Automatic construction of quadrilateral network of curves from triangular meshes

The aim of this study is to propose a method for building quadrilateral network of curves automatically from a huge number of triangular meshes. The curve net can be served as the framework of automatic surface reconstruction. The proposed method mainly includes three stages: mesh simplification, quadrangulation and curve net generation. Mesh simplification is employed to reduce the number of meshes in accordance with a quadratic error metric for each vertex. Additional post-processing criteria are also employed to improve the shape of the reduced meshes. For quadrangulation, a front composed of a sequence of edges is introduced. An algorithm is proposed to combine each pair of triangles along the front. A new front is then formed and quadrangulation is continued until all triangles are combined or converted. For curve net generation, each edge of quadrilateral meshes is projected onto the triangular meshes to acquire a set of slicing points first. A constrained curve fitting is then employed to convert all sets of slicing points into B-spline curves, with appropriate continuity conditions across adjacent curves. Several examples have been presented to demonstrate the feasibility of the proposed method and its application in automatic surface reconstruction.     

Automatic model construction

An algorithm for the construction of finite models of sets of predicate-calculus sentences is given. The algorithm differs from resolution in its ability to incorporate certain extra sentences (human advice) gracefully. Since the problem attacked by the algorithm is NP-complete, it is hoped that this ability to accept advice will make the algorithm useful more as a tool in the hands of a researcher than as a stand-alone procedure.     

Linear pose estimation from points or lines

Estimation of camera pose from an image of n points or lines with known correspondence is a thoroughly studied problem in computer vision. Most solutions are iterative and depend on nonlinear optimization of some geometric constraint, either on the world coordinates or on the projections to the image plane. For real-time applications, we are interested in linear or closed-form solutions free of initialization. We present a general framework which allows for a novel set of linear solutions to the pose estimation problem for both n points and n lines. We then analyze the sensitivity of our solutions to image noise and show that the sensitivity analysis can be used as a conservative predictor of error for our algorithms. We present a number of simulations which compare our results to two other recent linear algorithms, as well as to iterative approaches. We conclude with tests on real imagery in an augmented reality setup.     

Robust pose estimation from a planar target

In theory, the pose of a calibrated camera can be uniquely determined from a minimum of four coplanar but noncollinear points. In practice, there are many applications of camera pose tracking from planar targets and there is also a number of recent pose estimation algorithms which perform this task in real-time, but all of these algorithms suffer from pose ambiguities. This paper investigates the pose ambiguity for planar targets viewed by a perspective camera. We show that pose ambiguities - two distinct local minima of the according error function - exist even for cases with wide angle lenses and close range targets. We give a comprehensive interpretation of the two minima and derive an analytical solution that locates the second minimum. Based on this solution, we develop a new algorithm for unique and robust pose estimation from a planar target. In the experimental evaluation, this algorithm outperforms four state-of-the-art pose estimation algorithms     

Gravitational pose estimation

Problem of relative pose estimation between a camera and rigid object, given an object model with feature points and image(s) with respective image points (hence known correspondence) has been extensively studied in the literature. We propose a “correspondenceless” method called gravitational pose estimation (GPE), which is inspired by classical mechanics. GPE can handle occlusion and uses only one image (i.e., perspective projection of the object). GPE creates a simulated gravitational field from the image and lets the object model move and rotate in that force field, starting from an initial pose. Experiments were carried out with both real and synthetic images. Results show that GPE is robust, consistent, and fast (runs in less than a minute). On the average (including up to 30% occlusion cases) it finds the orientation within 6° and the position within 17% of the object’s diameter. SoftPOSIT was so far the best correspondenceless method in the literature that works with a single image and point-based object model like GPE. However, SoftPOSIT’s convergence to a result is sensitive to the choice of initial pose. Even “random start SoftPOSIT,” which performs multiple runs of SoftPOSIT with different initial poses, can often fail. However, SoftPOSIT finds the pose with great precision when it is able to converge. We have also integrated GPE and SoftPOSIT into a single method called GPEsoftPOSIT, which finds the orientation within 3° and the position within 10% of the object’s diameter even under occlusion. In GPEsoftPOSIT, GPE finds a pose that is very close to the true pose, and then SoftPOSIT is used to enhance accuracy of the result. Unlike SoftPOSIT, GPE also has the ability to work with three points as well as planar object models.     

