Welcome to the InfoSci Platform
Vehicle Type Classification Using Hybrid Features and a Deep Neural Network

Vehicle Type Classification Using Hybrid Features and a Deep Neural Network

Sathyanarayana N., Anand M. Narasimhamurthy
Copyright: © 2022 |Volume: 13 |Issue: 1 |Pages: 22
ISSN: 1947-8283|EISSN: 1947-8291|EISBN13: 9781799885405|DOI: 10.4018/IJAMC.292518
Cite Article Cite Article

MLA

N., Sathyanarayana, and Anand M. Narasimhamurthy. "Vehicle Type Classification Using Hybrid Features and a Deep Neural Network." IJAMC vol.13, no.1 2022: pp.1-22. http://doi.org/10.4018/IJAMC.292518

APA

N., S. & Narasimhamurthy, A. M. (2022). Vehicle Type Classification Using Hybrid Features and a Deep Neural Network. International Journal of Applied Metaheuristic Computing (IJAMC), 13(1), 1-22. http://doi.org/10.4018/IJAMC.292518

Chicago

N., Sathyanarayana, and Anand M. Narasimhamurthy. "Vehicle Type Classification Using Hybrid Features and a Deep Neural Network," International Journal of Applied Metaheuristic Computing (IJAMC) 13, no.1: 1-22. http://doi.org/10.4018/IJAMC.292518

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Currently, considerable research has been done in vehicle type classification, especially due to the success of deep learning in many image classification problems. In this research, a system incorporating hybrid features is proposed to improve the performance of vehicle type classification. The feature vectors are extracted from the pre-processed images using Gabor features, a histogram of oriented gradients and a local optimal oriented pattern. The hybrid set of features contains complementary information that could help discriminate between the classes better, further, an ant colony optimizer is utilized to reduce the dimension of the extracted feature vectors. Finally, a deep neural network is used to classify the types of vehicles in the images. The proposed approach was tested on the MIO vision traffic camera dataset and another more challenging real-world dataset consisting of videos of multiple lanes of a toll plaza. The proposed model showed an improvement in accuracy ranging from 0.28% to 8.68% in the MIO TCD dataset when compared to well-known neural network architectures.