Filters








19,741 Hits in 5.4 sec

Determination of 3D human body postures from a single view

Hsi-Jian Lee, Zen Chen
1985 Computer Vision Graphics and Image Processing  
In this paper a method is proposed to recover and interpret the 3D body structures of a person from a single view, provided that (1) at least six feature points on the head and a set of body joints are  ...  Starting from the coordinates of the neck, which is a head feature point, the 3D coordinates of other joints one-by-one are determined under the assumption of the fixed lengths of the body segments.  ...  SUMMARY We have provided a method to determine the 3D body configuration from a single view.  ... 
doi:10.1016/0734-189x(85)90094-5 fatcat:y2vpvip235astm3xqnr6qrlz6u

Human Posture Sequence Estimation Using Two Un-calibrated Cameras

R. Wang, W. K. Leow
2005 Procedings of the British Machine Vision Conference 2005  
3D Human posture sequence estimation from single or multiple image sequences is essential in many applications.  ...  Quantitative and qualitative results of experiments show that the algorithm is able to estimate 3D posture sequence from a pair of un-calibrated image sequences.  ...  Posture Estimation by mNBP A modified NBP (mNBP) method is introduced that can cope with partial self-occlusion and different body image sizes in estimating 2D (or 3D) human posture from single (or multiple  ... 
doi:10.5244/c.19.46 dblp:conf/bmvc/WangL05 fatcat:6kknc5q7e5gynhvjaabezv5jf4

Retrieval and constraint-based human posture reconstruction from a single image

Chih-Yi Chiu, Chun-Chih Wu, Yao-Cyuan Wu, Ming-Yang Wu, Shih-Pin Chao, Shi-Nine Yang
2006 Journal of Visual Communication and Image Representation  
In this study, we present a novel model-based approach to reconstruct the 3D human posture from a single image. The approach is guided by a posture library and a set of constraints.  ...  Given a 2D human figure, i.e., a set of labeled body segments and estimated root orientation in the image, a 3D pivotal posture whose 2D projection is similar to the human figure is first retrieved from  ...  Moreover, posture reconstruction from a single image and motion recovery from single-view video are discussed in the following review. onto the 3D body posture parameters.  ... 
doi:10.1016/j.jvcir.2005.01.002 fatcat:ewohe4b6zfcxjbt6h32godwj4y

Posture recognition with a top-view camera

Ninghang Hu, Gwenn Englebienne, Ben Krose
2013 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems  
In particular, we address posture recognition in a robot assisted-living scenario, where the environment is equipped with a top-view camera for monitoring human activities.  ...  We describe a system that recognizes human postures with heavy self-occlusion.  ...  By combining the matching scores from all posture descriptors into a single feature vector, we apply a binary classifier to determine whether the image belongs to a certain posture category or not. top-view  ... 
doi:10.1109/iros.2013.6696657 dblp:conf/iros/HuEK13 fatcat:y45f6kim45eknnuu2cqhdg6uuy

Anthropocentric video analysis for film and games postproduction

Ioannis Pitas, Nikolaos Nikolaidis
2010 Proceedings of the 11th International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing on International Conference on Computer Systems and Technologies - CompSysTech '10  
The interest of the scientific community for anthropocentric (human-centered) video analysis stems from the fact that the extracted information (e.g. human presence, identity, body posture, emotional status  ...  In this paper, we shall review recent research results in a number of diverse areas, such as face/person detection, human activity recognition and face/facial expression recognition, either from a single  ...  ACKNOWLEDGEMENT The research leading to these results has received funding from the European Community's Seventh Framework Programme (FP7/2007-2013) under Grant Agreement 211471 (i3DPost).  ... 
doi:10.1145/1839379.1839382 dblp:conf/compsystech/PitasN10 fatcat:iquyjujxt5d5hlj3zfqef5hi4y

3D-Posture Recognition Using Joint Angle Representation [chapter]

Adnan Al Alwani, Youssef Chahir, Djamal E. Goumidi, Michèle Molina, François Jouen
2014 Communications in Computer and Information Science  
In this context, 3D joint locations of skeletal data are initially processed. Furthermore, the 3D locations computed from the sequences of actions are described as the angles features.  ...  This paper presents an approach for action recognition performed by human using the joint angles from skeleton information.  ...  Action Coordinates Description for Skeletal Joints View invariance is a challenging problem in action recognition. With the use of 3D body skeleton, we can capture the 3D positions of the human body.  ... 
doi:10.1007/978-3-319-08855-6_12 fatcat:dpyyhxrqfvhmddkuvlttueoi5q

Multi-view Human Action Recognition: A Survey

Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas
2013 2013 Ninth International Conference on Intelligent Information Hiding and Multimedia Signal Processing  
This paper provides a comprehensive survey of multi-view human action recognition approaches.  ...  While single-view human action recognition has attracted considerable research study in the last three decades, multi-view action recognition is, still, a less exploited field.  ...  This publication reflects only the authors views. The European Union is not liable for any use that may be made of the information contained therein.  ... 
doi:10.1109/iih-msp.2013.135 dblp:conf/iih-msp/IosifidisTP13 fatcat:jj24d5dqi5e63in6ojy3xmxmdq

