In this work, we present a novel segmentation method for deformable objects in monocular videos. Firstly we introduce the dynamic shape to represent the prior knowledge about obje...
In the paper, an automatic spatio-temporal video sequence segmentation algorithm is proposed. To address this very di cult computer vision problem, several novel algorithms have b...
The design of a video surveillance system is directed on automatic identification of events of interest, especially on tracking and classification of moving vehicles or pedestrian...
In spite of recent progress in the development of hybrid block-based video codecs, it has been shown that for low-bitrate scenarios there is still coding gain applying object-base...
Matthias Kunter, Andreas Krutz, Michael Drose, Mic...
We present a method for live grouping of feature points into persistent 3D clusters as a single camera browses a static scene, with no additional assumptions, training or infrastr...