一种基于图结构模型的人体姿态估计算法

针对单幅图片中人体姿态的估计问题,在图结构模型的基础上提出了一种新的人体姿态估计算法。算法提出了一个新的部位观测模型和一种新的减小部位状态空间的方法：（1）对人体不同部位采用不同尺寸的细胞单元计算HOG特征,并利用线性SVM进行分类,从而提出一种新的部位观测模型;（2）利用人体部位定位的先验分布确定部位定位区域,然后通过邻域归并和设置与部位模板的匹配度阈值进一步减小状态空间,从而提出了一种减小部位状态空间的方法。仿真实验结果表明所提算法与传统算法相比更加有效。     

一种高精度鲁棒的基于直线对应的位姿估计迭代算法

2D-3D特征对应位姿估计问题算法多基于点对应,而基于直线对应求解比基于点对应求解更具有优势。从欧氏空间这一新颖角度出发,提出了一种从直线对应求解位姿估计问题的迭代算法,算法思想是先迭代求解出最优的旋转矩阵,然后再得到平移向量。针对不同的直线组情形,给出了相应的迭代初始值计算方法。仿真实验数据表明,算法具有对初始值较不敏感、高精度、鲁棒性好等特点。     

Fast and globally convergent pose estimation from video images

Determining the rigid transformation relating 2D images to known 3D geometry is a classical problem in photogrammetry and computer vision. Heretofore, the best methods for solving the problem have relied on iterative optimization methods which cannot be proven to converge and/or which do not effectively account for the orthonormal structure of rotation matrices. We show that the pose estimation problem can be formulated as that of minimizing an error metric based on collinearity in object (as opposed to image) space. Using object space collinearity error, we derive an iterative algorithm which directly computes orthogonal rotation matrices and which is globally convergent. Experimentally, we show that the method is computationally efficient, that it is no less accurate than the best currently employed optimization methods, and that it outperforms all tested methods in robustness to outliers     

Direct model based visual tracking and pose estimation using mutual information

This paper deals with model-based pose estimation (or camera localization). We propose a direct approach that takes into account the image as a whole. For this, we consider a similarity measure, the mutual information. Mutual information is a measure of the quantity of information shared by two signals (or two images in our case). Exploiting this measure allows our method to deal with different image modalities (real and synthetic). Furthermore, it handles occlusions and illumination changes. Results with synthetic (benchmark) and real image sequences, with static or mobile camera, demonstrate the robustness of the method and its ability to produce stable and precise pose estimations.     

基于全局姿态感知的轻量级人体姿态估计

人体姿态估计是近年来人机交互领域的热点话题.当前,常见的人体姿态估计方法集中在通过增加网络的复杂性来提高精度,却忽视了模型的效益问题,导致模型在实际应用中精度高但计算资源消耗巨大.针对这一问题设计了一个基于全局姿态感知的轻量级人体姿态估计模型,其在MSCOCO数据集上精度达68.2％AP,速度保持在255 fps,参数...     

