基于前景增强与背景抑制的显著性物体检测

显著性物体检测的关键在于准确地突出前景区域,多数传统方法在处理复杂背景图像时效果不理想。针对上述问题,提出了一种基于前景增强与背景抑制的显著性物体检测方法。首先,利用简单线性迭代聚类(SLIC)将图像进行分割得到多个超像素区域,通过区域间的对比和边界信息分别获得图像的显著区域与背景种子,并通过计算得到基于区域间对比和基于背景的两幅显著图。然后,在两幅图像中运用Seam Carving和Graph based的图像分割法区分显著与非显著区域,进而得到前景增强与背景抑制模板。最终,融合两幅显著图与模板得到最终的显著图。在公开数据集MSRA 1000上对算法进行验证,结果表明,所提算法与7种主流算法相比具有更好的查准率和查全率。     

Coarse to Fine: Weak Feature Boosting Network for Salient Object Detection

Salient object detection is to identify objects or regions with maximum visual recognition in an image, which brings significant help and improvement to many computer visual processing tasks. Although lots of methods have occurred for salient object detection, the problem is still not perfectly solved especially when the background scene is complex or the salient object is small. In this paper, we propose a novel Weak Feature Boosting Network (WFBNet) for the salient object detection task. In the WFBNet, we extract the unpredictable regions (low confidence regions) of the image via a polynomial function and enhance the features of these regions through a well-designed weak feature boosting module (WFBM). Starting from a coarse saliency map, we gradually refine it according to the boosted features to obtain the final saliency map, and our network does not need any post-processing step. We conduct extensive experiments on five benchmark datasets using comprehensive evaluation metrics. The results show that our algorithm has considerable advantages over the existing state-of-the-art methods.     

基于自适应背景模板与空间先验的显著性物体检测方法

目前,显著性检测已成为国内外计算机视觉领域研究的一个热点,但现有的显著性检测算法大多无法有效检测出位于图像边缘的显著性物体.针对这一问题,本文提出了基于自适应背景模板与空间先验的显著性物体检测方法,共包含三个步骤:第一,根据显著性物体在颜色空间上具有稀有性,获取基于自适应背景模板的显著图.将图像分割为超像素块,提取原图的四周边界作为原始背景区域.利用设计的自适应背景选择策略移除原始背景区域中显著的超像素块,获取自适应背景模板.通过计算每个超像素块与自适应背景模板的相异度获取基于自适应背景模板的显著图.并采用基于K-means的传播机制对获取的显著图进行一致性优化;第二,根据显著性物体在空间分布上具有聚集性,利用基于目标中心优先与背景模板抑制的空间先验方法获得空间先验显著图.第三,将获得的两种显著图进行融合得到最终的显著图.在公开数据集MSRA-1000、SOD、ECSSD和新建复杂数据集CBD上进行实验验证,结果证明本文方法能够准确有效地检测出图像中的显著性物体.     

Salient object detection based on regions

Salient object detection aims to automatically localize the attractive objects with respect to surrounding background in an image. It can be applied to image browsing, image cropping, image compression, content-based image retrieval, and etc. In the literature, the low-level (pixel-based) features (e.g., color and gradient) were usually adopted for modeling and computing visual attention; these methods are straightforward and efficient but limited by performance, due to losing global organization and inference. Some recent works attempt to use the region-based features but often lead to incomplete object detection. In this paper, we propose an efficient approach of salient object detection using region-based representation, in which two novel region-based features are extracted for proposing salient map and the salient object are localized with a region growing algorithm. Its brief procedure includes: 1) image segmentation to get disjoint regions with characteristic consistency; 2) region clustering; 3) computation of the region-based center-surround feature and color-distribution feature; 4) combination of the two features to propose the saliency map; 5) region growing for detecting salient object. In the experiments, we evaluate our method with the public dataset provided by Microsoft Research Asia. The experimental results show that the new approach outperforms other four state-of-the-arts methods with regard to precision, recall and F-measure.     

Salient object detection via saliency bias and diffusion

Salient object detection aims to identify both spatial locations and scales of the salient object in an image. However, previous saliency detection methods generally fail in detecting the whole objects, especially when the salient objects are actually composed of heterogeneous parts. In this work, we propose a saliency bias and diffusion method to effectively detect the complete spatial support of salient objects. We first introduce a novel saliency-aware feature to bias the objectness detection for saliency detection on a given image and incorporate the saliency clues explicitly in refining the saliency map. Then, we propose a saliency diffusion method to fuse the saliency confidences of different parts from the same object for discovering the whole salient object, which uses the learned visual similarities among object regions to propagate the saliency values across them. Benefiting from such bias and diffusion strategy, the performance of salient object detection is significantly improved, as shown in the comprehensive experimental evaluations on four benchmark data sets, including MSRA-1000, SOD, SED, and THUS-10000.     

Salient object detection via region contrast and graph regularization基于区域对比度和图正则化的显著目标检测

Detection of salient objects in an image is now gaining increasing research interest in computer vision community. In this study, a novel region-contrast based saliency detection solution involving three phases is proposed. First, a color-based super-pixels segmentation approach is used to decompose the image into regions. Second, three high-level saliency measures which could effectively characterize the salient regions are evaluated and integrated in an effective manner to produce the initial saliency map. Finally, we construct a pairwise graphical model to encourage that adjacent image regions with similar features take continuous saliency values, thus producing the more perceptually consistent saliency map. We extensively evaluate the proposed method on three public benchmark datasets, and show it can produce promising results when compared to 14 state-of-the-art salient object detection approaches.     

融合目标增强与稀疏重构的显著性检测

目的 为了解决图像显著性检测中存在的边界模糊,检测准确度不够的问题,提出一种基于目标增强引导和稀疏重构的显著检测算法（OESR）。方法 基于超像素,首先从前景角度计算超像素的中心加权颜色空间分布图,作为前景显著图;由图像边界的超像素构建背景模板并对模板进行预处理,以优化后的背景模板作为稀疏表示的字典,计算稀疏重构误差,并利用误差传播方式进行重构误差的校正,得到背景差异图;最后,利用快速目标检测方法获取一定数量的建议窗口,由窗口的对象性得分计算目标增强系数,以此来引导两种显著图的融合,得到最终显著检测结果。结果 实验在公开数据集上与其他12种流行算法进行比较,所提算法对具有不同背景复杂度的图像能够较准确的检测出显著区域,对显著对象的提取也较为完整,并且在评价指标检测上与其他算法相比,在MSRA10k数据集上平均召回率提高4.1%,在VOC2007数据集上,平均召回率和F检验分别提高18.5%和3.1%。结论 本文提出一种新的显著检测方法,分别利用颜色分布与对比度方法构建显著图,并且在显著图融合时采用一种目标增强系数,提高了显著图的准确性。实验结果表明,本文算法能够检测出更符合视觉特性的显著区域,显著区域更加准确,适用于自然图像的显著性目标检测、目标分割或基于显著性分析的图像标注。     

Joint salient object detection and existence prediction

Recent advances in supervised salient object detection modeling has resulted in significant performance improvements on benchmark datasets. However, most of the existing salient object detection models assume that at least one salient object exists in the input image. Such an assumption often leads to less appealing saliencymaps on the background images with no salient object at all. Therefore, handling those cases can reduce the false positive rate of a model. In this paper, we propose a supervised learning approach for jointly addressing the salient object detection and existence prediction problems. Given a set of background-only images and images with salient objects, as well as their salient object annotations, we adopt the structural SVM framework and formulate the two problems jointly in a single integrated objective function: saliency labels of superpixels are involved in a classification term conditioned on the salient object existence variable, which in turn depends on both global image and regional saliency features and saliency labels assignments. The loss function also considers both image-level and regionlevel mis-classifications. Extensive evaluation on benchmark datasets validate the effectiveness of our proposed joint approach compared to the baseline and state-of-the-art models.     

全局孤立性和局部同质性图表示的随机游走显著目标检测算法

目前的显著性检测算法主要依赖像素间的相互对比,缺乏对显著目标自身特性的分析理解. 依据显著目标是显眼、紧凑和完整的思路,提出一种基于目标全局孤立性和局部同质性的 随机游走显著目标检测算法,将视觉显著性检测公式化为马尔科夫随机游走问题. 首先将输入图像进行分块,根据像素块之间颜色特征和方向特征的相似性确定边的权重, 从而构建图模型;然后通过全连通图搜索提取全局特性,突出全局较孤立的区域; 同时通过k-regular图搜索提取局部特性,增强局部较均匀的区域;最后将全局特性和局部 特性相结合得到显著图,进而确定感兴趣区域位置. 实验结果表明,相比于其他两种具有代表性的算法,所提方法检测结果更加准确、合理, 证明该算法切实可行.     

Salient object detection: From pixels to segments

In this paper we propose a novel approach to the task of salient object detection. In contrast to previous salient object detectors that are based on a spotlight attention theory, we follow an object-based attention theory and incorporate the notion of an object directly into our saliency measurements. Particularly, we consider proto-objects as units of the analysis, where a proto-object is a connected image region that can be converted into a plausible object or object-part, once a focus of attention reaches it. As the object-based attention theory suggests, we start with segmenting a complex image into proto-objects and then assess saliency for each proto-object. The most salient proto-object is considered as being a salient object.     

基于图割精细化和可微分聚类的无监督显著性目标检测

针对传统显著性检测算法分割精度低以及基于深度学习的显著性检测算法对像素级人工注释数据依赖性过强等不足,提出一种基于图割精细化和可微分聚类的无监督显著性目标检测算法。该算法采用由“粗”到“精”的思想,仅利用单张图像的特征便可以实现精确的显著性目标检测。首先利用Frequency-tuned算法根据图像自身的颜色和亮度得到显著粗图,然后根据图像的统计特性进行二值化并结合中心优先假设得到显著目标的候选区域,进而利用基于单图像进行图割的GrabCut算法对显著目标进行精细化分割,最后为克服背景与目标极为相似时检测不精确的困难,引入具有良好边界分割效果的无监督可微分聚类算法对单张显著图做进一步的优化。所提出的算法在ECSSD和SOD数据集上进行测试并与现有的7种算法进行对比,结果表明得到的优化显著图更接近于真值图,在ECSSD和SOD数据集上分别实现了14.3%和23.4%的平均绝对误差（MAE）。     

Image saliency detection using Gabor texture cues

Image saliency analysis plays an important role in various applications such as object detection, image compression, and image retrieval. Traditional methods for saliency detection ignore texture cues. In this paper, we propose a novel method that combines color and texture cues to robustly detect image saliency. Superpixel segmentation and the mean-shift algorithm are adopted to segment an original image into small regions. Then, based on the responses of a Gabor filter, color and texture features are extracted to produce color and texture sub-saliency maps. Finally, the color and texture sub-saliency maps are combined in a nonlinear manner to obtain the final saliency map for detecting salient objects in the image. Experimental results show that the proposed method outperforms other state-of-the-art algorithms for images with complex textures.     

融合似物性前景对象与背景先验的图像显著性检测

为了在复杂背景图像中准确地提取出图像的显著区域,提出一种结合似物性前景对象与背景先验知识的图像显著性检测方法（OFOBP）。该方法首先对图像进行超像素分割,计算超像素颜色空间分布,得到初始显著图;利用似物性检测方法获取多个目标窗口,由窗口建立搜索区域,结合二值化的初始显著图优化目标窗口;再利用多窗口特征对超像素做前景对象预测,获取前景显著图;其次建立背景模板,计算稀疏重构误差获取背景先验图;最后融合两种显著图,得到最终显著检测结果。在公开数据集上与11种算法进行比较,本文算法能够较为准确地检测出显著区域,尤其是在复杂背景下对多个显著目标的检测,存在明显的优势。     

How important is location information in saliency detection of natural images

Location information, i.e., the position of content in image plane, is considered as an important supplement in saliency detection. The effect of location information is usually evaluated by integrating it with the selected saliency detection methods and measuring the improvement, which is highly influenced by the selection of saliency methods. In this paper, we provide direct and quantitative analysis of the importance of location information for saliency detection in natural images. We firstly analyze the relationship between content location and saliency distribution on four public image datasets, and validate the distribution by simply treating location based Gaussian distribution as saliency map. To further validate the effectiveness of location information, we propose a location based saliency detection approach, which completely initializes saliency maps with location information and propagate saliency among patches based on color similarity, and discuss the robustness of location information’s effect. The experimental results show that location information plays a positive role in saliency detection, and the proposed method can outperform most state-of-the-art saliency detection methods and handle natural images with different object positions and multiple salient objects.     

Shape-Based Object Detection via Boundary Structure Segmentation

We address the problem of object detection and segmentation using global holistic properties of object shape. Global shape representations are highly susceptible to clutter inevitably present in realistic images, and thus can be applied robustly only using a precise segmentation of the object. To this end, we propose a figure/ground segmentation method for extraction of image regions that resemble the global properties of a model boundary structure and are perceptually salient. Our shape representation, called the chordiogram, is based on geometric relationships of object boundary edges, while the perceptual saliency cues we use favor coherent regions distinct from the background. We formulate the segmentation problem as an integer quadratic program and use a semidefinite programming relaxation to solve it. The obtained solutions provide a segmentation of the object as well as a detection score used for object recognition. Our single-step approach achieves state-of-the-art performance on several object detection and segmentation benchmarks.     

