显著性检测之CVPR13（二）

《saliency detection via graph-based manifold ranking》

Abstract


      Most existing bottom-up methods measure the foreground saliency of a pixel or region based on its contrast within a local context or the entire image, whereas a few methods focus on segmenting out background regions and thereby salient objects. Instead of considering the contrast between the salient objects and their surrounding regions, we consider both foreground and background cues in a different way.  We rank the similarity of the image elements (pixels or regions) with foreground cues or background cues via graph-based manifold ranking. The saliency of the image elements is defined based on their relevances to the given seeds or queries. We represent the image as a close-loop graph with superpixels as nodes. These nodes are ranked based on the similarity to background and foreground queries, based on affinity matrices. Saliency detection is carried out in a two-stage scheme to extract background regions and foreground salient objects efficiently. Experimental results on two large benchmark databases demonstrate the proposed method performs well when against the state-of-the-art methods in terms of accuracy and speed. We also create a more difficult benchmark database containing 5,172 images to test the proposed saliency model and make this database publicly available with this paper for further studies in the saliency field.

本文的目的是：综合利用图像中背景、前景的先验位置分布及连通性，得到显著物体分割的更好结果。

采用的方法：利用图像边框大多是背景的先验信息，通过流行排序的方法将此先验扩散到并增加得到前景的比较可靠的估计；随后将前景的信息用类似的流行排序的方法加强，得到最终的显著性物体。

技术路线：SLIC图像过分割；构建相对应的图；背景先验的流行排序算法；自适应分割；前景上的流形排序算法

文章及code链接：http://faculty.ucmerced.edu/mhyang/project/cvpr13_saliency/cvprsaliency.htm(matlab)

https://github.com/yangchuancv/ranking_saliency(C++)

《Salient Object Detection: A Discriminative Regional Feature Integration Approach 》

Abstract

    Salient object detection has been attracting a lot of interest, and recently various heuristic computational models have been designed. In this paper, we regard saliency map computation as a regression problem. Our method, which is based on multi-level image segmentation, uses the supervised learning approach to map the regional feature vector to a saliency score, and finally fuses the saliency scores across multiple levels, yielding the saliency map. The contributions lie in two-fold. One is that we show our approach, which integrates the regional contrast, regional property and regional backgroundness descriptors together to form the master saliency map, is able to produce superior saliency maps to existing algorithms most of which combine saliency maps heuristically computed from different types of features. The other is that we introduce a new regional feature vector, backgroundness, to characterize the background, which can be regarded as a counterpart of the objectness descriptor. The performance evaluation on several popular benchmark data sets validates that our approach outperforms existing state-of-the-arts.

作者目的：利用监督性学习的方法，将多尺度分割得到的区域特征进行整合，得到最终的显著性物体。

解决方法：将图像进行多尺度分割；计算区域的显著性；多尺度显著性整合。

技术路线：基于图的过分割方法；区域的多特征描述（颜色，纹理，对比度及背景）

文章链接：http://people.cs.umass.edu/~hzjiang/projects/saliency_drfi/index.html（matlab）

https://github.com/playerkk/drfi_matlab（matlab）

《What Makes a Patch Distinct》

Abstract

What makes an object salient? Most previous work assert that distinctness is the dominating factor. The difference between the various algorithms is in the way they compute distinctness. Some focus on the patterns, others on the colors, and several add high-level cues and priors. We propose a simple, yet powerful, algorithm that integrates these three factors. Our key contribution is a novel and fast approach to compute pattern distinctness. We rely on the inner statistics of the patches in the image for identifying unique patterns. We provide an extensive evaluation and show that our approach outperforms all state-of-the-art methods on the five most commonly-used datasets.

作者目的：从图像模式与颜色区分度两个角度进行显著性检测

解决方案：利用图像块内部的统计信息度量图像块的模式；利用LAB颜色空间的差异度量颜色差别性

技术路线：利用PCA变换，度量图像块的模式差别

文章链接：http://cgm.technion.ac.il/Computer-Graphics-Multimedia/Software/DstnctSal/(matlab)

http://blog.csdn.net/zouxy09/article/details/8856490

http://www.slideserve.com/knox/what-makes-a-patch-distinct

《Exploiting Surroundedness for Saliency Detection: A Boolean Map Approach 》

这篇文章以稀疏表示分类（SRC）原理为基础，对分割图中的超像素进行稠密和稀疏重构，并通过多尺度重构残差建立显著图。这篇文章对与稀疏在显著性方面的应用值得参考，其大致流程如图所示。 
　　
下面对论文核心部分进行简单说明。 
(1) 论文首先利用SLIC算法将原图进行多尺度分割，并取图像边界超像素作为背景样本集B=[b1,b2,...,bM]。 
(2)重构误差：接着对每个超像素计算重构误差，包括两方面； 
a.稠密重构误差，首先利用PCA（主成份分析）对背景样本集B 进行降维处理，计算其特征向量UB=[u1,u2,...,uD′], 然后根据一下两个公式计算稠密重构误差： 

βi=U⊤B(xi−x¯)εdi=||xi−(UBβi+x¯)||22

这里的 x¯  表示所有超像素的平均特征。 
b.稀疏重构误差，该部分利用SRC的基本原理，以背景样本集为字典对超像素进行稀疏重构，其重构公式如下： 

αi=argminαi||xi−Bαi||22+λ||αi||1εsi=||xi−Bαi||22

(3) 在得到上述两个重构误差后，论文首先对它们进行了一个基于上下文的平滑处理（其实就是先聚类，然后在特征空间中去相邻区域进行一个加权均值处理）。最后，为得到一个全分辨率的显著图，论文以贝叶斯推断和高斯模型为基础进行了多尺度的误差融合（具体流程见论文，后面这部分可以作为算法后期处理参考，可改进的地方不多，不过过多叙述）。 

文章链接：http://202.118.75.4/lu/Project/DSR_saliency_iccv13/web_DSR_saliency.html

http://makerhacker.github.io/paper-mining/iccv/iccv2013/iccv-2013-Saliency_Detection_via_Dense_and_Sparse_Reconstruction.html

《Exploiting Surroundedness for Saliency Detection: A Boolean Map Approach 》

作者提出了一种基于布尔图特点的模型，具体实施步骤，一幅图像被表征为一系列的二值图像，这是通过随机二值化图像的特征图在一个白色增强的空间。基于图形-背景分离的完形原则，BMS通过拓扑分析布尔图发现周围地区来计算显著性图。

文章链接：http://cs-people.bu.edu/jmzhang/BMS/BMS.html

《Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection》

作者把一个有原则概率性目标显著性构想看成为一个抽样问题。 This novel formulation allows us to learn, from a large corpus of unlabelled images, which patches of an image are of the greatest interest and most likely to correspond to an object. We then sample the object saliency map to propose object locations.进一步，作者还证实 we show that our object proposal can be used as a simple unsupervised approach to the weakly supervised annotation problem. Our simple unsupervised approach to annotating objects of interest in images achieves a higher annotation accuracy than most weakly supervised approaches.

文章来源：http://www.psiva.ca/Papers/CVPR2013/CVPR2013.html（matlab）