基于GPU自适应的环境遮挡算法

针对传统的环境光遮挡算法中不能自适应的问题,提出了基于GPU自适应的环境遮挡算法.该算法充分利用了GPU并行计算技术和离屏渲染技术,快速计算出适合所载入场景的自适应步长;并将传统环境遮挡采样方法和抖动采样的思想相结合,对采样方法进行了改进;同时也简化了传统环境光遮挡算法中最终遮挡值的计算.实验结果表明,该方法不局限于特定场景,不需要对场景进行预处理,可以准确高效的计算环境光的遮挡情况,并且实现实时绘制.     

面向大尺度战场的地貌晕渲增强方法

地貌晕渲是大尺度战场仿真中的重要一环,针对现有的地貌晕渲技术在细节处纹理特征不明显的问题,提出了一种结合高程曲率和环境光遮蔽的大尺度战场地貌晕渲增强方法.第1步,通过分析数字高程数据的曲率属性生成地形曲率图,曲率图与卫星影像叠加可以突出显示地貌特征线.第2步,提出一种基于深度可分离卷积的环境光遮蔽计算方法,能够增强战场地形在沟壑处的视觉表现.最后将曲率图、环境光遮蔽与卫星影像三者融合生成实时地貌晕渲效果.实验表明,本文方法可以在较低级别的全球卫星影像上呈现更好的视觉效果,使得观察者在把握三维地形整体走势的同时,能进一步分析地貌细节处的纹理特征.     

A Fast Ambient Occlusion Method for Real-Time Plant Rendering

Global illumination effects are crucial for virtual plant rendering. Whereas real-time global illumination rendering of plants is impractical, ambient occlusion is an efficient alternative approximation. A tree model with millions of triangles is common, and the triangles can be considered as randomly distributed. The existing ambient occlusion methods fail to apply on such a type of object. In this paper, we present a new ambient occlusion method dedicated to real time plant rendering with limited user interaction. This method is a three-step ambient occlusion calculation framework which is suitable for a huge number of geometry objects distributed randomly in space. The complexity of the proposed algorithm is O（n）, compared to the conventional methods with complexities of O（n^2）. Furthermore, parameters in this method can be easily adjusted to achieve flexible ambient occlusion effects. With this ambient occlusion calculation method, we can manipulate plant models with millions of organs, as well as geometry objects with large number of randomly distributed components with affordable time, and with perceptual quality comparable to the previous ambient occlusion methods.     

基于卷积神经网络的实时环境光遮蔽计算

环境光遮蔽是一种常用于计算机游戏以及可视化领域的低频全局光照模拟算法。已有的基于屏幕空间的环境光遮蔽计算方法虽然保证了计算的实时性,但是存在估计失真以及细节丢失等难以解决的问题。针对该问题,本文提出了一种结合低频光线追踪采样以及蒙特卡罗去噪的算法框架对环境光遮蔽进行实时计算。为了解决传统蒙特卡洛去噪算法无法实时处理的问题,提出了一种基于卷积神经网络的蒙特卡罗去噪算法,并针对问题对网络结构进行了改进和优化。验证实验证明基于卷积神经网络的方法能够对环境光遮蔽的去噪问题进行准确的处理,同时本文对卷积网络的改进在保持精度的基础上显著地提高了计算效率。对比实验显示了本文算法在保持与高频采样光线追踪算法相近效果的前提下可达到与基于屏幕空间环境光遮蔽计算方法相近的每秒数百帧计算效率。     

Volumetric ambient occlusion for volumetric models

This paper presents new algorithms to compute ambient occlusion for volumetric data. Ambient occlusion is used in video-games and film animation to mimic the indirect lighting of global illumination. We extend a novel interpretation of ambient occlusion to volumetric models that measures how big portion of the tangent sphere of a surface belongs to the set of occluded points, and propose statistically robust estimates for the ambient occlusion value. The data needed by this estimate can be obtained by separable filtering of the voxel array. As ambient occlusion is meant to obtain global illumination effects, it can provide decisive clues in interpreting the data. The new algorithms obtain smooth shading and can be computed at interactive rates, being thus appropriate for dynamic models exploration.     

Line Integral Convolution for Real‐Time Illustration of Molecular Surface Shape and Salient Regions

We present a novel line drawing algorithm that illustrates surfaces in real‐time to convey their shape. We use line integral convolution (LIC) and employ ambient occlusion for illustrative surface rendering. Furthermore, our method depicts salient regions based on the illumination gradient. Our method works on animated surfaces in a frame‐coherent manner. Therefore, it yields an illustrative representation of time‐dependent surfaces as no preprocessing step is needed. In this paper, the method is used to highlight the structure of molecular surfaces and to illustrate important surface features like cavities, channels, and pockets. The benefit of our method was evaluated with domain experts. We also demonstrate the applicability of our method to medical visualization.     

High‐Quality Screen‐Space Ambient Occlusion using Temporal Coherence

Ambient occlusion is a cheap but effective approximation of global illumination. Recently, screen‐space ambient occlusion (SSAO) methods, which sample the frame buffer as a discretization of the scene geometry, have become very popular for real‐time rendering. We present temporal SSAO (TSSAO), a new algorithm which exploits temporal coherence to produce high‐quality ambient occlusion in real time. Compared to conventional SSAO, our method reduces both noise as well as blurring artefacts due to strong spatial filtering, faithfully representing fine‐grained geometric structures. Our algorithm caches and reuses previously computed SSAO samples, and adaptively applies more samples and spatial filtering only in regions that do not yet have enough information available from previous frames. The method works well for both static and dynamic scenes.     

复杂环境中基于视觉词袋模型的车辆再识别算法

根据公共安全部门在复杂环境中搜索出特定目标的迫切需求,将目标再识别（re-ID）技术应用到车辆识别领域,提出了一种基于视觉词袋（BoVW）模型的车辆再识别解决方案。首先,为解决复杂环境中遮挡、目标物位姿变化、目标物在图片中的大小位置存在差异等问题,提取出可基于不同尺度、不同位姿的改进基于部件的一对一局部特征（POOF）;其次,通过基于欧氏距离的聚类算法获取视觉词袋中的词汇集合;接着,将训练和测试集中的每张图像或目标转换为词袋中的词汇表述集;最后,利用基于改进保持直接简单原则的度量方法（KISSME）上的再排序方法分离出类间距离和类内距离,通过最近邻方法（KNN）获得识别结果。实验结果显示,在基础特征构建环节上该算法比冒泡银行算法（BB）识别率提升了3.85个百分点;其基于KISSME距离度量的改进再排序算法比贝叶斯再访问算法提升了3.14个百分点。最后,算法对目标位姿变化和局部遮挡具有的适应性和整体时效指标,进一步验证了其可适应于复杂环境应用的特色和优越性。     

引入特征重检的抗遮挡目标跟踪方法研究

针对视觉目标跟踪的遮挡问题,在TLD算法的基础上,引入特征重检环节,解决发生遮挡时因目标外观相似、背景聚类造成错判,提出了一种基于特征重检的抗遮挡目标跟踪研究方法(TLD-D),采用跟踪、检测、学习、再检测的策略。跟踪与检测相结合,对锁定的目标进行学习,获取目标最新的外观特征;当发生遮挡时,则启用特征重检环节,提取遮挡过程的"开始发生遮挡"和"遮挡结束"两个关键帧,然后在特征重检环节选用SIFT特征进行双向匹配标定目标,确保重新标定的目标为原被遮挡的跟踪目标,即"再检测"。OTB基准集上实验结果表明,与TLD算法、同类TLD改进算法以及其他经典跟踪算法相比较,TLD-D算法抗遮挡能力更强,鲁棒性更强,能够对目标长时间稳定跟踪。     

融合多特征表示和超像素优化的双目立体匹配

针对目前许多局部双目立体匹配方法在缺乏纹理区域、遮挡区域、深度不连续区域匹配精度低的问题,提出了基于多特征表示和超像素优化的立体匹配算法。通过在代价计算步骤中加入边缘信息特征,与图像局部信息代价相融合,增加了在视差计算时边缘区域的辨识度;在代价聚合步骤,基于超像素分割形成的超像素区域,利用米字骨架自适应搜索,得到聚合区域,对初始代价进行聚合;在视差精化步骤利用超像素分割信息,对匹配错误视差进行修正,提高匹配精度。基于Middlebury立体视觉数据集测试平台,与自适应权重AD-Census、FA等方法得出的视差图进行比较,该算法在深度不连续区域和缺乏纹理区域的匹配效果显著改善,提高了立体匹配精度。     

基于骨架和统计直方图的形状匹配算法

目标的柔性变化和局部遮挡是形状匹配的主要困难,传统的形状匹配算法对这类问题常不能奏效。针对该问题,提出了一种新的接合骨架和统计直方图匹配柔性变化和局部遮挡目标的方法。算法首先提取骨架接合点,根据骨架接合点将目标形状分块;基于每个骨架接合点构造各个子块的不变特征并将其直方图化;再构建了一种新的相似性度量函数;通过对骨架接合点的匹配实现目标形状的匹配。由于算法是提取骨架接合点,较骨架端点提取更稳定,从而能提高匹配精度;此外算法采用分块描述匹配的思想,所以能有效处理局部遮挡和柔性变化。理论分析和实验结果均表明算法是有效的。     

无人机对船舶目标的改进CamShift跟踪算法研究

针对由于CamShift算法跟踪特征单一引起的对颜色相似目标或背景的干扰和对目标遮挡情况较敏感的问题,提出了一种基于改进CamShift融合局部特征匹配的无人机目标跟踪算法.首先,采用基于 H分量和LBP二维模板的改进CamShift目标跟踪算法以提高对相似目标干扰的鲁棒性;其次,在能保证目标跟踪的实时性要求的前提下,融合局部特征匹配算法中的BRISK匹配算法,可有效改善CamShift对颜色相似目标或背景的干扰的敏感性,同时增强对目标遮挡鲁棒性.实验结果表明,该改进算法通过颜色特征和局部特征的共同定位目标,实现了目标的准确跟踪.     

人脸遮挡区域检测与重建

提出一种基于模糊主分量分析技术(FPCA)的人脸遮挡检测与去除方法.首先,有遮挡人脸被投影到特征脸空间并通过特征脸的线性组合得到一个重建人脸.计算重建图与原图的差图像,加权滤波后并归一化作为被遮挡的概率,以此概率为权重由原图和重建图合成新的人脸.在后续迭代中,根据遮挡概率使用模糊主分量分析进行分析重建,并使用累积误差进行遮挡检测.实验结果表明,算法可精确定位人脸遮挡区域,得到平滑自然的重建人脸图像,优于经典的迭代PCA方法.     

3D head tracking under partial occlusion

A new algorithm for 3D head tracking under partial occlusion from 2D monocular image sequences is proposed. The extended superquadric (ESQ) is used to generate a geometric 3D face model in order to reduce the shape ambiguity during tracking. Optical flow is then regularized by this model to estimate the 3D rigid motion. To deal with occlusion, a new motion segmentation algorithm using motion residual error analysis is developed. The occluded areas are successfully detected and discarded as noise. Furthermore, accumulation error is heavily reduced by a new post-regularization process based on edge flow. This makes the algorithm more stable over long image sequences. The algorithm is applied to both synthetic occlusion sequence and real image sequences. Comparisons with the ground truth indicate that our method is effective and is not sensitive to occlusion during head tracking.     

