Segmenting Salient Objects from Images and Videos. Rahtu, E., Kannala, J., Salo, M., & Heikkilä, J. In Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, volume 6315 LNCS, pages 366-379, 2010. Springer, Berlin, Heidelberg.
Segmenting Salient Objects from Images and Videos [link]Website  abstract   bibtex   
In this paper we introduce a new salient object segmentation method, which is based on combining a saliency measure with a conditional random field (CRF) model. The proposed saliency measure is formulated using a statistical framework and local feature contrast in illumination, color, and motion information. The resulting saliency map is then used in a CRF model to define an energy minimization based segmentation approach, which aims to recover well-defined salient objects. The method is efficiently implemented by using the integral histogram approach and graph cut solvers. Compared to previous approaches the introduced method is among the few which are applicable to both still images and videos including motion cues. The experiments show that our approach outperforms the current state-of-the-art methods in both qualitative and quantitative terms.
@inproceedings{
 title = {Segmenting Salient Objects from Images and Videos},
 type = {inproceedings},
 year = {2010},
 identifiers = {[object Object]},
 keywords = {Saliency measure,background subtraction,segmentation},
 pages = {366-379},
 volume = {6315 LNCS},
 issue = {PART 5},
 websites = {http://link.springer.com/10.1007/978-3-642-15555-0_27},
 publisher = {Springer, Berlin, Heidelberg},
 id = {b8f0311f-8c2c-3bf0-a92f-8510c371bf0f},
 created = {2019-09-15T16:34:27.416Z},
 file_attached = {false},
 profile_id = {bddcf02d-403b-3b06-9def-6d15cc293e20},
 last_modified = {2019-09-16T06:40:23.719Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 source_type = {CONF},
 private_publication = {false},
 abstract = {In this paper we introduce a new salient object segmentation method, which is based on combining a saliency measure with a conditional random field (CRF) model. The proposed saliency measure is formulated using a statistical framework and local feature contrast in illumination, color, and motion information. The resulting saliency map is then used in a CRF model to define an energy minimization based segmentation approach, which aims to recover well-defined salient objects. The method is efficiently implemented by using the integral histogram approach and graph cut solvers. Compared to previous approaches the introduced method is among the few which are applicable to both still images and videos including motion cues. The experiments show that our approach outperforms the current state-of-the-art methods in both qualitative and quantitative terms.},
 bibtype = {inproceedings},
 author = {Rahtu, Esa and Kannala, Juho and Salo, Mikko and Heikkilä, Janne},
 booktitle = {Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science}
}

Downloads: 0