Recognition of Moving Tracked and Wheeled Vehicles Based on Sound Analysis and Machine Learning Algorithms

Abstract

The paper presents results of a preliminary study on verification of the possibility to establish simple methods to process acquired sound signals that were generated by a vehicle in motion; to determine its characteristic features for classification as a wheeled or tracked one. The analysis covered 220 signals acquired from real experiment and pre-processed with the use of power spectral density estimation (PSD) and linear prediction coding (LPC). The signal processing methods were used to generate features for which applicability in the classification process was assessed using a statistical method. The set of features was then optimised to reduce the dimensionality of data. Results of recognition obtained with the proposed non-iterative procedures for solving linearly separable problems were compared with results from standard methods, including SVM and k-NN. The developed features as well as selected methods of classification were proposed with respect to the possibility to implement them in low computational power computers for embedded applications.

Determining the trajectory of the vehicle motion on the basis of the recorded physical quantities describing its dynamics during typical maneuvers in road traffic

“…during the modeling of autonomous lane change algorithms [1,2], compliance of technological solutions with applicable normative documents, e.g. LDWS (Lane Departure Warning System) or experts analyzing the records of UDS (Unfall Daten Speicher) or ADR (Accident Data Recorder) black boxes [3] or during modelling vehicle dynamics [4,5,6]. Determination of the trajectory of the vehicle motion takes place in the global reference system with the use of kinematic relationships in a situation where linear accelerations, angular velocities and linear velocities in the local system were measured directly.…”

Methods for determining the physical quantities describing the vehicle movement and the driver during a road accident

“…Obtaining physical quantities describing the movement of vehicles and people is of interest to many entities researching: passive safety systems [1,2,3], active safety systems e.g. during the modelling of autonomous lane change algorithms [4,5,6], dynamics of movement [7], compliance of technological solutions with the applicable standard documents, e.g. LDWS (Lane Departure Warning System), experts analyzing the records of UDS (Unfall Daten Speicher), ADR (Accident Data Recorder) black boxes [8,9], or road accidents experts [10,11].…”