CVPR 2011 Global contrast based salient region detection

Posted

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了CVPR 2011 Global contrast based salient region detection相关的知识,希望对你有一定的参考价值。

Two salient region detection methods are proposed in this paper: HC AND RC

HC: Histogram based contrast

1. Primary method

It is simply to calculate the saliency of each color in the input image, where each pixel‘s saliency is defined using its color contrast to all other pixels in the image in L*a*b space:

技术分享

The above equation can be expanded as,

技术分享

where N is the number of pixels. Therefore we can conclude that the same color have the same saliency, so saliency value for each color is,

技术分享

n is the number of distinct pixel colors, 技术分享 is the probability of the corresponding pixel color in the image I.

 

2. Speeding up strategy

To reduce the number of colors from 256^3 to 12^3 = 1728, and finally to n = 85 colors in this post. 

3. Color space smoothing

In order to reduce noisy saliency results caused by such randomness. We replace the saliency value of each color by the weighted average of the saliency values of similar colors. We choose m = n/4 nearsest colors to refine each color.

技术分享

See the original paper for the detail of this equation.

技术分享

 

 

RC: Region based contrast

1. Segment the input image into regions using [45](see the original paper)

2. Build the color histogram for each region

3. For a region r_k, we compute its saliency value by measuring its color contrast to all other regions in the image,

技术分享

where 技术分享 is the number of pixels of region r_i, designed to emphasize color contrast to bigger regions, and 

技术分享

f(c_k,i) is the probability of the i-th color among all n_k colors in the k-th region, used to emphasize the color differences between dominant colors.

4. Spatially weighted region contrast

We now can incorporate spatial information to the above equation to increase the effects of closer regions and decrease the farther ones.

技术分享

技术分享 is the spatial distance between the two regions. 技术分享controls the strength of spatial information, the bigger value make less effect of the close regions relatively, 技术分享 is a spatial prior weighting term similar to center bias.

 

 

5. Iteratively segmentation using graph-cut.

Dilation and erosion after each iteration. The region inside the eroded region is set to foreground, and the remaining areas are set to unknown.

 

技术分享

 However, the (f) is not understood...  ≡(▔﹏▔)≡

以上是关于CVPR 2011 Global contrast based salient region detection的主要内容,如果未能解决你的问题,请参考以下文章

CVPR2020:三维点云无监督表示学习的全局局部双向推理

compare contrast的区别

keras 演示代码 siamese_contrastive.py 保存和加载模型?

请问:SPSS中contrasts趋势检验结果怎么看

迁移学习(CDA)《CDA:Contrastive-adversarial Domain Adaptation 》

R 代码:model.matrix.default(mt, mf, contrasts) 中的错误:变量 1 没有级别