增强现实系统的设计与实现

研究了一种基于平面特征的视频动态跟踪方法,通过计算出初始帧图像的虚实坐标之间的单应矩阵,可以计算出任意一帧的虚实坐标之间的单应矩阵,可以实现动态跟踪的目的。在此基础之上设计并实现了基于平面特征的增强现实动态跟踪系统,实现了视频的动态跟踪功能。该增强现实跟踪系统具有实时性好、简单、方便的特点。     

基于局部背景感知的目标跟踪

经典视觉跟踪方法通常仅以目标区域内信息作为目标描述. 实际中, 目标局部背景信息也影响着跟踪性能. 本文首先在目标描述中引入局部背景信息, 并将目标表示为一带权点集. 然后通过K近邻计算目标观测概率, 并联合目标先验信息得到搜索区域内各点后验概率值. 最后, 利用均值漂移(Mean shift)算法估计目标状态. 本文算法优点如下: 1) 目标描述中联合局部背景信息, 增强了目标模型. 因此, 跟踪过程中提高了目标与背景的区分能力, 并进一步使跟踪算法更加稳定, 跟踪结果更加精准. 2)目标初始化时, 利用Mean shift对目标进行一次重定位. 由此解决了不精确初始化时跟踪算法容易失效的问题. 在不同视频上进行了定性和定量的实验验证. 结果表明本文算法具有较高的跟踪稳定性和准确性, 尤其当目标初始化比较粗糙时.     

基于GMS与FPME的视频目标跟踪方法

针对视频目标跟踪中因特征点误匹配造成跟踪性能下降的问题,在融合二进制特征描述算法（ORB）与网格统计的视频跟踪方法（GMS）框架下,提出一种基于GMS与特征点误匹配剔除（FPME）的视频目标跟踪方法。利用ORB算法确保在视频序列中特征点匹配的实时性,采用“粗-精”两阶段的剔除方法,即先利用K-means算法快速粗略地剔除误差较大的特征点匹配关系,提高正确匹配对所占的比例,再利用分裂法精确剔除偏离程度较大的匹配对,提高目标特征点之间的匹配成功率。实验结果表明,在视频序列的跨帧匹配与连续跟踪实验中,该方法相对于GMS、ASLA、HDT等当前主流算法在匹配精度、速度等评价指标上都能得到较好的结果。     

融合图像显著性与特征点匹配的形变目标跟踪

目的 针对目标在跟踪过程中出现剧烈形变,特别是剧烈尺度变化的而导致跟踪失败情况,提出融合图像显著性与特征点匹配的目标跟踪算法。方法 首先利用改进的BRISK（binary robust invariant scalable keypoints）特征点检测算法,对视频序列中的初始帧提取特征点,确定跟踪算法中的目标模板和目标模板特征点集合;接着对当前帧进行特征点检测,并与目标模板特征点集合利用FLANN（fast approximate nearest neighbor search library）方法进行匹配得到匹配特征点子集;然后融合匹配特征点和光流特征点确定可靠特征点集;再后基于可靠特征点集和目标模板特征点集计算单应性变换矩阵粗确定目标跟踪框,继而基于LC（local contrast）图像显著性精确定目标跟踪框;最后融合图像显著性和可靠特征点自适应确定目标跟踪框。当连续三帧目标发生剧烈形变时,更新目标模板和目标模板特征点集。结果 为了验证算法性能,在OTB2013数据集中挑选出具有形变特性的8个视频序列,共2214帧图像作为实验数据集。在重合度实验中,本文算法能够达到0.567 1的平均重合度,优于当前先进的跟踪算法;在重合度成功率实验中,本文算法也比当前先进的跟踪算法具有更好的跟踪效果。最后利用Vega Prime仿真了无人机快速抵近飞行下目标出现剧烈形变的航拍视频序列,序列中目标的最大形变量超过14,帧间最大形变量达到1.72,实验表明本文算法在该视频序列上具有更好的跟踪效果。本文算法具有较好的实时性,平均帧率48.6帧/s。结论 本文算法能够实时准确的跟踪剧烈形变的目标,特别是剧烈尺度变化的目标。     

