Björn Krebs

A task driven 3D object recognition system using Bayesian networks

In this paper we propose a general framework to build a task oriented 3D object recognition system for CAD based vision (CBV). Features from 3D space curves representing the objects rims provide sufficient information to allow identification and pose estimation of industrial CAD models. However, features relying on differential surface properties tend to be very vulnerable with respect to noise. To model the statistical behavior of the data we introduce Bayesian nets which model the relationship between objects and observable features. Furthermore, task oriented selection of the optimal action to reduce the uncertainty of recognition results is incorporated into the Bayesian nets. This enables the integration of intelligent recognition strategies depending on the already acquired evidence into a robust, and efficient, 3D CAD based recognition system.

A fuzzy ICP algorithm for 3D free-form object recognition

We propose a new object matching algorithm which can separate overlapping objects and which is robust against erroneous data. The algorithm is based on the well-known iterative closest point (ICP) algorithm. However all published contributions to the ICP algorithm can not provide a proper segmentation of the input data. A fuzzy ICP algorithm can handle these problems by a fuzzy membership valuation at each iteration level. Furthermore, we introduce an evidence accumulation algorithm which allows a determination of the best match. In combination with search routines for the most common CAD models we provide powerful and efficient tools for CAD based object recognition systems.

3D B-spline curve matching for model based object recognition

Introducing general CAD descriptions in object recognition systems has become a major field of research called CAD based vision (CBV). However, the major problem using free-form object descriptions is how to define recognizable features which can be extracted from sensor data. We propose new methods for the extraction of 3D space carves from CAD models and from range data. Object identification is performed by correlating feature vectors from significant subcurves.

Handling Uncertainty in 3D Object Recognition Using Bayesian Networks

In this paper we show how the uncertainty within a 3d recognition process can be modeled using Bayesian nets. Reliable object features in terms of object rims are introduced to allow a robust recognition of industrial free-form objects. Dependencies between observed features and the objects are modeled within the Bayesian net. An algorithm to build the Bayesian net from a set of CAD models is introduced. In the recognition, entering evidence into the Bayesian net reduces the set of possible object hypotheses. Furthermore, the expected change of the joint probability distribution allows an integration of decision reasoning in the Bayesian propagation. The selection of the optimal, next action is incorporated into the Bayesian nets to reduce the uncertainty.

A Bayesian Network for 3D Object Recognition in Range Data

Introducing general CAD descriptions in object recognition systems has become a major field of research called CAD based vision (CBV). However, the major problem using free-form object descriptions is how to define recognizable features which can be extracted from sensor data. In this paper we propose new methods for an extraction of 3d space curves from CAD models and from range data. Object identification is performed by correlating feature vectors from significant subcurves. However, features relying on differential surface properties tend to be very vulnerable with respect to noise. To cope with erroneous data we propose to model the statistical behavior of the features using a Bayesian network. Thus, providing a robust and powerful CAD based 3d object recognition system.

Automatic generation of Bayesian nets for 3D object recognition

This paper proposes a general framework to build 3D object recognition systems from a set of CAD object definitions. Reliable features from object corners, edges and 3D rim curves are introduced; they provide sufficient information to allow identification and pose estimation of CAD designed industrial parts. The statistical properties of the data, caused by noise, is modeled by means of Bayesian nets, representing the relations between objects and observable features. This allows to identify objects by a combination of several features considering the significance of each single feature with respect to the object model base. On this basis robust and powerful 3D CAD based object recognition systems can be built.

Correct 3D Matching via a Fuzzy ICP Algorithm for Arbitrary Shaped Objects

We propose a new object matching algorithm which can separate overlapping objects and which is robust against erroneous data. The algorithm is based on the well-known ICP (Iterative Closest Point) algorithm. However, all published contributions to the ICP algorithm can’t provide a proper segmentation of the input data. A Fuzzy ICP algorithm can handle these problems by a fuzzy membership valuation at each iteration level. Furthermore, we introduce an evidence accumulation algorithm which allows a determination of the best match.

Erkennung und Bestimmung der aktuellen Konstellation von Objekten mit Scharniergelenken

Es wird ein Konzept zur modellbasierten Erkennung und Konstellationsbestimmung von Scharniersystemen vorgestellt. Scharniersysteme bestehen aus mehreren starren Einzelkomponenten, die durch Gelenke mit einem rotatorischen Freiheitsgrad verbunden sind. Zuerst wird bezuglich des festen Referenzmodells die Bewegungsfreiheit eines jeden Scharniers eines Scharniersystems erlernt. Da das Lernen wie auch das Erkennen der Scharnierarten aufgrund desselben Sensors erfolgt, erhalt man wahrend der Lernphase eine vollstandige Beschreibimg des Scharniersystems, die auch implizite Informationen uber Fertigungs- und Sensorungenauigkeiten enthalt. In einer anschliesenden Erkennungsphase konnen die erlernten Scharniersysteme in behebigen Szenen detektiert werden und ihre aktuellen Konstellationen bestimmt werden.

Integration of Multiple Feature Detection by a Bayesian Net for 3D Object Recognition

This paper proposes a general framework to build a 3d object recognition system from a set of CAD object definitions. Various, reliable features from object corners, edges and 3d rim curves are introduced which provide sufficient information to allow identification and pose estimation of CAD designed industrial parts. As features relying on differential surface properties tend to be very vulnerable with respect to noise, we model the statistical behavior of the data by means of Bayesian nets, representing the relations between objects and observable features. This allows to identify objects by a combination of several features considering the significance of each single feature with respect to the object model base. On this basis robust and powerful 3d CAD based object recognition systems can be build.

Plausibilistic Preprocessing of Sparse Range Images

Range image interpretation often suffers from contaminating noise and sparseness of the input data. Non-Gaussian errors occur if the physical conditions in the scene violate sensor restrictions. To deal with such drawbacks we present a new approach for range image preprocessing. To provide dense range information initial sparse data is augmented via appropriate interpolation. Furthermore, we propose a measure of plausibility which depends on the density of the initial data to judge the result of the interpolation.