Detection of human activities in natural environments based on their acoustic emissions

In this work we address the problem of detecting human activities in natural environments based solely on the respective acoustic emissions. The primary goal is the continuous acoustic surveillance of a particular natural scene for illegal human activities (trespassing, hunting etc.) in order to promptly alert an authorized officer for taking the appropriate measures. We constructed a novel system which is mainly characterized by its hierarchical structure as well as the variety of the acoustic parameters. Each sound class is represented by a hidden Markov model created using descriptors from the time, frequency and wavelet domains. We conducted extensive experiments for assessing the performance of the system with respect to its recognition and detection capabilities.