Filters








335 Hits in 5.7 sec

Bingham Distribution-Based Linear Filter for Online Pose Estimation

Arun Srivatsan Rangaprasad, Mengyun Xu, Nicolas Zevallos-Roberts, Howie Choset
2017 Robotics: Science and Systems XIII  
A combination of Gaussian and Bingham distributions is used to develop a linear filter that accurately estimates the distribution of the pose parameters, in their true space.  ...  To the best of our knowledge our approach is the first implementation to use a Bingham distribution for 6 DoF pose estimation.  ...  CONCLUSION AND DISCUSSIONS In this work, a Bingham distribution-based linear filter (BF) was developed for online pose estimation.  ... 
doi:10.15607/rss.2017.xiii.016 dblp:conf/rss/RangaprasadXZC17 fatcat:kbb5h3gx6rhdjmevdpbxc74peq

Pose Invariant Approach for Face Recognition at Distance [chapter]

Eslam Mostafa, Asem Ali, Naif Alajlan, Aly Farag
2012 Lecture Notes in Computer Science  
We propose an automatic pose invariant approach for Face Recognition At a Distance (FRAD).  ...  The online phase is fast where a 2D image with unknown pose is matched with the closest virtual images in sampled poses. Experiments show that our approach outperforms the-state-of-the-art approaches.  ...  These approaches used a single distribution, which is not suitable for modeling wide range of poses.  ... 
doi:10.1007/978-3-642-33783-3_2 fatcat:5qbfkasjenfibiblgbavpnhuni

Estimating Motion Uncertainty with Bayesian ICP [article]

Fahira Afzal Maken, Fabio Ramos, Lionel Ott
2020 arXiv   pre-print
Our method combines recent developments in optimization for scalable Bayesian sampling such as stochastic gradient Langevin dynamics (SGLD) to infer a full posterior distribution of the pose transformation  ...  Accurate uncertainty estimation associated with the pose transformation between two 3D point clouds is critical for autonomous navigation, grasping, and data fusion.  ...  This paper introduced a novel ICP method, called Bayesian ICP, which computes not only the expected transformation between two point clouds but also estimates the full pose distribution.  ... 
arXiv:2004.07973v1 fatcat:4ljflouhcrguzgzr4z3symaniu

Monte Carlo Registration and Its Application with Autonomous Robots

Christian Rink, Simon Kriegel, Daniel Seth, Maximilian Denninger, Zoltan-Csaba Marton, Tim Bodenmüller
2016 Journal of Sensors  
For sampling the pose particles, uniform, normal, and Bingham distributions are compared.  ...  Curvature features are calculated online and the estimated poses are optimized in the particle weighting step.  ...  Most similar are special cases of Bingham distributions, which have already been used for pose estimation [30] .  ... 
doi:10.1155/2016/2546819 fatcat:drh36xo2dzhgplusbfcryx5gjm

A surgical system for automatic registration, stiffness mapping and dynamic image overlay [article]

Nicolas Zevallos, Rangaprasad Arun Srivatsan, Hadi Salman, Lu Li, Jianing Qian, Saumya Saxena, Mengyun Xu, Kartik Patath, Howie Choset
2017 arXiv   pre-print
First, the preoperative model is registered to the intra-operative scene using a Bingham distribution-based filtering approach.  ...  The estimated stiffness map is then dynamically overlaid onto the registered preoperative model of the organ.  ...  A Bingham distribution-based filtering approach is used to automatically register the stereo point cloud to the preoperative C.  ... 
arXiv:1711.08828v1 fatcat:nvpzslmjkvahxhb7c3stsii33a

Fast Compressive Tracking

Kaihua Zhang, Lei Zhang, Ming-Hsuan Yang
2014 IEEE Transactions on Pattern Analysis and Machine Intelligence  
It is a challenging task to develop effective and efficient appearance models for robust object tracking due to factors such as pose variation, illumination change, occlusion, and motion blur.  ...  First, while these adaptive appearance models are data-dependent, there does not exist sufficient amount of data for online algorithms to learn at the outset.  ...  A representation based on distribution of pixels at multiple layers is proposed to describe object appearance for tracking [29] . Oron et al.  ... 
doi:10.1109/tpami.2014.2315808 pmid:26352631 fatcat:tnwfx2y53ja4rlppnoe2bvlq6y

Kalman Filter-based Head Motion Prediction for Cloud-based Mixed Reality [article]

Serhan Gül, Sebastian Bosse, Dimitri Podborski, Thomas Schierl, Cornelius Hellge
2020 arXiv   pre-print
In this paper, we design a Kalman filter for head motion prediction in our cloud-based volumetric video streaming system.  ...  Our results show that the Kalman filter can predict head orientations 0.5 degrees more accurately than the autoregression model for a look-ahead time of 60 ms.  ...  In our future work, we will use recursive filters based on spherical distributions such as von-Mises-Fisher [23] and Bingham distribution [23] to predict head orientations more accurately.  ... 
arXiv:2007.14084v1 fatcat:bbgpzj2gzrf5blp3zrqmqcqmcq

Scene Analysis for Service Robots [chapter]

Robert Eidenberger, Thilo Grundmann, Martin Schneider, Wendelin Feiten, Michael Fiegert, Georg v. Wichert, Gisbert Lawitzky
2012 Springer Tracts in Advanced Robotics  
A scene analysis module for service robots is presented which uses SIFT in a stereo setting, a systematic handling of uncertainties and an active perception component.  ...  reference for the pose distribution.  ...  As the value function is not piecewise linear, it is evaluated at specific positions, which requires the online calculation of the reward for these specific actions and observations.  ... 
doi:10.1007/978-3-642-25116-0_15 fatcat:5x3ls6ethrd6rjrf46dbh4ohci

Real-Time Compressive Tracking [chapter]

Kaihua Zhang, Lei Zhang, Ming-Hsuan Yang
2012 Lecture Notes in Computer Science  
It is a challenging task to develop effective and efficient appearance models for robust object tracking due to factors such as pose variation, illumination change, occlusion, and motion blur.  ...  First, while these adaptive appearance models are data-dependent, there does not exist sufficient amount of data for online algorithms to learn at the outset.  ...  The tracking task was formulated as a binary classification problem with online update in the compressed domain.  ... 
doi:10.1007/978-3-642-33712-3_62 fatcat:u77rbj2swvca7kuww26rjkthay

Continuous interdomain orientation distributions reveal components of binding thermodynamics [article]

Yang Qi, Jeffrey W Martin, Adam W Barb, Francois Thelot, Anthony Yan, Bruce R Donald, Terrence G Oas
2017 bioRxiv   pre-print
The representation works especially well for multidomain systems with broad conformational distributions.  ...  We capture the smooth transitions between important states and demonstrate the utility of continuous distribution functions for computing components of binding thermodynamics.  ...  Thus, the affinity is enhanced by a pre-posed distribution of interdomain orientations while maintaining the flexibility is presumably required for function.  ... 
doi:10.1101/200238 fatcat:nvqkg4mkgndprhoeoqlyh7aa6a

A Real-time Augmented Reality Surgical System for Overlaying Stiffness Information

Nicolas Zevallos, Arun Srivatsan Rangaprasad, Hadi Salman, Lu Li, Jianing Qian, Saumya Saxena, Mengyun Xu, Kartik Patath, Howie Choset
2018 Robotics: Science and Systems XIV  
First, the preoperative model is registered to the intra-operative scene using a Bingham distribution-based filtering approach.  ...  We describe a surgical system that autonomously searches for tumors and dynamically displays a computer graphic model of them super-imposed on the organ (or in our case, phantom).  ...  ACKNOWLEDGMENTS This work has been funded through the National Robotics Initiative by NSF grant IIS-1426655 and the Center for Machine Learning and Health.  ... 
doi:10.15607/rss.2018.xiv.026 dblp:conf/rss/ZevallosRSLQSXP18 fatcat:ffcehsjelfffpghixj5qdn7d3a

Continuous Interdomain Orientation Distributions Reveal Components of Binding Thermodynamics

Yang Qi, Jeffrey W. Martin, Adam W. Barb, François Thélot, Anthony K. Yan, Bruce R. Donald, Terrence G. Oas
2018 Journal of Molecular Biology  
The representation works especially well for multidomain systems with broad conformational distributions.This analysis also can be extended to multiple probability density modes, using a Bingham mixture  ...  The representation works especially well for multidomain systems with broad conformational distributions.This analysis also can be extended to multiple probability density modes, using a Bingham mixture  ...  Thus, the affinity is enhanced by a pre-posed distribution of interdomain orientations while maintaining the flexibility is presumably required for function.  ... 
doi:10.1016/j.jmb.2018.06.022 pmid:29924964 pmcid:PMC6115201 fatcat:babon4q6nbhgzphulquheajb3m

A Quaternion Framework for Color Image Smoothing and Segmentation

Özlem N. Subakan, Baba C. Vemuri
2010 International Journal of Computer Vision  
We show that these filters are optimally localized both in the spatial and frequency domains and provide a good approximation to quaternionic quadrature filters.  ...  In this paper, we present feature/detail preserving models for color image smoothing and segmentation using the Hamiltonian quaternion framework.  ...  Acknowledgements Authors like to express their thanks to, Ajit Rajwade for helping with some of the experiments reported here and Dr. Angelos Barmpoutis for his help in revising the manuscript.  ... 
doi:10.1007/s11263-010-0388-9 fatcat:kwjuxvzy5rgmdfkvrebhsj6vzq

Survey of Motion Tracking Methods Based on Inertial Sensors: A Focus on Upper Limb Human Motion

Alessandro Filippeschi, Norbert Schmitz, Markus Miezal, Gabriele Bleser, Emanuele Ruffaldi, Didier Stricker
2017 Sensors  
IMU based estimation was matched against motion tracking based on the Vicon marker-based motion tracking system considered as ground truth.  ...  After a survey on IMU-based human tracking, five techniques for motion reconstruction were selected and compared to reconstruct a human arm motion.  ...  More complex approaches include particle filters (PF) and optimization-based approaches, which are now suitable for online IHMT.  ... 
doi:10.3390/s17061257 pmid:28587178 pmcid:PMC5492902 fatcat:xvdft2sf3re77k5l3ebkjgcvra

Variational Inference with Mixture Model Approximation: Robotic Applications [article]

Emmanuel Pignat, Teguh Lembono, Sylvain Calinon
2019 arXiv   pre-print
Our approach uses variational inference, a popular method in Bayesian computation, which has several advantages over sampling-based techniques.  ...  To be able to represent the complex and multimodal distribution of configurations, we propose to use a mixture model as approximate distribution, an approach that has gained popularity recently.  ...  f) Matrix Bingham-von Mises-Fisher distribution (BMF): To cope with orientation, for example represented as rotation matrix, Matrix Bingham-von Mises-Fisher distribution (BMF) [27] can be used.  ... 
arXiv:1905.09597v3 fatcat:adfsx26ldba6zdwbku5yskhrkm
« Previous Showing results 1 — 15 out of 335 results