Global Pose Research Articles

Generic and Robust Method for Head Pose Estimation

Head pose estimation has fascinated the research community due to its application in facial motion capture, human-computer interaction and video conferencing. It is a pre-requisite to gaze tracking, face recognition, and facial expression analysis. In this paper, we present a generic and robust method for model-based global 2D head pose estimation from single RGB Image. In our approach we use of the one part the Gabor filters to conceive a robust pose descriptor to illumination and facial expression variations, and that target the pose information. Moreover, we ensure the classification of these descriptors using a SVM classifier. The approach has proved effective view the rate for the correct pose estimations that we got.

A local-global coupled-layer puppet model for robust online human pose tracking

This paper addresses the problem of online tracking of articulated human body poses in dynamic environments. Many previous approaches perform poorly in realistic applications: often future frames or entire sequences are used anticausally to mutually refine the poses in each individual frame, making online tracking impossible; tracking often relies on strong assumptions about e.g. clothing styles, body-part colours and constraints on body-part motion ranges, limiting such algorithms to a particular dataset; the use of holistic feature models limits the ability of optimisation-based matching to distinguish between pose errors of different body parts. We overcome these problems by proposing a coupled-layer framework, which uses the previous notions of deformable structure (DS) puppet models. The underlying idea is to decompose the global pose candidate in any particular frame into several local parts to obtain a refined pose. We introduce an adaptive penalty with our model to improve the searching scope for a local part pose, and also to overcome the problem of using fixed constraints. Since the pose is computed using only current and previous frames, our method is suitable for online sequential tracking. We have carried out empirical experiments using three different public benchmark datasets, comparing two variants of our algorithm against four recent state-of-the-art (SOA) methods from the literature. The results suggest comparatively strong performance of our method, regardless of weaker constraints and fewer assumptions about the scene, and despite the fact that our algorithm is performing online sequential tracking, whereas the comparison methods perform mutual optimisation backwards and forwards over all frames of the entire video sequence.

Simulation study of a constant time hybrid approach for large scale terrain mapping using satellite stereo imagery

This work addresses the problem of performing large scale SLAM (Simultaneous Localization And Mapping) with satellite stereo imagery for terrain mapping, using a constant time estimation approach. The approach adopts the relative bundle adjustment approach (RBA) and integrates with it a particle-based framework to obtain a constant time probabilistic pose estimation model. The approach further uses a concept of fuzzy landmark-based similarity between poses to make common landmark identification across poses easier, especially when landmarks are sparsely encountered. In order to achieve robustness under varying environmental conditions, we use Speeded Up Robust Features (SURF) for computing spatial and temporal landmark correspondences across time steps. Finally, we use a fast loop closure approach to reduce drifts and obtain global pose estimates. For simulation study, the robot images are cropped from stereo-pair satellite images at different time steps incorporating errors in the robot’s control information. Extensive experimentation has been carried out to study the robot trajectories and the determination of Digital Elevation Model (DEM), with encouraging findings. We have also compared our work with 6D FastSLAM 2.0 (Thrun et al. (2005)) as well as Relative SLAM (RSLAM) due to Mei et al. (2010).

Robust world-centric stereo EKF localization with active loop closing for AUVs

Visual localization is a crucial task in Autonomous Underwater Vehicles (AUV) and it is usually complicated by the extreme irregularity of the natural aquatic environments, or by unfavorable water conditions. Visual Simultaneous Localization and Mapping (SLAM) approaches are widely used in land and represent the most precise techniques for localization, but applied underwater, they are still an open and ongoing challenge. This paper presents a general approach to visual 3D pose-based SLAM based on Extended Kalman Filters (EKF). This approach has a general design being applicable to any vehicle with up to 6 Degrees of freedom, so, it is particularly suitable for AUV. It uses only visual data coming from a stereo camera, all orientations involved in the system are represented in the quaternion space in order to avoid the gimbal lock singularities, and the sparsity of the covariance matrix is guaranteed during the whole trajectory since the state vector only includes the vehicle global pose. The vehicle pose is continuously predicted by means of a stereo visual odometer, and eventually corrected with the pose constraints given by a particularization of the Perspective N-Point problem (PNP) [1], applied to the registration of images that most likely close a loop. Experimental results show the important pose corrections given by the SLAM approach with respect to a ground truth, compared with the evident trajectory errors present in the visual odometer estimates.

