Audio Events Detection in Public Transport Vehicle

Abstract

Abstract-This paper addresses the problem of automatic audio analysis for aided surveillance application in public transport. The aim of such application is to detect critical situations and to warn the control room. We propose a comparative study of two methods of modelisation/classification of acoustical segments. The problem is quite similar to the "'audio indexing"' framework, nevertheless the environment here is very noisy. We present two general frameworks based on Gaussian Model Mixture (GMM) and Support Vector Machine (SVM) to achieve shout detection in railway embedded environment.

An overview of applications and advancements in automatic sound recognition

“…While audio surveillance can be seen as a subclass of sound event recognition, there are some differences as discussed in Section 4.1. Applications of audio surveillance and sound event recognition systems include security monitoring in a room [11] and public transport [12], intruder detection in wildlife areas [13], and monitoring of elderly people, also referred as medical telemonitoring [14]. Environmental sound recognition poses a greater challenge when compared to audio surveillance and sound event recognition applications.…”

A Relational Database Model and Tools for Environmental Sound Recognition

“…In [9] and [10], ESR is used for recognition of animal sounds. In the surveillance area, it is used for surveillance of road [11], public transport [12], elevator [13] and office corridor [14].designations. ESR system design is started with the training phase.…”

Scream and gunshot detection and localization for audio-surveillance systems

“…For this reason, research on automatic surveillance systems has recently received particular attention. In particular, the use of audio sensors in surveillance and monitoring applications has proved to be particularly useful for the detection of events like screams or gunshots [1] [2]. Such detection systems can be efficiently used to signal to an automated system that an event has occurred and, at the same time, to enable further processing like acoustic source localization for steering a video-camera.…”

“…This hierarchical approach has been employed in [2] to design a specific system able to detect screams/shouts in public transport environments. A slightly different technique is used in [1] to detect gunshots in public environments.…”