Filters








1,527 Hits in 6.4 sec

Marker-less motion capture in general scenes with sparse multi-camera setups [article]

Ahmed Elhayek, Universität Des Saarlandes, Universität Des Saarlandes
2015
In the area of marker-less human motion-capture, this thesis proposes several novel algorithms for simplifying the motion-capture to be applicable in new general outdoor scenes.  ...  Finally, we reduce the number of cameras employed by proposing a novel motion-capture method which uses as few as two cameras to capture high-quality motion in general environments, even outdoors.  ...  As a second step toward human motion capture in general scenes with sparse multi-camera setups, we introduce a new spatio-temporal method for marker-less motion capture.  ... 
doi:10.22028/d291-26634 fatcat:hqivm5yevnebvmzgw2xykwamg4

A Multi-spectral Dataset for Evaluating Motion Estimation Systems [article]

Weichen Dai, Yu Zhang, Shenzhou Chen, Donglei Sun, Da Kong
2021 arXiv   pre-print
Thermal images, in contrast, are more challenging to be used in motion estimation since they typically have lower resolution, less texture, and more noise.  ...  In addition to the sequences with bright illumination, the dataset also contains dim, varying, and complex illumination scenes.  ...  Fig. 1 : 1 The multi-spectral setup with Kinect2. Left: devices include an RGB camera, an LWIR camera, a Kinect2, an IMU, and the markers of motion capture systems.  ... 
arXiv:2007.00622v2 fatcat:elaajgrcmnej3eciw6q5yiwqyi

Outdoor Human Motion Capture by Simultaneous Optimization of Pose and Camera Parameters

A. Elhayek, C. Stoll, K. I. Kim, C. Theobalt
2014 Computer graphics forum (Print)  
The approach can be adopted in many practical applications to replace the complex and expensive motion capture studios with few consumer-grade cameras even in uncontrolled outdoor scenes.  ...  Abstract We present a method for capturing the skeletal motions of humans using a sparse set of potentially moving cameras in an uncontrolled environment.  ...  We therefore present a method for marker-less 3D skeletal human motion capture that succeeds in uncontrolled environments and uses only a sparse, heterogeneous and weakly constrained camera setup.  ... 
doi:10.1111/cgf.12519 fatcat:edsdqmdvf5ezdbxvdmoltvythu

EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras [article]

Helge Rhodin, Christian Richardt, Dan Casas, Eldar Insafutdinov, Mohammad Shafiei, Hans-Peter Seidel, Bernt Schiele, Christian Theobalt
2016 arXiv   pre-print
Marker-based and marker-less optical skeletal motion-capture methods use an outside-in arrangement of cameras placed around a scene, with viewpoints converging on the center.  ...  Our inside-in method captures full-body motion in general indoor and outdoor scenes, and also crowded scenes with many people in close vicinity.  ...  Introduction Traditional optical skeletal motion-capture methods -both markerbased and marker-less -use several cameras typically placed around a scene in an outside-in arrangement, with camera views approximately  ... 
arXiv:1609.07306v1 fatcat:xatetlqtpbbsbclzgv3ik2fxee

EgoCap

Helge Rhodin, Christian Richardt, Dan Casas, Eldar Insafutdinov, Mohammad Shafiei, Hans-Peter Seidel, Bernt Schiele, Christian Theobalt
2016 ACM Transactions on Graphics  
Marker-based and marker-less optical skeletal motion-capture methods use an outside-in arrangement of cameras placed around a scene, with viewpoints converging on the center.  ...  This allows full-body motion capture in general indoor and outdoor scenes, including crowded scenes with many people nearby, which enables reconstruction in larger-scale activities.  ...  Introduction Traditional optical skeletal motion-capture methods -both markerbased and marker-less -use several cameras typically placed around a scene in an outside-in arrangement, with camera views approximately  ... 
doi:10.1145/2980179.2980235 fatcat:kx3rcoljurb3xgewan4acsb2qa

Performance Capture of Interacting Characters with Handheld Kinects [chapter]

Genzhi Ye, Yebin Liu, Nils Hasler, Xiangyang Ji, Qionghai Dai, Christian Theobalt
2012 Lecture Notes in Computer Science  
We present an algorithm for marker-less performance capture of interacting humans using only three hand-held Kinect cameras.  ...  As opposed to previous performance capture methods, our algorithm succeeds on general uncontrolled indoor scenes with potentially dynamic background, and it succeeds even if the cameras are moving.  ...  At the other end of the spectrum are methods for marker-less motion capture from a single camera view.  ... 
doi:10.1007/978-3-642-33709-3_59 fatcat:5wpw5e6mpbaqhdx7wlv34hh5s4

MonoPerfCap: Human Performance Capture from Monocular Video [article]

Weipeng Xu, Avishek Chatterjee, Michael Zollhöfer, Helge Rhodin, Dushyant Mehta, Hans-Peter Seidel, Christian Theobalt
2018 arXiv   pre-print
We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video.  ...  Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid surface deformations in general scenes.  ...  We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video.  ... 
arXiv:1708.02136v2 fatcat:toewmmbynnbppmxsop43d4xk3e

High-Speed Object Tracking Using an Asynchronous Temporal Contrast Sensor [article]

Daniel Saner, Oliver Wang, Simon Heinzle, Yael Pritch, Aljoscha Smolic, Alexander Sorkine-Hornung, Markus Gross
2014 International Symposium on Vision, Modeling, and Visualization  
We present a multi-modal capture system incorporating both a DVS and a traditional video camera, a method to register the different types of sensor information, and finally apply these datasets to challenging  ...  to increased motion blur.  ...  Figure 2 : 2 Figure 2: (a) Capture rig with DVS128 on the left, video camera in front, and a 50/50 beamsplitter.  ... 
doi:10.2312/vmv.20141280 dblp:conf/vmv/SanerWHPSSG14 fatcat:p7l3skfksjgpnakugbkxrgot2a

