Learn More
This paper presents a novel method for detecting scale invariant keypoints. It fills a gap in the set of available methods, as it proposes a scale-selection mechanism for junction-type features. The method is a scale-space extension of the detector proposed by Förstner (1994) and uses the general spiral feature model of Bigün (1990) to unify(More)
We develop a qualitative measure for the completeness and complementarity of sets of local features in terms of covering relevant image information. The idea is to interpret feature detection and description as image coding, and relate it to classical coding schemes like JPEG. Given an image, we derive a feature density from a set of local features , and(More)
We present a scheme for measuring completeness of local feature extraction in terms of image coding. Completeness is here considered as good coverage of relevant image information by the features. As each feature requires a certain number of bits which are representative for a certain subregion of the image, we interpret the coverage as a sparse coding(More)
We present a novel surface model and reconstruction method for man-made environments that take prior knowledge about topology and geometry into account. The model favors but is not limited to horizontal and vertical planes that are pairwise orthogonal. The reconstruction method does not require one particular class of sensors, as long as a triangulated(More)
Although there has been much discussion of the current professional conflicts between psychiatrists and psychologist, few studies have attempted to empirically evaluate how the professions view their roles and responsibilities within the mental health system. In this study a questionnaire was sent to psychiatrists, psychologist, social workers, and nurses(More)
Zusammenfassung We propose a framework for object tracking in image sequences, following the concept of tracking-by-segmentation. The separation of object and background is achieved by a consecutive semantic superpi-xel segmentation of the images, yielding tight object boundaries. I.e., in the first image a model of the object's characteristics is learned(More)