Automated graph-based analysis and correction of cortical volumetopology

The human cerebral cortex is topologically equivalent to a sheet and can be considered topologically spherical if it is closed at the brain stem. Low-level segmentation of magnetic resonance (MR) imagery typically produces cerebral volumes whose tessellations are not topologically spherical. We present a novel algorithm that analyzes and constrains the topology of a volumetric object. Graphs are formed that represent the connectivity of voxel segments in the foreground and background of the image. These graphs are analyzed and minimal corrections to the volume are made prior to tessellation. We apply the algorithm to a simple test object and to cerebral white matter masks generated by a low-level tissue identification sequence. We tessellate the resulting objects using the marching cubes algorithm and verify their topology by computing their Euler characteristics. A key benefit of the algorithm is that it localizes the change to a volume to the specific areas of its topological defects.     

基于深度学习的复杂背景图像分类方法研究

复杂背景图像受背景干扰后不易被识别。针对这一问题,文中提出了基于前景分割机制的卷积神经网络图像分类方法。采用全卷积神经网络对图像前景区域进行自动分割,通过图像中前景区域周围的最小边界框对其进行定位。对于定位的前景区域,构建卷积神经网络对其进行处理以区分不同的类别,从而实现复杂背景图像的分类。将提出方法在公开数据集中提取的单一背景和复杂背景图像数据集上进行对比实验,并使用迁移学习与数据增强等方法优化模型。实验结果表明,所提方法使用前景区域分割相比于仅分类CNN具有更高的准确度,且复杂背景图像上的准确度提升幅度要远大于单一背景图像。该结果说明引入前景区域分割对于复杂背景图像分类模型准确度的提升具有一定帮助,能够显著前景区域特征并减少背景因素的干扰。     

Video inpainting under constrained camera motion.

A framework for inpainting missing parts of a video sequence recorded with a moving or stationary camera is presented in this work. The region to be inpainted is general: it may be still or moving, in the background or in the foreground, it may occlude one object and be occluded by some other object. The algorithm consists of a simple preprocessing stage and two steps of video inpainting. In the preprocessing stage, we roughly segment each frame into foreground and background. We use this segmentation to build three image mosaics that help to produce time consistent results and also improve the performance of the algorithm by reducing the search space. In the first video inpainting step, we reconstruct moving objects in the foreground that are "occluded" by the region to be inpainted. To this end, we fill the gap as much as possible by copying information from the moving foreground in other frames, using a priority-based scheme. In the second step, we inpaint the remaining hole with the background. To accomplish this, we first align the frames and directly copy when possible. The remaining pixels are filled in by extending spatial texture synthesis techniques to the spatiotemporal domain. The proposed framework has several advantages over state-of-the-art algorithms that deal with similar types of data and constraints. It permits some camera motion, is simple to implement, fast, does not require statistical models of background nor foreground, works well in the presence of rich and cluttered backgrounds, and the results show that there is no visible blurring or motion artifacts. A number of real examples taken with a consumer hand-held camera are shown supporting these findings.     

基于全卷积网络的语义显著性区域检测方法研究

基于底层视觉特征和先验知识的显著性区域检测算法难以检测一些复杂的显著性目标,人的视觉系统能分辨这些目标是由于其中包含丰富的语义知识.本文构建了一个基于全卷积结构的语义显著性区域检测网络,用数据驱动的方式构建从图像底层特征到人类语义认知的映射,提取语义显著性区域.针对网络提取的语义显著性区域的缺点,本文进一步引入颜色信息、目标边界信息、空间一致性信息获得准确的超像素级前景和背景概率.最后提出一个优化模型融合前景和背景概率信息、语义信息、空间一致性信息得到最终的显著性区域图.在6个数据集上与15种最新算法的比较实验证明了本文算法的有效性和鲁棒性.     

