TR2005-076
Systematic Acquisition of Audio Classes for Elevator Surveillance
-
- "Systematic Acquisition of Audio Classes for Elevator Surveillance", SPIE Conference on Image and Video Communications and Processing, March 2005, vol. 5685, pp. 64-71.BibTeX TR2005-076 PDF
- @inproceedings{Radhakrishnan2005mar,
- author = {Radhakrishnan, R. and Divakaran, A.},
- title = {Systematic Acquisition of Audio Classes for Elevator Surveillance},
- booktitle = {SPIE Conference on Image and Video Communications and Processing},
- year = 2005,
- volume = 5685,
- pages = {64--71},
- month = mar,
- url = {https://www.merl.com/publications/TR2005-076}
- }
,
- "Systematic Acquisition of Audio Classes for Elevator Surveillance", SPIE Conference on Image and Video Communications and Processing, March 2005, vol. 5685, pp. 64-71.
-
Research Areas:
Abstract:
We present a systematic framework for arriving at audio classes for detection of crimes in elevators. We use our time series analysis framework proposed in5 to low-level features extracted from the audio of an elevator surveillance content to perform an inlier/outlier based temporal segmentation. Since suspicious events in elevators are outliers in a background of usual events, such a segmentation help bring out such events without any a priori knowledge. Then, by performing an automatic clustering on the detected outliers, we identify consistent patterns for which we can train supervised detectors. We apply the proposed framework to a colleciton of elevator surveillance audio data to systematically acquire audio classes such as banging, footsteps, non-neutral speech and normal speech etc. Based on the observation that the banging audio class and non-neutral speech class are indicative of suspicous events in the elevator data set, we are able to detect all of the suspicious activities without any misses.
Related News & Events
-
NEWS SPIE Conference on Image and Video Communications and Processing 2005: 2 publications by Oncel Tuzel and Ajay Divakaran Date: March 15, 2005
Where: SPIE Conference on Image and Video Communications and Processing
Research Area: Computer VisionBrief- The papers "Systematic Acquisition of Audio Classes for Elevator Surveillance" by Radhakrishnan, R. and Divakaran, A. and "Object Tracking in Low-Frame-Rate Video" by Porikli, F. and Tuzel, O. were presented at the SPIE Conference on Image and Video Communications and Processing.