Filters








99 Hits in 8.8 sec

Stein ICP for Uncertainty Estimation in Point Cloud Matching [article]

Fahira Afzal Maken, Fabio Ramos, Lionel Ott
2021 arXiv   pre-print
Quantification of uncertainty in point cloud matching is critical in many tasks such as pose estimation, sensor fusion, and grasping.  ...  Iterative closest point (ICP) is a commonly used pose estimation algorithm which provides a point estimate of the transformation between two point clouds.  ...  Abstract-Quantification of uncertainty in point cloud matching is critical in many tasks such as pose estimation, sensor fusion, and grasping.  ... 
arXiv:2106.03287v1 fatcat:52zdhyzcmzfdrln2a36iqnvhpm

Toward mutual information based automatic registration of 3D point clouds

Gaurav Pandey, James R. McBride, Silvio Savarese, Ryan M. Eustice
2012 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems  
This paper reports a novel mutual information (MI) based algorithm for automatic registration of unstructured 3D point clouds comprised of co-registered 3D lidar and camera imagery.  ...  We apply a James-Stein-type shrinkage estimator to estimate the true MI from the marginal and joint histograms of the codewords extracted from the scans.  ...  Most of the ICP algorithms described above are based on 3D point clouds alone and very few incorporate visual information into the ICP framework.  ... 
doi:10.1109/iros.2012.6386053 dblp:conf/iros/PandeyMSE12 fatcat:gb37cyx3braazguuzg4pdeagky

Enhanced Lunar Topographic Mapping Using Multiple Stereo Images Taken by Yutu-2 Rover with Changing Illumination Conditions

Wenhui Wan, Jia Wang, Kaichang Di, Jian Li, Zhaoqin Liu, Peng Man, Yexin Wang, Tianyi Yu, Chuankai Liu, Lichun Li
2021 Photogrammetric Engineering and Remote Sensing  
Key steps of the method include dense matching of stereo images, 3D point-cloud generation, point-cloud co-registration, and fusion.  ...  This method, which does not involve complex operations, has great potential for application in planetary-rover and lander missions.  ...  By combining Equations 6 and 7, the 3D coordinate uncertainties of the point cloud are estimated for the following co-registration.  ... 
doi:10.14358/pers.87.8.567 fatcat:5bqj5ztncfed3fp6pawrqnys4a

Nonrigid registration using Gaussian processes and local likelihood estimation [article]

Ashton Wiens and William Kleiber and Douglas Nychka and Katherine R. Barnhart
2020 arXiv   pre-print
Surface registration, the task of aligning several multidimensional point sets, is a necessary task in many scientific fields.  ...  The nonrigid method is applied to a pair of massive remote sensing elevation data sets exhibiting complex geological terrain, with improved accuracy and uncertainty quantification in a cross validation  ...  criterion in point matching.  ... 
arXiv:2006.06864v1 fatcat:v3tm2wiuebeovocl6kdr3j3tqy

Synthetic Ground Truth for Presegmentation of Known Objects for Effortless Pose Estimation

Frederik Haarslev, William Juel, Norbert Krüger, Leon Bodenhagen
2020 Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications  
This data can be used for training a CNN for presegmentation of point clouds in a pose estimation pipeline.  ...  The output of the segmentation is then used to crop the point cloud and thereby allowing pose estimation using multi-hypothesis ICP.  ... 
doi:10.5220/0009163904820489 dblp:conf/visapp/HaarslevJKB20 fatcat:z3mkc6r5hrax7gufrhpnwtkaeq

Physics-based Scene-level Reasoning for Object Pose Estimation in Clutter [article]

Chaitanya Mitash, Abdeslam Boularias, Kostas Bekris
2019 arXiv   pre-print
This paper focuses on vision-based pose estimation for multiple rigid objects placed in clutter, especially in cases involving occlusions and objects resting on each other.  ...  In particular, the proposed framework first generates a labeled dataset for training a Convolutional Neural Network (CNN) for object detection in clutter.  ...  The point cloud segments extracted from the bounding box detections were used to perform pose estimation using two different approaches: i) PCA followed by ICP and ii) Super4PCS followed by ICP Besl and  ... 
arXiv:1806.10457v2 fatcat:hngnpzbfejhqbk6nez6pkeu6m4

An automated, open-source pipeline for mass production of digital elevation models (DEMs) from very-high-resolution commercial stereo satellite imagery

David E. Shean, Oleg Alexandrov, Zachary M. Moratto, Benjamin E. Smith, Ian R. Joughin, Claire Porter, Paul Morin
2016 ISPRS journal of photogrammetry and remote sensing (Print)  
These modifications include support for rigorous and rational polynomial coefficient (RPC) sensor models, sensor geometry correction, bundle adjustment, point cloud co-registration, and significant improvements  ...  An automated iterative closest-point (ICP) co-registration tool reduces absolute vertical and horizontal error to <0.5 m where appropriate groundcontrol data are available, with observed standard deviation  ...  Support for the Polar Geospatial Center was provided by the National Science Foundation  ... 
doi:10.1016/j.isprsjprs.2016.03.012 fatcat:6kss6vwwlzbtjnqhqyeops3b74

Quantifying uncertainty in high-resolution remotely sensed topographic surveys for ephemeral gully channel monitoring

