Optimal View Path Planning for Visual SLAM

Summary, in English

In experimental design and 3D reconstruction it is desirable to minimize the number of observations required to reach a prescribed estimation accuracy. Many approaches in the literature attempt to find the next best view from which to measure, and iterate this procedure. This paper discusses a continuous optimization method for finding a whole set of future imaging locations which minimize the reconstruction error of observed geometry along with the distance traveled by the camera between these locations. A computationally efficient iterative algorithm targeted toward application within real-time SLAM systems is presented and tested on simulated data.

• Författare: Sebastian Haner; Anders Heyden
• Redaktör: Anders Heyden; Fredrik Kahl
• Avdelning/ar: Matematik LTH; Mathematical Imaging Group; ELLIIT: the Linköping-Lund initiative on IT and mobile communication; eSSENCE: The e-Science Collaboration
• Publiceringsår: 2011
• Språk: Engelska
• Sidor: 370-380
• Publikation/Tidskrift/Serie: Lecture Notes in Computer Science
• Volym: 6688
• Länkar: http://dx.doi.org/10.1007/978-3-642-21227-7_35
• Dokumenttyp: Konferensbidrag
• Förlag: Springer
• Ämne: Computer Vision and Robotics (Autonomous Systems); Mathematics
• Nyckelord: Next best view planning; path optimization; SLAM
• Conference name: 17th Scandinavian Conference on Image Analysis (SCIA 2011)
• Conference date: 2011-05-23 - 2011-05-27
• Conference place: Ystad, Sweden
• Status: Published
• Forskningsgrupp: Mathematical Imaging Group
• ISBN/ISSN/Övrigt: ISSN: 1611-3349; ISSN: 0302-9743; ISBN: 978-3-642-21227-7 (online); ISBN: 978-3-642-21226-0 (print)