Filters








224 Hits in 3.8 sec

FlyCap: Markerless Motion Capture Using Multiple Autonomous Flying Cameras [article]

Lan Xu, Lu Fang, Wei Cheng, Kaiwen Guo, Guyue Zhou, Qionghai Dai, and Yebin Liu
2016 arXiv   pre-print
using multiple autonomous flying cameras (autonomous unmanned aerial vehicles(UAV) each integrated with an RGBD video camera).  ...  We propose a novel non-rigid surface registration method to track and fuse the depth of the three flying cameras for surface motion tracking of the moving target, and simultaneously calculate the pose  ...  multiple autonomous flying cameras.  ... 
arXiv:1610.09534v3 fatcat:mxtzspgpt5bepld2pfv4hz73fm

Pose-aware C-arm for automatic re-initialization of interventional 2D/3D image registration

Javad Fotouhi, Bernhard Fuerst, Alex Johnson, Sing Chun Lee, Russell Taylor, Greg Osgood, Nassir Navab, Mehran Armand
2017 International Journal of Computer Assisted Radiology and Surgery  
Conclusion-The pose-aware C-arm contributes to the 2D/3D registration process by globally re-initializing the relationship of C-arm image and pre-interventional CT data.  ...  A highly accurate multi-view calibration between RGBD and C-arm imaging devices is achieved using a custom-made multimodal calibration target.  ...  Acknowledgments The authors want to thank Wolfgang Wein and his team from ImFusion GmbH, Munich, for the opportunity of using the ImFusion Suite, and Gerhard Kleinzig and Sebastian Vogt from SIEMENS Healthineers  ... 
doi:10.1007/s11548-017-1611-8 pmid:28527025 pmcid:PMC5898215 fatcat:zlajbd3dx5hnbfzcpglkhezjce

Single-View RGBD-Based Reconstruction of Dynamic Human Geometry

Charles Malleson, Martin Klaudiny, Adrian Hilton, Jean-Yves Guillemaut
2013 2013 IEEE International Conference on Computer Vision Workshops  
We demonstrate that the approach is capable of reconstructing mid-resolution surface models of people from low-resolution noisy data acquired from a consumer RGBD camera.  ...  We introduce a framework for building a representation of the articulated scene geometry as a set of piecewise rigid parts which are tracked and accumulated over time using moving voxel grids containing  ...  We define a function Figure 6 : Integration of measurements with multiple rigid parts.  ... 
doi:10.1109/iccvw.2013.48 dblp:conf/iccvw/MallesonKHG13 fatcat:77k2hnczofak5jjr4wntwizjqy

Automatic intraoperative stitching of nonoverlapping cone-beam CT acquisitions

Javad Fotouhi, Bernhard Fuerst, Mathias Unberath, Stefan Reichenstein, Sing Chun Lee, Alex A. Johnson, Greg M. Osgood, Mehran Armand, Nassir Navab
2018 Medical Physics (Lancaster)  
Methods-A CBCT-capable mobile C-arm is augmented with a Red-Green-Blue-Depth (RGBD) camera.  ...  the stitching transformation. 15 The aforementioned methods only addressed stitching in 2D, and their generalization to 3D stitching has remained a challenge.  ...  Acknowledgments The authors want to thank Wolfgang Wein and his team from ImFusion GmbH for the opportunity of using ImFusion Suite, and Gerhard Kleinzig and Sebastian Vogt from SIEMENS for their support  ... 
doi:10.1002/mp.12877 pmid:29569728 pmcid:PMC5997569 fatcat:aag22oxksrb2xct75mo6dvjrpa

Multi-modal big-data management for film production

Hansung Kim, Simon Pabst, Justin Sneddon, Ted Waine, Jeff Clifford, Adrian Hilton
2015 2015 IEEE International Conference on Image Processing (ICIP)  
The processing and management of this massive amount of heterogeneous data consumes enormous resources. We propose an integrated pipeline for 2D/3D data registration for film production.  ...  A key requirement in the use of multi-modal 2D/3D data for content production is the registration into a common coordinate frame. 3D geometric information is reconstructed from 2D data and registered to  ...  Various capture devices such as LIDAR, spherical cameras, DSLR still cameras, HD (1920×1080) video cameras, HD 2.7 K cameras and RGBD cameras were used as illustrated in Fig. 5 . 5 Registration results  ... 
doi:10.1109/icip.2015.7351725 dblp:conf/icip/KimPSWCH15 fatcat:x6donhhx5zbrbjac3cjgt3uiu4

