Abnormal Event Detection Method in Multimedia Sensor Networks

Qi Li,Xinyu Yang,Ting Li,Xiaoming Liu

doi:10.1155/2015/154658

Abstract

Detecting abnormal events in multimedia sensor networks (MSNs) plays an increasingly essential role in our lives. Once video cameras cannot work (e.g., the sightline is blocked), audio sensor can provide us with critical information (e.g., in detecting the sound of gun-shot in the rainforest or the sound of car accident on a busy road). Audio sensors also have price advantage. Detecting abnormal audio events in complicated background environment is a very difficult problem; only few previous researches could offer good solution. In this paper, we proposed a novel method to detect the unexpected audio elements in multimedia sensor networks. Firstly, we collect enough normal audio elements and then use statistical learning method to train them offline. On the basis of these models, we establish a background pool by prior knowledge. The background pool contains expected audio effects. Finally, we decide whether an audio event is unexpected by comparing it with the background pool. In this way, we reduce the complexity of online training while ensuring the detection accuracy. We designed some experiments to verify the effectiveness of the proposed method. In conclusion, the experiments show that the proposed algorithm can achieve satisfying results.

Highlights

Nowadays, multimedia sensor networks (MSNs) become increasingly popular and important in our everyday lives [1, 2]
We decide whether an audio event is unexpected by comparing it with the background pool
We choose 4 different types of abnormal audio elements to evaluate the performance of the background pool model (BGP), namely, engine, animal screams, gun-shot, and tapping sound of sticks

Summary

Introduction

Multimedia sensor networks (MSNs) become increasingly popular and important in our everyday lives [1, 2]. It is becoming increasingly critical to use audio sensors to improve the effectiveness for monitoring systems, especially when video cameras cannot work effectively (e.g., the sightline is blocked). We set the transition probabilities between these expected audio effects by some prior knowledge By this way, we have established a hierarchical model, background pool model, to detect the unexpected audio effect. We have established a hierarchical model, background pool model, to detect the unexpected audio effect The advantage of this approach lies in the fact that we can reduce the costs of online training through training each basic audio effect model offline. The background pool will change in accordance with different monitoring environments

Objectives

Results

Conclusion