This paper presents an approach to the recognition of articulated 3D objects in monocular video images. A hierarchical object representation models objects as a composition of rigid components which are explicitly connected by specific kinematic constraints, e.g., rotational and/or translational joints. The recognition task follows this tree-like structure by first estimating the 3D pose of the static component (root) and afterwards determining the relative 3D pose of the remaining components recursively. This method limits the search space for the actual correspondences between image and model features and copes with the problem of self-occlusion. Experiments in the context of autonomous, mobile robots show the practicability of this approach.

The context of this contribution is the recognition and localization of a priori known 3D objects from single intensity images. The most difficult task is to establish appropriate correspondences between model and image features. The ranking of correspondences typically is based on properties of the features themselves as well as relations between the features. Useful relations can be derived from the topology of model features. This contribution focuses on the improvement of an existing object recognition system using binary topological constraints on model and image lines. A propagation mechanism decreases the impact of broken image lines on the underlying topological relations. Experiments with several objects show the usability of the proposed approach.

Canny (1983) presented criteria for measuring the quality of edge detectors and derived an optimal FIR-filter for step edges by optimizing them. Four years later Deriche proposed an approach to edge detection based on Canny's design utilizing IIR-filters which can be implemented very efficiently and recursively. Using the Deriche-filter leads to a distortion of the amplitudes of the edges depending on their direction. In this paper, it is shown that these distortions are systematic errors which can be eliminated by a simple modification of the edge detection procedure. Because of its obvious 'kinship' to the Deriche-filter the Shen-filter has been included in the investigations.>