Head pose estimation using improved label distribution learning with fewer annotations

Multimedia Tools and Applications - Head pose estimation in unconstrained environment remains a challenging task due to background clutter, illumination changes, and appearance variabilities....     

基于标签分布学习的三维手部姿态估计

快速、可靠的手部姿态估计在人机交互等领域有着广泛的应用.为了解决光照强度变化、自身遮挡以及姿态变化幅度较大等情况对手部姿态估计的影响,提出了一种基于标签分布学习的深度网络结构.该网络将手部点云作为输入数据,首先通过最远点采样和定向边界框(OBB)对点云数据进行归一化处理,然后采用PointNet++提取手部点云数据特征...     

Model free head pose estimation using stereovision

In this paper we present a stereovision based model free 3D head pose (orientation and position) estimation system suitable for human–machine interface applications. The system works by obtaining a ‘face plane’ from the 3D reconstructed face data, which is then used for head pose estimation. The key novelty in this work is the utilization of the face plane together with the eye locations on the reconstructed face data to obtain a robust head pose estimate. This approach leads to a model and initialization free head pose estimation system; therefore it is suitable for natural human–machine interfaces. In order to quantitatively asses the accuracy of the system for such applications, several evaluation experiments were conducted using a commercial motion capture system. The evaluation results indicate that this system can be used in human–computer and human–robot applications.     

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.     

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.     

Practical age estimation using deep label distribution learning

Age estimation plays an important role in humancomputer interaction system. The lack of large number of facial images with definite age label makes age estimation algorithms inefficient. Deep label distribution learning (DLDL) which employs convolutional neural networks (CNN) and label distribution learning to learn ambiguity from ground-truth age and adjacent ages, has been proven to outperform current state-of-the-art framework. However, DLDL assumes a rough label distribution which covers all ages for any given age label. In this paper, a more practical label distribution paradigm is proposed: we limit age label distribution that only covers a reasonable number of neighboring ages. In addition, we explore different label distributions to improve the performance of the proposed learning model. We employ CNN and the improved label distribution learning to estimate age. Experimental results show that compared to the DLDL, our method is more effective for facial age recognition.     

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.     

Improved dense multivariate polynomial factorization algorithms

We present new deterministic and probabilistic algorithms that reduce the factorization of dense polynomials from several variables to one variable. The deterministic algorithm runs in sub-quadratic time in the dense size of the input polynomial, and the probabilistic algorithm is softly optimal when the number of variables is at least three. We also investigate the reduction from several to two variables and improve the quantitative version of Bertini’s irreducibility theorem.     

基于粒的标记增强标记分布学习

标记分布学习能有效求解多标记学习任务,然而分类器构造以获得大规模具有更强监督信息的标注为前提,在许多应用中难以满足。一种替代的方案是以标记增强的方式从传统逻辑形式的标注中挖掘出隐含的数值型标记的重要程度。现有的标记增强方法大多假设增强后的标记需要在所有示例上保持原有逻辑标记的相关性,不能有效保持局部标记相关性。基于粒计算理论,提出了一种适用于标记分布学习的粒化标记增强学习方法。该方法通过k均值聚类构造具有局部相关性语义的信息粒,并在粒的抽象层面上,分别在图上依据逻辑标记的特性和属性空间的拓扑性质完成粒内示例的标记转化。最后,将得到的标记分布在示例层面进行融合,得到描述整个数据集标记重要程度的数值型标记。大量比较研究表明,所提出的模型可以显著地提升多标记学习的性能。     

An effective head pose estimation approach using Lie Algebrized Gaussians based face representation

The accuracy of head pose estimation is significant for many computer vision applications such as face recognition, driver attention detection and human-computer interaction. Most appearance-based head pose estimation works typically extract the low-dimensional face appearance features in some statistic subspaces, where the subspaces represent the underlying geometry structure of the pose space. However, there is an open problem, namely, how to effectively represent appearance-based subspace face for the head pose estimation problem. To address the problem, this paper proposes a head pose estimation approach based on the Lie Algebrized Gaussians (LAG) feature to model the pose characteristic. LAG is built on Gaussian Mixture Models (GMM), which actually not only models the distribution of local appearance features, but also captures the Lie group manifold structure of the feature space. Moreover, to keep multi-resolution structure information, LAG is operated on many subregions of the image. As a result, these properties of LAG enable it to effectively model the structure of subspace face which can lead to powerful discriminative ability for head pose estimation. After representing subspace face using the LAG, we treat the head pose estimation as a classification problem. The within-class covariance normalization (WCCN) based Support Vector Machine (SVM) classifier is employed to achieve robust performance as WCCN could reduce the within-class variabilities of the same pose. Extensive experimental analysis and comparison with both traditional and state-of-the-art algorithms on two challenging benchmarks demonstrate the effectiveness of our approach.     

VTG schemes for using back propagation for multivariate time series prediction

This research proposes the three schemes of estimating and adding mid-terms to multivariate time series. In this research, the back propagation is adopted as the approach to multivariate time series prediction. It is traditionally designed for the task with the two models: separated model and combined model. In the proposed version of time series prediction systems, the mid-term estimator is added as the additional module to the traditional version. It is validated empirically that the three VTG (Virtual Term Generation) schemes are effective on using the back propagation for multivariate time series prediction on the four test data sets: three artificial one and a real test one.     

Human head pose estimation based on HF method

This Paper addresses the problem of head pose estimation. Driving assistance technology utilizes head pose estimation as an indicator for visual focus and mental attention of the driver. Head pose estimation detects head orientation with respect to the camera. Model based and appearance-based methods are the two approaches in head pose estimation. The first approach uses the facial features to create a face geometrical models whereas the second method only takes into consideration the entire face image. The proposed appearance-based method work is performed using Hough transform and random forest to classify ninety-three classes of Hough values in order to find the exact head pose. The performance of the proposed work is evaluated based on accuracy and the time taken to detect the head pose. The paper outperforms many other previous works.     

