基于多特征扩散方法的显著性物体检测

现有的大部分基于扩散理论的显著性物体检测方法只用了图像的底层特征来构造图和扩散矩阵,并且忽视了显著性物体在图像边缘的可能性。针对此,该文提出一种基于图像的多层特征的扩散方法进行显著性物体检测。首先,采用由背景先验、颜色先验、位置先验组成的高层先验方法选取种子节点。其次,将选取的种子节点的显著性信息通过由图像的底层特征构建的扩散矩阵传播到每个节点得到初始显著图,并将其作为图像的中层特征。然后结合图像的高层特征分别构建扩散矩阵,再次运用扩散方法分别获得中层显著图、高层显著图。最后,非线性融合中层显著图和高层显著图得到最终显著图。该算法在3个数据集MSRA10K,DUT-OMRON和ECSSD上,用3种量化评价指标与现有4种流行算法进行实验结果对比,均取得最好的效果。     

Hierarchical Implicit Shape Modeling

In this paper, a new hierarchical approach for object detection is proposed. Object detection methods based on Implicit Shape Model (ISM) efficiently handle deformable objects, occlusions and clutters. The structure of each object in ISM is defined by a spring like graph. We introduce hierarchical ISM in which structure of each object is defined by a hierarchical star graph. Hierarchical ISM has two layers. In the first layer, a set of local ISMs are used to model object parts. In the second layer, structure of parts with respect to the object center is modeled by global ISM. In the proposed approach, the obtained parts for each object category have high discriminative ability. Therefore, our approach does not require a verification stage. We applied the proposed approach to some datasets and compared the performance of our algorithm to comparable methods. The results show that our method has a superior performance.     

A new challenging image dataset with simple background for evaluating and developing co-segmentation algorithms

Many image co-segmentation algorithms have been proposed over the last decade. In this paper, we present a new dataset for evaluating co-segmentation algorithms, which contains 889 image groups with 18 images in each and the pixel-wise hand-annotated ground truths. The dataset is characterized by simple background produced from nearly a single color. It looks simple but is actually very challenging for current co-segmentation algorithms, because of four difficult cases in it: easy-confused foreground with background, transparent regions in objects, minor holes in objects, and shadows. In order to test the usefulness of our dataset, we review the state-of-the-art co-segmentation algorithms and evaluate seven algorithms on our dataset. The obtained performance of each algorithm is compared with those previously reported in the datasets with complex background. The results prove that our dataset is valuable for the development of co-segmentation techniques. It is more feasible to solve the four difficulties above on the simple background and then extend the solutions to the complex background problems. Our dataset can be freely downloaded from: http://www.iscbit.org/source/MLMR-COS.zip.     

基于超像素和SVM的交互式联合分割算法研究*

联合分割是一类针对前景相同或相似的图像集进行处理的图像分割算法。本文将分割问题视为前背景像素的分类问题,提出了一种基于超像素和机器学习的联合分割算法, 其中使用支持向量机来实现超像素的分类。相比于其他联合分割算法,本文使用词袋(BOF)模型来描述每个超像素,并引入词频-逆向文件频率(Tf-idf)加权算法来优化提取到的特征。为了减少用户交互工作,通过只在一组前景相似的图像中使用一幅种子图像,并在训练分类器时采用样本抽取的方法来解决正负样本数量不平衡的问题。本文使用iCoSeg联合分割标准图像集来测试本文的算法,实验结果表明,相比其他联合分割算法,本文的方法在精确度和灵活性上都更有优势。     

Semantic loop closure detection based on graph matching in multi-objects scenes

Robust loop-closure detection is essential for visual SLAM. Traditional methods often focus on the geometric and visual features in most scenes but ignore the semantic information provided by objects. Based on this consideration, we present a strategy that models the visual scene as semantic sub-graph by only preserving the semantic and geometric information from object detection. To align two sub-graphs efficiently, we use a sparse Kuhn–Munkres algorithm to speed up the search for correspondence among nodes. The shape similarity and the Euclidean distance between objects in the 3-D space are leveraged unitedly to measure the image similarity through graph matching. Furthermore, the proposed approach has been analyzed and compared with the state-of-the-art algorithms at several datasets as well as two indoor real scenes, where the results indicate that our semantic graph-based representation without extracting visual features is feasible for loop-closure detection at potential and competitive precision.     

基于跨模态对比的场景图图像生成

条件图像生成根据不同形式的输入生成符合条件的图像,其中场景图是一类具有代表性的条件输入形式。场景图将图像中的物体抽象为节点,将物体之间的关系抽象为边,是一种广泛应用在计算机视觉和跨模态领域的结构化图表示。由于场景图中包含多个物体和物体之间的关系,现有的场景图图像生成方法容易导致生成结果和条件语义不一致,例如物体缺失和关系错误等。本文提出基于跨模态对比的生成方法解决上述问题。首先,本文提出关系一致性对比使生成的物体关系和输入的边保持一致。我们设计了联合特征代表图像中的物体的关系,并拉近联合特征和与其相关的边特征的距离,使其相比于不相关的边特征距离更接近。本文引入物体一致性对比使的生成的物体区域和输入的节点保持对应。在这个部分我们使用注意力机制获得节点对应的物体特征,然后拉近相关的节点特征于物体特征的距离。最后,本文提出全局一致性对比使的生成的图像整体和输入的场景图保持一致, 该对比损失将相关联的图像和场景图特征拉近,同时将不相关的样本特征相互远离。我们COCO-stuff和VG数据集上进行了详细的实验,实验结果表明我们的方法相比当前最佳性能分别在两个数据集上提升8.33%和8.87%的FID。消融实验表明每个对比损失模块都能够提升图像的生成质量,可视化结果展示了方法对于解决上述问题的有效性。从实验结果可知,我们的方法不仅能够提升图像的生成质量,并能够有效缓解物体缺失和关系错误等语义不一致问题。      

Spatio-temporal object relationships in image sequences using adjacency matrices

In this work, we bring together object tracking and digital watermarking to solve the spatio-temporal object adjacency problem in image sequences. Spatio-temporal relationships are established by embedding objects with unique digital watermarks and then by propagating the watermark frame by frame. Watermark propagation is accomplished by an existing object tracking module so that a tracked object acquires its watermark from the correspondences established by the object tracker. The spatio-temporally marked image sequences can then be searched to establish spatial and temporal adjacency among objects without using traditional spatio-temporal graphs. Borrowing from graph theory, we construct binary adjacency matrices among tracked objects and develop interpretation rules to establish a track history for each object. Track history can be used to determine the arrival of new objects in frames or the changing of spatial and temporal positions of objects with respect to each other as they move through time and space.     

RLP-AGMC: Robust label propagation for saliency detection based on an adaptive graph with multiview connections

There have been remarkable improvements in the salient object detection in the recent years. During the past few years, graph-based saliency detection algorithms have been proposed and made advances. Nevertheless, most of the state-of-the-art graph-based approaches are usually designed with low-level features, misleading assumption, fixed predefined graph structure and weak affinity matrix, which determine that they are not robust enough to handle images with complex or cluttered background.In this paper, we propose a robust label propagation-based mechanism for salient object detection throughout an adaptive graph to tackle above issues. Low-level features as well as deep features are integrated into the proposed framework to measure the similarity between different nodes. In addition, a robust mechanism is presented to calculate seeds based on the distribution of salient regions, which can achieve desirable results even if the object is in contact with the image boundary and the image scene is complex. Then, an adaptive graph with multiview connections is constructed based on different cues to learn the graph affinity matrix, which can better capture the characteristics between spatially adjacent and distant regions. Finally, a novel RLP-AGMC model, i.e. robust label propagation throughout an adaptive graph with multiview connections, is put forward to calculate saliency maps in combination with the obtained seed vectors. Comprehensive experiments on six public datasets demonstrate the proposed method outperforms fourteen existing state-of-the-art methods in terms of various evaluation metrics.     

Human object interaction detection based on feature optimization and key human-object enhancement

Aiming at the problem of unclear or missing human object interaction behavior objects in complex background, we propose a human object interaction detection algorithm based on feature optimization and key human-object enhancement. In order to solve the problem of missing human behavior objects, we propose Feature Optimized Faster Region Convolutional Neural Network (FOFR-CNN). FOFR-CNN is an object detection network optimized by multi-scale feature optimization algorithm, taking into account both image semantics and image structure. In order to reduce the interference of complex background, we propose a Key Human-Object Enhancement Network. The network uses an instance-based method to enhance the features of interactive objects. In order to enrich the interaction information, we use the graph convolutional network. Experimental results on HICO-DET, V-COCO and HOI-A datasets show that the proposed algorithm has significantly improved accuracy and multi-scale object detection ability compared with other human object interaction algorithms.     

A heuristic for the retrieval of objects in video in the framework of the rough indexing paradigm

In this paper, we tackle the problem of matching of objects in video in the framework of the rough indexing paradigm. In this context, the video data are of very low spatial and temporal resolution because they come from partially decoded MPEG compressed streams. This paradigm enables us to achieve our purpose in near real time due to the faster computation on rough data than on original full spatial and temporal resolution video frames.In this context, segmentation of rough video frames is inaccurate and the region features (texture, color, shape) are not strongly relevant. The structure of the objects must be considered in order to improve the robustness of the matching of regions. The problem of object matching can be expressed in terms of region adjacency graph (RAG) matching.Here, we propose a directed acyclic graph (DAG) matching method based on a heuristic in order to approximate object matching. The RAGs to compare are first transformed into DAGs by orienting edges. Then, we compute some combinatoric metrics on nodes in order to classify them by similarity. At the end, a top-down process on DAGs aims to match similar patterns that exist between the two DAGs.The results are compared with those of a method based on relaxation matching.     

基于模糊聚类的运动对象分割算法研究

为了从视频序列中分割出完整的、一致的运动视频对象,该文使用基于模糊聚类的分割算法获得组成对象边界的像素,从而提取对象。该算法首先使用了当前帧以及之前一些帧的图像信息计算其在小波域中不同子带的运动特征,并根据这些运动特征构造了低分辨率图像的运动特征矢量集;然后,使用模糊C-均值聚类算法分离出图像中发生显著变化的像素,以此代替帧间差图像,并利用传统的变化检测方法获得对象变化检测模型,从而提取对象;同时,使用相继两帧之间的平均绝对差值大小确定计算当前帧运动特征所需帧的数量,保证提取视频对象的精确性。实验结果证明该方法对于分割各种图像序列中的视频对象是有效的。     

Object-oriented analysis-synthesis coding based on moving two-dimensional objects

An object-oriented analysis-synthesis coder is presented which encodes arbitrarily shaped objects instead of rectangular blocks. The objects are described by three parameter sets defining their motion, shape and colour. Throughout this contribution, the colour parameters denote the luminance and chrominance values of the object surface. The parameter sets of each object are obtained by image analysis based on source models of moving 2D-objects and coded by an object-dependent parameter coding. Using the coded parameter sets an image can be reconstructed by model-based image synthesis. In order to cut down the generated bit-rate of the parameter coding, the colour updating of an object is suppressed if the modelling of the object by the source model is sufficiently exact, i.e., if only a relatively small colour update information would be needed for an errorless image synthesis. Omitting colour update information, small position errors of objects denoted as geometrical distortions are allowed for image synthesis instead of quantization error distortions. Tolerating geometrical distortions, the image area to be updated by colour coding can be decreased to 4% of the image size without introducing annoying distortions. As motion and shape parameters can efficiently be coded, about 1 bit per pel remains for colour updating in a 64 kbit/s coder compared to about 0.1 bit per pel in the standard reference coder (RM8) of the CCITT. Experimental results concerning the efficient coding of motion and shape parameters are given and discussed. The coding of the colour information will be dealt with in further research.     

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.     

