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.

This contribution focuses on the recognition of a priori known 3-D objects in single 2-D images. The underlying model is embedded in the domain of CAD-based vision using a viewer-centered approach to generate a set of normalized views. They serve as a basis for an optimal selection of properties of features. The idea of an aspect is used for grouping the values of the properties into aspect-trees. The aim of this approach is to identify fast the correct view of an object seen in the image and thereby to distinguish between different objects. Various experiments with different objects and under stepwise varied conditions clearly demonstrate the robustness of this approach and its ability of recognizing 3-D objects.