A diffusion framework for detection of moving vehicles

Automatic acoustic-based vehicle detection is a common task in security and surveillance systems. Usually, a recording device is placed in a designated area and a hardware/software system processes the sounds that are intercepted by this recording device to identify vehicles only as they pass by. We propose a novel algorithm for the real-time detection of vehicles based on their recordings. The algorithm uses the wavelet-packet transform in order to extract spatio-temporal characteristic features from the recordings where the underlying assumption is that these features constitute a unique acoustic signature for each of the recordings. The feature extraction procedure is followed by the Diffusion Maps (DM) dimensionality reduction algorithm which further reduces the size of the signature. A new recording is classified 1 

• Type: Journal
• Year: 2010
• Where: DSP
• Authors: Alon Schclar, Amir Averbuch, N. Rabin, Valery A. Zheludev, K. Hochman
• Keywords: Algorithm, Automatic Acoustic-based Vehicle, DSP 2010, Emerging Technology, Recording Device