Welcome to the InfoSci Platform
Reference Hub1
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: 10 |Issue: 1 |Pages: 18
ISSN: 2166-7160|EISSN: 2166-7179|EISBN13: 9781683182832|DOI: 10.4018/IJSI.297511
Cite Article Cite Article

MLA

Sathyanarayana N., and Anand M. Narasimhamurthy. "Vehicle Type Classification Using Hybrid Features and a Deep Neural Network." IJSI vol.10, no.1 2022: pp.1-18. http://doi.org/10.4018/IJSI.297511

APA

Sathyanarayana N. & Narasimhamurthy, A. M. (2022). Vehicle Type Classification Using Hybrid Features and a Deep Neural Network. International Journal of Software Innovation (IJSI), 10(1), 1-18. http://doi.org/10.4018/IJSI.297511

Chicago

Sathyanarayana N., and Anand M. Narasimhamurthy. "Vehicle Type Classification Using Hybrid Features and a Deep Neural Network," International Journal of Software Innovation (IJSI) 10, no.1: 1-18. http://doi.org/10.4018/IJSI.297511

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In this research, a framework incorporating hybrid features is proposed to improve the performance of vehicle type classification. The proposed model includes a camera response model to enhance the collected images and a Gaussian mixture model to localize the object of interest. The feature vectors are extracted from the pre-processed images using Gabor features, histogram of oriented gradients, and local optimal-oriented pattern. The hybrid set of features discriminate the classes better; further, an ant colony optimizer is used to reduce the dimension of the extracted feature vectors. Finally, deep neural network is used to classify the types of vehicles in the images. The proposed model was tested on the MIO vision traffic camera dataset and a 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 like AlexNet, Inception V3, ResNet 50, VGG 19, Xception, and DenseNet.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.