一种基于自适应梯度的运动估计算法

给出了一种基于Horn-Schunck的改进光流估计算法,计算了当前帧的前向梯度、后向梯度,根据代价函数自适应地选择前向梯度与后向梯度,减小光流估计时的遮挡问题。试验表明该算法是有效的。     

基于可变步长的常数模盲均衡算法

为了提高多输入多输出系统的通信质量,针对传统常数模盲均衡算法存在收敛速度慢、误码率高等缺点,提出来一种基于可变步长的常数模盲均衡算法。利用反正切函数建立一种步长因子与误差间的非线性函数关系,利用此非线性函数来调整步长,加快算法收敛速度,采用仿真实验测试算法的性能。结果表明,相对于其他盲均衡算法,该算法加快了收敛速度,大幅降低误码率,获得理想的均衡效果,具有一定的实用价值。     

一种改进的粒子滤波算法及其FPGA硬件实现

提出了一种改进的粒子滤波目标跟踪算法,提出了限定区域的伪随机算法和根据权值分布的自适应重采样算法来提升目标跟踪的精度和并行特性。同时在算法的FPGA硬件结构实现上,对程序结构进行调整,充分利用流水线并行处理数值计算,运用硬件并行特性加快粒子的权值排序过程。实验结果表明,提出的算法在实验室场景与遮挡情况下都具有良好的跟踪准确性和实时性。     

基于场景层次的遮挡建模与立体匹配

通过在扫描线和图像分割2个层面上建立基于场景层次的遮挡模型,实现了一种全新的从前景到后景分层处理的立体匹配算法.以像素灰度值为依据进行匹配时,离摄像机最近的物体因为不受遮挡的影响,总是最容易匹配成功;稍远一些的景物可以利用已经计算出来的前景建立局部的遮挡模型指导匹配.这样逐层递推,可求得场景中所有物体的视差.图像分割技术将处理单位由像素提升到了图像块,既提高了算法效率,也降低了视差映射图的不连续性.使用标准数据集的测试结果表明,文中算法精度高、强壮性好,在无纹理区域、深度变化边界区域和遮挡区域都达到了比较高的识别率.     

Multiview segmentation and tracking of dynamic occluding layers

We present an algorithm for the layered segmentation of video data in multiple views. The approach is based on computing the parameters of a layered representation of the scene in which each layer is modelled by its motion, appearance and occupancy, where occupancy describes, probabilistically, the layer’s spatial extent and not simply its segmentation in a particular view. The problem is formulated as the MAP estimation of all layer parameters conditioned on those at the previous time step; i.e., a sequential estimation problem that is equivalent to tracking multiple objects in a given number views. Expectation–Maximisation is used to establish layer posterior probabilities for both occupancy and visibility, which are represented distinctly. Evidence from areas in each view which are described poorly under the model is used to propose new layers automatically. Since these potential new layers often occur at the fringes of images, the algorithm is able to segment and track these in a single view until such time as a suitable candidate match is discovered in the other views. The algorithm is shown to be very effective at segmenting and tracking non-rigid objects and can cope with extreme occlusion. We demonstrate an application of this representation to dynamic novel view synthesis.     

Two Methods for Fast Ray‐Cast Ambient Occlusion

Ambient occlusion has proven to be a useful tool for producing realistic images, both in offline rendering and interactive applications. In production rendering, ambient occlusion is typically computed by casting a large number of short shadow rays from each visible point, yielding unparalleled quality but long rendering times. Interactive applications typically use screen‐space approximations which are fast but suffer from systematic errors due to missing information behind the nearest depth layer. In this paper, we present two efficient methods for calculating ambient occlusion so that the results match those produced by a ray tracer. The first method is targeted for rasterization‐based engines, and it leverages the GPU graphics pipeline for finding occlusion relations between scene triangles and the visible points. The second method is a drop‐in replacement for ambient occlusion computation in offline renderers, allowing the querying of ambient occlusion for any point in the scene. Both methods are based on the principle of simultaneously computing the result of all shadow rays for a single receiver point.