TY - GEN
T1 - Hand gesture detection and tracking methods based on background subtraction
AU - Song, Wei
AU - Lu, Zixiao
AU - Li, Jinhong
AU - Li, Jie
AU - Liao, Jinqiao
AU - Cho, Kyungeun
AU - Um, Kyhyun
PY - 2014
Y1 - 2014
N2 - This paper combines the background subtraction and frame difference methods to detect a moving-hand area. Currently, hand-gesture recognition contains the following parts: hand area detection, hand tracking, and recognition. In this paper, we describe the moving-hand area detection and tracking parts of our work. First, we constructed a background image model that did not contain a moving hand. Then, using a background updating algorithm to obtain the authentic background image, we obtained the moving-hand area by subtracting the current image frame from the background image frame. We utilized a novel dynamic threshold method to enhance detection. We used the Microsoft Kinect to track the hand region because Kinect can capture information about the human body and the position of various body parts. The experiments demonstrated that our methods can be used to detect a moving region from an original image.
AB - This paper combines the background subtraction and frame difference methods to detect a moving-hand area. Currently, hand-gesture recognition contains the following parts: hand area detection, hand tracking, and recognition. In this paper, we describe the moving-hand area detection and tracking parts of our work. First, we constructed a background image model that did not contain a moving hand. Then, using a background updating algorithm to obtain the authentic background image, we obtained the moving-hand area by subtracting the current image frame from the background image frame. We utilized a novel dynamic threshold method to enhance detection. We used the Microsoft Kinect to track the hand region because Kinect can capture information about the human body and the position of various body parts. The experiments demonstrated that our methods can be used to detect a moving region from an original image.
KW - Background subtraction
KW - Background updating methods
KW - Dynamic threshold
KW - Kinect
KW - Skeleton information
UR - http://www.scopus.com/inward/record.url?scp=84902377742&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-55038-6_76
DO - 10.1007/978-3-642-55038-6_76
M3 - Conference contribution
AN - SCOPUS:84902377742
SN - 9783642550379
T3 - Lecture Notes in Electrical Engineering
SP - 485
EP - 490
BT - Future Information Technology
PB - Springer Verlag
T2 - 9th FTRA InternationalConference on Future Information Technology, FutureTech 2014
Y2 - 28 May 2014 through 31 May 2014
ER -