This paper proposes a system that relates objects in an image using
occlusion cues and arranges them according to depth. The system does
not rely on a priori knowledge of the scene structure and focuses
on detecting special points, such as T-junctions and highly convex
contours, to infer the depth relationships between objects in the
scene. The system makes extensive use of the Binary Partition Tree
(BPT) as hierarchical region-based image representation jointly with
a new approach for candidate T-junction estimation. Since some regions
may not involve T-junctions, occlusion is also detected by examining
convex shapes on region boundaries. Combining T-junctions and convexity
leads to a system which only relies on low level depth cues and does
not rely on semantic information. However, it shows a similar or
better performance with the state of the art while not assuming any
type of scene. As an extension of the automatic depth ordering system,
a semiautomatic approach is also proposed. If the user provides the
depth order for a subset of regions in the image, the system is able
to easily integrate this user information to the final depth order
for the complete image. For some applications, user interaction can
naturally be integrated, improving the quality of the automatically
generated depth map.
:Users/guillem/Documents/Doctorat/Bibliografia/articles/Palou, Salembier\_2013\_Monocular Depth Ordering Using T-junctions and Convexity Occlusion Cues.pdf:pdf
%0 Journal Article
%1 Palou2013
%A Palou, G
%A Salembier, P
%D 2013
%J IEEE Trans. on Image Proc.
%K imported
%R 10.1109/TIP.2013.2240002
%T Monocular Depth Ordering Using T-junctions and Convexity Occlusion
Cues.
%U http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6410421&contentType=Early+Access+Articles&matchBoolean=true&searchField=Search\_All&queryText=(palou+monocular)
%X This paper proposes a system that relates objects in an image using
occlusion cues and arranges them according to depth. The system does
not rely on a priori knowledge of the scene structure and focuses
on detecting special points, such as T-junctions and highly convex
contours, to infer the depth relationships between objects in the
scene. The system makes extensive use of the Binary Partition Tree
(BPT) as hierarchical region-based image representation jointly with
a new approach for candidate T-junction estimation. Since some regions
may not involve T-junctions, occlusion is also detected by examining
convex shapes on region boundaries. Combining T-junctions and convexity
leads to a system which only relies on low level depth cues and does
not rely on semantic information. However, it shows a similar or
better performance with the state of the art while not assuming any
type of scene. As an extension of the automatic depth ordering system,
a semiautomatic approach is also proposed. If the user provides the
depth order for a subset of regions in the image, the system is able
to easily integrate this user information to the final depth order
for the complete image. For some applications, user interaction can
naturally be integrated, improving the quality of the automatically
generated depth map.
@article{Palou2013,
abstract = {This paper proposes a system that relates objects in an image using
occlusion cues and arranges them according to depth. The system does
not rely on a priori knowledge of the scene structure and focuses
on detecting special points, such as T-junctions and highly convex
contours, to infer the depth relationships between objects in the
scene. The system makes extensive use of the Binary Partition Tree
(BPT) as hierarchical region-based image representation jointly with
a new approach for candidate T-junction estimation. Since some regions
may not involve T-junctions, occlusion is also detected by examining
convex shapes on region boundaries. Combining T-junctions and convexity
leads to a system which only relies on low level depth cues and does
not rely on semantic information. However, it shows a similar or
better performance with the state of the art while not assuming any
type of scene. As an extension of the automatic depth ordering system,
a semiautomatic approach is also proposed. If the user provides the
depth order for a subset of regions in the image, the system is able
to easily integrate this user information to the final depth order
for the complete image. For some applications, user interaction can
naturally be integrated, improving the quality of the automatically
generated depth map.},
added-at = {2013-09-29T14:16:50.000+0200},
author = {Palou, G and Salembier, P},
biburl = {https://www.bibsonomy.org/bibtex/2511bd9384df3c0e9b2b63190cc247ef7/guillem.palou},
doi = {10.1109/TIP.2013.2240002},
file = {:Users/guillem/Documents/Doctorat/Bibliografia/articles/Palou, Salembier\_2013\_Monocular Depth Ordering Using T-junctions and Convexity Occlusion Cues.pdf:pdf},
interhash = {8b994b7c7f2864f4b61f52bc84dcc972},
intrahash = {511bd9384df3c0e9b2b63190cc247ef7},
issn = {1941-0042},
journal = {IEEE Trans. on Image Proc.},
keywords = {imported},
pmid = {23335666},
timestamp = {2013-09-29T14:16:50.000+0200},
title = {{Monocular Depth Ordering Using T-junctions and Convexity Occlusion
Cues.}},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=\&arnumber=6410421\&contentType=Early+Access+Articles\&matchBoolean=true\&searchField=Search\_All\&queryText=(palou+monocular)},
year = 2013
}