Cited 0 time in webofscience Cited 2 time in scopus

Demo abstract: Kintense: A robust, accurate, real-time and evolving system for detecting aggressive actions from streaming 3D skeleton data

Title
Demo abstract: Kintense: A robust, accurate, real-time and evolving system for detecting aggressive actions from streaming 3D skeleton data
Authors
Nirjon, ShahriarGreenwood, ChrisTorres, CarlosZhou StefanieStankovic, John A.Yoon, Hee JungRa, Ho-KyeongBasaran, CanPark, TaejoonSon, Sang H.
DGIST Authors
Yoon, Hee Jung; Ra, Ho-Kyeong; Basaran, Can; Park, Taejoon; Son, Sang H.
Issue Date
2013
Citation
11th ACM Conference on Embedded Networked Sensor Systems, SenSys 2013
Type
Conference
Article Type
Conference Paper
ISBN
9780000000000
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.
URI
http://hdl.handle.net/20.500.11750/3810
DOI
10.1145/2517351.2517396
Publisher
Association for Computing Machinery
Related Researcher
  • Author Son, Sang Hyuk RTCPS(Real-Time Cyber-Physical Systems Research) Lab
  • Research Interests
Files:
There are no files associated with this item.
Collection:
ETC2. Conference Papers


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE