Iterative Pose Estimation Using Coplanar Feature Points

This paper presents a new method for the computation of the position and orientation of a camera with respect to a known object, using four or morecoplanarfeature points. Starting with the scaled orthographic projection approximation, this method iteratively refines up to two different pose estimates, and provides an associated quality measure for each pose. When the camera distance is large compared with the object depth, or when the accuracy of feature point extraction is low because of image noise, the quality measures for the two poses are similar, and the two pose estimates are plausible interpretations of the available information. In contrast, known methods using a closed form pose solution for four coplanar points are not robust for distant objects in the presence of image noise because they provide only one of the two possible poses and may choose the wrong pose.     

Pose Estimation in Conformal Geometric Algebra Part II: Real-Time Pose Estimation Using Extended Feature Concepts

Part II uses the foundations of Part I [35] to define constraint equations for 2D-3D pose estimation of different corresponding entities. Most articles on pose estimation concentrate on specific types of correspondences, mostly between points, and only rarely use line correspondences. The first aim of this part is to extend pose estimation scenarios to correspondences of an extended set of geometric entities. In this context we are interested to relate the following (2D) image and (3D) model types: 2D point/3D point, 2D line/3D point, 2D line/3D line, 2D conic/3D circle, 2D conic/3D sphere. Furthermore, to handle articulated objects, we describe kinematic chains in this context in a similar manner. We ensure that all constraint equations end up in a distance measure in the Euclidean space, which is well posed in the context of noisy data. We also discuss the numerical estimation of the pose. We propose to use linearized twist transformations which result in well conditioned and fast solvable systems of equations. The key idea is not to search for the representation of the Lie group, describing the rigid body motion, but for the representation of their generating Lie algebra. This leads to real-time capable algorithms.Bodo Rosenhahn gained his diploma degree in Computer Science in 1999. Since then he has been pursuing his Ph.D. at the Cognitive Systems Group, Institute of Computer Science, Christian-Albrechts University Kiel, Germany. He is working on geometric applications of Clifford algebras in computer vision.Prof. Dr. Gerald Sommer received a diploma degree in physics from the Friedrich-Schiller-Universität Jena, Germany, in 1969, a Ph.D. degree in physics from the same university in 1975, and a habilitation degree in engineering from the Technical University Ilmenau, Germany, in 1988. Since 1993 he is leading the research group Cognitive Systems at the Christian-Albrechts-Universität Kiel, Germany. Currently he is also the scientific coordinator of the VISATEC project.     

基于人体和场景上下文的多人3D姿态估计

深度歧义是单帧图像多人3D姿态估计面临的重要挑战,提取图像上下文对缓解深度歧义极具潜力.自顶向下方法大多基于人体检测建模关键点关系,人体包围框粒度粗背景噪声占比较大,极易导致关键点偏移或误匹配,还将影响基于人体尺度因子估计绝对深度的可靠性.自底向上的方法直接检出图像中的人体关键点再逐一恢复3D人体姿态.虽然能够显式获取场景上下文,但在相对深度估计方面处于劣势.提出新的双分支网络,自顶向下分支基于关键点区域提议提取人体上下文,自底向上分支基于三维空间提取场景上下文.提出带噪声抑制的人体上下文提取方法,通过建模“关键点区域提议”描述人体目标,建模姿态关联的动态稀疏关键点关系剔除弱连接减少噪声传播.提出从鸟瞰视角提取场景上下文的方法,通过建模图像深度特征并映射鸟瞰平面获得三维空间人体位置布局;设计人体和场景上下文融合网络预测人体绝对深度.在公开数据集MuPoTS-3D和Human3.6M上的实验结果表明:与同类先进模型相比,所提模型HSC-Pose的相对和绝对3D关键点位置精度至少提高2.2%和0.5%;平均根关键点位置误差至少降低4.2 mm.     

