Gerald Kühne

Learn More
The segmentation of objects in video sequences constitutes a prerequisite for numerous applications ranging from computer vision tasks to second-generation video coding.We propose an approach for segmenting video objects based on motion cues. To estimate motion we employ the 3D structure tensor, an operator that provides reliable results by integrating(More)
In this paper we propose an approach to the segmentation of video objects based on motion cues. Motion analysis is performed by estimating local orientations in the spatio-temporal domain using the three-dimensional structure ten-sor. These estimates are integrated as an external force into an active contour model, thus stopping the evolving curve when it(More)
Implicit active contour models are widely used in image processing and computer vision tasks. Most implementations, however, are based on explicit updating schemes and are therefore of limited computational efficiency. In this paper, we present fast algorithms based on the semi-implicit additive operator splitting (AOS) scheme for both the geometric and the(More)
1 ABSTRACT In this work we discuss the transmission of MPEG4 video streams over lossy packet networks like the Internet. Due to the efficient compression achieved by the MPEG-4 standard , parts of the bitstream show high inter-dependencies. Consequently, without any precautions packet loss within the transmission of a video session severely affects the(More)
The recognition of objects that appear in a video sequence is an essential aspect of any video content analysis system. We present an approach which classifies a segmented video object based on its appearance (object views) in successive video frames. The classification is performed by matching curvature features of the contours of these object views to a(More)
A two-stage methodology for interactive segmentation of volume data sets is presented in this paper. In the first stage (presegmen-tation) a 3D watershed transformation is used for segmenting the data in different small regions. According to the neighboring relationships between this regions a region adjacency graph (RAG) is constructed. During the second(More)
A wealth of evidence exists about the adoption of new practices and technologies in agriculture but there does not appear to have been any attempt to simplify this vast body of research knowledge into a model to make quantitative predictions across a broad range of contexts. This is despite increasing demand from research, development and extension agencies(More)