For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
Vehicle recognition is the important information detected in intelligent transportation systems. Mature research methods mostly use induction coils, lasers, cameras, etc. for recognition, while the use of radar for vehicle recognition is relatively rare. This paper proposes a vehicle identification technology based on the multi-feature-SVM method, which processes millimeter-wave radar echo data, adopts vehicle length acquisition technology based on one-dimensional range spectrum broadening method and target scattering cross-sectional area acquisition based on gain compensation method Technology, extract the two effective vehicle identification features of vehicle length and target scattering cross-sectional area, obtain temporary vehicle classification results through the SVM best model, and finally combine the multi-frame fusion method to remove random errors that may occur in the discrimination process to ensure the reliability of the output results. The results show that the vehicle identification method proposed in this paper can achieve 92% accuracy, ideal results and strong practicability.
Inspec keywords: image fusion; traffic engineering computing; support vector machines; intelligent transportation systems; radar signal processing; road vehicles; image classification; feature extraction; millimetre wave devices
Subjects: Computer vision and image processing techniques; Support vector machines; Radar equipment, systems and applications; Signal processing and detection; Microwave circuits and devices; Optical, image and video signal processing; Traffic engineering computing