Robert R. Wells, Henrique G. Momm, Carlos Castillo
2017 Earth Surface Dynamics  
The utilization of ground control points was a prerequisite to three-dimensional registration between datasets and improved the confidence in the morphology information generated.  ...  for model development and validation.  ...  The authors would like to acknowledge the support provided by Nathan Stein (remote pilot for the quadcopter UAV), Daniel Murphy (remote pilot for the fixed-wing UAV), Justin Hobart, Tom Buman, Bob Buman  ... 
doi:10.5194/esurf-5-347-2017 fatcat:jelcbt45qbhhtjoejivs5ko7mu

Hand-guided 3D surface acquisition by combining simple light sectioning with real-time algorithms [article]

Oliver Arold, Svenja Ettl, Florian Willomitzer, Gerd Häusler
2014 arXiv   pre-print
For registration, a variant of the iterative closest point algorithm - adapted to the specific nature of our 3D views - is introduced.  ...  In contrast to most existing sensors no bandwidth is wasted for spatial or temporal encoding of the projected lines. Nor is an expensive color camera necessary for 3D acquisition.  ...  For the fine registration of two point clouds most often methods based on the iterative closest point algorithm (ICP) are used. The ICP was first introduced by Besl and Chen (1992; .  ... 
arXiv:1401.1946v1 fatcat:ko2gph3ncrcnroq3l4q2uo6qhi

Quantifying uncertainty of remotely sensed topographic surveys for ephemeral gully channel monitoring

Robert R. Wells, Henrique G. Momm, Carlos Castillo
2017 Earth Surface Dynamics Discussions  
Utilization of ground control points were prerequisite to three-dimensional registration between datasets and improved confidence in the morphology information generated.  ...  for model development/validation.  ...  Authors would like to acknowledge the support provided by Nathan Stein, Daniel Murphy, Tom Buman and Justin Hobart. Earth Surf. Dynam.  ... 
doi:10.5194/esurf-2017-3 fatcat:3ylwwdqwjrfctpmk5lu5olf5sy

A new method for the registration of three-dimensional point-sets: The Gaussian Fields framework

Faysal Boughorbel, Muharrem Mercimek, Andreas Koschan, Mongi Abidi
2010 Image and Vision Computing  
(ICP) algorithms.  ...  We show that the size of the region of convergence can be significantly extended reducing the need for close initialization and overcoming local convergence problems of the standard Iterative Closest Point  ...  Acknowledgements This work was supported in part by the DOE University Research Program in Robotics under Grant DOE-DE-FG02-86NE37968 and by the DOD/TACOM/NAC/ARC Program, R01-1344-18.  ... 
doi:10.1016/j.imavis.2009.05.003 fatcat:n3oxkcqmujcorl2b7ukeb4p4wq

Creating HiRISE digital elevation models for Mars using the open-source Ames Stereo Pipeline

Adam J. Hepburn, Tom Holt, Bryn Hubbard, Felix Ng
2019 Geoscientific Instrumentation Methods and Data Systems Discussions  
In contrast to the globally-available but low-resolution datasets, such models enable the study of landforms <&amp;thinsp;10&amp;thinsp;km in size, which is the primary scale at which geomorphic processes  ...  software, making use of freely available data for cartographic rectification.  ...  For point clouds that are already close prior to alignment, the Point-to-Plane ICP transformation alone may suffice.  ... 
doi:10.5194/gi-2019-11 fatcat:ioxzepyy6ndjzmswpetlvpkfme

A Survey Of Free-Form Object Representation and Recognition Techniques

Richard J. Campbell, Patrick J. Flynn
2001 Computer Vision and Image Understanding  
This survey reviews recent literature on both the 3D model building process and techniques used to match and identify free-form objects from imagery.  ...  Advances in computer speed, memory capacity and hardware graphics acceleration have made the interactive manipulation and visualization of complex, detailed (and therefore large) three-dimensional models  ...  The authors thank three anonymous reviewers and Kevin Bowyer for helpful comments and suggestions.  ... 
doi:10.1006/cviu.2000.0889 fatcat:lujlciputzdb7e3pjhm4sfknfy

Creating HiRISE digital elevation models for Mars using the open-source Ames Stereo Pipeline

Adam J. Hepburn, Tom Holt, Bryn Hubbard, Felix Ng
2019 Geoscientific Instrumentation, Methods and Data Systems  
This pipeline is designed for simple application by researchers interested in the use of high-resolution digital elevation models.  ...  In this paper, we present and test the output of a new pipeline for producing digital elevation models from HiRISE stereo pairs that is built entirely upon the open-source NASA Ames Stereo Pipeline photogrammetric  ...  We thank NASA/JPL/University of Arizona for making available all of the data used in this study. Review statement.  ... 
doi:10.5194/gi-8-293-2019 fatcat:zzs5dyspszemtk7zbnfhuw75wm

Long-range rover localization by matching LIDAR scans to orbital elevation maps

Patrick J.F. Carle, Paul T. Furgale, Timothy D. Barfoot
2010 Journal of Field Robotics  
Output uncertainties were large due to large input uncertainties, but these could be reduced in future experimentation by minimizing the use of simulated input data.  ...  Long-Range Rover Localization by Matching Lidar Scans to Orbital Elevation Maps Current planetary rover localization techniques are lacking in autonomy and accuracy.  ...  However, the use of 2D images would present the extra challenge of matching image-based features to features extracted from 3D lidar point clouds.  ... 
doi:10.1002/rob.20336 fatcat:dpo46nrpwfe5xcazj3h5whqxpq
« Previous Showing results 1 — 15 out of 99 results