Self-calibration and visual SLAM with a multi-camera system on a micro aerial vehicle

The use of a multi-camera system enables a robot to obtain a surround view, and thus, maximize its perceptual awareness of its environment. If vision-based simultaneous localization and mapping (vSLAM) is expected to provide reliable pose estimates for a micro aerial vehicle (MAV) with a multi-camera system, an accurate calibration of the multi-camera system is a necessary prerequisite. We propose a novel vSLAM-based self-calibration method for a multi-camera system that includes at least one calibrated stereo camera, and an arbitrary number of monocular cameras. We assume overlapping fields of view to only exist within stereo cameras. Our self-calibration estimates the inter-camera transforms with metric scale; metric scale is inferred from calibrated stereo. On our MAV, we set up each camera pair in a stereo configuration which facilitates the estimation of the MAV’s pose with metric scale. Once the MAV is calibrated, the MAV is able to estimate its global pose via a multi-camera vSLAM implementation based on the generalized camera model. We propose a novel minimal and linear 3-point algorithm that uses relative rotation angle measurements from a 3-axis gyroscope to recover the relative motion of the MAV with metric scale and from 2D-2D feature correspondences. This relative motion estimation does not involve scene point triangulation. Our constant-time vSLAM implementation with loop closures runs on-board the MAV in real-time. To the best of our knowledge, no published work has demonstrated real-time on-board vSLAM with loop closures. We show experimental results from simulation experiments, and real-world experiments in both indoor and outdoor environments.

Distributed Leader-Assistive Localization Method for a Heterogeneous Multirobotic System

This paper presents a distributed leader-assistive localization approach for a heterogeneous multirobotic system (MRS). The localization algorithm is formulated to estimate the position and orientation (pose) of a group of robots in a given reference coordinate frame (or global coordinate frame). It is assumed that the heterogeneous-MRS has one or a group of robots (which we refer as leader robots) with higher sensor payload, higher processing power, and larger memory capacity, enabling accurate self-localization capabilities. Robots with limited resources (which we refer as child robots) rely on leader robots, and inter-robot observations between leaders and themselves for localization. Finite-range sensing is a key challenge for such leader-assistive localization. This study presents a sensor sharing technique which virtually enhances the sensing range of leader robots. In the proposed method, each robot locally runs a cubature Kalman filter to estimate its own pose and hosts a low cost, lightweight, and low-power sensory system to periodically measure relative pose of neighbors. Each robot transmits these relative pose measurements to leader robots. Leader robots then combine available relative observations in order to synthesise global pose measurements and associated noise covariances for child robots. Child robots are acknowledged by the leader robots with the synthesized global pose measurements and fuse these measurements with their local belief in order to improve their localization. Theoretical developments are presented to virtually enhance the leader robots’ sensing range. The performance of the proposed distributed leader-assistive localization algorithm is evaluated on a multirobot simulation test-bed and on a publicly available multirobot localization and mapping data-set. The results illustrate that the proposed algorithm is capable of establishing accurate and consistent localization for the child robots even when they operate beyond the sensing range of the leader robots.

Improving Prehensile Mobile Manipulation Performance through Experience Reuse

During pick and place tasks, a mobile manipulator performs recurring relative moves within the close proximities of the object of interest and the destination independent of their global poses. The...

Global Localization Using Dead-Reckoning and Kinect Sensors for Robots with Omnidirectional Mecanum Wheels

This paper presents a low-cost global pose localization method using least-squares method and extended Kalman filter (EKF) for an anthropomorphous dual-arm mobile robot (ADAMR) driven by omnidirectional Mecanum wheels in indoor environments. This method is developed by fusing measurements from the KINECT sensor and four encoders mounted on the omnidirectional Mecanum wheels. The KINECT sensor is used to recognize landmarks in the working environments of the robot, and then obtain the azimuth angles and distances between these landmarks and the robot. Based on these measured information, a static global pose initialization algorithm using least-squares method is applied to estimate both unknown start-up position and orientation of the robot. Once the initial pose has been roughly determined, an EKF approach is proposed to fuse the odometric measurements from the four encoders and the azimuth angles and distances from the KINECT sensor to corresponding landmarks. Simulations are conducted to show performance of the proposed method. Experimental results are used to illustrate that the proposed method provides accurate static estimation of both unknown initial poses of the robot.

Error analysis and optimization of a 3-degree of freedom translational Parallel Kinematic Machine

In this paper, error modeling and analysis of a typical 3-degree of freedom translational Parallel Kinematic Machine is presented. This mechanism provides translational motion along the Cartesian X-, Y- and Z-axes. It consists of three limbs each having an arm and forearm with prismatic-revolute-revolute-revolute joints. The moving or tool platform maintains same orientation in the entire workspace due to its joint arrangement. From inverse kinematics, the joint angles for a given position of tool platform necessary for the error modeling and analysis are obtained. Error modeling is done based on the differentiation of the inverse kinematic equations. Variation of pose errors along X, Y and Z directions for a set of dimensions of the parallel kinematic machine is presented. A non-dimensional performance index, namely, global error transformation index is used to study the influence of dimensions and its corresponding global maximum pose error is reported. An attempt is made to find the optimal dimensions of the Parallel Kinematic Machine using Genetic Algorithms in MATLAB. The methodology presented and the results obtained are useful for predicting the performance capability of the Parallel Kinematic Machine under study.

Statistical analysis of relative pose of the thalamus in preterm neonates.

Preterm neonates are at higher risk of neurocognitive and neurosensory abnormalities. While numerous studies have looked at the effect of prematurity on brain anatomy, none to date have attempted to understand the relative pose of subcortical structures and to assess its potential as a biomarker of abnormal growth. Here, we perform the first relative pose analysis on a point distribution model (PDM) of the thalamus between 17 preterm and 19 term-born healthy neonates. Initially, linear registration and constrained harmonic registration were computed to remove the irrelevant global pose information and obtain correspondence in vertices. All the parameters for the relative pose were then obtained through similarity transformation. Subsequently, all the pose parameters (scale, rotation and translation) were projected into a log-Euclidean space, where univariate and multivariate statistics were performed. Our method detected relative pose differences in the preterm birth for the left thalamus. Our results suggest that relative pose in subcortical structures is a useful indicator of brain injury, particularly along the anterior surface and the posterior surface. Our study supports the concept that there are regional thalamic asymmetries in the preterm that may be related to subtle white matter injury, have prognostic significance, or be related to preterm birth itself.

Recovering upper-body motion using a reinitialization particle filter

An important problem associated with particle filtering is track drift, which is caused by the inaccurate likelihood measurement function and state model; another problem is the heavy computation cost in high state space. A human body is an articulated object with high degrees of freedom, and humans often perform versatile unconstrained motions. Therefore, these two problems are invariably encountered when human motion is reconstructed from monocular video sequences using particle filters. To overcome these problems, we present a novel approach to recover three-dimensional human upper-body pose using a combination of a deterministic and stochastic method that takes full advantage of the benefits of both methods—highly accurate pose reconstruction and low computation cost. The reconstruction of the human upper-body pose is divided into two parts: global pose estimation and pose estimation of the remaining joints. The global pose is determined by solving a system of six nonlinear equations established by three scale invariant feature transform (SIFT) correspondences within the left and right shoulder segments. Estimation of the pose of the remaining joints is accomplished using two particle filters, one for left arm pose estimation and the other for right arm pose estimation. The image projection of the segment model is obtained by forward kinematics under a perspective camera model, and the likelihood measurement functions involving two features are presented to enhance the model fitting performance. To avoid track drift, the particle filters can reinitialize particle sets if most of the particles deviate from the target object. The probability distribution of the new particle set is modeled by a Gaussian mixture model, in which each Gaussian is determined by matched SIFT correspondences. Experimental results show that our proposed approach effectively and efficiently achieves human upper-body tracking and is more accurate than the standard particle filter.

Multi-observation sensor resetting localization with ambiguous landmarks

Successful approaches to the robot localization problem include particle filters, which estimate non-parametric localization belief distributions. Particle filters are successful at tracking a robot's pose, although they fare poorly at determining the robot's global pose. The global localization problem has been addressed for robots that sense unambiguous visual landmarks with sensor resetting, by performing sensor-based resampling when the robot is lost. Unfortunately, for robots that make sparse, ambiguous and noisy observations, standard sensor resetting places new pose hypotheses across a wide region, in poses that may be inconsistent with previous observations. We introduce multi-observation sensor resetting (MOSR) to address the localization problem with sparse, ambiguous and noisy observations. MOSR merges observations from multiple frames to generate new hypotheses more effectively. We demonstrate experimentally on the NAO humanoid robots that MOSR converges more efficiently to the robot's true pose than standard sensor resetting, and is more robust to systematic vision errors.

Risks Facing the Profit-loss Sharing Banking System Within The Global Financial Crisis

While conventional banks are facing challenges to resolve problems emanating from the worst financialcrisis in living memory, the Islamic banking sector is flourishing and remains in relative prosperity.However, dynamic changes occurring in the global financial world pose various risks to bankinginstitutions. Islamic banks are not immune to such risks. Their relative continuous prosperity depends on howwell they manage such risks. Identifying these risks sheds light on challenging these risks. Unlike conventionalbanks, Islamic banks share business risks with investors and borrowers. The difference lies in the nature of risksharing. This paper examines the different types of risks associated with different schemes of financialcontracts that Islamic banks are facing. The paper also addresses several policy implications to promote riskmanagement in terms of globalization and culture changes within profit-loss sharing banking industry.

직선기반 SLAM에서의 루프결합

The loop closure problem is one of the most challenging issues in the vision-based simultaneous localization and mapping community. It requires the robot to recognize a previously visited place from current camera measurements. While the loop closure often relies on visual bag-of-words based on point features in the previous works, however, in this paper we propose a line-based method to solve the loop closure in the corridor environments. We used both the floor line and the anchored vanishing point as the loop closing feature, and a two-step loop closure algorithm was devised to detect a known place and perform the global pose correction. We propose an anchored vanishing point as a novel loop closure feature, as it includes position information and represents the vanishing points in bi-direction. In our system, the accumulated heading error is reduced using an observation of a previously registered anchored vanishing points firstly, and the observation of known floor lines allows for further pose correction. Experimental results show that our method is very efficient in a structured indoor environment as a suitable loop closure solution.

Design of a Ball-shaped Robot with Stereovision-based Localization

In view of the existing localization problems of ball-shaped robots,a ball-shaped robot BYQ-6b with stereovision-based localization is proposed.A binocular camera is used to capture real-time image sequences of the environment around the robot.Features are detected,matched between left and right images,and tracked in the image sequences.An egomotion algorithm is adopted to estimate the frame-to-frame incremental motion of the BYQ-6b robot,and finally the robot’s global pose is obtained.The ball-shaped robot BYQ-6b are presented in detail about its mechanical structure,its control system and the implementation of the proposed stereovision-based localization.The experimental results demonstrate the feasibility of the proposed system design and the stereovision-based localization.

Pose Space Surface Manipulation

Example-based mesh deformation techniques produce natural and realistic shapes by learning the space of deformations from examples. However, skeleton-based methods cannot manipulate a global mesh structure naturally, whereas the mesh-based approaches based on a translational control do not allow the user to edit a local mesh structure intuitively. This paper presents an example-driven mesh editing framework that achieves both global and local pose manipulations. The proposed system is built with a surface deformation method based on a two-step linear optimization technique and achieves direct manipulations of a model surface using translational and rotational controls. With the translational control, the user can create a model in natural poses easily. The rotational control can adjust the local pose intuitively by bending and twisting. We encode example deformations with a rotation-invariant mesh representation which handles large rotations in examples. To incorporate example deformations, we infer a pose from the handle translations/rotations and perform pose space interpolation, thereby avoiding involved nonlinear optimization. With the two-step linear approach combined with the proposed multiresolution deformation method, we can edit models at interactive rates without losing important deformation effects such as muscle bulging.

