PublicaHier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.
View Planning for Unknown Indoor Scenes Based on a Cost Benefit Analysis
|Radig, B. ; Deutsche Arbeitsgemeinschaft für Mustererkennung -DAGM-:|
Pattern Recognition 2001. Proceedings 23rd DAGM Symposium : Munich, Germany, September 12 - 14, 2001 ; proceedings
Berlin: Springer, 2001 (Lecture Notes in Computer Science 2191)
|Deutsche Arbeitsgemeinschaft für Mustererkennung (Symposium) <23, 2001, München>|
| Conference Paper|
|Fraunhofer IGD ()|
| view planning; active vision; range image fusion; 3D reconstruction; modeling; autonomous exploration|
From the task of automatically reconstructing real world scenes using range images, the problem of planning the image acquisition arises. Although solutions for small objects in known environments are already available, these approaches lack scalability to large scenes and to a high number of degrees of freedom. In this paper, we present a new planning algorithm for initially unknown, large indoor environments. Using a surface representation of seen and unseen parts of the environment, we propose a method based on the analysis of occlusions. In addition to previous approaches, we take into account both a quality criterion and the cost of the next acquisition. Results are shown for two large indoor scenes - an artificial scene and a real world room - with numerous self occlusions.