Loading...
Loading...

Go to the content (press return)

From local occlusion cues to global monocular depth estimation

Author
Palou, G.; Salembier, P.
Type of activity
Presentation of work at congresses
Name of edition
2012 IEEE International Conference on Acoustics, Speech, and Signal Processing
Date of publication
2012
Presentation's date
2012-03-14
Book of congress proceedings
2012 IEEE International Conference on Acoustics, Speech, and Signal Processing: March 25–30, 2012, Kyoto, Japan
First page
793
Last page
796
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
DOI
https://doi.org/10.1109/ICASSP.2012.6288003 Open in new window
Repository
http://hdl.handle.net/2117/18317 Open in new window
URL
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6288003 Open in new window
Abstract
In this paper, we propose a system to obtain a depth ordered seg- mentation of a single image based on low level cues. The algorithm first constructs a hierarchical, region-based image representation of the image using a Binary Partition Tree (BPT). During the building process, T-junction depth cues are detected, along with high convex boundaries. When the BPT is built, a suitable segmentation is found and a global depth ordering is found using a probabilistic framework. Results are compared wit...
Citation
Palou, G.; Salembier, P. From local occlusion cues to global monocular depth estimation. A: IEEE International Conference on Acoustics, Speech, and Signal Processing. "2012 IEEE International Conference on Acoustics, Speech, and Signal Processing: March 25–30, 2012, Kyoto, Japan". Kyoto: Institute of Electrical and Electronics Engineers (IEEE), 2012, p. 793-796.
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants