Filters








3,314 Hits in 5.0 sec

Gesture recognition using a probabilistic framework for pose matching

A. Elgammal, V. Shet, Y. Yacoob, L.S. Davis
7th International Conference on Control, Automation, Robotics and Vision, 2002. ICARCV 2002.  
Matching individual poses to image data is pegormed using a probabilistic formulation for edge matching to obtain a likelihood measurement for each individual pose.  ...  The probabilistic framework also imposes temporal constrains between different pose through a learned Hidden Markov Model (HMM) for each gesture.  ...  The approach is based on representing each gesture as a sequence of learned body poses through a probabilistic framework for matching these body poses to the the image data.  ... 
doi:10.1109/icarcv.2002.1238518 dblp:conf/icarcv/ElgammalSYD02 fatcat:uis6dg6qkvepnnzlk4ufalvi3u

Guest Editors' Introduction to the Special Issue on Multimodal Human Pose Recovery and Behavior Analysis

Sergio Escalera, Jordi Gonzalez, Xavier Baro, Jamie Shotton
2016 IEEE Transactions on Pattern Analysis and Machine Intelligence  
recognition, and driver assistance technology, to mention just a few.  ...  The set of 16 accepted papers can be split into three main categories within M2HuPBA: (i) human pose recovery and tracking; (ii) action and gesture recognition; and (iii) datasets.  ...  For information on obtaining reprints of this article, please send e-mail to: reprints@ieee.org, and reference the Digital Object Identifier below.  ... 
doi:10.1109/tpami.2016.2557878 fatcat:ee3j7nre4fgdtjrozavgexvhi4

Semantic Representation and Recognition of Continued and Recursive Human Activities

M. S. Ryoo, J. K. Aggarwal
2008 International Journal of Computer Vision  
This paper describes a methodology for automated recognition of complex human activities.  ...  The methodology uses a context-free grammar (CFG) based representation scheme as a formal syntax for representing composite activities.  ...  A.2 Full CFG Representation Syntax In this subsection, we present the full CFG representation syntax for human activities.  ... 
doi:10.1007/s11263-008-0181-1 fatcat:l3ptiiombbdsrh3lymwqzk7ctm

Real-time continuous gesture recognition for natural human-computer interaction

Ying Yin, Randall Davis
2014 2014 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC)  
Our probabilistic recognition framework based on hidden Markov models (HMMs) unifies the recognition of the two forms of gestures.  ...  We also collected a new gesture dataset that contains the two forms of gestures, and propose a new hybrid performance metric for evaluating gesture recognition methods for real-time interaction.  ...  We collected a new dataset that includes two forms of gestures, a combination currently lacking in the community, and plan to make it public.  ... 
doi:10.1109/vlhcc.2014.6883032 dblp:conf/vl/YinD14 fatcat:3u6vxwpvwfditmdtb7jz2xfobq

Language-Motivated Approaches to Action Recognition [chapter]

Manavender R. Malgireddy, I. Nwogu, V. Govindaraju
2017 Gesture Recognition  
We also introduce a probabilistic framework for detecting and localizing pre-specified activities (or gestures) in a video sequence, analogous to the use of filler models for keyword detection in speech  ...  We demonstrate the robustness of our classification model and our spotting framework by recognizing activities in unconstrained real-life video sequences and by spotting gestures via a one-shot-learning  ...  Acknowledgments The authors wish to thank the associate editors and anonymous referees for all their advice about the structure, references, experimental illustration and interpretation of this manuscript  ... 
doi:10.1007/978-3-319-57021-1_5 fatcat:byt4ayc6nrcyfjh4o2av2btmae

Stochastic regular grammar-based learning for basic dance motion recognition

Yaya Heryadi, Mohamad Ivan Fanany, Aniati Murni Arymurthy
2013 2013 International Conference on Advanced Computer Science and Information Systems (ICACSIS)  
this paper presents a simple and computationally efficient framework for 3D dance basic motion recognition based on syntactic pattern recognition.  ...  A single test using the learned grammar in average takes only about 5 ms compared to around 20 s using kNN whilst the overhead time to build all grammars takes only about 3.4 s.  ...  DTW has also been used for dance similarity matching in [3] .  ... 
doi:10.1109/icacsis.2013.6761612 fatcat:24nzzznxobho3jtbmt5dkjzaru

Computers Seeing Action

Prof. Aaron F Bobick
1996 Procedings of the British Machine Vision Conference 1996  
For two of the domains | whole body actions and hand gestures | I described the approaches in detail while two others | constrained semantic domains (e.g. watching someone cooking) and labeling dynamic  ...  Fundamental to understanding action is reasoning about time, in either an implicit or explicit framework.  ...  The second technique, applied to hand gesture understanding, develops a state-based model of time captured in a probabilistic framework.  ... 
doi:10.5244/c.10.4 dblp:conf/bmvc/Bobick96 fatcat:taz6q7uou5e2vmokyxdwoow6by

Probability-Based Dynamic Time Warping for Gesture Recognition on RGB-D Data [chapter]

