Rule-based approach to recognizing human body poses and gestures in real time. Hachaj, T. & Ogiela, M. R. Multimedia Systems, 20(1):81–99, February, 2014. 00101![Rule-based approach to recognizing human body poses and gestures in real time [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex In this paper we propose a classifier capable of recognizing human body static poses and body gestures in real time. The method is called the gesture description language (GDL). The proposed methodology is intuitive, easily thought and reusable for any kind of body gestures. The very heart of our approach is an automated reasoning module. It performs forward chaining reasoning (like a classic expert system) with its inference engine every time new portion of data arrives from the feature extraction library. All rules of the knowledge base are organized in GDL scripts having the form of text files that are parsed with a LALR-1 grammar. The main novelty of this paper is a complete description of our GDL script language, its validation on a large dataset (1,600 recorded movement sequences) and the presentation of its possible application. The recognition rate for examined gestures is within the range of 80.5–98.5 %. We have also implemented an application that uses our method: it is a three-dimensional desktop for visualizing 3D medical datasets that is controlled by gestures recognized by the GDL module.
@article{hachaj_rule-based_2014,
title = {Rule-based approach to recognizing human body poses and gestures in real time},
volume = {20},
issn = {0942-4962, 1432-1882},
url = {http://link.springer.com/article/10.1007/s00530-013-0332-2},
doi = {10.1007/s00530-013-0332-2},
abstract = {In this paper we propose a classifier capable of recognizing human body static poses and body gestures in real time. The method is called the gesture description language (GDL). The proposed methodology is intuitive, easily thought and reusable for any kind of body gestures. The very heart of our approach is an automated reasoning module. It performs forward chaining reasoning (like a classic expert system) with its inference engine every time new portion of data arrives from the feature extraction library. All rules of the knowledge base are organized in GDL scripts having the form of text files that are parsed with a LALR-1 grammar. The main novelty of this paper is a complete description of our GDL script language, its validation on a large dataset (1,600 recorded movement sequences) and the presentation of its possible application. The recognition rate for examined gestures is within the range of 80.5–98.5 \%. We have also implemented an application that uses our method: it is a three-dimensional desktop for visualizing 3D medical datasets that is controlled by gestures recognized by the GDL module.},
language = {en},
number = {1},
urldate = {2017-02-02},
journal = {Multimedia Systems},
author = {Hachaj, Tomasz and Ogiela, Marek R.},
month = feb,
year = {2014},
note = {00101},
pages = {81--99}
}
Downloads: 0
{"_id":"E9xAfyEDeRhiqJuPE","bibbaseid":"hachaj-ogiela-rulebasedapproachtorecognizinghumanbodyposesandgesturesinrealtime-2014","authorIDs":[],"author_short":["Hachaj, T.","Ogiela, M. R."],"bibdata":{"bibtype":"article","type":"article","title":"Rule-based approach to recognizing human body poses and gestures in real time","volume":"20","issn":"0942-4962, 1432-1882","url":"http://link.springer.com/article/10.1007/s00530-013-0332-2","doi":"10.1007/s00530-013-0332-2","abstract":"In this paper we propose a classifier capable of recognizing human body static poses and body gestures in real time. The method is called the gesture description language (GDL). The proposed methodology is intuitive, easily thought and reusable for any kind of body gestures. The very heart of our approach is an automated reasoning module. It performs forward chaining reasoning (like a classic expert system) with its inference engine every time new portion of data arrives from the feature extraction library. All rules of the knowledge base are organized in GDL scripts having the form of text files that are parsed with a LALR-1 grammar. The main novelty of this paper is a complete description of our GDL script language, its validation on a large dataset (1,600 recorded movement sequences) and the presentation of its possible application. The recognition rate for examined gestures is within the range of 80.5–98.5 %. We have also implemented an application that uses our method: it is a three-dimensional desktop for visualizing 3D medical datasets that is controlled by gestures recognized by the GDL module.","language":"en","number":"1","urldate":"2017-02-02","journal":"Multimedia Systems","author":[{"propositions":[],"lastnames":["Hachaj"],"firstnames":["Tomasz"],"suffixes":[]},{"propositions":[],"lastnames":["Ogiela"],"firstnames":["Marek","R."],"suffixes":[]}],"month":"February","year":"2014","note":"00101","pages":"81–99","bibtex":"@article{hachaj_rule-based_2014,\n\ttitle = {Rule-based approach to recognizing human body poses and gestures in real time},\n\tvolume = {20},\n\tissn = {0942-4962, 1432-1882},\n\turl = {http://link.springer.com/article/10.1007/s00530-013-0332-2},\n\tdoi = {10.1007/s00530-013-0332-2},\n\tabstract = {In this paper we propose a classifier capable of recognizing human body static poses and body gestures in real time. The method is called the gesture description language (GDL). The proposed methodology is intuitive, easily thought and reusable for any kind of body gestures. The very heart of our approach is an automated reasoning module. It performs forward chaining reasoning (like a classic expert system) with its inference engine every time new portion of data arrives from the feature extraction library. All rules of the knowledge base are organized in GDL scripts having the form of text files that are parsed with a LALR-1 grammar. The main novelty of this paper is a complete description of our GDL script language, its validation on a large dataset (1,600 recorded movement sequences) and the presentation of its possible application. The recognition rate for examined gestures is within the range of 80.5–98.5 \\%. We have also implemented an application that uses our method: it is a three-dimensional desktop for visualizing 3D medical datasets that is controlled by gestures recognized by the GDL module.},\n\tlanguage = {en},\n\tnumber = {1},\n\turldate = {2017-02-02},\n\tjournal = {Multimedia Systems},\n\tauthor = {Hachaj, Tomasz and Ogiela, Marek R.},\n\tmonth = feb,\n\tyear = {2014},\n\tnote = {00101},\n\tpages = {81--99}\n}\n\n","author_short":["Hachaj, T.","Ogiela, M. R."],"key":"hachaj_rule-based_2014","id":"hachaj_rule-based_2014","bibbaseid":"hachaj-ogiela-rulebasedapproachtorecognizinghumanbodyposesandgesturesinrealtime-2014","role":"author","urls":{"Paper":"http://link.springer.com/article/10.1007/s00530-013-0332-2"},"downloads":0,"html":""},"bibtype":"article","biburl":"http://www.telemidia.puc-rio.br/~alan/files/all.bib","creationDate":"2020-03-03T14:08:14.911Z","downloads":0,"keywords":[],"search_terms":["rule","based","approach","recognizing","human","body","poses","gestures","real","time","hachaj","ogiela"],"title":"Rule-based approach to recognizing human body poses and gestures in real time","year":2014,"dataSources":["jAxurbvLP8q5LTdLa"]}