Object Recognition and Scene Analysis

Recognition

The general problem of recognition from stereo processing, laser scanning, or ordinary image data provides basic environmental information for a robot to act autonomously. Results may be the identity and pose of known objects or object parts in possibly cluttered scenes, as well as grasp points or other generic affordances of objects from a known class.

Related publications:

Ulrich Hillenbrand. Pose clustering from stereo data. Proceedings VISAPP International Workshop on Robotic Perception – RoboPerc 2008, pp. 23-32.

Ulrich Hillenbrand. Consistent parameter clustering: definition and analysis. Pattern Recognition Letters 28 (2007), pp. 1112-1122.

Christoph Borst, Christian Ott, Thomas Wimböck, Bernhard Brunner, Franziska Zacharias, Berthold Bäuml, Ulrich Hillenbrand, Sami Haddadin, Alin Albu-Schäffer, and Gerd Hirzinger. A humanoid upper-body system for two-handed manipulation. Video Proceedings IEEE International Conference on Robotics and Automation – ICRA 2007, DVD. (Best Video Award)

Eric Wahl. Rapid histogram-based scene interpretation in three-dimensional surface point clouds. Doctoral thesis, Technische Universität München, 2007, http://mediatum2.ub.tum.de/doc/625116/document.pdf.

Christian Ott, Oliver Eiberger, Werner Friedl, Berthold Bäuml, Ulrich Hillenbrand, Christoph Borst, Alin Albu-Schäffer, Bernhard Brunner, Heiko Hirschmüller, Simon Kielhöfer, Rainer Konietschke, Michael Suppa, Thomas Wimböck, Franziska Zacharias, and Gerd Hirzinger. A humanoid two-arm system for dexterous manipulation. Proceedings IEEE-RAS International Conference on Humanoid Robots – Humanoids 2006, pp. 276-283.

Christian Ott, Christoph Borst, Ulrich Hillenbrand, Bernhard Brunner, Berthold Bäuml, and Gerd Hirzinger. The Robutler: towards service robots for the human environment. Video Proceedings IEEE International Conference on Robotics and Automation – ICRA 2005, DVD. (Finalist for the Video Award)

Eric Wahl and Gerd Hirzinger. A method for fast search of variable regions on dynamic 3D point clouds. Proceedings Annual meeting of the German Association for Pattern Recognition – DAGM 2005.

Eric Wahl and Gerd Hirzinger. Local point cloud analysis for rapid scene interpretation. Proceedings Annual meeting of the German Association for Pattern Recognition – DAGM 2005.

Ulrich Hillenbrand and Roberto Lampariello. Motion and parameter estimation of a free-floating space object from range data for motion prediction. Proceedings International Symposium on Artificial Intelligence, Robotics and Automation in Space – iSAIRAS 2005, CD.

Ulrich Hillenbrand. On the relation between probabilistic inference and fuzzy sets in visual scene analysis. Pattern Recognition Letters 25 (2004), pp. 1691-1699.

Ulrich Hillenbrand, Christian Ott, Bernhard Brunner, Christoph Borst, and Gerd Hirzinger. Towards service robots for the human environment: the Robutler. Proceedings Mechatronics & Robotics – MechRob 2004, pp. 1497-1502.

Ulrich Hillenbrand, Bernhard Brunner, Christoph Borst, and Gerd Hirzinger. The Robutler: a vision-controlled hand-arm system for manipulating bottles and glasses. Proceedings International Symposium on Robotics – ISR 2004, CD.

Eric Wahl, Ulrich Hillenbrand, and Gerd Hirzinger. Surflet-pair-relation histograms: a statistical 3D-shape representation for rapid classification. Proceedings International Conference on 3-D Digital Imaging and Modeling – 3DIM 2003, IEEE Computer Society Press, pp. 474-481.

Ulrich Hillenbrand and Gerd Hirzinger. Probabilistic search for object segmentation and recognition. Proceedings European Conference on Computer Vision – ECCV 2002, Lecture Notes in Computer Science Vol. 2352, Springer, pp. 791-806.

Ulrich Hillenbrand and Gerd Hirzinger. Object recognition and pose estimation from 3D geometric relations. Proceedings International Conference on Knowledge-Based Intelligent Engineering Systems & Allied Technologies – KES 2000, IEEE, pp. 113-116.

Patrick Wunsch. Modellbasierte 3-D Objektlageschätzung für visuell geregelte Greifvorgänge in der Robotik. Shaker Verlag, Aachen (Germany), 1998.

A Probabilistic Hypothesize-and-Test Paradigm (2004)

Model-based object recognition or, more generally, scene interpretation may be conceptualized as a two-part process: one that generates a sequence of hypotheses on object identities and poses, the other that evaluates them based on the object models. Viewed as an optimization problem, the former is concerned with the search sequence, the latter with the objective function.

Pose-Invariant Object Recognition (2004)

Robust scene interpretation by means of machine vision is a key factor in various new applications in robotics. Part of this problem is the efficient recognition and classification of previously known three-dimensional (3D) shapes in arbitrary scenes. So far, heavily constrained conditions have been utilized, or otherwise solutions have not been achieved in real time.

Analyzing Scenes on a Supporting Plane (2004)

Suppose we constrain objects from a known set to stand in certain `upright' poses on a supporting plane, for instance, chairs and tables on the floor, or glasses and bottles on a table. The orientation of such planes is often known, as for a mobile robot in flat terrain.