DOI:​10.1007/978-3-319-10605-2_48
Corpus ID: 8541055
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition
H. Rahmani, A. Mahmood, +1 author A. Mian
Published 2014
Mathematics, Computer Science

ArXiv
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… Expand
View PDF On ArXiv
Share This Paper




140 Citations
Highly Influential Citations
11
Background Citations
52
Methods Citations
45
Results Citations
1
Figures and Topics from this paper
Figure 1
Algorithm
Data descriptor
Benchmark (computing)
140 Citations
Histogram of Oriented Principal Components for Cross-View Action Recognition
H. Rahmani, A. Mahmood, D. Huynh, A. Mian
Computer Science, Medicine
IEEE Transactions on Pattern Analysis and Machine Intelligence
2016
TLDR
The histogram of oriented principal components (HOPC) descriptor is proposed that is robust to noise, viewpoint, scale and action speed variations and a global descriptor computed from the normalized spatio-temporal distribution of STKs in 4-D, which is referred to as STK-D. Expand
121 Citations
PDF
Modeling spatial layout of features for real world scenario RGB-D action recognition
Michal Koperski, F. Brémond
Computer Science
2016 13th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
2016
TLDR
The results show that the method is competitive to skeleton based methods, while requiring much simpler people detection instead of skeleton detection, and introduces descriptor which encodes static information for actions with low amount of motion.Expand
14 Citations
PDF
Human contour extraction from RGBD camera for action recognition
Xiaohui Huang, Jun Cheng, Xiaopeng Ji
Computer Science
2016 IEEE International Conference on Information and Automation (ICIA)
2016
TLDR
This paper segments and extracts human contour in the color image using convolutional network model and re-segmented utilizing depth information to reduce noise and extract features from cuboids and recognize human actions. Expand
5 Citations
Cross-view human action recognition from depth maps using spectral graph sequences
Tommi Kerola, Nakamasa Inoue, Koichi Shinoda
Mathematics, Computer Science
Comput. Vis. Image Underst.
2017
TLDR
A graph-based method for 3D view-invariant human action recognition from depth cameras based on graph signal processing techniques that captures the temporal interaction between depth map interest points and achieves a 19.8% increase in performance compared to state-of-the-art results for cross-view action recognition. Expand
Local mean spatio-temporal feature for depth image-based speed-up action recognition
Xiaopeng Ji, Jun Cheng, Dapeng Tao
Computer Science
2015 IEEE International Conference on Image Processing (ICIP)
2015
TLDR
This paper proposes a local mean spatio-temporal feature (LMSF) to speed up depth image based action recognition and proposes a method to reduce redundant normals extracted from depth cloud points by sparse coding. Expand
6 Citations
Local Surface Geometric Feature for 3D human action recognition
E. Zhang, Wanjun Chen, Zhuomin Zhang, Yan Zhang
Computer Science
Neurocomputing

2016
TLDR
The LSGF is extracted from each skeleton joint in point cloud space to capture the static appearance and pose cues, which includes joint position, normal, and local curvature, in a novel Local Surface Geometric Feature for human action recognition from video sequences captured by a depth camera.Expand
11 Citations
3D Action Recognition Using Multi-Temporal Depth Motion Maps and Fisher Vector
C. Chen, M. Liu, Baochang Zhang, J. Han, Junjun Jiang, Hong Liu
Mathematics, Computer ScienceIJCAI
2016
TLDR
Extensive experiments on the public MSRAction3D, MSRGesture3D and DHA datasets show that the proposed method outperforms state-of-the-art approaches for depth-based action recognition. Expand
Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3-D Human Action Recognition
C. Chen, M. Liu, Hong Liu, Baochang Zhang, J. Han, N. Kehtarnavaz
Mathematics, Computer ScienceIEEE Access
2017
TLDR
A local spatio-temporal descriptor for action recognistion from depth video sequences, which is capable of distinguishing similar actions as well as coping with different speeds of actions is presented. Expand
Viewpoint Invariant RGB-D Human Action Recognition
Jain Liu, Naveed Akhtar, A. Mian
Computer Science
2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
2017
TLDR
This work capitalizes on the complementary spatio-temporal information in RGB and Depth frames of the RGB-D videos to achieve viewpoint invariant action recognition, and extracts view invariant features from the dense trajectories of theRGB stream using a non-linear knowledge transfer model. Expand
Online action recognition from RGB-D cameras based on reduced basis decomposition
M. Arunraj, A. Srinivasan, A. Juliet
Computer Science
Journal of Real-Time Image Processing
2018
TLDR
An efficient dimensionality reduction technique and classification mechanism to recognize actions from depth motion map features and a Probabilistic Collaborative Representation Classifier (Pro-CRC) which helps in achieving the state-of-the-art efficiency. Expand
3 Citations
...
1
2
3
4
...
References
SHOWING 1-10 OF 42 REFERENCES
HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences
Omar Oreifej, Zicheng Liu
Computer Science, Mathematics
2013 IEEE Conference on Computer Vision and Pattern Recognition
2013
TLDR
A new descriptor for activity recognition from videos acquired by a depth sensor is presented that better captures the joint shape-motion cues in the depth sequence, and thus outperforms the state-of-the-art on all relevant benchmarks. Expand
830 Citations
PDF
Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera
Lu Xia, J. Aggarwal
Mathematics, Computer Science
2013 IEEE Conference on Computer Vision and Pattern Recognition
2013
TLDR
A filtering method to extract STIPs from depth videos (called DSTIP) that effectively suppress the noisy measurements is presented and a novel depth cuboid similarity feature (DCSF) is built to describe the local 3D depth cuboids around the DSTips with an adaptable supporting size. Expand
414 Citations
PDF
View invariant human action recognition using histograms of 3D joints
Lu Xia, Chia-Chih Chen, J. Aggarwal
Mathematics, Computer Science
2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
2012
TLDR
This paper presents a novel approach for human action recognition with histograms of 3D joint locations (HOJ3D) as a compact representation of postures and achieves superior results on the challenging 3D action dataset. Expand
1,183 Citations
PDF
A Spatio-Temporal Descriptor Based on 3D-Gradients
Alexander Kläser, Marcin Marszalek, C. Schmid
Computer Science
BMVC

