Salient object detection via boosting object-level distinctiveness and saliency refinement

Many salient object detection approaches share the common drawback that they cannot uniformly highlight heterogeneous regions of salient objects, and thus, parts of the salient objects are not discriminated from background regions in a saliency map. In this paper, we focus on this drawback and accordingly propose a novel algorithm that more uniformly highlights the entire salient object as compared to many approaches. Our method consists of two stages: boosting the object-level distinctiveness and saliency refinement. In the first stage, a coarse object-level saliency map is generated based on boosting the distinctiveness of the object proposals in the test images, using a set of object-level features and the Modest AdaBoost algorithm. In the second stage, several saliency refinement steps are executed to obtain a final saliency map in which the boundaries of salient objects are preserved. Quantitative and qualitative comparisons with state-of-the-art approaches demonstrate the superior performance of our approach.     

Bayesian salient object detection based on saliency driven clustering

Salient object detection is essential for applications, such as image classification, object recognition and image retrieval. In this paper, we design a new approach to detect salient objects from an image by describing what does salient objects and backgrounds look like using statistic of the image. First, we introduce a saliency driven clustering method to reveal distinct visual patterns of images by generating image clusters. The Gaussian Mixture Model (GMM) is applied to represent the statistic of each cluster, which is used to compute the color spatial distribution. Second, three kinds of regional saliency measures, i.e, regional color contrast saliency, regional boundary prior saliency and regional color spatial distribution, are computed and combined. Then, a region selection strategy integrating color contrast prior, boundary prior and visual patterns information of images is presented. The pixels of an image are divided into either potential salient region or background region adaptively based on the combined regional saliency measures. Finally, a Bayesian framework is employed to compute the saliency value for each pixel taking the regional saliency values as priority. Our approach has been extensively evaluated on two popular image databases. Experimental results show that our approach can achieve considerable performance improvement in terms of commonly adopted performance measures in salient object detection.     

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.     

Are emotional objects visually salient? The Emotional Maps Database

The visual system prioritizes emotional content in natural scenes, but it is unclear whether emotional objects are systematically more salient. We compare emotional maps - created by averaging multiple manual selections of the most meaningful regions in images of negative, positive, and neutral affective valence - with saliency maps generated by Graph-Based Visual Saliency, Proto-object, and SalGAN models. We found that similarity between emotional and saliency maps is modulated by the scenes’ arousal and valence ratings: the more negative and high-arousing content, the less it was salient. Simultaneously, the negative and high-arousing content was the easiest to identify by the participants, as shown by the highest inter-individual agreement in the selections. Our results support the “affective gap” hypothesis, i.e., decoupling of emotional meaning from image’s formal features. The Emotional Maps Database created for this study, proven useful in gaze fixation prediction, is available online for scientific use.     

IR saliency detection via a GCF-SB visual attention framework

Infrared (IR) saliency detection with high detection accuracy is a challenging task due to the complex background and low contrast of IR images. In this paper, an IR saliency detection method via a new visual attention framework is proposed, which comprises two phases. In the first phase, a Gray & Contrast Features (GCF) model is established, in which the IR image is processed in two feature channels, a gray feature channel and a contrast feature channel. And then a primary feature map can be obtained by fusing the gray and contrast features from these two channels, which is the basis of the second phase. In the second phase, a Similarity-based Bayes (SB) model is established, in which two prior probabilities and two likelihood functions are calculated according to the previously obtained primary feature map. Finally, the saliency map is calculated with the obtained prior probabilities and likelihood functions by Bayes formula. Experimental results indicate that the proposed method can effectively reduce noise and enhance contrast of IR images with complex background and low contrast, and obtain a higher detection accuracy and robustness than seven state-of-the-art methods.     

应用图像融合与多样性的舰船显著性检测

基于单源的图像显著性检测存在较大的虚警或漏检,文章提出了利用约简后的特征点和CPD算法对海面实拍船只图像进行多源图像匹配,获得图像间的变换投影方程并利用投影方程对单源图像的显著性检测结果进行叠加与虚警控制器分类,从而达到提高检测率与控制虚警的目的。显著性检测方面,文章分析了基于图等级多样性的显著性检测方法的不足和优点,引入了最大稳定区域检测方法对图像做前期处理,并对获得区域进行联合获得新区域,使得新区域能够最大限度地满足基于图的等级多样性显著性检测最优条件。对于检测获得的联合区域目标显著性不完整的情况,利用了区域的叠加性进行加权求和,最终获得了具有较好联通性的多舰船目标图像显著性检测结果。对于显著性检测结果中存在较大虚警的情况,文章进一步提出计算船只与浪花的多尺度分形维数,并结合Adaboost算法训练浪花虚警控制器。实验结果显示控制器能够消除一部分浪花带来的虚警,但是对于灰度与舰船极为相似的虚警无法消除。     

Saliency detection based on singular value decomposition

Saliency detection has gained popularity in many applications, and many different approaches have been proposed. In this paper, we propose a new approach based on singular value decomposition (SVD) for saliency detection. Our algorithm considers both the human-perception mechanism and the relationship between the singular values of an image decomposed by SVD and its salient regions. The key concept of our proposed algorithms is based on the fact that salient regions are the important parts of an image. The singular values of an image are divided into three groups: large, intermediate, and small singular values. We propose the hypotheses that the large singular values mainly contain information about the non-salient background and slight information about the salient regions, while the intermediate singular values contain most or even all of the saliency information. The small singular values contain little or even none of the saliency information. These hypotheses are validated by experiments. By regularization based on the average information, regularization using the leading largest singular values or regularization based on machine learning, the salient regions will become more conspicuous. In our proposed approach, learning-based methods are proposed to improve the accuracy of detecting salient regions in images. Gaussian filters are also employed to enhance the saliency information. Experimental results prove that our methods based on SVD achieve superior performance compared to other state-of-the-art methods for human-eye fixations, as well as salient-object detection, in terms of the area under the receiver operating characteristic (ROC) curve (AUC) score, the linear correlation coefficient (CC) score, the normalized scan-path saliency (NSS) score, the F-measure score, and visual quality.     

选择性背景优先的显著性检测模型

在检测图像显著性区域的领域中,背景优先是一个较新的思路,但会遇到背景鉴别这个具有挑战性的难题。该文提出背景真实性的判断问题,在探索的过程中发现背景通常具有连续性的特征,根据这一特性实现了判定背景的方法,并将判断的结果作为显著性先验值应用于后继的计算中,最终结果的准确性和正确性得到有效提高。该文首先采用均值漂移(MS)分割算法将图片预分为超像素,计算所有超像素的初始显著值;随后提取原图的4个边界条,计算每两条之间的色彩直方图距离,判定小于预设阈值的两条边界作为真的背景,选择它们作为优先边界,计算先验显著性值;最后进行显著性计算,得到最终的显著图。实验结果表明,该算法能够准确检测出显著性区域,与其他6种算法相比具有较大优势。     

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.     

3D saliency detection based on background detection

Unlike 2D saliency detection, 3D saliency detection can consider the effects of depth and binocular parallax. In this paper, we propose a 3D saliency detection approach based on background detection via depth information. With the aid of the synergism between a color image and the corresponding depth map, our approach can detect the distant background and surfaces with gradual changes in depth. We then use the detected background to predict the potential characteristics of the background regions that are occluded by foreground objects through polynomial fitting; this step imitates the human imagination/envisioning process. Finally, a saliency map is obtained based on the contrast between the foreground objects and the potential background. We compare our approach with 14 state-of-the-art saliency detection methods on three publicly available databases. The proposed model demonstrates good performance and succeeds in detecting and removing backgrounds and surfaces of gradually varying depth on all tested databases.     

基于低秩背景约束与多线索传播的图像显著性检测

针对当前基于流形排序的显著性检测算法缺乏子空间信息的挖掘和节点间传播不准确的问题,该文提出一种基于低秩背景约束与多线索传播的图像显著性检测算法.融合颜色、位置和边界连通度等初级视觉先验形成背景高级先验,约束图像特征矩阵的分解,强化低秩矩阵与稀疏矩阵的差异,充分描述子空间结构信息,从而有效地将前景与背景分离;引入稀疏感知和局部平滑等线索改进传播矩阵的构建,增强颜色特征出现概率低的节点的传播能力,加强局部区域内节点的关联性,准确凸显节点的属性,得到紧密且连续的显著区域.在3个基准数据集上的实验结果与图像检索领域的应用证明了该文算法的有效性和鲁棒性.     

Saliency detection via coarse-to-fine diffusion-based compactness with weighted learning affinity matrix

Diffusion-based compactness is an effective method for foreground-based saliency detection, in which one key is the conventional graph construction. However, the conventional graph only displays the local structure but not preserves global relevance information. Therefore, diffusion-based compactness cannot highlight complete salient object which contains multiple areas with different features, and the extracted salient regions with weak homogeneous. Aiming to address these problems, we propose a saliency detection method via coarse-to-fine diffusion-based compactness with a weighted learning affinity matrix. Firstly, we construct multi-view conventional graphs to calculate the rough compactness cue. Secondly, we build a two-stage multi-view weighted graphs using a weighted learning affinity matrix and compute the coarse-to-fine compactness cue. Extensive experiments tested on three benchmark datasets, demonstrating the superior against several state-of-the-art methods.     

基于稀疏和低秩表示的显著性目标检测

文中研究了无监督自下而上的显著性目标检测方法。基于显著性目标在自然图像中稀疏分布的这一先验性假设,提出了一种用低秩和稀疏表示进行显著性目标检测的方法。根据图像背景的先验分布,首先选取一个有效的背景字典来低秩表示图像的背景部分,进而更好地分离出显著性前景。由于人类视觉中心偏好可知,图像的边缘部分不易引起关注,故选取这些边缘部分作为背景先验来选取背景字典。与其他基于稀疏和低秩分解的显著性目标检测相比,文中选取的背景字典更简单有效,且能得到更好的显著性图。实验结果显示,该方法比主流的显著性检测方法得到的显著性图更令人满意。     

基于空时域特征的视觉显著度图生成算法

本文提出了一种新的计算图像空时域显著图的方法,该算法首先用lucas-kanade金字塔算法求绝对运动矢量,用8参数透视模型计算背景运动矢量,再用二者的差值求时域显著图;然后利用颜色对比度和纹理信息计算空域显著图;最后,融合空时域并设置阈值得到总的图像显著图。实验结果表明,新算法能比已有算法更有效的提取视频图像的显著性区域。     

基于区域特征融合的RGBD显著目标检测

为了对各类自然场景中的显著目标进行检测,本文提出了一种将图像的深度信息引入区域显著性计算的方法,用于目标检测。首先对图像进行多尺度分割得到若干区域,然后对区域多类特征学习构建回归随机森林,采用监督学习的方法赋予每个区域特征显著值,最后采用最小二乘法对多尺度的显著值融合,得到最终的显著图。实验结果表明,本文算法能较准确地定位RGBD图像库中每幅图的显著目标。     

Finding spatio-temporal salient paths for video objects discovery

Many videos capture and follow salient objects in a scene. Detecting such salient objects is thus of great interests to video analytics and search. However, the discovery of salient objects in an unsupervised way is a challenging problem as there is no prior knowledge of the salient objects provided. Different from existing salient object detection methods, we propose to detect and track salient object by finding a spatio-temporal path which has the largest accumulated saliency density in the video. Inspired by the observation that salient video objects usually appear in consecutive frames, we leverage the motion coherence of videos into the path discovery and make the salient object detection more robust. Without any prior knowledge of the salient objects, our method can detect salient objects of various shapes and sizes, and is able to handle noisy saliency maps and moving cameras. Experimental results on two public datasets validate the effectiveness of the proposed method in both qualitative and quantitative terms. Comparisons with the state-of-the-art methods further demonstrate the superiority of our method on salient object detection in videos.     

面向显著性目标检测的SSD改进模型

传统显著性目标检测方法常假设只有单个显著性目标,其效果依赖显著性阈值的选取,并不符合实际应用需求。近来利用目标检测方法得到显著性目标检测框成为一种新的解决思路。SSD模型可同时精确检测多个不同尺度的目标对象,但小尺寸目标检测精度不佳。为此,该文引入去卷积模块与注意力残差模块,构建了面向多显著性目标检测的DAR-SSD模型。实验结果表明,DAR-SSD检测精度显著高于SOD模型;相比原始SSD模型,在小尺度和多显著性目标情形下性能提升明显;相比MDF和DCL等深度学习框架下的方法,也体现了复杂背景情形下的良好检测性能。