Citation

Ismail NN, Rashid NEA, Nasarudin MNF, Mohamed WMW, Zainuddin S, Khan ZI. Plann. Malays. 2023; 21(4): 13-23.

Copyright

(Copyright © 2023, Malaysian Institute of Planners)

DOI

10.21837/pm.v21i28.1312

PMID

unavailable

Abstract

The importance of automatic vehicle detection and classification has grown significantly in recent years, as it has become a crucial component of traffic management and monitoring systems. To overcome the limitations of traditional video vehicle detection, this paper proposes the use of forward scatter radar (FSR) technology. The FSR system is tested for the classification of four different vehicle types, each with distinct sizes. To improve the classification accuracy of the FSR system, the paper utilizes a well-established neural network known as a convolutional neural network (CNN). Two time-frequency analyses, continuous wavelet transform (CWT) and short-time Fourier transform (STFT), are used to evaluate the classification performance of the FSR system. The study demonstrates that the CNN classifier significantly improves the classification accuracy of the FSR system in vehicle detection and classification. This finding is supported by the evaluation of the time-frequency analyses, CWT and STFT. Overall, the proposed approach has the potential to enhance traffic management and monitoring systems, thereby improving road safety and traffic efficiency.

Language: en

Keywords

Continuous Wavelet Transform (CWT); Convolutional Neural Network (CNN); Forward Scatter Radar (FSR); Short-time Fourier Transform (STFT); Vehicle Classification