ECCV
2008
Springer
13 years 6 months ago
2008
Springer
We analyze the problem of reconstructing a 2D function that approximates a set of desired gradients and a data term. The combined data and gradient terms enable operations like mod...
ECCV
2008
Springer
13 years 6 months ago
2008
Springer
Abstract. We present a detection-based three-level hierarchical association approach to robustly track multiple objects in crowded environments from a single camera. At the low lev...
ECCV
2008
Springer
13 years 6 months ago
2008
Springer
Extraction and matching of discriminative feature points in images is an important problem in computer vision with applications in image classification, object recognition, mosaici...
ECCV
2008
Springer
13 years 6 months ago
2008
Springer
Abstract. The ability to localise a camera moving in a previously unknown environment is desirable for a wide range of applications. In computer vision this problem is studied as m...
ECCV
2008
Springer
13 years 6 months ago
2008
Springer
Abstract. We address the problem of visual event recognition in surveillance where noise and missing observations are serious problems. Common sense domain knowledge is exploited t...
ECCV
2008
Springer
13 years 6 months ago
2008
Springer
Retrieval of similar heart sounds from a sound database has applications in physician training, diagnostic screening, and decision support. In this paper, we exploit a visual rende...
ECCV
2008
Springer
13 years 6 months ago
2008
Springer
We derive a probabilistic framework for robust, real-time, visual tracking of previously unseen objects from a moving camera. The tracking problem is handled using a bag-of-pixels ...
ECCV
2008
Springer
13 years 6 months ago
2008
Springer
Abstract. In the matching tasks which form an integral part of all types of tracking and geometrical vision, there are invariably priors available on the absolute and/or relative i...
ECCV
2008
Springer
13 years 6 months ago
2008
Springer
For many tasks in computer vision, it is very important to produce the groundtruth data. At present, this is mostly done manually. Manual data labeling is labor-intensive and prone...
ECCV
2008
Springer
13 years 6 months ago
2008
Springer
Active contour formulations predominate current minimization of the Mumford-Shah functional (MSF) for image segmentation and filtering. Unfortunately, these formulations necessitat...