Christopher Bulla

Learn More
—In a modern video conferencing application, the people participating at each client can be detected, tracked and placed in a virtual scene where all persons are of equal size and occupy a predefined rectangular space. This virtual scene can then be rendered on screen instead of a whole room with several people. As a result, a more immerse video(More)
—In this paper, we present a region of interest encoding system for video conference applications. We will utilize the fact that the main focus in a typical video conference lies upon the participating persons in order to save bit-rate in less interesting parts of the video. A Viola-Jones face detector will be used to detect the regions of interest. Once a(More)
In this paper, we present an affine invariant feature descriptor, which is based on the well known Scale Invariant Feature Transform algorithm. The descriptor is a weighted histogram of gradient orientations and invariant against scale, in-plane rotation, stretch and skew. To cover the geometrical distortions introduced by an affine image transformation, we(More)
In this paper, we present a method for affine invariant feature description. Based on the gradient distribution of an image region we calculate two basis vectors defining an affine invariant coordinate system, used to normalize the image region. The estimated basis vectors are non-orthogonal and allow for a precise representation of the gradient(More)
Fisher Vectors have shown great capability for visual search. Their main drawback is their high dimensionality. We propose several methods to reduce the size of the Fisher Vectors by applying different preprocessing steps and dimension reduction techniques to SIFT descriptors. Also, we investigate the effects of PCA and DCT transforms employed on SIFT(More)
In this paper we present a method for the detection of wrong feature correspondences in a local feature based object detection system. Common visual objects in different images share not only similar local features but also a similar spatial layout of their features. We will utilize this fact in order to distinguish between correct and wrong feature(More)
  • 1