Linear-time robot localization and pose tracking using matching signatures

A feature-based method for global localization of mobile robot using a concept of matching signatures is presented. A group of geometric features, their geometric constraints invariant to frame transform, and location dependent constraints, together are utilized in defining signature of a feature. Plausible global poses are found out by matching signatures of observed features with signatures of global map features. The concept of matching signatures is so developed that the proposed method provides a very efficient solution for global localization. Worst-case complexity of the method for estimating and verifying global poses is linear with the size of global reference map. It will also be shown that with the approach of random sampling the proposed algorithm becomes linear with both the size of global map and number of observed features. In order to avoid pose ambiguity, simultaneous tracking of multiple pose hypotheses staying within the same framework of the proposed method is also addressed. Results obtained from simulation as well as from real world experiment demonstrate the performance and effectiveness of the method.

Control and Robust Vision Relative Navigation for Autonomous Aerial Refueling

A relative navigation and control scheme based on multiple camera systems was presented for autonomous operations in close proximity for autonomous air refueling (AAR) mission. The relative navigation system employed non-iterative fast global optimal pose estimation algorithm, and the result was filtered and fused with velocity’s measurements to increase accuracy and robustness by using Kalman filtering algorithm. To attenuate effect of tanker’s vortex and atmospheric turbulence, an H-infinity tracking control law was designed for docking phase of air refueling. Simulation results showed that accuracy of both vision navigation system and trajectory tracking could meet requirements of aerial refueling.

Fringe inverse videogrammetry based on global pose estimation

Fringe inverse videogrammetry based on global pose estimation is presented to measure a three-dimensional (3D) coordinate. The main components involve an LCD screen, a tactile probe equipped with a microcamera, and a portable personal computer. The LCD is utilized to display fringes, a microcamera is installed on the tactile probe, and the 3D coordinate of the center of the probe tip can be calculated through the microcamera's pose. Fourier fringe analysis is exploited to complete subpixel location of reference points. A convex-relaxation optimization algorithm is employed to estimate the global camera pose, which guarantees global convergence compared with bundle adjustment, a local pose estimation algorithm. The experiments demonstrate that fringe inverse videogrammetry can measure the 3D coordinate precisely.

Steven Wheatley. The Democratic Legitimacy of International Law

The concept of global governance epitomizes transformations in the structure of political organization and highlights changes in the ways in which public authority is exercised. Times of change invite scholars to contemplate the plausibility of orthodox beliefs and doctrinal concepts. They push them towards innovation and there is indeed a strong sense among international lawyers that the terms of debate about the legitimacy of international law are shifting. A number of contributions over the past years have tried to respond to the challenges which phenomena of global governance pose to international legal scholarship. 1 The mounting wealth of literature now comes to speak in Steven Wheatley's book on The Democratic Legitimacy of International Law in which he calls on the legal profession to engage with questions of first principle, to reflect on the nature of international law, and to consider in closer detail the justification of legal constraints beyond the state. The book's main argument is at the outset rather straightforward. Wheatley observes a proliferation of sites of norm production and argues that the delegation of authority to international or transnational actors inevitably involves a loss for democracy. To remedy this deficit, he suggests restating requirements for democratic legitimacy in terms of the deliberative ideal as it is developed in the work of Jurgen Habermas. The book claims the use of Habermas� thought as its innovative edge, and develops its core argument accordingly. �[T]he legitimate exercise of public authority through law�, it claims, �is conditioned by respect for the cardinal principles of deliberative democracy: equality and public reason� (at 2). The book begins by taking stock of accounts suggesting that state sovereignty has lost its plausibility as an exclusive reference point in normative argument. While the grand variety of approaches under discussion converge in agreement on the facts of what �