WeBox:locating small objects from weak edges

In the object detection task, how to better deal with small objects is a great challenge. The detection accuracy of small objects greatly affects the final detection performance. Our propose a detection framework WeBox based on weak edges for small object detection in dense scenes, and proposes to train the richer convolutional features (RCF) edges detection network in a weakly supervised way to generate multi-instance proposals. Then through the region proposal network (RPN) network to locate each object in the multi-instance proposals, in order to ensure the effectiveness of the multi-instance proposals, we correspondingly proposed a multi-instance proposals evaluation criterion. Finally, we use faster region-based convolutional neural network (R-CNN) to process WeBox single-instance proposals and fine-tune the final results at the pixel level. The experiments have been carried out on BDCI and TT100K proves that our method maintains high computational efficiency while effectively improving the accuracy of small objects detection.     

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.     

基于稀疏方位超图匹配的图像配准算法

为提高超图匹配的正确匹配率并降低其计算复杂度,提出了一种基于稀疏方位超图匹配的图像配准算法。提取图像的结构特征点为图节点,采用最小生成树算法获取节点间的主要连接关系,并用包含邻近的节点与边的三元组结构定义超边,计算超边的方位角度信息,由此构建稀疏方位超图;利用方位信息构建亲近矩阵,并采用全局最优匹配方法实现匹配。实验表明,对于实际图像的配准,该算法既具有较低的计算复杂度,又有良好的匹配效果。     

Object segmentation and labeling by learning from examples

We propose a system that employs low-level image segmentation followed by color and two-dimensional (2-D) shape matching to automatically group those low-level segments into objects based on their similarity to a set of example object templates presented by the user. A hierarchical content tree data structure is used for each database image to store matching combinations of low-level regions as objects. The system automatically initializes the content tree with only "elementary nodes" representing homogeneous low-level regions. The "learning" phase refers to labeling of combinations of low-level regions that have resulted in successful color and/or 2-D shape matches with the example template(s). These combinations are labeled as "object nodes" in the hierarchical content tree. Once learning is performed, the speed of second-time retrieval of learned objects in the database increases significantly. The learning step can be performed off-line provided that example objects are given in the form of user interest profiles. Experimental results are presented to demonstrate the effectiveness of the proposed system with hierarchical content tree representation and learning by color and 2-D shape matching on collections of car and face images.     

BALLS: A structured peer-to-peer system with integrated load balancing

Load balancing is an important problem for structured peer-to-peer systems. We are particularly interested in the consumption of network bandwidth for routing traffic and in the usage of computer resources for object storage. In this paper, we investigate the possibility to simultaneously balance these two types of load. We present a structured peer-to-peer overlay that efficiently performs such simultaneous load balancing. The overlay is constructed by partitioning the nodes of a de Bruijn graph and by allocating the partitions to the peers. Peers balance network bandwidth consumption by repartitioning the nodes. Balancing of computer resources for storage is enabled by dissociating the actual storage location of an object from the location of its search key. The paper presents and analyzes the protocols required to maintain the overlay structure and perform load balancing. We demonstrate their efficiency by simulation. We also compare our proposed overlay network with other approaches.     

Multilevel segmentation of histopathological images using cooccurrence of tissue objects

This paper presents a new approach for unsupervised segmentation of histopathological tissue images. This approach has two main contributions. First, it introduces a new set of high-level texture features to represent the prior knowledge of spatial organization of the tissue components. These texture features are defined on the tissue components, which are approximately represented by tissue objects, and quantify the frequency of two component types being cooccurred in a particular spatial relationship. As they are defined on components, rather than on image pixels, these object cooccurrence features are expected to be less vulnerable to noise and variations that are typically observed at the pixel level of tissue images. Second, it proposes to obtain multiple segmentations by multilevel partitioning of a graph constructed on the tissue objects and combine them by an ensemble function. This multilevel graph partitioning algorithm introduces randomization in graph construction and refinements in its multilevel scheme to increase diversity of individual segmentations, and thus, improve the final result. The experiments on 200 colon tissue images reveal that the proposed approach--the object cooccurrence features together with the multilevel segmentation algorithm--is effective to obtain high-quality results. The experiments also show that it improves the segmentation results compared to the previous approaches.