Classification of Vehicles Based on Audio Signals using Quadratic Discriminant Analysis and High Energy Feature Vectors

Abstract

The focusof this paper is on classification of different vehicles using sound emanated from the vehicles. In this paper,quadratic discriminant analysis classifies audio signals of passing vehicles to bus, car, motor, and truck categories based on features such as short time energy, average zero cross rate, and pitch frequency of periodic segments of signals. Simulation results show that just by considering high energy feature vectors, better classification accuracy can be achieved due to the correspondence of low energy regions with noises of the background. To separate these elements, short time energy and average zero cross rate are used simultaneously.In our method,we have used a few features which are easy to be calculated in time domain and enable practical implementation of efficient classifier. Although, the computation complexity is low, the classification accuracy is comparable with other classification methodsbased on long feature vectors reported in literature for this problem.

Acoustic Vehicle Classification Using Mel-Frequency Features with Long Short-Term Memory Neural Networks

“…Previously, ML-based classification was focused on supervised machine learning approach, consisting of two stages: extracting 'hand-crafted' features from audio signals, followed by classifying the features using a classifier algorithm. Commonly used features include Mel Frequency Cepstral Coefficients (MFCC) [11], [12], other less studied features includes harmonics components [13], [14], and spectral based features such as zero-crossing rate [15], pitch frequency [16] while k-nearest neighbour (k-NN) [11] support vector machine (SVM) [17], and artificial neural-network (ANN) [18] are the commonly used classifier algorithms. However, this approach can be problematic due to the potential bias and uncertainty of the expert creating the features, as well as the difficulty of acquiring prior knowledge of optimal features from large datasets.…”

A new spectral estimation-based feature extraction method for vehicle classification in distributed sensor networks

“…Sensor networks are common to use for human/animal classification [2], human footstep discrimination [3], condition monitoring in the railway industry [4], vehicle detection and classification [5,6], urban traffic management [7], vehicle speed estimation [8], supporting environments for multimedia surveillance [9], or discriminating humans, animals, and vehicles [10]. Tracked and trackless vehicle detection and classification with distributed sensor networks as a counter camouflage technique is also one of the popular application areas [11].…”