Salient object detection using local,global and high contrast graphs

In this paper, we propose a novel multi-graph-based method for salient object detection in natural images. Starting from image decomposition via a superpixel generation algorithm, we utilize color, spatial and background label to calculate edge weight matrix of the graphs. By considering superpixels as the nodes and region similarities as the edge weights, local, global and high contrast graphs are created. Then, an integration technique is applied to form the saliency maps using degree vectors of the graphs. Extensive experiments on three challenging datasets show that the proposed unsupervised method outperforms the several different state-of-the-art unsupervised methods.     

基于流形排名与迟滞阈值法的视觉显著性检测

视觉显著性检测是机器视觉领域的关键技术之一.提出一种基于流形排名与迟滞阈值的检测方法,首先将图像划分成超像素集合,以之作为结点形成闭环图;再按照基于图的流形排名方法计算各个结点的显著值,形成图像的显著图;然后利用显著图直方图统计出高、低两个阈值,将显著图划分为三个部分,使用伽马校正技术分别进行处理,最终整合校正结果得到输出显著图.实验结果表明,相对于现有算法,本文算法得到的显著图能够更好地区分背景区域和显著目标,同时也更具稳健性.     

Salient object detection via a boundary-guided graph structure

Graph-based salient object detection methods have gained more and more attention recently. However, existing works fail to separate effectively salient object and background in some challenging scenes. Inspired by this observation, we propose an effective salient object detection method based on a novel boundary-guided graph structure. More specifically, the input image is firstly segmented into a series of superpixels. Then we integrate two prior cues to generate the coarse saliency map, a novel weighting mechanism is proposed to balance the proportion of two prior cues according to their performance. Secondly, we propose a novel boundary-guided graph structure to explore deeply the intrinsic relevance between superpixels. Based on the proposed graph structure, an iterative propagation mechanism is constructed to refine the coarse saliency map. Experimental results on four datasets show adequately the superiority of the proposed method than other state-of-the-art methods.     

基于鲁棒前景选择的显著性检测

显著性检测是指自动提取未知场景中符合人类视觉习惯的兴趣目标的方法。为了进一步提高检测的准确性,该文提出了利用鲁棒前景种子的流形排序进行显著性检测的算法。首先利用角点检测和边缘连接算法得到两个不同的凸包,用它们的交集初步确立目标区域的大致位置;然后利用凸包外边缘作为标准对凸包内的超像素进行相似度检测,将与大部分外边缘相似的超像素去除,得到更准确的目标样本作为前景种子;利用锚点图构建新的图结构表示数据节点之间的关系;接着通过基于前景和背景种子的流形排序算法对图像所有区域进行排序,并得到两种不同的显著性检测图;最后借助代价函数对显著性图进行优化,得到最终的显著性检测结果。经实验表明,与几种经典算法对比,该文方法可以进一步提高显著性算法的精确度和召回率。     

基于KL散度及多尺度融合的显著性区域检测算法

基于对超像素颜色概率分布间KL散度的计算,以及对多尺度显著图的融合处理,该文提出一种新的显著性区域检测算法。首先,采用超像素算法多尺度分割图像,在各尺度下用分割产生的超像素为节点,并依据超像素分割数量对各超像素进行适当邻接连通扩展,构建无向扩展闭环连通图。 其次,依据颜色判别力聚类量化各超像素内颜色,统计颜色聚类标签的概率分布,用概率分布间KL散度的调和平均值为扩展闭环连通图的边加权,再依据区域对比度并结合边界连通性,获取各尺度下的显著图。 最后,平均融合各尺度下显著图,并进行优化处理,得到最终的显著图。 在一些大型参考数据集上进行大量实验表明,所提算法优于当前一些先进算法,具有较高精确度和召回率,并且可以产生平滑显著图。     

