Open AccessProceedings Article
Human action recognition using a temporal hierarchy of covariance descriptors on 3D joint locations
Mohamed E. Hussein,Marwan Torki,Mohammad Gowayyed,Motaz El-Saban +3 more
- 03 Aug 2013
- pp 2466-2472
652
TL;DR: A novel approach to human action recognition from 3D skeleton sequences extracted from depth data that uses the covariance matrix for skeleton joint locations over time as a discriminative descriptor for a sequence to encode the relationship between joint movement and time.
read more
Abstract: Human action recognition from videos is a challenging machine vision task with multiple important application domains, such as human-robot/machine interaction, interactive entertainment, multimedia information retrieval, and surveillance. In this paper, we present a novel approach to human action recognition from 3D skeleton sequences extracted from depth data. We use the covariance matrix for skeleton joint locations over time as a discriminative descriptor for a sequence. To encode the relationship between joint movement and time, we deploy multiple covariance matrices over sub-sequences in a hierarchical fashion. The descriptor has a fixed length that is independent from the length of the described sequence. Our experiments show that using the covariance descriptor with an off-the-shelf classification algorithm outperforms the state of the art in action recognition on multiple datasets, captured either via a Kinect-type sensor or a sophisticated motion capture system. We also include an evaluation on a novel large dataset using our own annotation.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Two-Stream CNNs for Gesture-Based Verification and Identification: Learning User Style
Jonathan Wu,Prakash Ishwar,Janusz Konrad +2 more
- 01 Jun 2016
TL;DR: This work uses two-stream convolutional neural networks, a form of deep learning, to learn a user's gesture "style" from a set of training gestures, and finds that it is able to outperform state-of-the-art methods in identification and verification for two biometrics-oriented gesture datasets for body and in-air hand gestures.
DSRF: A flexible trajectory descriptor for articulated human action recognition
Yao Guo,Youfu Li,Zhanpeng Shao +2 more
TL;DR: Experimental results on three benchmark datasets demonstrate that the proposed approach outperforms existing skeleton representations in terms of recognition accuracy.
41
Si-GCN: Structure-induced Graph Convolution Network for Skeleton-based Action Recognition
Rong Liu,Chunyan Xu,Tong Zhang,Wenting Zhao,Zhen Cui,Jian Yang +5 more
- 14 Jul 2019
TL;DR: Comprehensive evaluations on two public datasets well demonstrate the superiority of the proposed Si-GCN when compared with existing skeleton-based action recognition approaches.
40
•Posted Content
Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognition
TL;DR: In this paper, a local descriptor called trajectorylet is proposed to capture the static and kinematic information within a short temporal interval and a discriminative trajectorylet detector set is selected from a large number of candidate detectors trained through exemplar-SVMs.
40
•Posted Content
Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation
TL;DR: An effective method is proposed to extract mid-level features from Kinect skeletons for 3D human action recognition and this new representation yields state-of-the-art results on MSR DailyActivity3D and MSR ActionPairs3D.
40
References
LIBSVM: A library for support vector machines
Chih-Chung Chang,Chih-Jen Lin +1 more
TL;DR: Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Svetlana Lazebnik,Cordelia Schmid,Jean Ponce +2 more
- 17 Jun 2006
TL;DR: This paper presents a method for recognizing scene categories based on approximate global geometric correspondence that exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories.
Real-time human pose recognition in parts from single depth images
Jamie Shotton,Andrew Fitzgibbon,Mat Cook,Toby Sharp,Mark J. Finocchio,Richard E. Moore,Alex Aben-Athar Kipman,Andrew Blake +7 more
- 20 Jun 2011
TL;DR: This work takes an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation problem into a simpler per-pixel classification problem, and generates confidence-scored 3D proposals of several body joints by reprojecting the classification result and finding local modes.
Real-time human pose recognition in parts from single depth images
Jamie Shotton,Toby Sharp,Alex Aben-Athar Kipman,Andrew Fitzgibbon,Mark J. Finocchio,Andrew Blake,Mat Cook,Richard Moore +7 more
TL;DR: This work takes an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation problem into a simpler per-pixel classification problem, and generates confidence-scored 3D proposals of several body joints by reprojecting the classification result and finding local modes.
The recognition of human movement using temporal templates
Aaron F. Bobick,James W. Davis +1 more
TL;DR: A view-based approach to the representation and recognition of human movement is presented, and a recognition method matching temporal templates against stored instances of views of known actions is developed.
Related Papers (5)
Yong Du,Wei Wang,Liang Wang +2 more
- 07 Jun 2015
Wanqing Li,Zhengyou Zhang,Zicheng Liu +2 more
- 13 Jun 2010