Miguel Ángel Bautista, Antonio Hernández-Vela, Victor Ponce, Xavier Perez-Sala, Xavier Baró, Oriol Pujol, Cecilio Angulo, Sergio Escalera
2013 Lecture Notes in Computer Science  
In this paper, a probability-based DTW for gesture recognition is proposed.  ...  Different samples of the same gesture pattern obtained from RGB-Depth data are used to build a Gaussian-based probabilistic model of the gesture.  ...  One of the most common dynamic programming methods used for gesture recognition is Dynamic Time Warping (DTW) [5] .  ... 
doi:10.1007/978-3-642-40303-3_14 fatcat:ibf6tpoosbas3l4gz7kqdm36ta

Human–computer interaction based on visual hand-gesture recognition using volumetric spatiograms of local binary patterns

Ana I. Maqueda, Carlos R. del-Blanco, Fernando Jaureguizar, Narciso García
2015 Computer Vision and Image Understanding  
For this purpose, a robust vision-based hand-gesture recognition system has been developed, and a new database has been created to test it.  ...  which is delivered to a bank of SVM classifiers to perform the gesture recognition.  ...  Two of the most popular approaches for hand-gesture recognition are based on machine learning approaches and template matching, using both color-based and depth-based imagery.  ... 
doi:10.1016/j.cviu.2015.07.009 fatcat:75dne4lacnefzgqusa6ot6npp4

Recognition of temporal structures: Learning prior and propagating observation augmented densities via hidden Markov states

Shaogang Gong, M. Walter, A. Psarrou
1999 Proceedings of the Seventh IEEE International Conference on Computer Vision  
The method is based on (1) learning prior probabilistic knowledge using Hidden Markov Models, (2) automatic temporal clustering of hidden Markov states based on Expectation Maximisation and (3) using observation  ...  augmented conditional density distributions to reduce the number of samples required for propagation and therefore improve recognition speed and robustness.  ...  In this work, we introduce a framework for the recognition of temporal structures in state space and illustrate the method through gesture recognition.  ... 
doi:10.1109/iccv.1999.791212 dblp:conf/iccv/GongWP99 fatcat:3zfgrk7alfflfaolno4hj73yfq

Unified Learning Approach for Egocentric Hand Gesture Recognition and Fingertip Detection [article]

Mohammad Mahmudul Alam, Mohammad Tariqul Islam, S. M. Mahbubur Rahman
2021 arXiv   pre-print
In this paper, a unified approach of convolutional neural network for both hand gesture recognition and fingertip detection is introduced.  ...  Since the whole pipeline uses a single network, it is significantly fast in computation.  ...  Acknowledgment We gratefully acknowledge the support of NVIDIA Corporation for the donation of a Titan Xp GPU that was used in this research.  ... 
arXiv:2101.02047v2 fatcat:deelzllzzzg6hp3qkwwx6alwjm

Simultaneous Localization and Recognition of Dynamic Hand Gestures

Jonathan Alon, Vassilis Athitsos, Quan Yuan, Stan Sclaroff
2005 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1  
The proposed framework includes translation invariant recognition of gestures, a desirable property for many HCI systems.  ...  Although DSTW is illustrated in a gesture recognition setting, the proposed algorithm is a general method for matching time series, that allows for multiple candidate feature vectors to be extracted at  ...  In a real application, the user could indicate the start and end of a gesture, for example by using a distinct pose for the non-gesturing hand [8] , or by pressing a key.  ... 
doi:10.1109/acvmot.2005.110 dblp:conf/wacv/AlonAYS05 fatcat:25rnyqc27nfrfkihtdccea6kwu

Video-Based Face Recognition: State of the Art [chapter]

Zhaoxiang Zhang, Chao Wang, Yunhong Wang
2011 Lecture Notes in Computer Science  
Face recognition in videos is a hot topic in computer vision and biometrics over many years.  ...  of facial images, illumination changes, pose variations and occlusions.  ...  [5] developed the probabilistic appearance manifold approach for tracking and recognition using video sequences.  ... 
doi:10.1007/978-3-642-25449-9_1 fatcat:c2z4v4arlzeelhw67ogg7jocwq

Body Posture Recognition as a Discovery Problem: A Semantic-Based Framework [chapter]

Michele Ruta, Floriano Scioscia, Maria di Summa, Saverio Ieva, Eugenio Di Sciascio, Marco Sacco
2014 Lecture Notes in Computer Science  
In this paper a framework is proposed for automated posture recognition, exploiting depth data provided by a commercial tracking device.  ...  Finally, non-standard inferences and a similarity-based ranking support the discovery of the best matching posture.  ...  Future work aims to enhance the presented framework toward gesture recognition.  ... 
doi:10.1007/978-3-319-09912-5_14 fatcat:2aumm6q7szbivae4dystphmaja

CGAP2: Context and gap aware predictive pose framework for early detection of gestures [article]

Nishant Bhattacharya, Suresh Sundaram
2020 arXiv   pre-print
In this paper, we propose a novel context and gap aware pose prediction framework(CGAP2), which predicts future pose data for anticipatory recognition of gestures in an online fashion.  ...  CGAP2 has a 1-second time advantage compared to other gesture recognition systems, which can be crucial for autonomous vehicles.  ...  In this paper, we present a context and gap aware pose prediction (CGAP2) framework for anticipatory gesture recognition.  ... 
arXiv:2011.09216v1 fatcat:aaqeyu3nfnakdkt2zackjs7pmu
« Previous Showing results 1 — 15 out of 3,314 results