一种基于图的流形排序的显著性目标检测改进方法

该文针对现有的基于图的流形排序的显著性目标检测方法中仅使用k-正则图刻画各个节点的空间连接性的不足以及先验背景假设过于理想化的缺陷,提出一种改进的方法,旨在保持高查全率的同时,提高准确率。在构造图模型时,先采用仿射传播聚类将各超像素(节点)自适应地划分为不同的颜色类,在传统的k-正则图的基础上,将属于同一颜色类且空间上位于同一连通区域的各个节点也连接在一起;而在选取背景种子点时,根据边界连接性赋予位于图像边界的超像素不同的背景权重,采用图割方法筛选出真正的背景种子点;最后,采用经典的流形排序算法计算显著性。在常用的MSRA-1000和复杂的SOD数据库上同7种流行算法的4种量化评价指标的实验对比证明了所提改进算法的有效性和优越性。     

Interactive image segmentation based on samples reconstruction and FLDA

Existing interactive image segmentation methods heavily rely on manual input, i.e. a sufficient quantity and correct locations of labels. In this paper, we propose a new interactive segmentation algorithm which aims to reduce human intervention and to generate high-quality segmentation results. In contrast to most energy minimizing based segmentation methods, the segmentation is cast as multi-classification in our proposed method. First, the input image is segmented into superpixels by using different methods. Then we build a dictionary consisting of all obtained superpixels and reconstruct samples represented by certain labeled superpixels. Finally, we learn a discriminative projection matrix through Fishers linear discriminant analysis (FLDA) algorithm, which learns a discriminative subspace for classification. The unlabeled superpixels are grouped into foreground or background, via calculating their minimal norm. Our method can capture long range grouping cues and reduce the sensitivity with respect to input label quantity and location of labels, by the combination of superpixels and discriminative dictionary. Extensive experiments are conducted both on MSRC and another challenging database in order to demonstrate the effectiveness of the proposed method. Quantitative and qualitative results show that our method is competitive to the state-of-the-art performance.     

一种基于视觉注意模型的可移动目标检测方法

提出了一种基于视觉显著性的目标检测算法,用于对位于地面上的车辆、飞 机等地面可移动目标进行检测和定位。针对地面可移动目标在场景中较小的特点,设计了一种用于对 目标检测进行引导的基于视觉注意机制的目标显著模型。首先,提取图像目标的颜色特征、强 度特征和方向Gabor特征,并将其结合起来用于计算显著图。然后以超像素为单位对 显著值进行计算,并结合人眼视觉敏感度对不同距离的超像素之间的差异进行加权处理。实 验结果表明,本文算法可以有效地检测并定位出复杂背景中的地面可移动目标。     

Saliency detection for panoramic landscape images of outdoor scenes

Saliency detection has been researched for conventional images with standard aspect ratios, however, it is a challenging problem for panoramic images with wide fields of view. In this paper, we propose a saliency detection algorithm for panoramic landscape images of outdoor scenes. We observe that a typical panoramic image includes several homogeneous background regions yielding horizontally elongated distributions, as well as multiple foreground objects with arbitrary locations. We first estimate the background of panoramic images by selecting homogeneous superpixels using geodesic similarity and analyzing their spatial distributions. Then we iteratively refine an initial saliency map derived from background estimation by computing the feature contrast only within local surrounding area whose range and shape are changed adaptively. Experimental results demonstrate that the proposed algorithm detects multiple salient objects faithfully while suppressing the background successfully, and it yields a significantly better performance of panorama saliency detection compared with the recent state-of-the-art techniques.     