利用改进生成对抗网络进行人体姿态识别

针对人体模型中某些重要关节点准确定位的问题,提出了一种新型深度卷积生成对抗网络以进行静态图像中人体姿态的估计的方法。该方法采用了深度卷积的堆叠沙漏网络来准确提取图像上关键关节点的位置,该网络的生成和辨别部分被设计用于编码第一层次结构（亲本）与第二层次结构（子本）中的空间关系,并且展示了人体部位的空间层次。生成器和判别器在网络中被设计为两部分,并按照顺序连接在一起用来编码外观可能的关系,同时为人体部位存在的可能性以及身体的每个部分与其亲本部分之间的关系进行编码。在静态图像中,可以较准确地识别人体模型关键节点以及大致人体姿态。该方法在不同的数据集上进行了实验,在大部分情况下,提出的方法获得的结果优于其他几种对比方法。     

融入双注意力的高分辨率网络人体姿态估计

在人体姿态估计任务中,针对高分辨率网络提取和融合特征图的特征信息时不能有效获取多通道信息和空间特征信息,导致人体姿态估计结果不够精确。在高分辨率网络（HRNet）的基础上,提出一种融入双注意力的高分辨率人体姿态估计网络ENNet。通过引入通道注意力,构造E-ecaneck模块和E-ecablock模块作为基础模块,最大程度地对多通道提取足够多的有用信息,在每一阶段子网的多分辨率融合阶段融入空间注意力机制,提取并融合不同分辨率特征信息,通过上采样的方式输出所有融合低分辨率的高分辨率表征。在公开数据集MS COCO2017上进行验证和测试,结果表明,相比于高分辨率网络,该方法mAP提高3.4%,有效改善网络多分辨率表征的信息融合能力,明显提升基础高分辨率网络HRNet的估计精确度。     

Infinitesimal Plane-Based Pose Estimation

Estimating the pose of a plane given a set of point correspondences is a core problem in computer vision with many applications including Augmented Reality (AR), camera calibration and 3D scene reconstruction and interpretation. Despite much progress over recent years there is still the need for a more efficient and more accurate solution, particularly in mobile applications where the run-time budget is critical. We present a new analytic solution to the problem which is far faster than current methods based on solving Pose from \(n\) Points (PnP) and is in most cases more accurate. Our approach involves a new way to exploit redundancy in the homography coefficients. This uses the fact that when the homography is noisy it will estimate the true transform between the model plane and the image better at some regions on the plane than at others. Our method is based on locating a point where the transform is best estimated, and using only the local transformation at that point to constrain pose. This involves solving pose with a local non-redundant 1st-order PDE. We call this framework Infinitesimal Plane-based Pose Estimation (IPPE), because one can think of it as solving pose using the transform about an infinitesimally small region on the surface. We show experimentally that IPPE leads to very accurate pose estimates. Because IPPE is analytic it is both extremely fast and allows us to fully characterise the method in terms of degeneracies, number of returned solutions, and the geometric relationship of these solutions. This characterisation is not possible with state-of-the-art PnP methods.     

部位级遮挡感知的人体姿态估计

随着深度学习的快速发展,人体姿态估计技术近年来取得显著进步,但是现有方法仍难以较好地处理普遍存在的遮挡问题.针对此问题,提出一种部位级遮挡感知的人体姿态估计方法.首先,采用基准人体姿态估计网络从含遮挡噪声的图像中获得各人体部位的带噪声特征表达.然后,通过遮挡部位预测模块估计人体被遮挡部位,从而获得可见性向量.遮挡部位预测模块由遮挡部位分类网络和可见性编码器组成,前者预测关节点的遮挡状态,后者利用注意力机制将遮挡状态转换为一组权重.最后,通过通道重加权方式融合可见性向量和带噪声特征,获得部位级遮挡感知的人体部位相关特征,用于计算关节点热图.在MPII和LSP(leeds sports pose)数据集上的实验结果表明,相比基准姿态估计网络,该方法能够在较小的额外计算代价下更好地应对遮挡问题,并且取得了比目前先进方法更佳的结果.     

Enhanced 3D Human Pose Estimation from Videos by Using Attention-Based Neural Network with Dilated Convolutions

International Journal of Computer Vision - The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work,...     

3D Free-Form Object Recognition Using Indexing by Contour Features

We address the problem of recognizing free-form 3D objects from a single 2D intensity image. A model-based solution within the alignment paradigm is presented which involves three major schemes—modeling, matching, and indexing. The modeling scheme constructs a set of model aspects which can predict the object contour as seen from any viewpoint. The matching scheme aligns the edgemap of a candidate model to the observed edgemap using an initial approximate pose. The major contribution of this paper involves the indexing scheme and its integration with modeling and matching to perform recognition. Indexing generates hypotheses specifying both candidate model aspects and approximate pose and scale. Hypotheses are ordered by likelihood based on prior knowledge of pre-stored models and the visual evidence from the observed objects. A prototype implementation has been tested in recognition and localization experiments with a database containing 658 model aspects from twenty 3D objects and eighty 2D objects. Bench tests and simulations show that many kinds of objects can be handled accurately and efficiently even in cluttered scenes. We conclude that the proposed recognition-by-alignment paradigm is a viable approach to many 3D object recognition problems.     