基于时间一致性局部颜色特征的无纹理3D物体实时跟踪

针对无纹理3D物体跟踪算法在复杂背景和运动模糊的情况下容易跟踪失败、跟踪速度难以达到强实时等问题,提出一种基于时间一致性局部颜色特征的3D物体实时跟踪算法.首先在物体3D模型投影轮廓法向搜索线上计算像素颜色的加权均值作为局部颜色特征,增强颜色特征在复杂环境中的表征能力,并对局部颜色特征进行时间一致性更新,剔除前景背景颜色相似的局部颜色特征,以避免相似前景背景颜色导致的跟踪失败;然后定义基于局部颜色特征的能量函数,并推导该能量函数的解析导函数;最后改进了优化物体姿态的高斯牛顿法,通过添加阻尼参数防止姿态优化陷入局部极值,提高姿态估计精度和跟踪速度.实验使用7组测试视频验证文中算法,结果表明,该算法能更有效地克服复杂背景和运动模糊的干扰,在未使用并行计算的前提下可实现强实时跟踪.     

实时人数计数系统

描述一个实时在线人数计数系统,该系统采用检测加跟踪的方法来实现人数计数功能。在检测阶段,采用MBLBP（multi-scale block LBP）特征,从运动区域上检测出行人。该特征速度快,并且在归一化下,能够适应多尺度的应用;在跟踪阶段,通过一个概率模型,将对行人的跟踪转化为对特征点的跟踪,并且在将检测目标和跟踪目标进行一一对应时,进一步利用各个目标内的特征点来完成相应的操作。最后用实际中不同场景下的视频,对系统的性能进行测试,同时还在一段公开的视频上进行了测试,实验结果表明,该系统能够在不同场景下较准确地实现人数计数功能。     

A versatile homography computation method based on two real points

In this paper, we present a novel 2D homography computation method based on two real points. The homography is thus decomposed into three parts. The two real points and their images can be utilized to compute the first and the last parts respectively, while other primitives (could be point(s), line(s) and conic) can be utilized to compute the middle part which is a hyperbolic similarity transformation. We introduce the proposed method in a 2D pattern with a conic and a coplanar line, and apply the method in various other geometric patterns. Subsequently, many plane-based vision tasks, such as camera calibration, pose estimation and metric rectification can be solved in a unified way as polynomial systems. The experiments with simulated and real data verify the correctness and the versatility of our algorithm.     

Multilevel Robustness for 2D Vector Field Feature Tracking,Selection and Comparison

Critical point tracking is a core topic in scientific visualization for understanding the dynamic behaviour of time-varying vector field data. The topological notion of robustness has been introduced recently to quantify the structural stability of critical points, that is, the robustness of a critical point is the minimum amount of perturbation to the vector field necessary to cancel it. A theoretical basis has been established previously that relates critical point tracking with the notion of robustness, in particular, critical points could be tracked based on their closeness in stability, measured by robustness, instead of just distance proximity within the domain. However, in practice, the computation of classic robustness may produce artifacts when a critical point is close to the boundary of the domain; thus, we do not have a complete picture of the vector field behaviour within its local neighbourhood. To alleviate these issues, we introduce a multilevel robustness framework for the study of 2D time-varying vector fields. We compute the robustness of critical points across varying neighbourhoods to capture the multiscale nature of the data and to mitigate the boundary effect suffered by the classic robustness computation. We demonstrate via experiments that such a new notion of robustness can be combined seamlessly with existing feature tracking algorithms to improve the visual interpretability of vector fields in terms of feature tracking, selection and comparison for large-scale scientific simulations. We observe, for the first time, that the minimum multilevel robustness is highly correlated with physical quantities used by domain scientists in studying a real-world tropical cyclone dataset. Such an observation helps to increase the physical interpretability of robustness.     

一种视频序列拼接的新方法

提出了一种基于视频序列拼接的新方法。首先,利用KLT算法对视频序列中特征点进行提取和跟踪,实现关键帧粗略选取;其次,在选取的关键帧中利用SURF算法进行特征提取,利用最近邻距离比进行特征点匹配,通过RANSAC估计算法求精单映矩阵,并结合关键帧选取判定寻找最佳关键帧;最后,利用级联单映矩阵和加权融合算法实现视频序列拼接。实验验证了该方法的有效性。     

Circular motion geometry using minimal data

Circular motion or single axis motion is widely used in computer vision and graphics for 3D model acquisition. This paper describes a new and simple method for recovering the geometry of uncalibrated circular motion from a minimal set of only two points in four images. This problem has been previously solved using nonminimal data either by computing the fundamental matrix and trifocal tensor in three images or by fitting conics to tracked points in five or more images. It is first established that two sets of tracked points in different images under circular motion for two distinct space points are related by a homography. Then, we compute a plane homography from a minimal two points in four images. After that, we show that the unique pair of complex conjugate eigenvectors of this homography are the image of the circular points of the parallel planes of the circular motion. Subsequently, all other motion and structure parameters are computed from this homography in a straighforward manner. The experiments on real image sequences demonstrate the simplicity, accuracy, and robustness of the new method.     