Content-based image retrieval in presence of foreground disturbances

The image retrieval problem in the presence of possible foreground disturbances is considered. The foreground may be irrelevant for the retrieval purposes but it occludes the background and hence reduces the retrieval accuracy. The accrued inaccuracy is quantified in terms of cardinality of the occluding region. The use of the sprite generated from a video clip is proposed as a query, so that the effect of moving foreground can be eliminated. The segmented foreground region is filled in by constructing the background sprite to increase the retrieval accuracy. The performance of a retrieval scheme under foreground disturbance is presented here     

Active volume models for medical image segmentation

In this paper, we propose a novel predictive model, active volume model (AVM), for object boundary extraction. It is a dynamic "object" model whose manifestation includes a deformable curve or surface representing a shape, a volumetric interior carrying appearance statistics, and an embedded classifier that separates object from background based on current feature information. The model focuses on an accurate representation of the foreground object's attributes, and does not explicitly represent the background. As we will show, however, the model is capable of reasoning about the background statistics thus can detect when is change sufficient to invoke a boundary decision. When applied to object segmentation, the model alternates between two basic operations: 1) deforming according to current region of interest (ROI), which is a binary mask representing the object region predicted by the current model, and 2) predicting ROI according to current appearance statistics of the model. To further improve robustness and accuracy when segmenting multiple objects or an object with multiple parts, we also propose multiple-surface active volume model (MSAVM), which consists of several single-surface AVM models subject to high-level geometric spatial constraints. An AVM's deformation is derived from a linear system based on finite element method (FEM). To keep the model's surface triangulation optimized, surface remeshing is derived from another linear system based on Laplacian mesh optimization (LMO). Thus efficient optimization and fast convergence of the model are achieved by solving two linear systems. Segmentation, validation and comparison results are presented from experiments on a variety of 2-D and 3-D medical images.     

Background foreground boundary aware efficient motion search for surveillance videos

The huge amount of data in surveillance video coding demands high compression rates with lower computational requirements for efficient storage and archival. The motion estimation is a very time-consuming process in the traditional video coding framework, and hence reducing computational complexity is a pressing task, especially for surveillance videos. The presence of significant background proportion in surveillance videos makes its special case for coding. The existing surveillance video coding methods propose separate search mechanisms for background and foreground regions. However, they still suffer from misclassification and inefficient search strategies since it does not consider the inherent motion characteristics of the foreground regions. In this paper, a background-foreground-boundary aware block matching algorithm is proposed to exploit special characteristics of the surveillance videos. A novel three-step framework is proposed for boundary aware block matching process. For this, firstly, the blocks are categorized into three classes, namely, background, foreground, and boundary blocks. Secondly, the motion search is performed by employing different search strategies for each class. The zero-motion vector-based search is employed for background blocks. Whereas, to exploit fast and directional motion characteristics of the boundary and foreground blocks, the eight rotating uni-wing diamond search patterns are proposed. Thirdly, the speed-up is achieved through the novel region-based sub-sampled structure. The experimental results demonstrate that two to four times speed-up over existing methods can be achieved through this scheme while maintaining better matching accuracy.     

基于场景模式的立体图像舒适度客观评价模型

为了预测双目立体图像内容对视觉健康可能产生的危害,该文提出一种基于场景模式的立体图像舒适度客观评价模型。根据场景中前景目标和后景区域相对于显示屏幕的凹凸性以及是否处于舒适观看区,将自然场景抽象为多种场景模式。在模式选择阶段,从视差图中自适应分割出前景目标和后景区域,根据前、后景的视差角特征确定场景所属的模式;在建模阶段,采用前、后景的视差角特征结合前景的宽度角和曲折度特征对各个场景模式分别进行建模,并量化了前、后景视差因素对视觉舒适度的影响。在IVY数据库上的实验结果表明,所提出的模型与主观感知存在较好的一致性,Pearson相关系数高于0.91, Spearman相关系数高于0.90, Kendall相关系数高于0.74,平均绝对值误差低于0.24,均方根误差低于0.32,与现有的方法相比,该文所提出的模型的评价效果更好,更接近于主观测试结果。     

