期刊
COMPUTER VISION - ECCV 2014, PT III
卷 8691, 期 -, 页码 92-109出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-319-10578-9_7
关键词
-
类别
资金
- 973 Basic Research Program of China [2014CB349303]
- National 863 High-Tech RAMP
- D Program of China [2012AA012503, 2012AA012504]
- National Nature Science Foundation of China [61370038, 61202327, 61303086]
- Natural Science Foundation of Beijing [4121003]
- Fundamental Research Funds for the Central Universities [2013121026]
- Guangdong Natural Science Foundation [S2012020011081]
Although depth information plays an important role in the human vision system, it is not yet well-explored in existing visual saliency computational models. In this work, we first introduce a large scale RGBD image dataset to address the problem of data deficiency in current research of RGBD salient object detection. To make sure that most existing RGB saliency models can still be adequate in RGBD scenarios, we continue to provide a simple fusion framework that combines existing RGB-produced saliency with new depth-induced saliency, the former one is estimated from existing RGB models while the latter one is based on the proposed multi-contextual contrast model. Moreover, a specialized multi-stage RGBD model is also proposed which takes account of both depth and appearance cues derived from low-level feature contrast, mid-level region grouping and high-level priors enhancement. Extensive experiments show the effectiveness and superiority of our model which can accurately locate the salient objects from RGBD images, and also assign consistent saliency values for the target objects.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据