3D Data Acquisition and Registration Using Two Opposing Kinects

Vahid Soleimani, Majid Mirmehdi, Dima Damen, Sion Hannuna, Massimo Camplani
2016 2016 Fourth International Conference on 3D Vision (3DV)  
First, the relative pose of the two RGBD sensors is estimated through a calibration stage and rigid transformation parameters are computed.  ...  Full terms of use are available: Abstract We present an automatic, open source data acquisition and calibration approach using two opposing RGBD sensors (Kinect V2) and demonstrate its efficacy for dynamic  ...  Acknowledgment The authors would like to thank the University of Bristol Alumni Foundation for funding this research.  ... 
doi:10.1109/3dv.2016.21 dblp:conf/3dim/SoleimaniMDHC16 fatcat:tdtfo3k3dbceffdfdcuvphhigy

Nonrigid reconstruction of 3D breast surfaces with a low-cost RGBD camera for surgical planning and aesthetic evaluation

R.M. Lacher, F. Vasconcelos, N.R. Williams, G. Rindermann, J. Hipwell, D. Hawkes, D. Stoyanov
2019 Medical Image Analysis  
In this paper we employ a single consumer-grade RGBD camera with an ICP-based registration approach to jointly align all points from a sequence of depth images non-rigidly.  ...  Subtle body deformation due to postural sway and respiration is successfully mitigated leading to a higher geometric accuracy through regularised locally affine transformations.  ...  in the RGBD se- quence and T i = { R i , t i } the individual rigid body camera transformation comprising a rotation matrix R ∈ SO (3) and a translation vector t ∈ R 3 .  ... 
doi:10.1016/j.media.2019.01.003 pmid:30660103 pmcid:PMC6854464 fatcat:ivodne4o5vfupf7u7twbwcz5tq

SparseFusion: Dynamic Human Avatar Modeling from Sparse RGBD Images [article]

Xinxin Zuo and Sen Wang and Jiangbin Zheng and Weiwei Yu and Minglun Gong and Ruigang Yang and Li Cheng
2020 arXiv   pre-print
In this paper, we propose a novel approach to reconstruct 3D human body shapes based on a sparse set of RGBD frames using a single RGBD camera.  ...  First, based on a generative human template, for every two frames having sufficient overlap, an initial pairwise alignment is performed; It is followed by a global non-rigid registration procedure, in  ...  Abstract-In this paper, we propose a novel approach to reconstruct 3D human body shapes based on a sparse set of RGBD frames using a single RGBD camera.  ... 
arXiv:2006.03630v1 fatcat:afganymonzhx5i4i6ttmi5uw6a

Plan in 2-D, execute in 3-D: an augmented reality solution for cup placement in total hip arthroplasty

Javad Fotouhi
2018 Journal of Medical Imaging  
planning system based on two C-arm X-ray images that is combined with 3D augmented reality (AR) visualization that simplifies impactor and cup placement according to the planning by providing a real-time RGBD  ...  The promising performance of this AR solution shows that deploying this system could eliminate the need for excessive radiation, simplify the intervention, and enable reproducibly accurate placement of  ...  Ultimately, this approach may aid in reducing the risk of revision surgery in patients with diseased hip joints.  ... 
doi:10.1117/1.jmi.5.2.021205 pmid:29322072 pmcid:PMC5753431 fatcat:5ccv6uocvzbqvbe7xr5sknmg5a

Loop closure detection using local 3D deep descriptors [article]

Youjie Zhou, Yiming Wang, Fabio Poiesi, Qi Qin, Yi Wan
2022 arXiv   pre-print
We present a simple yet effective method to address loop closure detection in simultaneous localisation and mapping using local 3D deep descriptors (L3Ds).  ...  This novel approach enables us to accurately detect loops and estimate six degrees-of-freedom poses in the case of small overlaps.  ...  Given that the rigid-body transformation S corresponding to the least-squares solution that maps the estimated pose of the camera C t onto its ground-truth pose G t at frame t, ATE can be computed as E  ... 
arXiv:2111.00440v2 fatcat:qxzcazmcbrggbbxlg5dwwhkvf4

Extracting Contact and Motion from Manipulation Videos [article]

Konstantinos Zampogiannis, Kanishka Ganguly, Cornelia Fermuller, Yiannis Aloimonos
2019 arXiv   pre-print
At the core of our approach lies non-rigid registration: we continuously warp a point cloud model of the observed scene to the current video frame, generating a set of dense 3D point trajectories.  ...  In this paper, we present an active, bottom-up method for the detection of actor-object contacts and the extraction of moved objects and their motions in RGBD videos of manipulation actions.  ...  Acknowledgments The support of ONR under grant award N00014-17-1-2622 and the support of the National Science Foundation under grants SMA 1540916 and CNS 1544787 are greatly acknowledged.  ... 
arXiv:1807.04870v3 fatcat:ndoz3k45lvfijeieel7tergrxy

Multimodal Visual Data Registration for Web-Based Visualization in Media Production

Hansung Kim, Alun Evans, Josep Blat, Adrian Hilton
2018 IEEE transactions on circuits and systems for video technology (Print)  
Current media production rely on both video from the principal camera together with a wide variety of heterogeneous source of supporting data (photos, LiDAR point clouds, witness video camera, HDRI and  ...  A new feature description and matching method is proposed, adaptively considering local geometry, semi-global geometry and colour information in the scene for more robust registration.  ...  Hybrid Feature Matching and Registration We propose the Hybrid RANSAC registration method to find an optimal 3D rigid transform matrix between feature sets.  ... 
doi:10.1109/tcsvt.2016.2642825 fatcat:y5en3zlvv5go5cofkmpq6aly3q

RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments [chapter]

Peter Henry, Michael Krainin, Evan Herbst, Xiaofeng Ren, Dieter Fox
2014 Springer Tracts in Advanced Robotics  
In this paper we investigate how such cameras can be used in the context of robotics, specifically for building dense 3D maps of indoor environments.  ...  RGB-D cameras are novel sensing systems that capture RGB images along with per-pixel depth information.  ...  We would like to thank Louis LeGrand and Brian Mayton for their support with the PrimeSense camera, and Marvin Cheng for his work on visualization.  ... 
doi:10.1007/978-3-642-28572-1_33 fatcat:3hlg5w4gzjfkpbugvllhuzkrdu

Automatic 3D Indoor Scene Updating with RGBD Cameras

Zhenbao Liu, Sicong Tang, Weiwei Xu, Shuhui Bu, Junwei Han, Kun Zhou
2014 Computer graphics forum (Print)  
After the segmentation, objects captured by RGBD camera are extracted to form a local updated scene. We formulate an optimization problem to compare to the initial scene to locate moved objects.  ...  Figure 1 : Six groups of scene update results, and comparison between original 3D scene (left) and automatically updated 3D scene (right) by capturing RGBD image (middle) with local variation.  ...  Geometric shape similarity term plays two important roles, one of which is to accurately determine registration error, and the other is to produce rigid transformation used to align a local changed scene  ... 
doi:10.1111/cgf.12495 fatcat:cryunitb2ravhgnn37aylqsdtm

Viewpoint Invariant Matching via Developable Surfaces [chapter]

Bernhard Zeisl, Kevin Köser, Marc Pollefeys
2012 Lecture Notes in Computer Science  
Stereo systems, time-of-flight cameras, laser range sensors and consumer depth cameras nowadays produce a wealth of image data with depth information (RGBD), yet the number of approaches that can take  ...  Here we normalize local image features with respect to the underlying geometry and show a significantly increased number of correspondences.  ...  In [5, 6] the authors have shown that it is possible to virtually move a camera to a frontal view and then render a canonical representation of a local image feature.  ... 
doi:10.1007/978-3-642-33868-7_7 fatcat:rac4z3kinfcvtkhjnuvt2ux7g4
« Previous Showing results 1 — 15 out of 224 results