Detection of Salient Curvature Features on Polygonal Surfaces

We develop an approach for stable detection of perceptually salient curvature features on surfaces approximated by dense triangle meshes. The approach explores an "area degenerating" effect of the focal surface near its singularities and combines together a new approximations of the mean and Gaussian curvatures, nonlinear averaging of curvature maps, histogram-based curvature extrema filtering, and an image processing skeletonization procedure adapted for triangular meshes. Finally we use perceptually significant curvature extrema triangles to enhance the Garland-Heckbert mesh decimation method.     

A Shrink Wrapping Approach to Remeshing Polygonal Surfaces

Due to their simplicity and flexibility, polygonal meshes are about to become the standard representation for surface geometry in computer graphics applications. Some algorithms in the context of multiresolution representation and modeling can be performed much more efficiently and robustly if the underlying surface tesselations have the special subdivision connectivity. In this paper, we propose a new algorithm for converting a given unstructured triangle mesh into one having subdivision connectivity. The basic idea is to simulate the shrink wrapping process by adapting the deformable surface technique known from image processing. The resulting algorithm generates subdivision connectivity meshes whose base meshes only have a very small number of triangles. The iterative optimization process that distributes the mesh vertices over the given surface geometry guarantees low local distortion of the triangular faces. We show several examples and applications including the progressive transmission of subdivision surfaces.     

融合纹理和颜色特征的显著目标检测

针对在无监督情况下,图像中显著性目标的不确定问题,提出了一种基于纹理和颜色特征的显著目标检测算法.首先,利用Gabor滤波器提取图像的纹理特征,构造背景模型.结合图像边缘信息更新背景先验信息.其次,利用颜色对比度来获取显著特征,利用贝叶斯增强来提高检测效果.最后,在MSRA和ECSSD两个公开数据集上,将论文算法与其他...     

Theoretical Developments on Polygonal Approximation of Parametric Surfaces for Ray Tracing

Some theoretical extensions are brought to Koparkar and Mudur's method which deals with a polygonal approximation of parametric surfaces using potential extrema. The proposed extensions allow the determination of both the existence and the equation of a curve solution of potential extrema. Solutions are given to solve the crack problem and to avoid the artificats due to an inexact ray-surface intersection point near the silhouette or on the higher curvature regions. Moreover, two methods of ray tracing surfaces are proposed.     

基于多尺度先验深度特征的多目标显著性检测方法

显著性检测是近年来国内外计算机视觉领域研究的热点问题,在图像压缩、目标识别与跟踪、场景分类等领域具有广泛的应用.针对大多显著性检测方法只针对单个目标且鲁棒性不强这一问题,本文提出一种基于深度特征的显著性检测方法.首先,在多个尺度上对输入图像进行超像素分割,利用目标先验知识对预显著区域进行提取和优化.然后,采用卷积神经网络提取预选目标区域的深度特征.对高维深度特征进行主成分分析并计算显著性值.最后,提出一种改进的加权多层元胞自动机方法,对多尺度分割显著图进行融合优化,得到最终显著图.在公开标准数据集SED2和HKU_IS的实验表明,与现有经典显著性检测方法相比,本文方法对多显著目标检测更准确.     

邻域与梯度显著特征融合的沥青路面裂缝检测方法

针对沥青路面裂缝检测中富纹理噪声影响和细小裂缝误识别严重等问题,提出一种邻域与梯度显著特征融合的沥青路面裂缝检测方法.首先采用灰度校正和形态学重建降低外界干扰和富纹理中较亮点状噪声导致亮度不均的影响,根据像素及其邻域的显著差异提取邻域显著特征,通过方向可调滤波器得到不同方向上的梯度显著特征,将两者卷积融合并优选方向生成...     

