stream into meaningful pieces, and how to extract and represent some feature (i.e., mo...

In this paper, we present a novel method for generating sports video summary highlights. Specifically, our method localizes semantically important events in sport programs by detecting slow motion replays of these events, and then generates highlights of these events at multiple levels. In our method, a hidden Markov model (HMM) is used to model slow motion replays, and an inference algorithm i...

A necessary requirement for many musculoskeletal modeling tasks is an estimation of skeletal motion from observations of the surface of a body segment. The skeletal motion may be used directly for inverse kinematic calculations or as an observation sequence for forward dynamic simulations. This paper describes a fundamentally new approach to human motion capture for biomechanical analysis. Tech...