DAGM
2009
Springer
13 years 3 months ago
2009
Springer
Abstract. We present a system for detecting shadows in dynamic outdoor scenes. The technique is based on fusing background subtraction operations performed on both color and dispar...
DAGM
2009
Springer
13 years 3 months ago
2009
Springer
Spherical harmonics are widely used in 3D image processing due to their compactness and rotation properties. For example, it is quite easy to obtain rotation invariance by taking t...
DAGM
2009
Springer
13 years 3 months ago
2009
Springer
Abstract. Guided Kanade-Lucas-Tomasi (GKLT) tracking is a suitable way to incorporate knowledge about camera parameters into the standard KLT tracking approach for feature tracking...
DAGM
2009
Springer
13 years 3 months ago
2009
Springer
Abstract. Automatic visual inspection has become an important application of pattern recognition, as it supports the human in this demanding and often dangerous work. Nevertheless,...
DAGM
2009
Springer
13 years 7 months ago
2009
Springer
In this paper we present a framework for computing depth images at interactive rates. Our approach is based on combining time-of-flight (TOF) range data with stereo vision. We use ...
DAGM
2009
Springer
13 years 7 months ago
2009
Springer
Abstract. We present a system that allows for changing the major camera parameters after the acquisition of an image. Using the high dynamic range composition technique and additio...
DAGM
2009
Springer
13 years 7 months ago
2009
Springer
Abstract. Graph cuts have become very popular in many areas of computer vision including segmentation, energy minimization, and 3D reconstruction. Their ability to find optimal res...
DAGM
2009
Springer
13 years 10 months ago
2009
Springer
Abstract. Approaches to visual navigation, e.g. used in robotics, require computationally efficient, numerically stable, and robust methods for the estimation of ego-motion. One of...
DAGM
2009
Springer
13 years 10 months ago
2009
Springer
DAGM
2009
Springer
13 years 10 months ago
2009
Springer
In this paper, we show that a better performance can be achieved by training a keypoint detector to only find those points that are suitable to the needs of the given task. We demo...