Chainsaw Sound Detection Based on Spectral Haar Coeffluents

Abstract

Illegal deforestation endangers the environment and facilitates the appearance of natural disasters as flooding and landslides. These actions lead also to major climate changes and to global warming. Illegal deforestation can be detected through a sound based monitoring system that records environmental sounds and decides whether the sound is generated by a chainsaw or the source is different. This paper presents a novel method of sound classification based on Haar like features extracted from the frequency domain and provides comparisons with other methods found in the related literature.