Pyramid Multi‐View Stereo with Local Consistency

In this paper, we propose a PatchMatch‐based Multi‐View Stereo (MVS) algorithm which can efficiently estimate geometry for the textureless area. Conventional PatchMatch‐based MVS algorithms estimate depth and normal hypotheses mainly by optimizing photometric consistency metrics between patch in the reference image and its projection on other images. The photometric consistency works well in textured regions but can not discriminate textureless regions, which makes geometry estimation for textureless regions hard work. To address this issue, we introduce the local consistency. Based on the assumption that neighboring pixels with similar colors likely belong to the same surface and share approximate depth‐normal values, local consistency guides the depth and normal estimation with geometry from neighboring pixels with similar colors. To fasten the convergence of pixelwise local consistency across the image, we further introduce a pyramid architecture similar to previous work which can also provide coarse estimation at upper levels. We validate the effectiveness of our method on the ETH3D benchmark and Tanks and Temples benchmark. Results show that our method outperforms the state‐of‐the‐art.     

局部特征描述改进的LK跟踪注册方法

针对KLT跟踪方法抗光照变化和抗遮挡较差的问题,提出一种使用局部特征描述改进的LK跟踪注册方法(DF-LK)。使用ORB特征点求解初始位姿,通过自适应非极大值抑制重新划分特征点,选择均匀分布的特征点作为LK方法跟踪的控制点集。相邻帧图像之间的单应性矩阵通过在DF描述后的图像上使用LK方法进行求解,跟踪的结果由向前向后错误检测进行评估,由单应性矩阵和初始位姿求解出当前帧的摄像机位姿,并叠加虚拟信息。实验结果表明,该方法在光照变化、部分遮挡和透视变化时均有较好的稳定性和鲁棒性。     

A generalized registration method for augmented reality systems

In augmented reality systems, registration is one of the most difficult problems currently limiting their applications. In this paper, we propose a generalized registration method using projective reconstruction technique in computer vision. This registration method is composed of embedding and tracking. Embedding involves specifying four points to build the world coordinate system on which a virtual object will be superimposed. In this stage, any arbitrary two unrelated images or any 3×4 projective matrices with rank 3 can be used to calculate the 3D pseudo-projective coordinates of the four specified points. In the tracking process, these 3D pseudo-projective coordinates are used to track the four specified points to compute the registration matrix for augmentation. The proposed method is simple, as only four points need to be specified at the embedding stage, and the virtual object can then be easily augmented onto a real scene from a video sequence. One advantage is that the virtual objects can still be superimposed on the specified regions even when the regions are occluded in the video sequence. Another advantage of the proposed method is that the registration errors can be adjusted in real-time to ensure that they are less than certain thresholds that have been specified at the initial embedding stage. Several experiments have been conducted to validate the performance of the proposed generalized method.     

基于关键点及光流的平面物体跟踪算法

为提高复杂场景下基于关键点的平面物体跟踪算法的鲁棒性,提出一种融合光流的平面物体跟踪算法.检测目标物体与输入图像的关键点及其对应描述符,由最近邻匹配方法构建目标与图像间关键点匹配集合,通过光流法构建相邻两张图像间关键点的对应关系,将已构建的关键点匹配集合与基于光流的对应关系通过加权平均的策略进行融合,得出修正的关键点匹...     

Scene-consistent detection of feature points in video sequences

Detection of feature points in images is an important preprocessing stage for many algorithms in Computer Vision. We address the problem of detection of feature points in video sequences of 3D scenes, which could be mainly used for obtaining scene correspondence. The main feature we use is the zero crossing of the intensity gradient argument. We analytically show that this local feature corresponds to specific constraints on the local 3D geometry of the scene, thus ensuring that the detected points are based on real 3D features. We present a robust algorithm that tracks the detected points along a video sequence, and suggest some criteria for quantitative evaluation of such algorithms. These criteria serve in a comparison of the suggested operator with four other feature trackers. The suggested criteria are generic and could serve other researchers as well for performance evaluation of stable point detectors.     

