Title :
Recognizing participants in interaction from observation of office environments
Author :
Kizumi, Yuki ; Kakusho, Koh ; Okadome, Takeshi ; Funatomi, Takuya ; Iiyama, Masaaki
Author_Institution :
Kwansei Gakuin Univ., Sanda, Japan
Abstract :
In this article, we discuss how to recognize each group of humans and objects that interact with each other, for some activity such as a conversation by some people looking at the same screen, from observation by cameras. Although the previous work on recognizing human behaviors by cameras mainly discusses those of a single person, such as moving from one place to another, we rather focus on the interactions that happen to occur among multiple humans and objects, because many human behaviors appear in the form of interaction with the others. By assuming an open office environment where many people are working by sharing the same space, we aim to recognize which persons, together with which objects, are currently interacting with each other, as well as which area of the environment is occupied by the interaction.
Keywords :
behavioural sciences computing; computer vision; image sensors; object recognition; office environment; user interfaces; computer vision; human behavior recognition; open office environment; participant recognition; Cameras; Humans; Image processing; Level set; Shape; Silicon; Three dimensional displays;
Conference_Titel :
System Integration (SII), 2011 IEEE/SICE International Symposium on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4577-1523-5
DOI :
10.1109/SII.2011.6147474