基于频域与空间域分析的显著区域检测算法

显著区域检测对于多种计算机视觉应用有所帮助,如图像分割、目标识别、图像检索及自适应压缩。为此,提出一个基于频域与空间域分析的显著区域检测算法。通过拥有不同尺寸窗口的中值滤波器对不显著的区域进行抑制,根据空间信息选择最佳的显著图。与 5个经典算法的比较实验结果表明,利用该算法得到的显著图既去除了背景,又突出了整个显著物体。     

Clustering ensemble via structured hypergraph learning

Clustering ensemble integrates multiple base clustering results to obtain a consensus result and thus improves the stability and robustness of the single clustering method. Since it is natural to use a hypergraph to represent the multiple base clustering results, where instances are represented by nodes and base clusters are represented by hyperedges, some hypergraph based clustering ensemble methods are proposed. Conventional hypergraph based methods obtain the final consensus result by partitioning a pre-defined static hypergraph. However, since base clusters may be imperfect due to the unreliability of base clustering methods, the pre-defined hypergraph constructed from the base clusters is also unreliable. Therefore, directly obtaining the final clustering result by partitioning the unreliable hypergraph is inappropriate. To tackle this problem, in this paper, we propose a clustering ensemble method via structured hypergraph learning, i.e., instead of being constructed directly, the hypergraph is dynamically learned from base results, which will be more reliable. Moreover, when dynamically learning the hypergraph, we enforce it to have a clear clustering structure, which will be more appropriate for clustering tasks, and thus we do not need to perform any uncertain postprocessing, such as hypergraph partitioning. Extensive experiments show that, our method not only performs better than the conventional hypergraph based ensemble methods, but also outperforms the state-of-the-art clustering ensemble methods.     

Oscillation analysis for salient object detection

Salient object detection from an image is important for many multimedia applications. Existing methods provide good solutions to saliency detection; however, their results often emphasize the high-contrast edges, instead of regions/objects. In this paper, we present a method for salient object detection based on oscillation analysis. Our study shows that salient objects and their backgrounds have different amplitudes of oscillation between the local minima and maxima. Based on this observation, our method analyzes the oscillation in an image by estimating its local minima and maxima and computes the saliency map according to the oscillation magnitude contrast. Our method detects the local minima and maxima and performs extreme interpolation to smoothly propagate these information to the whole image. In this way, the oscillation information is smoothly assigned to regions, retaining well-defined salient boundaries as there are large variations near the salient boundaries (edges between objects and their backgrounds). As a result, our saliency map highlights salient regions/objects instead of high-contrast boundaries. We experiment with our method on two large public data set. Our results demonstrate the effectiveness of our method. We further apply our salient object detection method to automatic salient object segmentation, which again shows the success.     

融合颜色属性和空间信息的显著性物体检测

摘 要：目的：提出了一种基于颜色属性和空间信息的显著性物体检测算法,并将其用于交通标志的检测。方法：首先,训练颜色属性得到颜色-像素值分布,据此将图像划分为不同的颜色聚簇,每个聚簇的显著性取决于其空间紧致性。其次,将每个聚簇分割为多个区域,用颜色属性描述子表示每个区域,计算区域的全局对比度。最后,同时考虑区域对比度和相应聚簇的空间紧致性,得到最终的显著图。在此基础上,将交通标志的先验知识转换为自上而下的显著性图,形成任务驱动的显著性模型,对交通标志进行检测。结果：在公开数据集上的测试结果表明,该算法取得最高92%的查准率,优于其它流行的显著性算法。在交通标志数据集上的检测取得了90.7%的正确率。结论：本文提出了一种新的显著性检测算法,同时考虑了区域的颜色和空间信息,在公开数据集上取得了较高的查准率和查全率。在对交通标志的检测中也取得了较好的结果。     

自动特征选择和加权的图像显著区域检测

视觉显著性度量是图像显著区域提取中的一个关键问题,现有的方法主要根据图像的底层视觉特征,构造相应的显著图。不同的特征对视觉显著性的贡献是不同的,为此提出一种能够自动进行特征选择和加权的图像显著区域检测方法。提取图像的亮度、颜色和方向等特征,构造相应的特征显著图。提出一种新的特征融合策略,动态计算各特征显著图的权值,整合得到最终的显著图,检测出图像中的显著区域。在多幅自然图像上进行实验,实验结果表明,该方法在运算速度和检测效果方面都取得了不错的效果。