基于条件先验人体模型的人体姿态估计

人体姿态估计算法中的人体模型是对人体部位或关节间外观和空间关联情况的数学描述。虽然当前已经有部分人体模型在建立时考虑到了部位或关节的空间定位会满足一定的先验分布,但却都将基于同样先验分布建立的人体模型用于不同待处理图片进行人体姿态估计,并没有考虑到不同图片中的实际定位对先验分布服从程度的不同。为此,提出了一种基于条件先验的人体模型,在人体模型中添加自适应调节参数,参数值根据待处理图片中关节可能定位与外观模型相似度的大小来确定,从而达到根据待处理图片自适应调节先验分布在计算关节定位概率时所起作用大小的目的。将基于条件先验的人体模型用于人体姿态估计,仿真实验表明,与现有基于先验的人体模型相比,所提人体模型用于人体姿态估计时获得了更高的估计准确度。     

Monocular head pose estimation using generalized adaptive view-based appearance model

Accurately estimating the person’s head position and orientation is an important task for a wide range of applications such as driver awareness, meeting analysis and human-robot interaction. Over the past two decades, many approaches have been suggested to solve this problem, each with its own advantages and disadvantages. In this paper, we present a probabilistic framework called Generalized Adaptive View-based Appearance Model (GAVAM) which integrates the advantages from three of these approaches: (1) the automatic initialization and stability of static head pose estimation, (2) the relative precision and user-independence of differential registration, and (3) the robustness and bounded drift of keyframe tracking. In our experiments, we show how the GAVAM model can be used to estimate head position and orientation in real-time using a simple monocular camera. Our experiments on two previously published datasets show that the GAVAM framework can accurately track for a long period of time with an average accuracy of 3.5° and 0.75 in. when compared with an inertial sensor and a 3D magnetic sensor.     

Multi-camera head pose estimation

Estimating people’s head pose is an important problem, for which many solutions have been proposed. Most existing solutions are based on the use of a single camera and assume that the head is confined in a relatively small region of space. If we need to estimate unintrusively the head pose of persons in a large environment, however, we need to use several cameras to cover the monitored area. In this work, we propose a novel solution to the multi-camera head pose estimation problem that exploits the additional amount of information that provides multi-camera configurations. Our approach uses the probability estimates produced by multi-class support vector machines to calculate the probability distribution of the head pose. The distributions produced by the cameras are fused, resulting in a more precise estimate than the one provided individually. We report experimental results that confirm that the fused distribution provides higher accuracy than the individual classifiers and a high robustness against errors.     

基于地形高程模型的飞行器位姿估计方法

针对无法依靠景象匹配手段进行导航定位和无法有效利用惯导姿态信息的情况,提出了一种基于地形高程模型的飞行器绝对姿态和位置的估计方法。该方法首先利用机载下视摄像系统获取实时立体图像对及利用传感器获得飞行速度信息,通过修改双像运动模型来重建飞行器下方的地形信息;然后利用三维重建结果的刚体约束给出一种匹配机载地形高程模型数据的方法,用于估计飞行器在世界坐标系中的绝对位姿。仿真结果表明：改进的双像运动模型具有更高的精度,更有利于在世界坐标系下进行位姿估计。     

Model-free non-rigid head pose tracking by joint shape and pose estimation

Head pose estimation under non-rigid face movement is particularly useful in applications relating to eye-gaze tracking in less constrained scenarios, where the user is allowed to move naturally during tracking. Existing vision-based head pose estimation methods often require accurate initialisation and tracking of specific facial landmarks, while methods that handle non-rigid face deformations typically necessitate a preliminary training phase prior to head pose estimation. In this paper, we propose a method to estimate the head pose in real-time from the trajectories of a set of feature points spread randomly over the face region, without requiring a training phase or model-fitting of specific facial features. Conversely, our method exploits the 3-dimensional shape of the surface of interest, recovered via shape and motion factorisation, in combination with Kalman and particle filtering to determine the contribution of each feature point to the estimation of head pose based on a variance measure. Quantitative and qualitative results reveal the capability of our method in handling non-rigid face movement without deterioration of the head pose estimation accuracy.     

