TY - JOUR
T1 - Gesture recognition using low-cost devices: Techniques, applications, perspectives
AU - Gentile, Vito
AU - Sorce, Salvatore
AU - Malizia, Alessio
AU - Gentile, Antonio
PY - 2016/4/1
Y1 - 2016/4/1
N2 - In the last decades, we have witnessed to the increase of the socalled Kinect-like devices, which are based on a set of low-cost sensors to acquire RGB and depth data of a scene. The high accessibility of such devices, mainly in terms of costs, has pushed their adoption as fundamental tool for gesture recognition in a large number of applications, both commercial and research-related ones. In this paper, we first discuss some of the general principles adopted by most of the main gesture recognition techniques described in literature. Then we present some application fields in which Kinect-like devices and gesture recognition algorithms have been used, ranging from educational-recreational examples to more complex and scientific fields (e.g. domotics, robotics and biomedical engineering). In two annexes, we list and shortly compare the main features of the Kinect-like devices available on the market, and we describe one of the most popular algorithm for skeletal tracking, which is the basis for the gesture recognition.
AB - In the last decades, we have witnessed to the increase of the socalled Kinect-like devices, which are based on a set of low-cost sensors to acquire RGB and depth data of a scene. The high accessibility of such devices, mainly in terms of costs, has pushed their adoption as fundamental tool for gesture recognition in a large number of applications, both commercial and research-related ones. In this paper, we first discuss some of the general principles adopted by most of the main gesture recognition techniques described in literature. Then we present some application fields in which Kinect-like devices and gesture recognition algorithms have been used, ranging from educational-recreational examples to more complex and scientific fields (e.g. domotics, robotics and biomedical engineering). In two annexes, we list and shortly compare the main features of the Kinect-like devices available on the market, and we describe one of the most popular algorithm for skeletal tracking, which is the basis for the gesture recognition.
UR - http://www.scopus.com/inward/record.url?scp=84973590850&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:84973590850
SN - 1720-898X
VL - 15
SP - 161
EP - 169
JO - Mondo Digitale
JF - Mondo Digitale
IS - 63
ER -