Title :
Indoor Structure Understanding from Single 360 Cylindrical Panoramic Image
Author :
Hao Yang ; Hui Zhang
Author_Institution :
Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
Abstract :
We address the problem of room structure recognition from a 360 cylindrical panorama. The proposed approach first transforms the original panorama into four perspective projected sub-images, then predicts the final layout based on a holistic parameterization framework via candidate evaluation using a linear scoring function, whose weights are trained on a normal indoor image data set. Experiments show that the proposed algorithm is capable of producing reasonable predictions which can be used for further applications such as 3D reconstruction.
Keywords :
object recognition; candidate evaluation; cylindrical panoramic image; holistic parameterization framework; indoor structure understanding; linear scoring function; normal indoor image data set; perspective projected subimages; room structure recognition; Computer vision; Conferences; Educational institutions; Layout; Partitioning algorithms; Periodic structures; Prediction algorithms; 360 cylindrical panorama; indoor structure recognition;
Conference_Titel :
Computer-Aided Design and Computer Graphics (CAD/Graphics), 2013 International Conference on
Conference_Location :
Guangzhou
DOI :
10.1109/CADGraphics.2013.77