Title :
Planar orientation from blur gradients in a single image
Author :
McCloskey, Scott ; Langer, Marco
Author_Institution :
Honeywell Labs., Golden Valley, MN, USA
Abstract :
We present a focus-based method to recover the orientation of a textured planar surface patch from a single image. The method exploits the relationship between the orientation of equifocal (i.e. uniformly-blurred) contours in the image and the plane´s tilt and slant angles. Compared to previous methods that determine planar orientation, we make fewer assumptions about the texture and remove the restriction that images must be acquired through a pinhole aperture. Our method estimates slant and tilt of an image patch in a single image, as compared to depth from defocus methods that require two or more input images. Experiments are performed using a large set of test images.
Keywords :
edge detection; image texture; blur gradients; focus-based method; image contours; image patch; planar orientation; textured planar surface patch; Apertures; Cameras; Computer vision; Focusing; Layout; Lenses; Optical sensors; Pixel; Shape; Testing;
Conference_Titel :
Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on
Conference_Location :
Miami, FL
Print_ISBN :
978-1-4244-3992-8
DOI :
10.1109/CVPR.2009.5206618