Representing cyclic human motion using functional analysis

We present a robust automatic method for modeling cyclic 3D human motion such as walking using motion-capture data. The pose of the body is represented by a time-series of joint angles which are automatically segmented into a sequence of motion cycles. The mean and the principal components of these cycles are computed using a new algorithm that enforces smooth transitions between the cycles by operating in the Fourier domain. Key to this method is its ability to automatically deal with noise and missing data. A learned walking model is then exploited for Bayesian tracking of 3D human motion.     

A survey of advances in vision-based human motion capture and analysis

This survey reviews advances in human motion capture and analysis from 2000 to 2006, following a previous survey of papers up to 2000 [T.B. Moeslund, E. Granum, A survey of computer vision-based human motion capture, Computer Vision and Image Understanding, 81(3) (2001) 231–268.]. Human motion capture continues to be an increasingly active research area in computer vision with over 350 publications over this period. A number of significant research advances are identified together with novel methodologies for automatic initialization, tracking, pose estimation, and movement recognition. Recent research has addressed reliable tracking and pose estimation in natural scenes. Progress has also been made towards automatic understanding of human actions and behavior. This survey reviews recent trends in video-based human capture and analysis, as well as discussing open problems for future research to achieve automatic visual analysis of human movement.     

Monocular human motion tracking

Human motion tracking from monocular image sequences has been explored widely. However, a framework that addresses the variety of sensing conditions is lacking. In this paper, we present a simple, efficient, and robust method for recovering plausible 3D motion from a video without knowledge of the cameras parameters. Our method transforms the motion capture problem into a convex problem and employs a hierarchical geometrical solver for the minimization. This algorithm was applied to numerous synthetic and real image sequences with very encouraging results. Specifically, our results indicate that it can handle challenges posed by variation of lighting, partial self-occlusion, and rapid motion.Published online: 21 October 2004     

Understanding human behavior from motion imagery

Computer vision is gradually making the transition from image understanding to video understanding. This is due to the enormous success in analyzing sequences of images that has been achieved in recent years. The main shift in the paradigm has been from recognition followed by reconstruction (shape from X) to motion-based recognition. Since most videos are about people, this work has focused on the analysis of human motion. In this paper, I present my perspective on understanding human behavior. Automatically understanding human behavior from motion imagery involves extraction of relevant visual information from a video sequence, representation of that information in a suitable form, and interpretation of visual information for the purpose of recognition and learning about human behavior. Significant progress has been made in human tracking over the last few years. As compared with tracking, not much progress has been made in understanding human behavior, and the issue of representation has largely been ignored. I present my opinion on possible reasons and hurdles for slower progress in understanding human behavior, briefly present our work in tracking, representation, and recognition, and comment on the next steps in all three areas.Published online: 28 August 2003     

The human motion database: A cognitive and parametric sampling of human motion

Motion databases have a strong potential to guide progress in the field of machine recognition and motion-based animation. Existing databases either have a very loose structure that does not sample the domain according to any controlled methodology or too few action samples which limit their potential to quantitatively evaluate the performance of motion-based techniques. The controlled sampling of the motor domain in the database may lead investigators to identify the fundamental difficulties of motion cognition problems and allow the addressing of these issues in a more objective way. In this paper, we describe the construction of our Human Motion Database using controlled sampling methods (parametric and cognitive sampling) to obtain the structure necessary for the quantitative evaluation of several motion-based research problems. The Human Motion Database is organized into several components: the praxicon dataset, the cross-validation dataset, the generalization dataset, the compositionality dataset, and the interaction dataset. The main contributions of this paper include (1) a survey of human motion databases describing data sources related to motion synthesis and analysis problems, (2) a sampling methodology that takes advantage of a systematic controlled capture, denoted as cognitive sampling and parametric sampling, and (3) a novel structured motion database organized into several datasets addressing a number of aspects in the motion domain.     