A New Analytical Method for Relative Camera Pose Estimation Using Unknown Coplanar Points

We present a new analytical method for solving the problem of relative camera pose estimation. This method first calculates the homography matrix between two calibrated views using unknown coplanar points, and then, it decomposes the matrix to estimate the relative camera pose. We derive a set of new analytical expressions that are more concise than other homography decomposition methods. These analytical expressions are also used to improve the efficiency of a traditional SVD-based homography decomposition method. The performance of our analytical method is studied in terms of both efficiency and accuracy, and it is compared with other homography decomposition methods. Furthermore, the accuracy of our analytical method is tested under different conditions and compared with that of the five-point method through simulations and real image experiments. The experimental results demonstrate that our method is faster and more accurate than other homography decomposition methods and more accurate than the five-point method.     

基于Transformer的野生动物关键点检测

濒危野生动物需要得到保护,对野生动物进行姿态追踪是保护野生动物的一种可行性方法.关键点检测是对野生动物进行姿态追踪的重要步骤.基于深度卷积网络(Deep Convolutional Neural Network,DCNN),首次使用Transformer模型实现野生动物的关键点检测任务,Transformer可以捕捉野生动物关键点的长距离依赖关系.在网络的基本模块(BasicBlock)中引入SGE(Spatial Group-wise Enhance)注意力机制,改善所提取特征的分布.提出了一种基于空间注意力的多分辨率表征融合方法,在特征融合时关注更有用的特征信息.在野生动物关键点检测的公共数据集上进行实验,实验结果显示,所提方法获得了良好的效果.     

一种综合的姿态估计算法-CMIA

结合CPCA(连续主成分分析)与MND(最大法向量分布)两种姿态估计方法,提出一种综合的姿态估计算法CMIA(CPCA and MND Integrated Algorism).研究发现CPCA与MND所适合的模型具有互补性,故将两者结合起来,根据模型的具体特征,选择合适的姿态估计算法.通过深度缓存算法对规范后的模型进行特征提取,并用PSB(Princeton Shape Benchmark)进行测试.实验结果验证了该算法的有效性.该算法的精确度较MND提高了24%,较CPCA提高了5%.可见通过选择合适的姿态估计算法,明显提高了模型的规范化效果.     

一种新的人脸姿态估计算法

提出基于正射投影模型的人脸姿态参数估计算法.从图像获取特征点,计算这些点到正面姿态参考模型特征点的最佳姿态变换参数,算法只需获取4个特征点就能确定图像人脸姿态.同时基于该模型提出新的人脸图像姿态拟合方法,以最小化SSD为目标函数,迭代法求姿态参数.该方法的优势是人脸姿态估计并不依赖于特征点检测,给定初始姿态就能找到模型到图像的最佳姿态拟合.模拟图像和真实图像的姿态估计实验结果显示,拟合算法的迭代过程能迅速收敛,并且该算法可有效用于姿态跟踪.     

一种基于图像表观的鲁棒姿态估计方法

提出一种利用图像的表观特征进行头部姿态估计的方法.该方法首先使用了一维Gabor 滤波器对头部图像进行特征提取,然后对提取得到的一维Gabor 特征进一步使用了基于核函数的局部费舍尔判别分析方法增强特征的判别能力.与传统二维Gabor 特征相比,一维Gabor 特征除了在计算速度和存储空间上具有明显的优势以外,更与姿态紧密相关.而基于核函数的局部费舍尔判别分析方法,能够解决姿态问题中存在的非线性问题和多模态问题.大量的实验结果表明,该算法对于姿态估计问题是有效的.特别需要指出的是,该算法具有良好的推广能力     

典型相关分析在人脸姿态估计中的应用

在单一物体角度估计中,典型相关分析(CCA)可以用来建立图像空间和角度空间的联系.基于人脸总体形状的相似性,提出了基于外观的人脸姿态估计方法.使用CCA建立姿态变化时人脸这一类物体的外观空间和姿态空间的关系.典型相关向量最大化人脸外观空间和姿态空间的相关性,张成了它们的相关子空间.在相关子空间中,通过线性回归的方法,估计未知姿态图像的角度.为了更好的处理外观空间的非线性问题,引入了该方法.在CUbiC FacePix数据库上的实验验证了这两种算法的有效性.