Title :
Acoustic based abnormal event detection using robust feature compensation
Author :
Sasou, Akira ; Tanaka, Kouki ; Tanaka, Shinichi ; Tanimoto, Masumi
Author_Institution :
Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan
Abstract :
In addition to traditional video-surveillance applications, the use of acoustic surveillance is becoming increasingly important. The acoustic clues are appropriate for detecting target that are hidden or in a dark location and assumed to make a sound. In the conventional acoustic surveillance systems, the false alarms tend to frequently occur because the conventional acoustic surveillance systems are not robust against the interferences of other sounds. In this study, in order to overcome the conventional difficulty, we apply the Hidden Markov Model (HMM) based robust recognizer with feature compensation to the detection of glass destruction sounds. Experimental results confirmed that the feature compensation method is effective not only to speech signals but also to the material sounds like the glass destruction sound.
Keywords :
acoustic signal detection; hidden Markov models; surveillance; HMM; acoustic based abnormal event detection; acoustic surveillance systems; glass destruction sound; hidden Markov model; robust feature compensation; speech signals; video-surveillance applications; Acoustics; Gaussian distribution; Glass; Hidden Markov models; Noise; Surveillance; HMM; acoustic surveillance; feature compensation; glass destruction sound;
Conference_Titel :
TENCON 2011 - 2011 IEEE Region 10 Conference
Conference_Location :
Bali
Print_ISBN :
978-1-4577-0256-3
DOI :
10.1109/TENCON.2011.6129103