Journal ArticleDOI
Human action recognition based on skeleton splitting
Sang Min Yoon,Arjan Kuijper +1 more
TLDR
A novel human action recognition methodology by extracting the human skeletal features and separating them into several human body parts such as face, torso, and limbs to efficiently visualize and analyze the motion ofhuman body parts is proposed.Abstract:
Human action recognition, defined as the understanding of the human basic actions from video streams, has a long history in the area of computer vision and pattern recognition because it can be used for various applications. We propose a novel human action recognition methodology by extracting the human skeletal features and separating them into several human body parts such as face, torso, and limbs to efficiently visualize and analyze the motion of human body parts. Our proposed human action recognition system consists of two steps: (i) automatic skeletal feature extraction and splitting by measuring the similarity between neighbor pixels in the space of diffusion tensor fields, and (ii) human action recognition by using multiple kernel based Support Vector Machine. Experimental results on a set of test database show that our proposed method is very efficient and effective to recognize the actions using few parameters.read more
Citations
More filters
Journal ArticleDOI
Human action recognition via multi-task learning base on spatial-temporal feature
Wenzhong Guo,Guolong Chen +1 more
TL;DR: A novel human action recognition method using regularized multi-task learning that completely represents the local visual characteristics of the human body structure and has significantly better performance than the standard Bag- of-Words+Support Vector Machine (BoW+SVM) method and other state-of-the-art methods.
Journal ArticleDOI
An Online Continuous Human Action Recognition Algorithm Based on the Kinect Sensor
TL;DR: An online CHAR algorithm is proposed based on skeletal data extracted from RGB-D images captured by Kinect sensors, which shows that the proposed algorithm is effective and highly-efficient for recognizing continuous human actions.
Journal ArticleDOI
iSurveillance: Intelligent framework for multiple events detection in surveillance videos
TL;DR: An intelligent framework for detection of multiple events in surveillance videos is presented, based on the principle of compositionality, which modularize the surveillance problems into a set of variables comprising regions-of-interest, classes, attributes and rules to construct a knowledge-based understanding of the environment.
Journal ArticleDOI
Efficient large-scale action recognition in videos using extreme learning machines
Gül Varol,Albert Ali Salah +1 more
TL;DR: The results show that it is possible to obtain a high accuracy with extreme learning machines in an efficient way, without using the extensively trained and computationally heavy deep neural networks that the top performing systems of the challenge incorporated.
Journal ArticleDOI
An efficient human action recognition framework with pose-based spatiotemporal features
TL;DR: A novel framework to recognize human actions using 3D skeleton information using Fisher Vector representation and encoding is proposed and achieved competitive results compared to the other methods in the literature.
References
More filters
Journal ArticleDOI
Snakes : Active Contour Models
TL;DR: This work uses snakes for interactive interpretation, in which user-imposed constraint forces guide the snake near features of interest, and uses scale-space continuation to enlarge the capture region surrounding a feature.
Journal ArticleDOI
Estimation of the Effective Self-Diffusion Tensor from the NMR Spin Echo
TL;DR: The diagonal and off-diagonal elements of the effective self-diffusion tensor, Deff, are related to the echo intensity in an NMR spin-echo experiment.
Journal ArticleDOI
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.
Proceedings Article
Recognizing Action at a Distance
TL;DR: A novel motion descriptor based on optical flow measurements in a spatiotemporal volume for each stabilized human figure is introduced, and an associated similarity measure to be used in a nearest-neighbor framework is introduced.