Unsupervised Joint Salient Region Detection and Object Segmentation

Wenbin Zou 1, * Zhi Liu 2, 3 Kidiyo Kpalma 4 Joseph Ronsin 4 Yong Zhao 5 Nikos Komodakis 6, 7
* Auteur correspondant
3 Sirocco - Analysis representation, compression and communication of visual data
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
7 IMAGINE [Marne-la-Vallée]
CSTB - Centre Scientifique et Technique du Bâtiment, LIGM - Laboratoire d'Informatique Gaspard-Monge, ENPC - École des Ponts ParisTech
Abstract : This paper presents a novel unsupervised algorithm to detect salient regions and to segment out foreground objects from background. In contrast to previous unidirectional saliency-based object segmentation methods, in which only the detected saliency map is used to guide the object segmentation, our algorithm mutually exploits detection/segmentation cues from each other. To achieve this goal, an initial saliency map is generated by the proposed segmentation driven low-rank matrix recovery model. Such a saliency map is exploited to initialize object segmentation model, which is formulated as energy minimization of Markov random field. Mutually, the quality of saliency map is further improved by the segmentation result, and serves as a new guidance for the object segmentation. The optimal saliency map and the final segmentation are achieved by jointly optimizing the defined objective functions. Extensive evaluations on MSRA-B and PASCAL-1500 datasets demonstrate that the proposed algorithm achieves the state-of-the-art performance for both the salient region detection and the object segmentation.
Type de document :
Article dans une revue
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2015, 24 (11), 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7159095&tag=1〉. 〈10.1109/TIP.2015.2456497〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01243552
Contributeur : Kidiyo Kpalma <>
Soumis le : mardi 15 décembre 2015 - 10:12:47
Dernière modification le : jeudi 5 juillet 2018 - 14:29:01

Identifiants

Citation

Wenbin Zou, Zhi Liu, Kidiyo Kpalma, Joseph Ronsin, Yong Zhao, et al.. Unsupervised Joint Salient Region Detection and Object Segmentation. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2015, 24 (11), 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7159095&tag=1〉. 〈10.1109/TIP.2015.2456497〉. 〈hal-01243552〉

Partager

Métriques

Consultations de la notice

898