Abstract | ||
---|---|---|
In this paper we present a framework to recognize objects and to determine their pose from a set of objects in a scene for automatic manipulation (bin picking) using pixel-synchronous range and intensity images. The approach uses three-dimensional object models. The object identification and pose estimation process is structured into three stages. The first stage is the feature collection stage, where the feature detection is performed in an area of interest followed by the hypothesis generation, which tries to form hypotheses from consistent features. The last stage, the hypothesis verification, tries to evaluate the hypotheses by comparing the measured range data to the predicted range data from hypothesis and the model. |
Year | DOI | Venue |
---|---|---|
2001 | 10.1007/3-540-44690-7_7 | RobVis |
Keywords | Field | DocType |
measured range data,automatic manipulation,object identification,hypothesis verification,feature collection stage,pose estimation,feature detection,hypothesis generation,range data,consistent feature,pixel-synchronous range,last stage,three dimensional | Computer vision,Bin picking,Feature detection,Computer science,3D pose estimation,Pose,Artificial intelligence,Three dimensional model,Hypothesis verification,Area of interest,Cognitive neuroscience of visual object recognition | Conference |
ISBN | Citations | PageRank |
3-540-41694-3 | 0 | 0.34 |
References | Authors | |
5 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Benjamin Hohnhaeuser | 1 | 0 | 0.34 |
Günter Hommel | 2 | 657 | 134.35 |