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

School of Information Science and Engineering, Central South University, Changsha 410083, People's Republic of China
Pattern Recognition (Impact Factor: 2.58). 07/2009; DOI: 10.1016/j.patcog.2008.12.024
Source: DBLP

ABSTRACT 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.

  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, the problem of automatic dance performance evaluation from human Motion Capture (MoCap) data is addressed. A novel framework is presented, using data captured by Kinect-based human skeleton tracking, where the evaluation of user’s performance is achieved against a gold-standard performance of a teacher. The framework addresses several technical challenges, including global and local temporal synchronization, spatial alignment and comparison of two “dance motion signals.” Towards the solution of these technical challenges, a set of appropriate quaternionic vector-signal processing methodologies is proposed, where the 4D (spatiotemporal) human motion data are represented as sequences of pure quaternions. Such a quaternionic representation offers several advantages, including the facts that joint angles and rotations are inherently encoded in the phase of quaternions and the three coordinates variables ($X,Y,Z$) are treated jointly, with their intra-correlations being taken into account. Based on the theory of quaternions, a number of advantageous algorithms are formulated. Initially, global temporal synchronization of dance MoCap data is achieved by the use of quaternionic cross-correlations, which are invariant to rigid spatial transformations between the users. Secondly, a quaternions-based algorithm is proposed for the fast spatial alignment of dance MoCap data. Thirdly, the MoCap data can be temporally synchronized in a local fashion, using Dynamic Time Warping techniques adapted to the specific problem. Finally, a set of quaternionic correlation-based measures (scores) are proposed for evaluating and ranking the performance of a dancer. These quaternions-based scores are invariant to rigid transformations, as proved and demonstrated. A total score metric, through a weighted combination of three different metrics is proposed, where the weights are optimized us- ng Particle Swarm Optimization (PSO). The presented experimental results using the $hbox{Huawei/3DLife/EMC}^2$ dataset are promising and verify the effectiveness of the proposed methods.
    IEEE Transactions on Multimedia 08/2014; 16(5):1391-1406. DOI:10.1109/TMM.2014.2317311 · 1.78 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In wireless body sensor networks, sensors may be installed on various body limbs to wirelessly collect body information for homecare services. The orientations and accel-erations on each limb are different for various motion states. For example, each limb has different acceleration when walking versus running, and orientation when standing versus lying. According to the above information, the body motion state may be decided. Furthermore, each person has unique body characteristics such as height, foot pitch, and motion habit to effect the body reconstruction. Therefore, it is a challenging issue how to present human motions through 3D skeleton system simulation, and achieve an adaptive reconstruction of human motion according to the different body characteristics of each person. In this study, we proposed a novel scheme to utilize multiple triple axis accelerometer and gyroscopes to measure limb accelerations, then calculated the locations of limbs and try to employ kinematic theory to reconstruct human body skeleton, called 3D Adaptive human Motion Reconstruction (AMR). And we applied Body Correction Algorithm (BCA) to correct human body characteristics and fighted the error of transmission noise. This system was tested and validated with success.
  • [Show abstract] [Hide abstract]
    ABSTRACT: 3D human motion tracking has received increasing attention in recent years due to its broad applications. Among various 3D human motion tracking methods, the particle filter is regarded as one of the most effective algorithms. However, there are still several limitations of current particle filter approaches such as low prediction accuracy and sensitivity to discontinuous motion caused by low frame rate or sudden change of human motion velocity. Targeting such problems, this paper presents a full-body human motion tracking system by proposing exemplar-based conditional particle filter (EC-PF) for monocular camera. By introducing a conditional term with respect to exemplars and image data, dynamic model is approximated and used to predict current states of particles in prediction phase. In update phase, weights of particles are refined by matching images with projected human model using a set of features.