Title :
Dense depth recovery based on adaptive image segmentation
Author :
Shangli Liang ; Chun Yuan
Author_Institution :
Dept. of Comput. Sci. & Technol., Tsinghua Univ., Shenzhen, China
Abstract :
Stereoscopic vision has been a hot research topic in recent years. As one of the most important steps for 3D reconstruction from image sequences, dense depth recovery has attracted much attention in computer vision recently. A lot of efficient algorithms based on stereo matching have been proposed. But the difficulties in depth recovery are not overcome completely yet. In this paper, we aim at the main problems of depth recovery and propose our solutions. And an effective approach for dense depth recovery based on adaptive image segmentation is also presented. Experiments show that accurate depth results can be achieved through the proposed approach.
Keywords :
computer graphics; computer vision; image matching; image reconstruction; image segmentation; image sequences; stereo image processing; 3D reconstruction; adaptive image segmentation; computer vision; dense depth recovery; image sequences; stereo matching; stereoscopic vision; Cameras; Computer vision; Estimation; Image reconstruction; Image segmentation; Minimization; Stereo vision; Belief Propagation; Camera Self-calibration; Depth Recovery; Scene Reconstruction;
Conference_Titel :
ICCE-China Workshop (ICCE-China), 2013 IEEE
Conference_Location :
Shenzhen
Print_ISBN :
978-1-4799-0319-1
DOI :
10.1109/ICCE-China.2013.6780863