基于图像融合的运动前景检测方法

提出了一种有效的运动前景检测方法。该方法根据图像融合思想,将背景帧与监控视频的当前帧在R,G和B颜色通道分别进行融合,形成包含背景帧和当前帧视觉信息的单一融合图像。之后根据背景区域与前景运动目标在饱和度上存在较大差异的现象,使用大津算法分割融合图像的饱和度分量图,形成运动前景二值图。经形态学处理后,形成了目标区域较完整、背景干净的运动前景检测图。实验结果显示,该算法具有较好的前景检测性能,解决了背景减法过分依赖背景帧的缺陷。     

Bilayer representation for three dimensional visual communication

This paper proposes a bilayer representation of scene consisting of foreground and background. It uses two layers to represent foreground and background, respectively. Unlike previous layer-based approaches, both layers cover the whole region instead of interested regions. Based on the bilayer representation, bilayer stereo matching, view synthesis approach and foreground/background separation algorithm are developed for three dimensional visual communication. They all consist of two steps: recovery of disparity fields of both layers and composition of these disparity fields; synthesis of images of both layers and composition of these images; computation of two layer costs and separation of foreground and background. Experimental results demonstrate that both high quality and high efficiency are achieved by above approaches. They meet the requirements of desktop-based three dimensional visual communication.     

一种抗光照突变的前景提取方法研究

针对经典前景提取算法无法在光照突变情况下正确提取前景的问题,根据LBP算子对光照不敏感的特性,提出了一种基于截尾均值的纹理特征提取算法,即通过对噪声的抑制及对平坦区域序列的稳定性处理,解决了原有LBP算子易受噪声干扰,平坦区域序列不稳定及得到的纹理图信息冗余的问题.结合高质量纹理特征,根据纹理特征的光照不变性,设计了一种能有效应对光照突变情况的背景更新模型,实验结果表明,本文提出的融合纹理特征的前景提取模型不仅能够在光照缓慢变化的情况下有效地对运动目标前景进行提取,而且在光照突变情况下仍然能够进行准确提取,前景提取的准确率相比平均背景模型提高61.7%,相比混合高斯模型提高59.3%.     

基于多线索概率分布图像融合的目标跟踪

为了克服多线索目标跟踪中固定线索权值的不足,提出采用颜色、运动历史、视觉显著性等多种概率分布图像来描述目标的观测信息,通过目标在前一帧的位置确定中心区域和周边区域,并计算不同概率分布图像基于这两个区域的直方图,即中心直方图和周边直方图.每个概率分布图像的置信度由其中心直方图和周边直方图的差异度来描述.根据不同线索的置信度,在线调节当前帧各种概率分布图像在目标位置判断中所占的权重,实现对目标的多线索融合跟踪.实验结果表明,比常用的固定线索权值的融合算法效果更好.     

基于多尺度特征校准的图像协调化方法

图像组合是图像处理中一个重要操作，然而组合图像中前景区域与背景区域的外观不协调使得组合图像看起来不真实。图像协调化是图像组合中极其重要的一个环节，其目的是调整组合图像前景区域的外观使其与背景区域一致，从而让组合图像在视觉上看起来真实。然而，现有方法只考虑了组合图像前景与背景之间的外观差异，忽略了图像局部的亮度变化差异，这使得图像整体的光照不协调。为此，该文提出一个新的多尺度特征校准模块(MFCM)学习不同尺度的感受野之间细微的特征差异。基于所提模块，该文进一步设计了一个新的编码器学习组合图像中前景与背景的外观差异和局部亮度变化，然后利用解码器重构出图像，并通过一个对前景区域归一化的回归损失指导网络学习调整前景区域的外观。在广泛使用的iHarmony4数据集上进行实验验证，结果表明该方法的效果超过了目前最优的方法，验证了该方法的有效性。     