局部和全局特征融合的红外图像显著性检测

为了更好地凸显复杂环境的红外目标特征,提出 一种融合局部和全局特征的红外图像 显著性检测方法。在获取图像超像素的基础上,提取每个区域空间距离加权的邻域对比度特 征,并考虑区域大小和位置的影响,构建局部显著图;然后提取每个区域空间距离加权的全 局灰度特征,构建全局显著图;最后融合局部和全局显著图,实现图像显著性检测。实验结 果 表明,本文方法的显著图结果目标区域一致高亮且边缘清晰,同时背景杂波抑制效果好。无 论 主观评价还是客观指标,本文方法都优于当前流行的图像显著性检测方法。     

基于加权的K近邻线性混合显著性目标检测

显著性目标检测旨在于一个场景中自动检测能够引起人类注意的目标或区域,在自底向上的方法中,基于多核支持向量机(SVM)的集成学习取得了卓越的效果。然而,针对每一张要处理的图像,该方法都要重新训练,每一次训练都非常耗时。因此,该文提出一个基于加权的K近邻线性混合(WKNNLB)显著性目标检测方法：利用现有的方法来产生初始的弱显著图并获得训练样本,引入加权的K近邻(WKNN)模型来预测样本的显著性值,该模型不需要任何训练过程,仅需选择一个最优的K值和计算与测试样本最近的K个训练样本的欧式距离。为了减少选择K值带来的影响,多个加权的K近邻模型通过线性混合的方式融合来产生强的显著图。最后,将多尺度的弱显著图和强显著图融合来进一步提高检测效果。在常用的ASD和复杂的DUT-OMRON数据集上的实验结果表明了该算法在运行时间和性能上的有效性和优越性。当采用较好的弱显著图时,该算法能够取得更好的效果。     

A heuristic framework for perceptual saliency prediction

Saliency prediction can be regarded as the human spontaneous activity. The most effective saliency model should highly approximate the response of viewers to the perceived information. In the paper, we exploit the perception response for saliency detection and propose a heuristic framework to predict salient region. First, to find the perceptually meaningful salient regions, an orientation selectivity based local feature and a visual Acuity based global feature are proposed to jointly predict candidate salient regions. Subsequently, to further boost the accuracy of saliency map, we introduce a visual error sensitivity based operator to activate the meaningful salient regions from a local and global perspective. In addition, an adaptive fusion method based on free energy principle is designed to combine the sub-saliency maps from each image channel to obtain the final saliency map. Experimental results on five natural and emotional datasets demonstrate the superiority of the proposed method compared to twelve state-of-the-art algorithms.     

基于目标紧密性与区域同质性策略的图像显著性检测

针对基于图模型的显著性检测算法中节点间特征差异描述不准确的问题,该文提出一种目标紧密性与区域同质性策略相结合的图像显著性检测算法。区别于常用的图模型,该算法建立更贴近人眼视觉系统的稀疏图结构与新颖的区域同质性图结构,以便描述图像前景内部的关联性与前景背景间的差异性,从而摒弃众多节点的冗余连接,强化节点局部空间关系;并且结合聚类簇紧密性采取流形排序的方式形成显著图,利用背景区域簇的相似性,引入背景置信度进行显著性优化,最终得到精细的检测结果。在4个基准数据集上与4种基于图模型的流行算法对比,该算法能清晰地突出显著区域,且在多种综合指标评估中,具备更优越的性能。     

Hedging static saliency models to predict dynamic saliency

In recent years, many computational models for saliency prediction have been introduced. For dynamic scenes, the existing models typically combine different feature maps extracted from spatial and temporal domains either by following generic integration strategies such as averaging or winners take all or using machine learning techniques to set each feature’s importance. Rather than resorting to these fixed feature integration schemes, in this paper, we propose a novel weakly supervised dynamic saliency model called HedgeSal, which is based on a decision-theoretic online learning scheme. Our framework uses two pretrained deep static saliency models as experts to extract individual saliency maps from appearance and motion streams, and then generates the final saliency map by weighted decisions of all these models. As visual characteristics of dynamic scenes constantly vary, the models providing consistently good predictions in the past are automatically assigned higher weights, allowing each expert to adjust itself to the current conditions. We demonstrate the effectiveness of our model on the CRCNS, UCFSports and CITIUS datasets.     