2008
TLDR
This work presents a novel local descriptor for video sequences based on histograms of oriented 3D spatio-temporal gradients based on regular polyhedrons which outperform the state-of-the-art. Expand
1,825 Citations
PDF
Real time action recognition using histograms of depth gradients and random decision forests
H. Rahmani, A. Mahmood, D. Huynh, A. Mian
Computer Science
IEEE Winter Conference on Applications of Computer Vision
2014
TLDR
An algorithm which combines the discriminative information from depth images as well as from 3D joint positions to achieve high action recognition accuracy and outperform all other algorithms in accuracy and have a processing speed of over 112 frames/second is proposed. Expand
97 Citations
PDF
Mining actionlet ensemble for action recognition with depth cameras
Jiang Wang, Zicheng Liu, Y. Wu, Junsong Yuan
Computer Science
2012 IEEE Conference on Computer Vision and Pattern Recognition
2012
TLDR
An actionlet ensemble model is learnt to represent each action and to capture the intra-class variance, and novel features that are suitable for depth data are proposed. Expand
1,311 Citations
PDF
Human Daily Action Analysis with Multi-view and Color-Depth Data
Zhongwei Cheng, Lei Qin, Yituo Ye, Qingming Huang, Q. Tian
Computer ScienceECCV Workshops
2012
TLDR
A new descriptor of depth information for action representation is proposed, which depicts the structural relations of spatiotemporal points within action volume using the distance information in depth data. Expand
123 Citations
PDF
Robust 3D Action Recognition with Random Occupancy Patterns
Jiang Wang, Zicheng Liu, J. Chorowski, Zhuoyuan Chen, Y. Wu
Computer Science
ECCV

2012
TLDR
This work extracts semi-local features called random occupancy pattern ROP features, which employ a novel sampling scheme that effectively explores an extremely large sampling space and utilizes a sparse coding approach to robustly encode these features. Expand
469 Citations
PDF
Action Recognition from Arbitrary Views using 3D Exemplars
Daniel Weinland, Edmond Boyer, Rémi Ronfard
Computer Science
2007 IEEE 11th International Conference on Computer Vision
2007
TLDR
A new framework is proposed where actions are model actions using three dimensional occupancy grids, built from multiple viewpoints, in an exemplar-based HMM, where a 3D reconstruction is not required during the recognition phase, instead learned 3D exemplars are used to produce 2D image information that is compared to the observations. Expand
494 Citations
PDF
A Performance Evaluation of 3D Keypoint Detectors
Samuele Salti, Federico Tombari, L. D. Stefano
Computer Science
2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission
2011
TLDR
A performance evaluation of the state-of-the-art in 3D key point detection, mainly addressing the task of 3D object recognition, is carried out by analyzing the performance of several prominent methods in terms of robustness to noise, presence of clutter, occlusions and point- of-view variations.Expand
188 Citations
PDF
...
1
2
3
4
...
SORT BY
Related Papers
Histogram of Oriented Principal Components for Cross-View Action Recognition
H. Rahmani, A. Mahmood, D. Huynh, A. Mian
Computer Science, Medicine
IEEE Transactions on Pattern Analysis and Machine…
2016
Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from d...
121 Citations
A Spatio-Temporal Descriptor Based on 3D-Gradients
Alexander Kläser, Marcin Marszalek, C. Schmid
Computer Science
BMVC

2008
In this work, we present a novel local descriptor for video sequences. The proposed descriptor is based on histograms of...
1,825 Citations
Show More
2/10
Abstract
Figures and Topics
140 Citations
42 References
Related Papers
Stay Connected With Semantic Scholar
What Is Semantic Scholar?
Semantic Scholar is a free, AI-powered research tool for scientific literature, based at the Allen Institute for AI.
Learn More
About
About Us
Publishers
Beta Program
Contact
Research
Team
Datasets
Open Corpus
Supp.ai
Resources
Librarians
Tutorials
FAQ
API
Proudly built by AI2
Terms of ServicePrivacy Policy
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License
ACCEPT & CONTINUE