Fall detection in multi-camera surveillance videos: experimentations and observations

Wang, Sen, Xu, Zhongwen, Yang, Yi, Li, Xue, Pang, Chaoyi and Haumptmann, Alexander G. (2013). Fall detection in multi-camera surveillance videos: experimentations and observations. In: Alexia Briasouli, Jenny Benois-Pineau and Alexander Hauptmann, MIIRH 2013: Proceedings of the 1st ACM International Workshop on Multimedia Indexing and Information Retrieval for Heathcare. 1st ACM International Workshop on Multimedia Indexing and Information Retrieval for Heathcare (MIIRH 2013), Barcelona, Spain, (33-38). 22 October 2013. doi:10.1145/2505323.2505331

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Wang, Sen
Xu, Zhongwen
Yang, Yi
Li, Xue
Pang, Chaoyi
Haumptmann, Alexander G.
Title of paper Fall detection in multi-camera surveillance videos: experimentations and observations
Conference name 1st ACM International Workshop on Multimedia Indexing and Information Retrieval for Heathcare (MIIRH 2013)
Conference location Barcelona, Spain
Conference dates 22 October 2013
Proceedings title MIIRH 2013: Proceedings of the 1st ACM International Workshop on Multimedia Indexing and Information Retrieval for Heathcare
Journal name MIIRH 2013 - Proceedings of the 1st ACM International Workshop on Multimedia Indexing and Information Retrieval for Heathcare, Co-located with ACM Multimedia 2013
Place of Publication New York, United States
Publisher ACM
Publication Year 2013
Sub-type Fully published paper
DOI 10.1145/2505323.2505331
Open Access Status
ISBN 9781450323987
Editor Alexia Briasouli
Jenny Benois-Pineau
Alexander Hauptmann
Start page 33
End page 38
Total pages 6
Collection year 2014
Abstract/Summary This paper presents our study on fall detection for ageing care monitoring. We collected a choreographed multi-camera dataset that contains fall actions and other actions such as walking, standing up, sitting down and so forth. In our work, MoSIFT feature is extracted from the videos recorded by each camera. We conduct a series of experiments to show the performance variations of fall detection when different methods are used. We first compare the performance of the standard Bag-of-Words and spatial Bag-of-Words with different codebook sizes. Then, we test different fusion methods which combines the information from the videos recorded by two orthogonally deployed cameras, where a non-linear χ2 kernel Support Vector Machine (SVM) is trained to detect fall actions. In addition, we also use explicit feature maps along with linear kernel for fall detection and compare it to the standard bag of word representation with a non-linear χ2 kernel. Our experiment results show that late fusion of Bag-of-Words with a 1000 centers codebook obtains the best performance. The best result reaches 90.46% in average precision, which in turn may provide a more independent and safer living environment for the elderly.
Subjects 1704 Computer Graphics and Computer-Aided Design
1710 Information Systems
2718 Health Informatics
Keyword Automatic geriatric care
Fall detection
Video surveillance
Q-Index Code E1
Q-Index Status Confirmed Code
Institutional Status UQ
Additional Notes The 1st ACM International Workshop on Multimedia Indexing and Information Retrieval for Heathcare (MIIRH 2013) was part of the 21st ACM International Conference on Multimedia (ACM Multimedia 2013) held from 21-25 October 2013 in Barcelona, Spain.

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 1 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 03 Dec 2013, 00:44:50 EST by System User on behalf of Scholarly Communication and Digitisation Service