Identification and localization of task-relevant objects is an essential problem for advanced service robots. We integrate state-of-the-art techniques both for object identification and object localization to solve this problem. Based on a multilevel spatial representation architecture, our approach integrates methods for mapping, self-localization and spatial reasoning for navigation with visu...

In this paper we extend a recent approach for 3D object recognition in order to deal with rotationally symmetric objects, which are frequent in daily environments. We base our work in a recent method that represents objects using a hash table of shape features, which in the case of symmetric objects contains redundant information. We propose a way to remove redundant features by adding a weight...

This paper proposes a novel approach that detects and tracks carried objects by modelling the person-carried object relationship that is characteristic of the carry event. In order to detect a generic class of carried objects, we propose the use of geometric shape models, instead of using pre-trained object class models or solely relying on protrusions. In order to track the carried objects, we...

Often, a data object described by many features can be naturally decomposed into multiple “views”, where each view consists of a subset of features. For example, a video clip may have a video view and an audio view. Given a set of training data objects with multiple views, where some objects are labeled and the others are not, semi-supervised learning with graphs from multi-views tries to learn...

This paper introduces an original method to perform augmented or mixed reality on deformable objects. Compared to state-of-the-art techniques, our method is able to track deformations of volumetric objects and not only surfacic objects. A flexible framework that relies on the combination of a 3D motion estimation and a physicsbased deformable model used as a regularization and interpolation ste...

Robust real time object pose tracking is an essential component for robotic applications as well as for the growing field of augmented reality. Currently available systems are typically either optimized for textured objects or for uniformly colored objects. The proposed approach combines complementary interest points in a common tracking framework which allows to handle a broad variety of objec...

In this paper we discuss a the support of users in adding spatial information semi-automatically to annotations of images. Descriptions of objects depicted in an image are extended with information about the position of those objects. We distinguish two types of spatial concepts: absolute positions of objects (e.g., east, west) and relative spatial relations between objects (e.g., left, above)....

Objects often occlude each other in scenes; Inferring their appearance beyond their visible parts plays an important role in scene understanding, depth estimation, object interaction and manipulation. In this paper, we study the challenging problem of completing the appearance of occluded objects. Doing so requires knowing which pixels to paint (segmenting the invisible parts of objects) and wh...

On the integration of www based information systems into the daily research and teaching practices of Art History departments. The online presentation of Art History departments in conventional HTML format is becoming a vital forum for the key research and teaching information. A www-project at the Art History department of the Humboldt University, Berlin shows the potential of how dynamically ...

We develop a 3D object detection algorithm that uses latent support surfaces to capture contextual relationships in indoor scenes. Existing 3D representations for RGB-D images capture the local shape and appearance of object categories, but have limited power to represent objects with different visual styles. The detection of small objects is also challenging because the search space is very la...