• CVPR 2007 Learning to detect a salient object


    Dataset: MSRA A&B are introduced in this paper.

    A conditional Random Field based method was proposed as

    where 

    with K features contributing to the first term and a pairwise features being the second.

    The pairwise is learning-free. 

    a_x is the label of pixel x indicating whether it is salient, d_(x, x') is the L2 norm of the color difference. beta is a robust parameter that weights the color contrast., where <.> is the expectation operator.

    NOW let me introduce the three features used in the first term of the obove equation(E(A|I)) that are allowed for learning. The inference detail of learning process can be found in the original paper and is excluded in this blog.

     

    1. Multi-scale contrast

    where I^l is the lth-level image in the pyramid and the number of pyramid levels L is 6. N(x) is a 9*9 window. The feature map is normalized to [0,1]

     2. Center-surround histogram

    We measure the distance between two rectangles R(the center area) and R_s(the surrounding rectangle, with the same area of R) in RGB color space.

     

    By varying rectangle size([0.1,0.7]*min(w,h)) and aspect ratios({0.5,0.75,1.0,1.5,2.0}), we find the most distinct rectangle R^*(x) centered at each pixel x.

    Then the center-surround histogram feature f_h(x,I) is defined as a sum of spatially weighted disances:

     

     3. Color spatial-distribution

    The wider a color is distributed in the image, the less possible a salient object contains this color.

    First all colors in the image are represented by GMMs, thus each pixel is assigned to a color component with a probability.

     Then the horizontal and vertical variance are calculated respectively and summed up as the color variance. This variance is then used as a weight to get a weighted sum and the final spatial-variance feature is obtained. 

    (Pictures are alwayse pasted unsuccessfully, so please turn to the author's paper when you need the detailed equations.)

    一叶浮萍归大海,人生何处不相逢
  • 相关阅读:
    arrayObj.splice(start, deleteCount, [item1[, item2[, . . . [,itemN]]]])
    运算符 ||
    ajax 本地测试,使用Chrome 浏览器
    js set
    js get 传参 汉字 乱码问题
    删除对象中的key
    html 返回页面顶部
    js 设置回车事件
    盘面,盘口
    ST股
  • 原文地址:https://www.cnblogs.com/guanyu-zuike/p/6224097.html
Copyright © 2020-2023  润新知