Analysis of head pose accuracy in augmented reality

A method is developed to analyze the accuracy of the relative head-to-object position and orientation (pose) in augmented reality systems with head-mounted displays. From probabilistic estimates of the errors in optical tracking sensors, the uncertainty in head-to-object pose can be computed in the form of a covariance matrix. The positional uncertainty can be visualized as a 3D ellipsoid. One useful benefit of having an explicit representation of uncertainty is that we can fuse sensor data from a combination of fixed and head-mounted sensors in order to improve the overall registration accuracy. The method was applied to the analysis of an experimental augmented reality system, incorporating an optical see-through head-mounted display, a head-mounted CCD camera, and a fixed optical tracking sensor. The uncertainty of the pose of a movable object with respect to the head-mounted display was analyzed. By using both fixed and head mounted sensors, we produced a pose estimate that is significantly more accurate than that produced by either sensor acting alone     

Assessment of human head pose in human-computer interaction

A system is described that estimates a user??s head position from a video image of it. The system includes three base algorithms: segmentation, detection of markers, and assessment of motion direction. The direction of head motion is determined by the dynamics of changing geometrical correlations between facial markers in the picture sequence. It is shown that the change in the angle formed by straight lines connecting the corners of the eyes and the tip of the nose have change dynamics similar to that of ??yawing.?? This system operates in real time (7 fps) and ensures high precision in assessing the direction of motions (p = 0.95).     

结合局部标记序关系的弱监督标记分布学习

标记分布学习（label distribution learning,LDL）是一种用于解决标记多义性的新颖学习范式。现有的LDL方法大多基于完整数据信息进行设计,然而由于高昂的标注成本以及标注人员水平的局限性,很难获取到完整标注数据信息,且会导致传统LDL算法性能的下降。为此,本文提出了一种新型的结合局部序标记关系的弱监督标记分布学习算法,通过维持尚未缺失标记之间的相对关系,并利用标记相关性来恢复缺失的标记,在数据标注不完整的情况下提升算法性能。在14个数据集上进行了大量的实验来验证算法的有效性。     

Quantum simultaneous secret distribution with dense coding by using cluster states

A new communication mode, quantum simultaneous secret distribution (QSSD) is put forward, where one sender distributes different classical secret message to multiparty receivers simultaneously. Based on the properties of the one-dimensional four-qubit cluster states, a three-party QSSD protocol is proposed, and then it is extended to the case that there are many receivers. Owing to the idea of quantum dense coding, each receiver can receive two bits of classical message by the sender only using a cluster state. In order to check security of quantum channels, a strategy which can prevent common attacks efficiently is put forward. QSSD is distinct from quantum secret sharing (QSS) and quantum broadcast communication (QBC), but it can be easily converted into QSS and QBC. QSSD is also different from the multiple-QKD communication mode where the sender shares a private key with each receiver at first, while in QSSD the sender doesn’t; in addition, only one round of one-to-many communication is performed in QSSD, while in multiple-QKD communication mode many rounds of one-to-one communication are performed.     

Long-term traffic flow prediction using multivariate SSA forecasting in SDN based networks

Accurate and real-time traffic flow forecasting plays an important role in optimizing traffic routing enabling adaptive and sophisticated applications on the network. Managing and routing enormous traffic flow with dynamic behavior is a highly challenging task. However, arriving at a precise model for traffic forecasting in a short interval of time is not trivial because of the dynamic nature of traffic flow. A novel multivariate time series framework is designed to analyze and forecast the dynamic traffic flow in SDN based networks. The proposed framework adapts the Multivariate Singular Spectrum Analysis (MSSA) forecasting model and incorporates the Randomized Singular Value Decomposition (RSVD) to improve the accuracy of flow prediction. Simulations are conducted to evaluate the effectiveness of the proposed MSSA method. The proposed method predicts the long-term traffic fluctuation from the observed traffic traces. The SDN controller is trained using the traffic traces and future traffic flows are forecasted. The performance evaluation of the proposed method predicts real-time traffic trends accurately with 2.2% MAPE, 9.44 MAE and 13.803 RMSE. The results show that the learning ability of MSSA helps to forecast future network traffic with low prediction errors.     

Dynamic random regression forests for real-time head pose estimation

For real-time evaluation of the position and orientation of the human head using depth image, we propose a novel algorithm, the dynamic random regression forests (DRRF), which enhances the conventional random forests (RF) in four aspects. Firstly, the DRRF employs the boosting strategy for data induction to upgrade the learning quality; secondly, the key parameters are optimized in a dynamic manner in order to train the DRRF classifier efficiently; thirdly, a stem operator is integrated into the conventional tree-shaped classifier to increase the possibility of optimum data split; fourthly, a weighted voting scheme utilizes the learning knowledge to determine the regression result more efficiently and accurately. Comparative experiments verify the advantages of the aforementioned four improvement schemes, and demonstrate the DRRF’s accuracy and robustness against partial occlusion and the variations of head pose, illumination, and facial expression.     

一种基于改进的LEA头部姿态估计方法

局部嵌入分析(LEA)是图嵌入化的局部线性嵌入(LLE)方法。在头姿态估计问题上,选择局部邻域时只考虑属于同一类的姿态,但失去了相邻姿态的几何拓扑信息。为此,提出一种改进的邻域选择方法,充分利用先验姿态信息,使降维后的流形更加平滑,同类姿态互相靠近,不同类姿态之间的距离随着姿态差值变大而增大,且能够使训练及测试样本的低维流形更加靠近,降低了估计误差。在Facepix人脸数据库上的实验证明了该方法的有效性。