Title :
Recovering Depth from a Single Image Using Dark Channel Prior
Author :
Zou, Chengming ; Chen, Jinrui
Author_Institution :
Sch. of Comput. Sci., Wuhan Univ. of Technol., Wuhan, China
Abstract :
It is well known that depth can be recovered from a single image using defogging method. Inspiriting by the idea of defogging using dark channel prior, we propose a new approach to recover depth. The input is a foggy image. We defog the image using an improved dark channel prior method. We adopt the dilating and eroding method to refine the block effect. Experimental results show that our method can recover an accuracy depth from a single image.
Keywords :
computer vision; image reconstruction; block effect; computer vision; dark channel prior method; defogging method; depth recovery; dilating method; eroding method; single image; Cameras; Computer science; Degradation; Differential equations; Layout; Light scattering; Nonlinear equations; Particle scattering; Shape; Solid modeling; dark channel prior; defog; depth; dilate; erode;
Conference_Titel :
Software Engineering Artificial Intelligence Networking and Parallel/Distributed Computing (SNPD), 2010 11th ACIS International Conference on
Conference_Location :
London
Print_ISBN :
978-1-4244-7422-6
Electronic_ISBN :
978-1-4244-7421-9
DOI :
10.1109/SNPD.2010.24