Paper Info
Title
Kintense: a robust, accurate, real-time and evolving system for detecting aggressive actions from streaming 3D skeleton data
Abstract
Kintense is a robust, accurate, real-time, and evolving system for detecting aggressive actions such as hitting, kicking, pushing, and throwing from streaming 3D skeleton joint coordinates obtained from Kinect sensors. Kintense uses a combination of: (1) an array of supervised learners to recognize a predefined set of aggressive actions, (2) an unsupervised learner to discover new aggressive actions or refine existing actions, and (3) human feedback to reduce false alarms and to label potential aggressive actions. This abstract provides an overview of the design and implementation of Kintense and provides empirical evidence that Kintense is 11% -- 16% more accurate when compared to standard techniques such as dynamic time warping (DTW) and posture based gesture recognizers.
Year
DOI
Venue
2013
10.1109/PerCom.2014.6813937
Pervasive Computing and Communications
Keywords
Field
DocType
gesture recognition,unsupervised learning,accuracy,vectors,sensors,image sensors
Evolving systems,Dynamic time warping,Gesture,Computer science,Throwing,Real-time computing,Artificial intelligence,Machine learning
Conference
ISSN
Citations 
PageRank 
2474-2503
6
0.80
References 
Authors
15
10
Name
Order
Citations
PageRank
Shahriar Nirjon122426.55
Chris Greenwood271.15
Carlos Torres360.80
Stefanie Zhou460.80
John A. Stankovic572.50
Hee Jung Yoon671.49
Ho-Kyeong Ra7166.51
Can Başaran8877.72
Tae-joon Park934937.39
Sang H. Son102433202.20