Vehicle Feature Extraction Method Based on Gammatone Filter Bank

Abstract

The invention discloses a vehicle model feature extraction method based on a Gammatone filter bank, belongs to the field of mode recognition, and relates to a method for feature extraction of a vehicle radiation sound signal, specifically to a method for feature extraction which simulates hearing characteristics of human ears by calculating a cepstrum coefficient of the vehicle sound signal under the Gammatone filter bank. The method can simulate the characteristic of nonlinear frequency resolution of human ears by using the Gammatone filter bank, and divides vehicle sound signal filtering into different sub-band signals and obtains a cepstrum coefficient. Based on the principle of frequency resolution in the hearing characteristics, the vehicle model feature extraction method based on the Grammatone filter bank extracts a Grammatone cepstrum coefficient from the vehicle sound signal, and obtains frequency band-energy features of an original signal, involved calculation concerns commonly-used signal processing techniques, the principle is simple, the steps are clear, programming realization is facilitated, and the applicability is wide.

Description

technical field [0001] The invention belongs to the field of pattern recognition, and relates to a feature extraction method of a vehicle radiated acoustic signal, specifically a feature extraction method for calculating the cepstral coefficient of a vehicle acoustic signal under a Gammatone filter bank, and the obtained features can simulate the hearing of the human ear characteristic. Background technique [0002] The process of car model recognition mainly includes two parts: feature extraction and classifier training and recognition. Feature extraction is one of the key technologies of pattern recognition, and using vehicle movement to generate acoustic signals to classify and recognize them is an important way for vehicle model recognition. Vehicle identification is widely used in areas such as traffic management, regional protection, and important areas of warning. [0003] At present, the feature extraction of vehicle acoustic signals is mainly based on the frequenc...

AI Technical Summary

Problems solved by technology

[0003] At present, the feature extraction of vehicle acoustic signals is mainly based on the frequency characteristics of the signal. The AR parameter model is a widely used spectrum analysis method for calculating the signal power spectrum. It has strict theoretical support and mature technical implementation. , it is very difficult to improve the accuracy of feature classification; in addition, there is an energy coefficient feature extraction method based on wavelet and wavelet packet, which further improves the classification accuracy of features, but its principle is profound and the implementation is complicated; Frequency-based feature extraction methods based on new principles such as spectral analysis, Mel cepstral coefficients, and empirical mode decomposition can obtain relatively accurate acoustic signal features, but overall, the amount of calculation is large, the implementation is complicated, and some extraction methods are not sensitive to the background Strong noise dependence, limited application

Images