Performance capture from sparse multi-view video

Edilson de Aguiar, Carsten Stoll, Christian Theobalt, Naveed Ahmed, Hans-Peter Seidel, Sebastian Thrun
2008 ACM SIGGRAPH 2008 papers on - SIGGRAPH '08  
Abstract This paper proposes a new marker-less approach to capturing human performances from multi-view video.  ...  Our method delivers captured performance data at high level of detail, is highly versatile, and is applicable to many complex types of scenes that could not be handled by alternative marker-based or marker-free  ...  Chan for helping us with the video. This work has been developed within the Max-Planck-Center for Visual Computing and Communication (MPC VCC) collaboration.  ... 
doi:10.1145/1399504.1360697 fatcat:cajucl3wczfuvicpixyfcy22ga

Performance capture from sparse multi-view video

Edilson de Aguiar, Carsten Stoll, Christian Theobalt, Naveed Ahmed, Hans-Peter Seidel, Sebastian Thrun
2008 ACM Transactions on Graphics  
Abstract This paper proposes a new marker-less approach to capturing human performances from multi-view video.  ...  Our method delivers captured performance data at high level of detail, is highly versatile, and is applicable to many complex types of scenes that could not be handled by alternative marker-based or marker-free  ...  Chan for helping us with the video. This work has been developed within the Max-Planck-Center for Visual Computing and Communication (MPC VCC) collaboration.  ... 
doi:10.1145/1360612.1360697 fatcat:rlsfb7tstre7bndsgae4dnaqlq

HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions [article]

Han Liang, Yannan He, Chengfeng Zhao, Mutian Li, Jingya Wang, Jingyi Yu, Lan Xu
2022 arXiv   pre-print
We present a light-weight, hybrid mocap technique called HybridCap that augments the camera with only 4 Inertial Measurement Units (IMUs) in a learning-and-optimization framework.  ...  Monocular 3D motion capture (mocap) is beneficial to many applications.  ...  The high-end vison-based solutions require attaching dense optical markers [53] or expensive multi-camera setup [50, 20, 7, 21] to capture professional motions, which are undesirable for consumer-level  ... 
arXiv:2203.09287v1 fatcat:flktyexgivewjng6uxy6kdkqf4

Real-Time Full-Body Motion Capture from Video and IMUs

Charles Malleson, Andrew Gilbert, Matthew Trumble, John Collomosse, Adrian Hilton, Marco Volino
2017 2017 International Conference on 3D Vision (3DV)  
A real-time full-body motion capture system is presented which uses input from a sparse set of inertial measurement units (IMUs) along with images from two or more standard video cameras and requires no  ...  The results demonstrate the effectiveness of the approach for tracking a wide range of human motion in real time in unconstrained indoor/outdoor scenes.  ...  We wish to thank Anna Korzeniowska, Evren Imre, Joao Regateiro and Armin Mustafa for their help with data capture.  ... 
doi:10.1109/3dv.2017.00058 dblp:conf/3dim/MallesonGTCHV17 fatcat:bu7tp6rqhjcvbg62i7d27kpxjy

Rapid Pose Label Generation through Sparse Representation of Unknown Objects [article]

Rohan Pratap Singh, Mehdi Benallegue, Yusuke Yoshiyasu, Fumio Kanehiro
2020 arXiv   pre-print
The sparse representation leads to the development of a dense model and the pose labels for each image frame in the set of scenes.  ...  Our method not only circumvents the need for a prior 3D object model (textured or otherwise) but also bypasses complicated setups of fiducial markers, turntables, and sensors.  ...  However, their reliance on additional hardware such as multi-sensor rigs, turntables with markers, or motion capture systems limits their application in arbitrary environments.  ... 
arXiv:2011.03790v1 fatcat:qykamwl4iff4fhz2gw4u4q44hm

Performance Capture of High-Speed Motion Using Staggered Multi-View Recording

Di Wu, Yebin Liu, Ivo Ihrke, Qionghai Dai, Christian Theobalt
2012 Computer graphics forum (Print)  
To this end we introduce two novel concepts: First, a staggered surround multi-view recording setup that enables us to perform model-based motion capture on motion-blurred images, and second, a model-based  ...  We present a markerless performance capture system that can acquire the motion and the texture of human actors performing fast movements using only commodity hardware.  ...  Through model-based marker-less performance capture, the dynamic scene geometry can then be reconstructed at the effective frame rate fe.  ... 
doi:10.1111/j.1467-8659.2012.03194.x fatcat:ohexg3vrfbfappgx5tvkl6urce

Full Body Performance Capture under Uncontrolled and Varying Illumination: A Shading-Based Approach [chapter]

Chenglei Wu, Kiran Varanasi, Christian Theobalt
2012 Lecture Notes in Computer Science  
This paper presents a marker-less method for full body human performance capture by analyzing shading information from a sequence of multi-view images, which are recorded under uncontrolled and changing  ...  Both the articulated motion of the limbs and then the fine-scale surface detail are estimated in a temporally coherent manner.  ...  Introduction Marker-less capture of human skeletal motion from images is one of the wellstudied problems of computer vision, with recent advances being able to reconstruct human motion at increasing speed  ... 
doi:10.1007/978-3-642-33765-9_54 fatcat:eebqrtpke5faljmaj6y6ve566m
« Previous Showing results 1 — 15 out of 1,527 results