Sample size calculations for a functional human motion analysis: Application to vehicle ingress discomfort prediction

The ease of entering a vehicle, known as ingress, is one of the important ergonomic factors that car manufacturers consider during the process of vehicle design. Manufacturers frequently conduct human subject tests to assess ingress discomfort for different vehicle designs. Using subject tests, manufacturers are able to estimate the proportion of participants that report that they are discomfortable entering a vehicle, referred to in this paper as fraction disaccommodated (FD). Manufacturers then conduct statistical tests in order to determine if the FD of two vehicle designs are significantly different, and to determine the required sample size in testing the FD difference between two vehicle designs under pre-specified testing power. Since conducting human subject tests is often expensive and time consuming, another alternative is to estimate the FD using simulated human motion data. Determining the number of simulations that is required is an important statistical question that is dependent on the prediction performance of the simulation analysis. In this paper, a dual bootstrap approach is proposed to obtain the standard deviation of the estimated FD based on functional predictors. This standard deviation is then used to calculate the power in testing the difference between two estimated FDs.     

人体运动分析的实例学习方法

目的 面向实时、准确、鲁棒的人体运动分析应用需求,从运动分析的特征提取和运动建模问题出发,本文人体运动分析的实例学习方法。方法 在构建人体姿态实例库基础上,首先,采用运动检测方法得到视频每帧的人体轮廓;其次,基于形状上下文轮廓匹配方法,从实例库中检索得到每帧视频的候选姿态集;最后,通过统计建模和转移概率建模实现人体运动分析。结果 对步行、跑步、跳跃等测试视频进行实验,基于轮廓的形状上下文特征表示和匹配方法具有良好的表达能力;本文方法运动分析结果,关节夹角平均误差在5°左右,与其他算法相比,有效提高了运动分析的精度。结论 本文人体运动分析的实例学习方法,能有效分析单目视频中的人体运动,并克服了映射的深度歧义,对运动的视角变化鲁棒,具有良好的计算效率和精度。     

Action-specific motion prior for efficient Bayesian 3D human body tracking

In this paper, we aim to reconstruct the 3D motion parameters of a human body model from the known 2D positions of a reduced set of joints in the image plane. Towards this end, an action-specific motion model is trained from a database of real motion-captured performances, and used within a particle filtering framework as a priori knowledge on human motion. First, our dynamic model guides the particles according to similar situations previously learnt. Then, the state space is constrained so only feasible human postures are accepted as valid solutions at each time step. As a result, we are able to track the 3D configuration of the full human body from several cycles of walking motion sequences using only the 2D positions of a very reduced set of joints from lateral or frontal viewpoints.     

Automatic reconstruction of 3D human motion pose from uncalibrated monocular video sequences based on markerless human motion tracking

We present a method to reconstruct human motion pose from uncalibrated monocular video sequences based on the morphing appearance model matching. The human pose estimation is made by integrated human joint tracking with pose reconstruction in depth-first order. Firstly, the Euler angles of joint are estimated by inverse kinematics based on human skeleton constrain. Then, the coordinates of pixels in the body segments in the scene are determined by forward kinematics, by projecting these pixels in the scene onto the image plane under the assumption of perspective projection to obtain the region of morphing appearance model in the image. Finally, the human motion pose can be reconstructed by histogram matching. The experimental results show that this method can obtain favorable reconstruction results on a number of complex human motion sequences.     

Learning intentions for improved human motion prediction

For many tasks robots need to operate in human populated environments. Human motion prediction is gaining importance since this helps minimizing the hinder robots cause during the execution of these tasks. The concept of social forces defines virtual repelling and attracting forces from and to obstacles and points of interest. These social forces can be used to model typical human movements given an environment and a person’s intention. This work shows how such models can exploit typical motion patterns summarized by growing hidden Markov models (GHMMs) that can be learned from data online and without human intervention. An extensive series of experiments shows that exploiting a person’s intended position estimated using a GHMM within a social forces based motion model yields a significant performance gain in comparison with the standard constant velocity-based models.     