基于时空上下文信息增强的目标跟踪算法

充分利用视频中的时空上下文信息能明显提高目标跟踪性能,但目前大多数基于深度学习的目标跟踪算法仅利用当前帧的特征信息来定位目标,没有利用同一目标在视频前后帧的时空上下文特征信息,导致跟踪目标易受到邻近相似目标的干扰,从而在跟踪定位时会引入一个潜在的累计误差。为了保留时空上下文信息,在SiamMask算法的基础上引入一个短期记忆存储池来存储历史帧特征;同时,提出了外观显著性增强模块（ASBM）,一方面增强跟踪目标的显著性特征,另一方面抑制周围相似目标对目标的干扰。基于此,提出一种基于时空上下文信息增强的目标跟踪算法。在VOT2016、VOT2018、DAVIS-2016和DAVIS-2017等四个数据集上进行实验与分析,结果表明所提出的算法相较于SiamMask算法在VOT2016上的准确率和平均重叠率（EAO）分别提升了4个百分点和2个百分点;在VOT2018上的准确率、鲁棒性和EAO分别提升了3.7个百分点、2.8个百分点和1个百分点;在DAVIS-2016上的区域相似度、轮廓精度指标中的下降率均分别降低了0.2个百分点;在DAVIS-2017上的区域相似度、轮廓精度指标中的下降率分别降低了1.3和0.9个百分点。     

3D human pose estimation in motion based on multi-stage regression

3D human pose estimation in motion is a hot research direction in the field of computer vision. However, the performance of the algorithm is affected by the complexity of 3D spatial information, self-occlusion of human body, mapping uncertainty and other problems. In this paper, we propose a 3D human joint localization method based on multi-stage regression depth network and 2D to 3D point mapping algorithm. First of all, we use a single RGB image as the input, through the introduction of heatmap and multi-stage regression to constantly optimize the coordinates of human joint points. Then we input the 2D joint points into the mapping network for calculation, and get the coordinates of 3D human body joint points, and then to complete the 3D human body pose estimation task. The MPJPE of the algorithm in Human3.6 M dataset is 40.7. The evaluation of dataset shows that our method has obvious advantages.     

Point matching under large image deformations and illumination changes

To solve the general point correspondence problem in which the underlying transformation between image patches is represented by a homography, a solution based on extensive use of first order differential techniques is proposed. We integrate in a single robust M-estimation framework the traditional optical flow method and matching of local color distributions. These distributions are computed with spatially oriented kernels in the 5D joint spatial/color space. The estimation process is initiated at the third level of a Gaussian pyramid, uses only local information, and the illumination changes between the two images are also taken into account. Subpixel matching accuracy is achieved under large projective distortions significantly exceeding the performance of any of the two components alone. As an application, the correspondence algorithm is employed in oriented tracking of objects.     

融合重检测机制的卷积回归网络目标跟踪算法

针对基于人工特征的背景感知相关滤波（CACF）算法在形变、运动模糊、低分辨率情形跟踪效果较差以及跟踪器遇到严重遮挡等情形容易陷入局部最优而导致跟踪失败的问题，提出一种融合重检测机制的卷积回归网络（CRN）目标跟踪算法。在训练阶段，将相关滤波作为CRN层融入进深度神经网络，使网络成为一个整体进行端到端训练；在跟踪阶段，通过残差连接融合不同网络层及其响应值，同时引入重检测机制使算法从潜在的跟踪失败中恢复，当响应值低于给定阈值时激活检测器。在数据集OTB-2013上的实验表明，所提算法在50个视频序列上精确度达到88.1%，相比原始CACF算法提高9.7个百分点，在具有形变、运动模糊等属性的视频序列上相比原始算法表现更优秀。     

剖析DDoS攻击对抗技术

由于目前Internet的体系结构、认证机制的缺乏等多方面原因使得DDoS攻击很容易发生,而且僵尸网络的快速发展也为DDoS攻击提供了强大的工具。DDoS(Distributed Denial of Service)攻击一直是网络安全的主要威胁之一,如何对抗DDoS攻击成为网络安全研究的热点之一。在对DDoS攻击模型、产生原因进行分析的基础上,从攻击预防、攻击检测、攻击响应和攻击源追踪四个方面对现有的DDoS攻击对抗技术进行综述,并提出了值得研究的方向建议。