Topic
Orientation (computer vision)
About: Orientation (computer vision) is a research topic. Over the lifetime, 17196 publications have been published within this topic receiving 358181 citations.
Papers published on a yearly basis
Papers
More filters
TL;DR: Results show that the notion of scale plays an important role in the interpretation of textures and the computation of the orientation field, resulting in the intrinsic images, is indispensible in the analysis of oriented textures.
228 citations
Patent•
30 Jun 1993
TL;DR: Adaptive interpolation is performed by apparatus operating upon a digitized image signal obtained from an image sensor having color photosites that generate a plurality of color values, but only one color per photosite as discussed by the authors.
Abstract: Adaptive interpolation is performed by apparatus operating upon a digitized image signal obtained from an image sensor having color photosites that generate a plurality of color values, but only one color per photosite. A digital processor obtains gradient values from the differences between luminance values in vertical and horizontal image directions. The gradient values are compared to a programmable threshold in order to select one of the directions as the preferred orientation for the interpolation of additional luminance values. The interpolation is then performed upon values selected to agree with the preferred orientation.
227 citations
Patent•
03 Sep 1991TL;DR: In this article, the position and orientation of an invasive device, such as a catheter, are measured with radio frequency fields and displayed stereoscopically, by superposition of a graphic symbol on static X-ray images obtained at two different view angles.
Abstract: During an X-ray procedure, the position and orientation of an invasive device, such as a catheter are measured with radio frequency fields and displayed stereoscopically. Instantaneous three-dimensional positions of the invasive device are displayed by superposition of a graphic symbol on static X-ray images obtained at two different view angles. The X-ray images are obtained only when deemed necessary by the operator to minimize X-ray dose. A single X-ray source and detector may be implemented since it is not necessary to obtain the X-ray images simultaneously.
226 citations
09 Sep 2003
TL;DR: This work proposes an exact method for efficiently and robustly computing the visual hull of an object from image contours that is fast and allows real-time recovery of both manifold and watertight visual hull polyhedra.
Abstract: We propose an exact method for efficiently and robustly computing the visual hull of an object from image contours. Unlike most existing approaches, ours computes an exact description of the visual hull polyhedron associated to polygonal image contours. Furthermore, the proposed approach is fast and allows real-time recovery of both manifold and watertight visual hull polyhedra. The process involves three main steps. First, a coarse geometrical approximation of the visual hull is computed by retrieving its viewing edges, an unconnected subset of the wanted mesh. Then, local orientation and connectivity rules are used to walk along the relevant viewing cone intersection boundaries, so as to iteratively generate the missing surface points and connections. A final connection walkthrough allows us to identify the planar contours for each face of the polyhedron. Implementation details and results with synthetic and real data are presented.
225 citations
TL;DR: The results demonstrate that the complex of deep brain structures shows a statistically significant shape difference between control and DS subjects, and the deformation-based modeling is able to classify subjects with very high specificity and sensitivity, thus showing important generalization capability even given a low sample size.
225 citations