Optimizing Partition Trees for Multi-Object Segmentation with Shape Prior

Emmanuel Maggiori 1, 2 Yuliya Tarabalka 1, 2 Guillaume Charpiat 3, 4
1 TITANE - Geometric Modeling of 3D Environments
CRISAM - Inria Sophia Antipolis - Méditerranée
3 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
4 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : A partition tree is a hierarchical representation of an image. Once constructed, it can be repeatedly processed to extract information. Multi-object multi-class image segmentation with shape priors is one of the tasks that can be efficiently done upon an available tree. The traditional construction approach is a greedy clustering based on color similarities. However, not considering higher level cues during the construction phase leads to trees that might not accurately represent the underlying objects in the scene, inducing mistakes in the later segmentation. We propose a method to optimize a tree based both on color distributions and shape priors. It consists in pruning and regrafting tree branches in order to minimize the energy of the best segmentation that can be extracted from the tree. Theoretical guarantees help reducing the search space and make the optimization efficient. Our experiments show that we succeed in incorporating shape information to restructure a tree, which in turn enables to extract from it good quality multi-object segmentations with shape priors.
Document type :
Conference papers
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download

https://hal.inria.fr/hal-01182776
Contributor : Emmanuel Maggiori <>
Submitted on : Monday, August 3, 2015 - 2:34:23 PM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM
Long-term archiving on : Wednesday, November 4, 2015 - 10:22:37 AM

File

BMVC2015_Maggiori.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01182776, version 1

Citation

Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat. Optimizing Partition Trees for Multi-Object Segmentation with Shape Prior. 26th British Machine Vision Conference, Sep 2015, Swansea, United Kingdom. ⟨hal-01182776⟩

Share

Metrics

Record views

709

Files downloads

628