Name
Abstract | ||
|---|---|---|
In this paper, we propose a saliency detection model for RGB-D images based on the contrasting features of colour and depth with a generative mixture model. The depth feature map is extracted based on superpixel contrast computation with spatial priors. We model the depth saliency map by approximating the density of depth-based contrast features using a Gaussian distribution. Similar to the depth saliency computation, the colour saliency map is computed using a Gaussian distribution based on multi-scale contrasts in superpixels by exploiting low-level cues. By assuming that colour-and depth-based contrast features are conditionally independent, given the classes, a discriminative mixed-membership naive Bayes (DMNB) model is used to calculate the final saliency map from the depth saliency and colour saliency probabilities by applying Bayes' theorem. The Gaussian distribution parameter can be estimated in the DMNB model by using a variational inferencebased expectation maximization algorithm. The experimental results on a recent eye tracking database show that the proposed model performs better than other existing models. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1007/978-3-319-54193-8_2 | COMPUTER VISION - ACCV 2016, PT V |
Field | DocType | Volume |
Computer vision,Naive Bayes classifier,Pattern recognition,Computer science,Salience (neuroscience),Expectation–maximization algorithm,Gaussian,Artificial intelligence,Prior probability,Discriminative model,Mixture model,Generative model | Conference | 10115 |
ISSN | Citations | PageRank |
0302-9743 | 2 | 0.39 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Song-Tao Wang | 1 | 2 | 0.39 |
| Zhen Zhou | 2 | 30 | 12.87 |
| Han-Bing Qu | 3 | 4 | 1.79 |
| Bin Li | 4 | 2 | 0.39 |