High-speed human motion recovery employing back projection

This paper describes a novel technique for high-speed human motion recovery. For 3-D human motion recovery, stereoscopic vision is a normal technique, as well as the employment of a magnetic field, but this cannot avoid the difficulty of marker tracking. In this article, a novel motion recovery technique is proposed based on the back projection of silhouette images. This technique has some advantages over others because it does not employ markers, and it has a simple architecture. In the experiment performed, the proposed motion recovery technique is implemented on a system containing a LAN, a host computer, and four pairs of camera and computer, and it achieves high-speed human motion recovery. This work was presented in part at the 10th International Symposium on Artificial Life and Robotics, Oita, Japan, February 4–6, 2005     

Image sequence analysis of real world human motion

Three fundamental problems of image sequence analysis are investigated for real world human motions. The first one is the modelling of body motion, which is approached by the methods of key frame sequence of stick figures and generalized cone approximation of body parts. The second problem is the correspondence of feature points in the consecutive frames, for which a method called “window code matching” is proposed. The last one is the analysis of occluding regions, which is studied on the bases of occlusion prediction by model and difference images.     

Tracking in dense crowds using prominence and neighborhood motion concurrence

Methods designed for tracking in dense crowds typically employ prior knowledge to make this difficult problem tractable. In this paper, we show that it is possible to handle this problem, without any priors, by utilizing the visual and contextual information already available in such scenes.     

Exploiting linked data to create rich human digital memories

Memories are an important aspect of a person’s life and experiences. The area of human digital memories focuses on encapsulating this phenomenon, in a digital format, over a lifetime. Through the proliferation of ubiquitous devices, both people and the surrounding environment are generating a phenomenal amount of data. With all of this disjointed information available, successfully searching it and bringing it together, to form a human digital memory, is a challenge. This is especially true when a lifetime of data is being examined. Linked Data provides an ideal, and novel, solution for overcoming this challenge, where a variety of data sources can be drawn upon to capture detailed information surrounding a given event. Memories, created in this way, contain vivid structures and varied data sources, which emerge through the semantic clustering of content and other memories. This paper presents DigMem, a platform for creating human digital memories, based on device-specific services and the user’s current environment. In this way, information is semantically structured to create temporal “memory boxes” for human experiences. A working prototype has been successfully developed, which demonstrates the approach. In order to evaluate the applicability of the system a number of experiments have been undertaken. These have been successful in creating human digital memories and illustrating how a user can be monitored in both indoor and outdoor environments. Furthermore, the user’s heartbeat information is analysed to determine his or her heart rate. This has been achieved with the development of a QRS Complex detection algorithm and heart rate calculation method. These methods process collected electrocardiography (ECG) information to discern the heart rate of the user. This information is essential in illustrating how certain situations can make the user feel.     

一种人体运动重定向方法*

提出人体下肢向量的概念,通过分析人体运动指出下肢向量能保持运动的主要特征,由此提出基于下肢向量特征不变性的人体运动重定向方法,以此提高运动捕获数据的可重用性。该方法面向人体下肢的运动重定向,能够将运动数据从原始骨骼模型重定向到具有不同骨骼长度比例的目标骨骼模型,同时保持原始运动的主要特征。实验结果表明,该方法具有较好的运动重定向效果和较快的计算效率。     

Recent developments in structural sensitivity analysis

The present paper reviews recent developments in two major areas of structural sensitivity analysis: sensitivity of static and transient response; and sensitivity of vibration and buckling eigenproblems. Recent developments from the standpoint of computational cost, accuracy, and ease of implementation are presented.In the area of static response, current interest is focused on sensitivity to shape variation and sensitivity of nonlinear response. Two general approaches are used for computing sensitivities: differentiation of the continuum equations followed by discretization, and the reverse approach of discretization followed by differentiation. It is shown that the choice of methods has important accuracy and implementation implications.In the area of eigenproblem sensitivity, there is a great deal of interest and significant progress in sensitivity of problems with repeated eigenvalues. The paper raises the issue of differentiability and continuity that is inherent to the repeated eigenvalue case.