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: 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.     

RGB-D salient object detection: A survey

Computational Visual Media - Salient object detection, which simulates human visual perception in locating the most significant object(s) in a scene, has been widely applied to various computer...     

Salient object detection via robust dictionary representation

Multimedia Tools and Applications - The theory of sparse and low-rank representation has worked competitive performance in the field of salient object detection. Generally, the salient object is...     

Salient object detection method using random graph

In this paper, a bottom-up salient object detection method is proposed by modeling image as a random graph. The proposed method starts with portioning input image into superpixels and extracting color and spatial features for each superpixel. Then, a complete graph is constructed by employing superpixels as nodes. A high edge weight is assigned into a pair of superpixels if they have high similarity. Next, a random walk prior on nodes is assumed to generate the probability distribution on edges. On the other hand, a complete directed graph is created that each edge weight represents the probability for transmitting random walker from current node to next node. By considering a threshold and eliminating edges with higher probability than the threshold, a random graph is created to model input image. The inbound degree vector of a random graph is computed to determine the most salient nodes (regions). Finally, a propagation technique is used to form saliency map. Experimental results on two challenging datasets: MSRA10K and SED2 demonstrate the efficiency of the proposed unsupervised RG method in comparison with the state-of-the-art unsupervised methods.     

Salient object detection via multiple saliency weights

Multimedia Tools and Applications - Salient object detection aims to emulate the extraordinary capability of human visual system, which has the ability to find the most visually attractive objects...     

基于背景学习的显著物体检测

目的 显著物体检测的目标是提取给定图像中最能吸引人注意的物体或区域,在物体识别、图像显示、物体分割、目标检测等诸多计算机视觉领域中都有广泛应用。已有的基于局部或者全局对比度的显著物体检测方法在处理内容复杂的图像时,容易造成检测失败,其主要原因可以总结为对比度参考区域设置的不合理。为提高显著物体检测的完整性,提出背景驱动的显著物体检测算法,在显著值估计和优化中充分利用背景先验。方法 首先采用卷积神经网络学习图像的背景分布,然后从得到的背景图中分割出背景区域作为对比度计算参考区域来估计区域显著值。最后,为提高区域显著值的一致性,采用基于增强图模型的优化实现区域显著值的扩散,即在传统k-正则图局部连接的基础上,添加与虚拟节点之间的先验连接和背景区域节点之间的非局部连接,实现背景先验信息的嵌入。结果 在公开的ASD、SED、SOD和THUS-10000数据库上进行实验验证,并与9种流行的算法进行对比。本文算法在4个数据库上的平均准确率、查全率、F-measure和MAE指标分别为0.873 6、0.795 2、0.844 1和0.112 2,均优于当前流行的算法。结论 以背景区域作为对比度计算参考区域可以明显提高前景区域的显著值。卷积神经网络可以有效学习图像的背景分布并分割出背景区域。基于增强图模型的优化可以进一步实现显著值在前景和背景区域的扩散,提高区域显著值的一致性,并抑制背景区域的显著性响应。实验结果表明,本文算法能够准确、完整地检测图像的显著区域,适用于复杂图像的显著物体检测或物体分割应用。     

Salient object detection using the phase information and object model

Multimedia Tools and Applications - One of the most important features of saliency detection algorithms is to reduce the size of processing data for algorithms with higher processing size such as...     

Correction to: Salient object detection using the phase information and object model

Multimedia Tools and Applications - The article Salient object detection using the phase information and object model, written by Hooman Afsharirad and Seyed Alireza Seyedin, was originally...     

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.     

基于邻域优化机制的图像显著性目标检测

在显著性目标检测中,背景区域和前景区域区分度不高会导致检测结果不理想。针对这一问题,提出一种基于邻域优化机制的图像显著性目标检测算法。首先对图像进行超像素分割;然后在CIELab颜色空间建立对比图和分布图,并通过一种新的合并方式进行融合;最后在空间距离等约束下,建立邻域更新机制,对初始显著性图进行优化。实验对比表明,该算法显著性目标检测效果更好。     

Salient object detection and classification for stereoscopic images

Stereoscopic images have become more and more prevalent following the rapid advances in 3D capturing and display techniques. However, there has been little research on visual content analysis for stereoscopic images. In this paper, we address the challenging problem of object detection and classification for stereoscopic images. An iterative method that can mutually boost salient object detection and object classification is proposed for stereoscopic images. This method includes two steps. In the first step, a 3D saliency detection method, which includes the contrastive and occlusion cues contained in each stereoscopic image pair along with the discriminative features provided by the SVM classifier, is proposed to localize object of interest in the stereoscopic images. In the second step, the bag of word features of foreground and background is pooled by using the localization information, and then is applied to train the SVM classifier. Each of the two steps benefits from the gradual improvement result in the other, no matter in the training or the testing process. To evaluate the performance of our approach, a 6-object class dataset of stereoscopic images real objects viewed under general lighting conditions, poses and viewpoints is set up. Our experimental results on the dataset, for object localization and object classification, demonstrate the effectiveness of the method.     

A survey of 3D object detection

Multimedia Tools and Applications - Due to the rapid development of science and technology, object detection has become a promising research direction in computer vision. In recent years, most...     

深度聚类注意力机制下的显著对象检测

目的 为了得到精确的显著对象分割结果,基于深度学习的方法大多引入注意力机制进行特征加权,以抑制噪声和冗余信息,但是对注意力机制的建模过程粗糙,并将所有特征均等处理,无法显式学习不同通道以及不同空间区域的全局重要性。为此,本文提出一种基于深度聚类注意力机制（deep cluster attention,DCA）的显著对象检测算法DCANet （DCA network）,以更好地建模特征级别的像素上下文关联。方法 DCA显式地将特征图分别在通道和空间上进行区域划分,即将特征聚类分为前景敏感区和背景敏感区。然后在类内执行一般性的逐像素注意力加权,并在类间进一步执行语义级注意力加权。DCA的思想清晰易懂,参数量少,可以便捷地部署到任意显著性检测网络中。结果 在6个数据集上与19种方法的对比实验验证了DCA对得到精细显著对象分割掩码的有效性。在各项评价指标上,部署DCA之后的模型效果都得到了提升。在ECSSD （extended cornplex scene saliency dataset）数据集上,DCANet的性能比第2名在F值上提升了0.9%;在DUT-OMRON （Dalian University of Technology and OMRON Corporation）数据集中,DCANet的性能比第2名在F值上提升了0.5%,平均绝对误差（mean absolute error,MAE）降低了3.2%;在HKU-IS数据集上,DCANet的性能比第2名在F值上提升了0.3%, MAE降低了2.8%;在PASCAL （pattern analysis,statistical modeling and computational learning）-S （subset）数据集上,DCANet的性能则比第2名在F值上提升了0.8%,MAE降低了4.2%。结论 本文提出的深度聚类注意力机制通过细粒度的通道划分和空间区域划分,有效地增强了前景敏感类的全局显著得分。与现有的注意力机制相比,DCA思想清晰、效果明显、部署简单,同时也为一般性的注意力机制研究提供了新的可行的研究方向。     

基于注意力机制的显著性目标检测方法

针对目前主流的基于全卷积神经网络的显著性目标检测方法,受限于卷积层感受野大小,低层特征缺少全局性的信息,而高层特征由于多次池化操作分辨率较低,无法准确地预测目标边缘等细节的问题,本文提出了基于注意力的显著性目标检测方法。在ResNet-50网络中加入注意力精炼模块,利用训练样本的显著真值图对空间注意力进行有监督的学习,使得不同像素位置的相关性更准确。通过深度融合多尺度的特征,用低层特征优化高层特征,精修网络的预测结果使其更加准确。在DUT-OMRON和ECSSD数据集上的测试结果显示,本文方法能显著提升检测效果,F-measure和平均绝对误差都优于其他同类方法。     

Salient object detection using biogeography-based optimization to combine features

In recent studies, ontology related concepts have been introduced into FIPA ACL content language to convey information for agent communication. However, these works have only applied ontology-based knowledge representation in communication message and then demonstrated the advantage of this association. In fact, although ontology can represent semantic implications needed for decidable reasoning support, it has no mechanism for defining complex rule-based representation to support inference. The motivation of this study is to address this issue by developing a semantic-based infrastructure to integrate Semantic Web technologies into ACL message contents. This semantic-based infrastructure defines two different semantic frameworks: the three-tier knowledge representation framework for message content and the Multi-layer Ontology Architecture for content language. The former is developed based on Semantic Web stack to support ontology-based reasoning and rule-based inference. The latter is adopted to develop a Lightweight Ontology-based Content Language (LOCL) to describe agent communication messages in an unambiguous and computer-interpretable way Jena reasoner is used in an application scenario that exploits agent communication with LOCL as content language, OWL as ontology language, and SWRL as rule language to demonstrate the feasibility of the proposed infrastructure.     

Salient object detection using feature clustering and compactness prior

Multimedia Tools and Applications - Salient object detection has been challenging computer vision though some advances have been made recently. In this study, we propose a novel salient object...     

Salient object detection using content-sensitive hypergraph representation and partitioning

As an important problem in image understanding, salient object detection is essential for image classification, object recognition, as well as image retrieval. In this paper, we propose a new approach to detect salient objects from an image by using content-sensitive hypergraph representation and partitioning. Firstly, a polygonal potential Region-Of-Interest (p-ROI) is extracted through analyzing the edge distribution in an image. Secondly, the image is represented by a content-sensitive hypergraph. Instead of using fixed features and parameters for all the images, we propose a new content-sensitive method for feature selection and hypergraph construction. In this method, the most discriminant color channel which maximizes the difference between p-ROI and the background is selected for each image. Also the number of neighbors in hyperedges is adjusted automatically according to the image content. Finally, an incremental hypergraph partitioning is utilized to generate the candidate regions for the final salient object detection, in which all the candidate regions are evaluated by p-ROI and the best match one will be the selected as final salient object. Our approach has been extensively evaluated on a large benchmark image database. Experimental results show that our approach can not only achieve considerable improvement in terms of commonly adopted performance measures in salient object detection, but also provide more precise object boundaries which is desirable for further image processing and understanding.     

基于TI-DMC642的显著性物体检测

基于硬件平台的显著性物体检测技术应用到生产生活中,便可以通过便携设备,实现诸如盲人的视觉导航、交通系统中的路牌识别等问题,具有很高的实用价值.基于TI-DMC642平台,采用谱残差的方法,解决图像分辨率调整、IFFT编码、滤波和阈值化等问题后,可以最终得到效果不错的显著性物体检测并实现在PC机上很难做到的动态实时显示.     

Salient object detection using task simulation as a new input

Multimedia Tools and Applications - Saliency or the salient region changes in the human vision system depending on the type of its behavior and task. That is, the salient region in human vision...