In this paper, we propose an approach to accurately localize detected objects. The goal is to predict which features pertain to the object and define the object extent with segme...
We present a method for reconstructing a trajectory of an object moving in front of non-overlapping fully or partially calibrated cameras. The non-overlapping setup turns that pro...
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
The sliding window approach is the most widely used technique to detect faces in an image. Usually a classifier is applied on a regular grid and to speed up the scanning, the gri...
A convexhull H(S)of a 3Dset S is rarely used to accelerateinterferencedetection or as a substitutefor rendering small projection of S,because it typically has too many faces. An a...
A semi-automatic approach is presented that enables the generation of a high-quality 3D model of a static object from an image sequence that was taken by a moving, uncalibrated co...
Evaluation of object detection algorithms is a non-trivial task: a detection result is usually evaluated by comparing the bounding box of the detected object with the bounding box...
Abstract. In this paper we present an algorithm for 3-dimensional orthogonal graph drawing based on the movement of vertices from an initial layout along the main diagonal of a cub...
In this paper, we study the problem of the fast selection of video objects, as an aid for the efficient semi-automatic annotation of video programs. In a regular system, the user ...
We present new algorithms for labeling a set P of n points in the plane with labels that are aligned to the left of the bounding box of P. The points are connected to their labels ...
Marc Benkert, Herman J. Haverkort, Moritz Kroll, M...