基于时间窗的自适应核密度估计运动检测方法

在对非参数核密度估计算法改进的基础上,针对远程视频监控中存在前景检测不够精确、实时性低等问题,提出了用于自适应背景更新的基于像素时间信息窗的核密度估计(TIW-KDE)算法,该算法充分利用时间轴上的前景帧的信息,自适应地将背景划分为动态背景区域和非动态背景区域,对动态背景区域用改进的非参数核密度估计算法进行更新,对非动态背景区域采用渐进式算法更新,有效解决了非参数核密度估计算法在背景更新时引起的背景污染和计算量大问题。实验结果表明,该算法在提高前景检测精确性的前提下,在处理实时性方面得到很大提高。     

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.     

基于分割图像的小波编码

提出一种基于分割的小波编码方法.该方法将一幅图像分割成两个区域:静止区域(背景)和包含边缘信息的区域(前景),然后对每个区域以最优编码器分别进行编码.背景区域小波变换后,用SPIHT算法对其编码.对前景区域使用PVQ(预测矢量量化)进行编码.实验结果表明,与SPIHT算法相比,在相同压缩比的情况下,该方法改善了重构图像客观(均方误差,MSE)和主观(视觉)的质量.     

Statistical modeling of complex backgrounds for foreground object detection

This paper addresses the problem of background modeling for foreground object detection in complex environments. A Bayesian framework that incorporates spectral, spatial, and temporal features to characterize the background appearance is proposed. Under this framework, the background is represented by the most significant and frequent features, i.e., the principal features, at each pixel. A Bayes decision rule is derived for background and foreground classification based on the statistics of principal features. Principal feature representation for both the static and dynamic background pixels is investigated. A novel learning method is proposed to adapt to both gradual and sudden "once-off" background changes. The convergence of the learning process is analyzed and a formula to select a proper learning rate is derived. Under the proposed framework, a novel algorithm for detecting foreground objects from complex environments is then established. It consists of change detection, change classification, foreground segmentation, and background maintenance. Experiments were conducted on image sequences containing targets of interest in a variety of environments, e.g., offices, public buildings, subway stations, campuses, parking lots, airports, and sidewalks. Good results of foreground detection were obtained. Quantitative evaluation and comparison with the existing method show that the proposed method provides much improved results.     

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。     

分区域的医学图像高容量无损信息隐藏方法

针对医学图像的分区域典型特征,提出一种基于区域和直方图平移的高容量无损信息隐藏方法。本方法用最大类间距分割法求得原始图像的前景区域,再用聚合多边形逼近和图像拟合法得到其数据嵌入区域。在数据嵌入过程中,提出利用差值直方图循环平移和基于编码的直方图平移方法分别在前景和背景区域嵌入数据,提高了原始直方图平移方法容量和解决了溢出问题。实验结果表明该方法总的嵌入容量可达1 bit/packet以上,并且隐秘图像质量在40dB左右,适用于具有区域特征的质量敏感图像的大容量信息隐藏。     

Annular filters for binary images

A binary annular filter removes isolated points in the foreground and the background of an image. Here, the adjective "isolated" refers to an underlying adjacency relation between pixels, which may be different for foreground and background pixels. In this paper, annular filters are represented in terms of switch pairs. A switch pair consists of two operators which govern the removal of points from foreground and background, respectively. In the case of annular filters, switch pairs are completely determined by foreground and background adjacency. It is shown that a specific triangular condition in terms of both adjacencies is required to establish idempotence of the resulting annular filter. In the case of translation-invariant operators, an annular filter takes the form X-->(X plus sign in circleA) intersectionX union or logical sum(X minus sign in circleB), where A and B are structuring elements satisfying some further conditions: when A intersectionB intersection(A plus sign in circleB) not equal?, it is an (idempotent) morphological filter; when A union or logical sumB subsetA plus sign in circleB, it is a strong filter and in this case it can be obtained by composing in either order the annular opening X-->(X plus sign in circleA) intersectionX and the annular closing X--> union or logical sum(X plus sign in circleB).