Two-stage salient region detection by exploiting multiple priors

Saliency detection has become a valuable tool for many image processing tasks, like image retargeting, object recognition, and adaptive compression. With the rapid development of the saliency detection methods, people have approved the hypothesis that “the appearance contrast between the salient object and the background is high”, and build their saliency methods on some priors that explain this hypothesis. However, these methods are not satisfactory enough. We propose a two-stage salient region detection method. The input image is first segmented into superpixels. In the first stage, two measures which measure the isolation and distribution of each superpixel are proposed, we consider that both of these two measures are important for finding the salient regions, thus the image-feature-based saliency map is obtained by combining the two measures. Then, in the second stage, we incorporate into the image-feature-based saliency map a location prior map to emphasize the foci of attention. In this algorithm, six priors that explain what is the salient region are exploited. The proposed method is compared with the state-of-the-art saliency detection methods using one of the largest publicly available standard databases, the experimental result indicates that the proposed method has better performance. We also demonstrate how the saliency map of the proposed method can be used to create high quality of initial segmentation masks for subsequent image processing, like Grabcut based salient object segmentation.     

融合颜色特征和对比度特征的图像显著性检测

图像显著性检测能够获取一幅图像的视觉显著性区域,是计算机视觉的研究热点之一。提出一种结合颜色特征和对比度特征的图像显著性检测方法。首先构造图像在HSV空间的颜色函数以获取图像颜色特征;然后使用SLIC超像素分割算法对图像进行预处理,基于超像素块的对比度特征计算图像显著性;最后将融合颜色特征和对比度特征的显著图经过导向滤波优化形成最终的显著图。使用本文算法在公开数据集MSRA-1000上进行图像显著性检测,并与其他6种算法进行比较。实验结果表明本文算法结合了图像像素点和像素块的信息,检测的图像显著性区域轮廓更加完整,优于其他方法。     

显著中心先验和显著-深度概率矫正的RGB-D显著目标检测

随着深度特征在图像显著检测领域中发挥越来越重要的作用,传统的RGB图像显著检测模型由于未能充分利用深度信息已经不能适用于RGB-D图像的显著检测。该文提出显著中心先验和显著-深度(S-D)概率矫正的RGB-D显著检测模型,使得深度特征和RGB特征间相互指导,相互补充。首先,依据3维空间权重和深度先验获取深度图像初步显著图;其次,采用特征融合的流形排序算法获取RGB图像的初步显著图。接着,计算基于深度的显著中心先验,并以该先验作为显著权重进一步提升RGB图像的显著检测结果,获取RGB图像最终显著图;再次,计算显著-深度矫正概率,并对深度图的初步显著检测结果使用此概率进行矫正。接着,计算基于RGB的显著中心先验,并以该先验作为显著权重进一步提升深度图像矫正后的显著检测结果,获取深度图像的最终显著图;最后,采用优化框架对深度图像最终显著图进行优化得到RGB-D图像最终的显著图。所有的对比实验都是在公开的数据集NLPR RGBD-1000数据集上进行,实验结果显示该文算法较当前流行的算法有更好的性能。     

Surroundedness based multiscale saliency detection

In this paper, a surroundedness-based multiscale saliency method is proposed based on the Gestalt principles for figure-ground segregation, which states that (1) surrounded regions are more likely to be perceived as figures, (2) the humans understand the external stimuli as whole rather than the sum of their parts. First, an image is characterized by a set of binary images, which is generated by a simple and effective homogeneous region extraction method with well contour preservation. And the contour confidence map is obtained by a fast contour detection method. Then for each connect homogeneous region in a binary map, surroundedness is defined by the average outer contour confidence. Finally, integrating the background priors, multiscale saliency maps are generated and combined to the final saliency map. The proposed method is evaluated on two widely used public datasets with pixel accurate salient region annotations using both precision and recall analysis and ROC analysis. And the experimental results show that the proposed method outperforms 14 alternative methods.