Flexible Human Behavior Analysis Framework for Video Surveillance Applications

Weilun Lao, Jungong Han, Peter H. N. de With
2010 International Journal of Digital Multimedia Broadcasting  
We study a flexible framework for semantic analysis of human motion from surveillance video.  ...  Thirdly, we perform a fast scheme to detect different body parts and generate a fitting skeleton model, without using the explicit assumption of upright body posture.  ...  model to each of the predefined posture types for the observed human body.  ... 
doi:10.1155/2010/920121 fatcat:olpdmqx5y5fmzfx3dv27t7ehhi

3D Periodic Human Motion Reconstruction from 2D Motion Sequences

Zonghua Zhang, Nikolaus F. Troje
2007 Neural Computation  
In this report, we present and evaluate a method of reconstructing three-dimensional (3D) periodic human motion from two-dimensional (2D) motion sequences.  ...  Based on a Fourier decomposition of a training set of 3D data, we construct a linear, morphable representation.  ...  Just like reconstructing 3D face shape from a single image based on a morphable model [13] , Bowden et al reconstructed the 3D structure of a subject from a single view of its outline.  ... 
doi:10.1162/neco.2007.19.5.1400 pmid:17381271 fatcat:uf42ludqabdvhas7rxa4bobfle

An audio-driven dancing avatar

Ferda Ofli, Yasemin Demir, Yücel Yemez, Engin Erzin, A. Murat Tekalp, Koray Balcı, İdil Kızoğlu, Lale Akarun, Cristian Canton-Ferrer, Joëlle Tilmanne, Elif Bozkurt, A. Tanju Erdem
2008 Journal on Multimodal User Interfaces  
The video is analyzed to capture the time-varying posture of the dancer's body  ...  We present a framework for training and synthesis of an audio-driven dancing avatar. The avatar is trained for a given musical genre using the multicamera video recordings of a dance performance.  ...  Murat Tekalp acknowledges support from Turkish Academy of Sciences (TUBA). 6  ... 
doi:10.1007/s12193-008-0009-x fatcat:vnxmuu63rjgf3pvtgfcieh4lqq

3D Body Reconstruction for Immersive Interaction [chapter]

Isaac Cohen, Mun Wai Lee
2002 Lecture Notes in Computer Science  
In this paper we present an approach for capturing 3D body motion and inferring human body posture from detected silhouettes.  ...  We show that the integration of two or more silhouettes allows us to perform a 3D body reconstruction while each silhouette can be used for identifying human body postures.  ...  Acknowledgment This research was supported by a grant from the Institute for Creative Technologies (ict.usc.edu).  ... 
doi:10.1007/3-540-36138-3_10 fatcat:r2nqll72n5e33l66wknigqdkei

Human 3D Pose Estimation with a Tilting Camera for Social Mobile Robot Interaction

Mercedes Garcia-Salguero, Javier Gonzalez-Jimenez, Francisco-Angel Moreno
2019 Sensors  
This work investigates the capabilities of wide field-of-view RGB cameras to estimate the 3D position and orientation (i.e., the pose) of a user in the environment.  ...  pose from the detection of their feet and does not require either the robot or the user to remain static during the reconstruction; and (2) a method that takes some views of the scene while the camera  ...  In this paper, we investigate the use of a wide FoV RGB camera for determining the 3D position of the joints of a human body (human body pose), and estimating from them the human 3D position and orientation  ... 
doi:10.3390/s19224943 pmid:31766197 pmcid:PMC6891307 fatcat:qmnoo5egqfdzhn3o4dyj7nnf2u

A posture optimization algorithm for model-based motion capture of movement sequences

Jure Zakotnik, Tom Matheson, Volker Dürr
2004 Journal of Neuroscience Methods  
Based on the stochastic search algorithm of Simulated Annealing (SA), it utilizes a kinematic body model that includes joint angle constraints to reconstruct posture from an arbitrary number of views.  ...  The resulting joint angle RMS errors range between 0.7 • and 4.9 • , limited by the pixel resolution of the digital video. 3D-movement reconstruction is possible even from a single view.  ...  Part of this work was supported by research grants from the Isaac Newton Trust (Cambridge, UK) and BBSRC (UK) to Tom Matheson.  ... 
doi:10.1016/j.jneumeth.2003.11.013 pmid:15020088 fatcat:4mqashtdnvg7dch2tgclltmc5u

Robust arbitrary view gait recognition based on parametric 3D human body reconstruction and virtual posture synthesis

Jian Luo, Jin Tang, Tardi Tjahjadi, Xiaoming Xiao
2016 Pattern Recognition  
The 3D 35 body shape is derived from a base mesh shape obtained by morphing, and a skeleton is embedded into the target 36 human subject's reconstructed body model to form different postures.  ...  AVGR-BRPS uses a 3D statistical parametric model of human body shapes and poses.  ...  − = − , (17) However, single view images provide only one-side surface portion of the human body.  ... 
doi:10.1016/j.patcog.2016.05.030 fatcat:szs7qz3yqbfalnsrns6spje57y

Human Posture Tracking and Classification through Stereo Vision and 3D Model Matching

Stefano Pellegrini, Luca Iocchi
2008 EURASIP Journal on Image and Video Processing  
The system provides both a robust way to segment and track people in the scene and 3D information about tracked people. The proposed method is based on matching 3D data with a 3D human body model.  ...  Experimental results show the effectiveness of the system in determining human postures with different orientations of the people with respect to the stereo sensor, in presence of partial occlusions and  ...  from different points of view.  ... 
doi:10.1155/2008/476151 fatcat:jxhbscuamjb75mkrvpasbvw2mi
« Previous Showing results 1 — 15 out of 19,741 results