Open AccessHuman Action recognition using STIP Evaluation techniques
Author(s) -
B Latha,
BK Manjula,
CH Venkata Sumana,
K. H. Hemalatha
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/925/1/012026
Subject(s) - action (physics) , computer science , identification (biology) , action recognition , process (computing) , identity (music) , feature (linguistics) , artificial intelligence , interpersonal communication , human–computer interaction , pattern recognition (psychology) , psychology , communication , linguistics , philosophy , botany , physics , quantum mechanics , acoustics , biology , class (philosophy) , operating system
Human action recognition plays a big role in human-to-human interaction and interpersonal relations. As a result, it provides information regarding the identity of someone, their temperament, and condition, it’s tough to extract. Recognition of actions within the video isn’t a matter for human sensory system. The identification of the actions of the person by the system wants someone special mechanisms. The identification of the actions by the systems are going to be useful in computer vision method. This method is divided into low level action recognition process and high level recognition process. Recognizing the actions victimization the one feature values extracted goes under low level action recognition method. These method is simple to implement and that they don’t seem to be reliable all the time. The high level action recognition method needs some special hardware’s to discover the actions within the video. The experimental results proved that the proposed methodology achieved better performance in terms of accuracy, sensitivity and specificity.