Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/611496
Title: Interactive Crowd-Behavior Learning for Surveillance and Training
Authors: Aniket Bera;Sujeong Kim;Dinesh Manocha
subject: computer graphics|interactive crowd behavior|anomaly detection|pedestrian motion|defense applications|interactive computer graphics
Year: 2016
Publisher: IEEE
Abstract: The proposed interactive crowd-behavior learning algorithms can be used to analyze crowd videos for surveillance and training applications. The authors' formulation combines online tracking algorithms from computer vision, nonlinear pedestrian motion models from computer graphics, and machine learning techniques to automatically compute trajectory-level pedestrian behaviors for each agent in the video. These learned behaviors are used to automatically detect anomalous behaviors, perform motion segmentation, and generate realistic behaviors for virtual reality training applications.
Description: 
URI: http://localhost/handle/Hannan/142790
http://localhost/handle/Hannan/611496
ISSN: 0272-1716
volume: 36
issue: 6
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7750521.pdf2.92 MBAdobe PDFThumbnail
Preview File
Title: Interactive Crowd-Behavior Learning for Surveillance and Training
Authors: Aniket Bera;Sujeong Kim;Dinesh Manocha
subject: computer graphics|interactive crowd behavior|anomaly detection|pedestrian motion|defense applications|interactive computer graphics
Year: 2016
Publisher: IEEE
Abstract: The proposed interactive crowd-behavior learning algorithms can be used to analyze crowd videos for surveillance and training applications. The authors' formulation combines online tracking algorithms from computer vision, nonlinear pedestrian motion models from computer graphics, and machine learning techniques to automatically compute trajectory-level pedestrian behaviors for each agent in the video. These learned behaviors are used to automatically detect anomalous behaviors, perform motion segmentation, and generate realistic behaviors for virtual reality training applications.
Description: 
URI: http://localhost/handle/Hannan/142790
http://localhost/handle/Hannan/611496
ISSN: 0272-1716
volume: 36
issue: 6
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7750521.pdf2.92 MBAdobe PDFThumbnail
Preview File
Title: Interactive Crowd-Behavior Learning for Surveillance and Training
Authors: Aniket Bera;Sujeong Kim;Dinesh Manocha
subject: computer graphics|interactive crowd behavior|anomaly detection|pedestrian motion|defense applications|interactive computer graphics
Year: 2016
Publisher: IEEE
Abstract: The proposed interactive crowd-behavior learning algorithms can be used to analyze crowd videos for surveillance and training applications. The authors' formulation combines online tracking algorithms from computer vision, nonlinear pedestrian motion models from computer graphics, and machine learning techniques to automatically compute trajectory-level pedestrian behaviors for each agent in the video. These learned behaviors are used to automatically detect anomalous behaviors, perform motion segmentation, and generate realistic behaviors for virtual reality training applications.
Description: 
URI: http://localhost/handle/Hannan/142790
http://localhost/handle/Hannan/611496
ISSN: 0272-1716
volume: 36
issue: 6
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7750521.pdf2.92 MBAdobe PDFThumbnail
Preview File