凸多边形域上的参数曲面自由变形

为了获得丰富的曲面造型效果,构造了一种兼具单峰性和区域峰值性,支撑区域为任意凸多边形域的伸缩因子.首先引入基于凸多边形域的伸缩因子;然后构造了空间变形矩阵;最后将上述变形矩阵作用于待变形曲面的方程上,获得相应的变形效果.数值实例结果表明,通过调控支撑区域、峰值区域、变形中心、主方向、伸缩参数和光滑参数,可以灵活地对曲面变形;该方法不仅计算简单、易于控制,还能精确地控制变形的范围,迭加使用可以得到丰富的变形效果.     

A Perceptually Constrained GSVD-Based Approach for Enhancing Speech Corrupted by Colored Noise

The singular value decomposition (SVD)-based method for single-channel speech enhancement has been shown to be very useful when the additive noise is white. For colored noise, with this approach, one needs to whiten the noise spectrum prior to SVD-based approach and perform the inverse whitening processing afterwards. A truncated quotient SVD (QSVD)-based approach has been proposed to handle this problem and found very useful. In this paper, a generalized SVD (GSVD)-based subspace approach for speech enhancement is first extended from the concept of the truncated QSVD-based approach, in which the dimension of the signal subspace can be precisely and automatically determined for each frame of the noisy signal. But with this new approach some residual noise is still perceivable under lower signal-to-noise ratio conditions. Therefore a perceptually constrained GSVD (PCGSVD)-based approach is further proposed to incorporate the masking properties of human auditory system to make sure the undesired residual noise to be nearly un-perceivable. Closed-form solutions are obtained for both the GSVD- and PCGSVD-based enhancement approaches. Very carefully performed objective evaluations and subjective listening tests show that the PCGSVD-based approach proposed here can offer improved speech quality, intelligibility and recognition accuracy, whether the noise is stationary or nonstationary, especially when the additive noise is nonwhite     

显著性物体检测研究综述

人类的视觉系统能够迅速地、有选择地从视觉场景中检测出感兴趣的目标或者具有显著特征的物体,并根据更高层次的视觉任务目的对它们进行处理和理解,从而实现相应的行为或决策.将人类这种选择性视觉注意机制引入到计算机视觉的信息处理中,可以有效地减少视觉计算所需处理的数据量、加速整个处理过程,并进一步方便更高层次视觉任务的处理,因而...     

A Two-Stage Bayesian Integration Framework for Salient Object Detection on Light Field

Unique visual features of 4D light field data have been shown to affect detection of salient objects. Nevertheless, only a few studies explore it yet. In this study, several helpful visual features extracted from light field data are fused in a two-stage Bayesian integration framework for salient object detection. First, background weighted color contrast is computed in high dimensional color space, which is more distinctive to identify object of interest. Second, focusness map of foreground slice is estimated. Then, it is combined with the color contrast results via first-stage Bayesian fusion. Third, background weighted depth contrast is computed. Depth contrast has been proved to be an extremely useful cue for salient object detection and complementary to color contrast. Finally, in the second-stage Bayesian fusion step, the depth-induced contrast saliency is further fused with the first-stage saliency fusion results to get the final saliency map. Experiments of comparing with eight existing state-of-the-art methods on light field benchmark datasets show that the proposed method can handle challenging scenarios such as cluttered background, and achieves the most visually acceptable salient object detection results.     

基于支持向量机的显著性建筑物检测

提出了一种针对自然图像中显著性建筑物的检测方法.首先,采用自底向上的注意力机制,对图像进行Haar小波分解,对得到的HL,LH分量进行平方求和,得到增强图像,然后对该增强图像在垂直方向上进行侧投影,基于得到的投影曲线进行多层阈值分割,找到显著性建筑物候选区域.进而,利用Sobel算子进行水平边缘与垂直边缘的检测,并统计较长的水平边缘与垂直边缘的数目,组成特征矢量.最后利用线性支持向量机对特征进行分类.实验证明了所提算法的有效性.     

基于中心-对角对比度的显著性检测

针对图像显著性检测中广泛运用的中心-四周对比度方法存在的缺陷,提出了中心-对角对比度（Corner-Surround Contrast,CSC）算法,实现从背景中有效提取显著区域;中心-四周对比度方法难以保证分割的准确性,容易导致错误的显著检测结果,并且仅使用中心-四周对比度对目标物体进行显著性编码并不十分有效;CSC算法在提取中心和周边区域差异性的同时,结合它们之间位置的相对性,并设计了一个多核信息融合模型,以不同权重融合多种对比度方法以产生最优显著图,最后用图分割算法来进行二元分割,获得准确的显著图;实验结果表明CSC算法能够有效捕捉显著物体的局部差异,提高显著性物体定位及分割精度的性能,减少噪声的影响,从背景中分离出精确的显著性区域,获得更优的显著性检测结果。     

一种基于词袋模型的新的显著性目标检测方法

提出一种基于词袋模型的新的显著性目标检测方法.该方法首先利用目标性计算先验概率显著图,然后在图像的超像素区域内建立词袋模型,并基于此特征计算条件概率显著图,最后根据贝叶斯推断将先验概率和条件概率显著图进行合成.在ASD、SED以及SOD显著性目标公开数据库上与目前16种主流方法进行对比,实验结果表明本文方法具有更高的精度和更好的查全率,能够一致高亮地凸显图像中的显著性目标.     

基于mel标度频谱和音素分割的汉语语音单词端点检测方法

利用语音声学信号的频谱分析来寻找连续语音信号帧的分割点,再结合音素分割方法,成功的提高了分割精度。实验表明mel标度频谱法比传统的以信号的短时能量,过零率等简单特征作为判决特征参数的语音端点检测方法更适合语音的分割。     

基于Faster R-CNN的显著性目标检测方法

显著性目标检测成为计算机视觉领域中的研究热点问题之一，但目前的方法在面对前景和背景对比度不强及复杂背景的图像时，较难取得好的检测效果。融合多尺度超像素分割方法，提出一种在背景信息相对复杂的场景中基于Faster R-CNN的显著性目标检测方法。首先对图像进行多尺度超像素分割，同时利用Faster R-CNN对图像进行目标检测，根据似物性特点对超像素进行显著性筛选，得到初始目标位置特征后进行显著性检测及优化，最后使用元胞自动机方法对多尺度超像素显著性图进行融合。通过在特定类数据集进行实验，与已有典型显著性检测进行对比分析，验证了本文方法在背景复杂的图像中可提升显著性目标检测的精度。     

基于通勤距离的显著性检测方法

针对图像显著性检测问题,提出一种基于通勤距离度量区域显著性,并提取图像中重要目标的方法.首先用聚类算法检测图像边界的背景种子点,构建初始背景先验图;其次利用显著点构建包围显著目标的凸包,提取凸包内前景种子点诱导其他区域的显著性值,从而得到改进的凸包先验图;最后将2个先验图融合得到最终的显著图.该算法中涉及的区域间的特征对比均应用了新颖而鲁棒的通勤距离.实验结果表明,通勤距离能够更准确有效地度量区域间的相似性,比传统的测地距离和欧氏距离更加优越,并优于现有的大多数算法.     

基于曲线和曲面控制的多边形物体变形反走样

基于参数曲线和曲面控制的空间变形是重要的几何外形编辑和柔性物体动画实现手段．当这两类变形方法的对象是多边形物体时,如何对变形物体进行重采样以得到高质量结果,是计算机动画和几何造型领域中的一个重要问题．该文针对B-样条曲线和曲面控制的空间变形方法,提出了面向多边形物体的空间变形反走样方法．在该方法中,利用等距技术将B-样条曲线或曲面所张成的变形空间近似表示为张量积B-样条参数体,结合作者提出的多边形物体精确B-样条自由变形方法,实现了参数曲线和曲面控制的多边形物体变形反走样．