YOLOv3剪枝模型的多人姿态估计

目的 为了解决复杂环境中多人姿态估计存在的定位和识别等问题,提高多人姿态估计的准确率,减少算法存在的大量冗余参数,提高姿态估计的运行速率,提出了基于批量归一化层（batch normalization,BN）通道剪枝的多人姿态估计算法（YOLOv3 prune pose estimator,YLPPE）。方法 以目标检测算法YOLOv3（you only look once v3）和堆叠沙漏网络（stacked hourglass network,SHN）算法为基础,通过重叠度K-means算法修改YOLOv3网络锚框以更适应行人目标检测,并训练得到Trimming-YOLOv3网络;利用批量归一化层的缩放因子对Trimming-YOLOv3网络进行循环迭代式通道剪枝,设置剪枝阈值与缩放因子,实现较为有效的模型剪枝效果,训练得到Trim-Prune-YOLOv3网络;为了结合单人姿态估计网络,重定义图像尺寸为256×256像素（非正方形图像通过补零实现）;再级联4个Hourglass子网络得到堆叠沙漏网络,从而提升整体姿态估计精度。结果 利用斯坦福大学的MPⅡ数据集（MPⅡ human pose dataset）进行实验验证,本文算法对姿态估计的准确率达到了83.9%;同时,时间复杂度为O（n²）,模型参数量与未剪枝原始YOLOv3相比下降42.9%。结论 结合YOLOv3剪枝算法的多人姿态估计方法可以有效减少复杂环境对人体姿态估计的负面影响,实现复杂环境下的多人姿态估计并提高估计精度,有效减少模型冗余参数,提高算法的整体运行速率,能够实现较为准确的多人姿态估计,并具有较好的鲁棒性和泛化能力。     

Multiple human 3D pose estimation from multiview images

Multimedia Tools and Applications - Multiple human 3D pose estimation is a challenging task. It is mainly because of large variations in the scale and pose of humans, fast motions, multiple persons...     

Coarse head pose estimation of construction equipment operators to formulate dynamic blind spots

Several hundred workers die in construction in the United States every year because equipment operators are unable to see their fellow workers during operation of their vehicle. In this paper we propose a step towards improving this situation by providing an automated method based on range imaging for estimating the coarse head orientation of a construction equipment operator. This research utilizes commercially-available low resolution range cameras to measure the continuously changing field-of-view (FOV) of an equipment operator in outdoor construction. This paper presents a methodology to measure so-called dynamic blind spot maps. The dynamic blind spot map is then projected on a known static equipment blind spot map that already exists to each construction vehicle. A robust computational coarse head pose estimation algorithm and results to three different pieces of construction equipment and multiple operators are presented. The developed method has the potential in automatically determining the spaces around vehicles that are currently not in the field-of-view of the vehicle operator thus providing eventually additional means and technology for improving safety in construction.     

Multiple people tracking and pose estimation with occlusion estimation

Simultaneously tracking poses of multiple people is a difficult problem because of inter-person occlusions and self occlusions. This paper presents an approach that circumvents this problem by performing tracking based on observations from multiple wide-baseline cameras. The proposed global occlusion estimation approach can deal with severe inter-person occlusions in one or more views by exploiting information from other views. Image features from non-occluded views are given more weight than image features from occluded views. Self occlusion is handled by local occlusion estimation. The local occlusion estimation is used to update the image likelihood function by sorting body parts as a function of distance to the cameras. The combination of the global and the local occlusion estimation leads to accurate tracking results at much lower computational costs. We evaluate the performance of our approach on a pose estimation data set in which inter-person and self occlusions are present. The results of our experiments show that our approach is able to robustly track multiple people during large movement with severe inter-person occlusions and self occlusions, whilst maintaining near real-time performance.     

基于AAM和T型结构的人脸3D姿态估计

在分析已有的人脸姿态估计方法基础上,提出了一种基于主动表观模型(AAM)和T型结构的人脸3D姿态估计方法。对多姿态的人脸样本进行训练,得到多姿态的AAM模板集;利用训练得到的多姿态的AAM模板集进行最佳模板匹配,并对人脸的特征点进行精确定位;用人脸的双眼和嘴部构建T型模型,进行人脸3D姿态的参数估计。实验结果表明,该方法能适应较大的姿态旋转角度,并具有良好的姿态估计精度。