Novelty detection in the machine learning context refers to identifying unknown/novel data, i.e., data which vary greatly from the ones that the system was trained with. This paper explores this technique as applied to acoustic surveillance of abnormal situations. The ultimate goal of the system is to help an authorized person towards taking the appropriate actions for preventing life/property loss. A wide variety of acoustic parameters is employed towards forming a multidomain feature vector, which captures diverse characteristics of the audio signals. Subsequently the feature coefficients are fed to three probabilistic novelty detection methodologies. Their performance is computed using two measures which take into account misdetections and false alarms. Out dataset was recorded under real-world conditions including three different locations where various types of normal and abnormal sound events were captured. A smart-home environment, an open public space, and an office corridor were used. The results indicate that probabilistic novelty detection can provide an accurate analysis of the audio scene to identify abnormal events.
Probabilistic novelty detection for acoustic surveillance under real-world conditions / S. Ntalampiras, I. Potamitis, N. Fakotakis. - In: IEEE TRANSACTIONS ON MULTIMEDIA. - ISSN 1520-9210. - 13:4(2011 Aug), pp. 5723010.713-5723010.719.
|Titolo:||Probabilistic novelty detection for acoustic surveillance under real-world conditions|
|Parole Chiave:||Audio signal processing; MPEG-7 standard; probabilistic novelty detection; public safety; wavelet packets; Signal Processing; Media Technology; Computer Science Applications1707 Computer Vision and Pattern Recognition; Electrical and Electronic Engineering|
|Settore Scientifico Disciplinare:||Settore INF/01 - Informatica|
|Data di pubblicazione:||ago-2011|
|Digital Object Identifier (DOI):||http://dx.doi.org/10.1109/TMM.2011.2122247|
|Appare nelle tipologie:||01 - Articolo su periodico|