Filters








2,787 Hits in 9.6 sec

View invariant human action recognition using histograms of 3D joints

Lu Xia, Chia-Chih Chen, J. K. Aggarwal
2012 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
In this paper, we present a novel approach for human action recognition with histograms of 3D joint locations (HOJ3D) as a compact representation of postures.  ...  In addition, due to the design of our spherical coordinate system and the robust 3D skeleton estimation from Kinect, our method demonstrates significant view invariance on our 3D action dataset.  ...  [33] define a view-invariant representation of actions based on the theory of 2D and 3D invariants.  ... 
doi:10.1109/cvprw.2012.6239233 dblp:conf/cvpr/XiaCA12 fatcat:s6y7h3chu5azrmd5ey6zzu5dfq

Skeleton based View Invariant Human Action Recognition using Convolutional Neural Networks

2019 International journal of recent technology and engineering  
The skeletal based human action recognition has its significant applications in the field of human computer interaction and human recognition from surveillance videos.  ...  The task of human action recognition in this paper is performed in three stages.  ...  The problem is considered to solve by making the 3D human skeleton joint location immune to view variations with the help of sequence based view invariant transform.  ... 
doi:10.35940/ijrte.b3547.078219 fatcat:xiyh5cn47zfn3nm776amdrjaye

Efficient Pose-Based Action Recognition [chapter]

Abdalrahman Eweiwi, Muhammed S. Cheema, Christian Bauckhage, Juergen Gall
2015 Lecture Notes in Computer Science  
Despite of its efficiency, our approach achieves state-of-the-art accuracy on four different benchmarks. We further investigate differences of 2d and 3d pose data for action recognition.  ...  Action recognition from 3d pose data has gained increasing attention since the data is readily available for depth or RGB-D videos.  ...  This work was carried out in the project automatic activity recognition in large image databases which is funded by the German Research Foundation (DFG).  ... 
doi:10.1007/978-3-319-16814-2_28 fatcat:67snrpw325hylgxtnhrocey4ae

Human action recognition using multiple views

Michael B. Holte, Cuong Tran, Mohan M. Trivedi, Thomas B. Moeslund
2011 Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding - J-HGBU '11  
Additionally, we discuss some of the shortcomings of multi-view camera setups and outline our thoughts on future directions of 3D human action recognition.  ...  This paper presents a review and comparative study of recent multi-view 2D and 3D approaches for human action recognition. The approaches are reviewed and categorized due to their nature.  ...  They apply a cylindrical histogram and compute an invariant measure of the distribution of reconstructed voxels, which later was used by Pierobon et al. [37] for human action recognition.  ... 
doi:10.1145/2072572.2072588 dblp:conf/mm/Holte0TM11 fatcat:d6xmw4zwqjcapbatbg2256oyca

A View-invariant Framework for Fast Skeleton-based Action Recognition using a Single RGB Camera

Enjie Ghorbel, Konstantinos Papadopoulos, Renato Baptista, Himadri Pathak, Girum Demisse, Djamila Aouada, Björn Ottersten
2019 Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications  
View-invariant action recognition using a single RGB camera represents a very challenging topic due to the lack of 3D information in RGB images.  ...  Taking advantage of this impressive progress, we propose a simple framework for fast and view-invariant action recognition using a single RGB camera.  ...  The main contributions of this paper may be summarized as follows: • A novel framework for fast view-invariant human action recognition using a single RGB camera. • Comparison of two different view-invariant  ... 
doi:10.5220/0007524405730582 dblp:conf/visapp/GhorbelPBPDAO19 fatcat:g7565vyywnb6fkw2rrzzx54jf4

Histogram of Oriented Principal Components for Cross-View Action Recognition [article]

Hossein Rahmani, Arif Mahmood, Du Huynh, Ajmal Mian
2015 arXiv   pre-print
HOPC is also used for the detection of Spatio-Temporal Keypoints (STK) in 3D pointcloud sequences so that view-invariant STK descriptors (or Local HOPC descriptors) at these key locations only are used  ...  We have evaluated the performance of our proposed descriptors against nine existing techniques on two cross-view and three single-view human action recognition datasets.  ...  ACKNOWLEDGMENT We thank the authors of [29] for providing the Northwestern-UCLA Multiview Action3D dataset and especially Dr Jiang Wang for answering our questions about the implementation of AOG [29  ... 
arXiv:1409.6813v2 fatcat:mfxdqn53cnfhlhcm2ya6rjko4y

HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition [article]

Hossein Rahmani, Arif Mahmood, Du Q. Huynh, Ajmal Mian
2014 arXiv   pre-print
Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which change significantly with viewpoint.  ...  In contrast, we directly process the pointclouds and propose a new technique for action recognition which is more robust to noise, action speed and viewpoint variations.  ...  HOPC: Histogram of Oriented Principal Components for Action Recognition  ... 
arXiv:1408.3809v4 fatcat:wdyeedcg2vdw3nwcs27xql6hne

Arm-hand Action Recognition Based on 3D Skeleton Joints

Ling RUI, Shi-wei MA, Jia-rui WEN, Li-na LIU
2017 DEStech Transactions on Engineering and Technology Research  
In this paper, a simple and reliable method for arm-hand action recognition is proposed based on the representation of 3D skeleton joints.  ...  Finally, arm-hand action recognition is implemented by training SVMs using different kernel functions and parameters.  ...  Figure 1 . 1 20 Human Joints achieved from Kinect view. Figure 3 . 3 Draw circle action in 45 degree view. Figure 4 . 4 Overview of the proposed method.  ... 
doi:10.12783/dtetr/icca2016/6018 fatcat:v2dzizyfffehpepvlpkahf6qem

HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition [chapter]

Hossein Rahmani, Arif Mahmood, Du Q Huynh, Ajmal Mian
2014 Lecture Notes in Computer Science  
Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which change significantly with viewpoint.  ...  In contrast, we directly process the pointclouds and propose a new technique for action recognition which is more robust to noise, action speed and viewpoint variations.  ...  HOPC: Histogram of Oriented Principal Components for Action Recognition  ... 
doi:10.1007/978-3-319-10605-2_48 fatcat:5hq7seu2sbhm3ezf3vwdfv6ipq

Fusion of Skeletal and Silhouette-Based Features for Human Action Recognition with RGB-D Devices

Alexandros Andre Chaaraoui, Jose Ramon Padilla-Lopez, Francisco Florez-Revuelta
2013 2013 IEEE International Conference on Computer Vision Workshops  
Based on human silhouettes Silhouettes have been used extensively for human action recognition.  ...  The silhouette of the human body has been proven to be Pick-up and throw from the MSR Action3D dataset [11] useful for action recognition [16] .  ... 
doi:10.1109/iccvw.2013.19 dblp:conf/iccvw/ChaaraouiPF13 fatcat:jb5bhxrmmvb47hcbyms6yn37hq

Learning Action Recognition Model from Depth and Skeleton Videos

Hossein Rahmani, Mohammed Bennamoun
2017 2017 IEEE International Conference on Computer Vision (ICCV)  
Analysis of human actions based on 3D skeleton data has become popular recently, due to its robustness and view-invariant representation.  ...  Depth sensors open up possibilities of dealing with the human action recognition problem by providing 3D human skeleton data and depth images of the scene.  ...  Proposed Approach This section presents a view-invariant human action recognition model using a depth camera. The proposed architecture is illustrated in Fig. 1 .  ... 
doi:10.1109/iccv.2017.621 dblp:conf/iccv/RahmaniB17 fatcat:m5bienrtybfrbnouuom5lwzgra

Space-Time Representation of People Based on 3D Skeletal Data: A Review [article]

Fei Han, Brian Reily, William Hoff, Hao Zhang
2017 arXiv   pre-print
Spatiotemporal human representation based on 3D visual perception data is a rapidly growing research area.  ...  This paper presents a comprehensive survey of existing space-time representations of people based on 3D skeletal data, and provides an informative categorization and analysis of these methods from the  ...  Srivastava, Action recognition using rate-invariant [161] C. Zhang, Y.  ... 
arXiv:1601.01006v3 fatcat:zgpmw3xqunajtctu4e7minjyx4

Combining Pose-Invariant Kinematic Features and Object Context Features for RGB-D Action Recognition

Manoj Ramanathan, Institute for Media Innovation, Nanyang Technological University, Singapore, Jaroslaw Kochanowicz, Nadia Magnenat Thalmann
2019 International Journal of Machine Learning and Computing  
Using RGB, depth and skeletal joints, the proposed framework extracts a novel set of pose-invariant motion kinematic features based on 3D scene flow and captures the motion of body parts with respect to  ...  Action recognition using RGB-D cameras is a popular research topic.  ...  ACKNOWLEDGEMENTS This research is supported by the BeingTogether Centre, a collaboration between Nanyang Technological University (NTU) Singapore and University of North Carolina (UNC) at Chapel Hill.  ... 
doi:10.18178/ijmlc.2019.9.1.763 fatcat:etvpm6gfnfasjgetbcinuugpda

Human Pose Estimation and Activity Recognition From Multi-View Videos: Comparative Explorations of Recent Developments

Michael B. Holte, Cuong Tran, Mohan M. Trivedi, Thomas B. Moeslund
2012 IEEE Journal on Selected Topics in Signal Processing  
We report a comparison of the most promising methods for multi-view human action recognition using two publicly available datasets: the INRIA Xmas Motion Acquisition Sequences (IXMAS) Multi-View Human  ...  Finally, we discuss some of the shortcomings of multi-view camera setups and outline our thoughts on future directions of 3D body pose estimation and human action recognition.  ...  Nikolaidis, Informatics, and Telematics Institute, Center for Research and Technology Hellas, Greece, and Department of Informatics, Aristotle University of Thessaloniki, Greece, for their support on the  ... 
doi:10.1109/jstsp.2012.2196975 fatcat:2sqvghpigzczzlrrl3iziyg63a

Computer Based Human Gesture Recognition With Study Of Algorithms

Mr. Kaushik I Manavadariya
2013 IOSR Journal of Computer Engineering  
Two different approaches in gesture recognition is related to 3D model and related to appearance-based.3D model is used to provide information related the body parts like thumb, position of palm, joint  ...  Gesture recognition is a technology of computer science with the goal of interpreting human gestures or human motion via mathematical algorithms.  ...  A view-based approach to the representation and recognition of human movement using temporal templates is presented.  ... 
doi:10.9790/0661-1124150 fatcat:waqx335o2rgezj7c3omkiie4di
« Previous Showing results 1 — 15 out of 2,787 results