Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Supervised Evaluation of the Quality of BinaryPartition Trees based on Uncertain Semantic Ground-Truth for Image Segmentation Purpose

Abstract: 

The binary partition tree (BPT) is a hierarchical data-structure that
models the content of an image in a multiscale way. In particular,
a cut of the BPT of an image provides a segmentation, as a partition
of the image support. Actually, building a BPT allows for
dramatically reducing the search space for segmentation purposes,
based on intrinsic (image signal) and extrinsic (construction metric)
information. A large literature has been devoted to the construction
on such metrics, and the associated choice of criteria (spectral, spatial,
geometric, etc.) for building relevant BPTs, in particular in the
challenging context of remote sensing. But, surprisingly, there exists
few works dedicated to evaluate the quality of BPTs, i.e. their
ability to further provide a satisfactory segmentation. In this paper,
we propose a framework for BPT quality evaluation, in a supervised
paradigm. Indeed, we assume that ground-truth segments
are provided by an expert, possibly with a semantic labelling and a
given uncertainty. Then, we describe local evaluation metrics, BPT
nodes / ground-truth segments fitting strategies, and global quality
score computation considering semantic information, leading to a
complete evaluation framework. This framework is illustrated in the
context of BPT segmentation of multispectral satellite images.

up
0 users have voted:

Paper Details

Authors:
Jimmy Francky Randrianasoa, Camille Kurtz, Pierre Ganc¸arski, Eric Desjardin, Nicolas Passat
Submitted On:
16 September 2017 - 1:37am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Tianatahina Jimmy Francky Randrianasoa
Paper Code:
2054
Document Year:
2017
Cite

Document Files

ICIP-2017-JF-Poster.pdf

(37 downloads)

Subscribe

[1] Jimmy Francky Randrianasoa, Camille Kurtz, Pierre Ganc¸arski, Eric Desjardin, Nicolas Passat, "Supervised Evaluation of the Quality of BinaryPartition Trees based on Uncertain Semantic Ground-Truth for Image Segmentation Purpose", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2174. Accessed: Dec. 18, 2017.
@article{2174-17,
url = {http://sigport.org/2174},
author = {Jimmy Francky Randrianasoa; Camille Kurtz; Pierre Ganc¸arski; Eric Desjardin; Nicolas Passat },
publisher = {IEEE SigPort},
title = {Supervised Evaluation of the Quality of BinaryPartition Trees based on Uncertain Semantic Ground-Truth for Image Segmentation Purpose},
year = {2017} }
TY - EJOUR
T1 - Supervised Evaluation of the Quality of BinaryPartition Trees based on Uncertain Semantic Ground-Truth for Image Segmentation Purpose
AU - Jimmy Francky Randrianasoa; Camille Kurtz; Pierre Ganc¸arski; Eric Desjardin; Nicolas Passat
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2174
ER -
Jimmy Francky Randrianasoa, Camille Kurtz, Pierre Ganc¸arski, Eric Desjardin, Nicolas Passat. (2017). Supervised Evaluation of the Quality of BinaryPartition Trees based on Uncertain Semantic Ground-Truth for Image Segmentation Purpose. IEEE SigPort. http://sigport.org/2174
Jimmy Francky Randrianasoa, Camille Kurtz, Pierre Ganc¸arski, Eric Desjardin, Nicolas Passat, 2017. Supervised Evaluation of the Quality of BinaryPartition Trees based on Uncertain Semantic Ground-Truth for Image Segmentation Purpose. Available at: http://sigport.org/2174.
Jimmy Francky Randrianasoa, Camille Kurtz, Pierre Ganc¸arski, Eric Desjardin, Nicolas Passat. (2017). "Supervised Evaluation of the Quality of BinaryPartition Trees based on Uncertain Semantic Ground-Truth for Image Segmentation Purpose." Web.
1. Jimmy Francky Randrianasoa, Camille Kurtz, Pierre Ganc¸arski, Eric Desjardin, Nicolas Passat. Supervised Evaluation of the Quality of BinaryPartition Trees based on Uncertain Semantic Ground-Truth for Image Segmentation Purpose [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2174