Citation: Alghamdi, A.S.; Saeed, A.;
Kamran, M.; Mursi, K.T.;
Almukadi, W.S. Vehicle
Classification Using Deep Feature
Fusion and Genetic Algorithms.
Electronics 2023, 12, 280. https://
doi.org/10.3390/electronics12020280
Academic Editor: Gwanggil Jeon
Received: 15 December 2022
Revised: 29 December 2022
Accepted: 2 January 2023
Published: 5 January 2023
Copyright: © 2023 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
electronics
Article
Vehicle Classification Using Deep Feature Fusion and
Genetic Algorithms
Ahmed S. Alghamdi
1
, Ammar Saeed
2
, Muhammad Kamran
1,
* , Khalid T. Mursi
1
and Wafa Sulaiman Almukadi
1
1
Department of Cybersecurity, College of Computer Science and Engineering, University of Jeddah,
Jeddah 21959, Saudi Arabia
2
Department of Computer Science, COMSATS University Islamabad, Wah Cantt 47010, Pakistan
* Correspondence: mkkamran@uj.edu.sa
Abstract: Vehicle classification is a challenging task in the area of image processing. It involves the
classification of various vehicles based on their color, model, and make. A distinctive variety of
vehicles belonging to various model categories have been developed in the automobile industry,
which has made it necessary to establish a compact system that can classify vehicles within a complex
model group. A well-established vehicle classification system has applications in security, vehicle
monitoring in traffic cameras, route analysis in autonomous vehicles, and traffic control systems. In
this paper, a hybrid model based on the integration of a pre-trained Convolutional Neural Network
(CNN) and an evolutionary feature selection model is proposed for vehicle classification. The
proposed model performs classification of eight different vehicle categories including sports cars,
luxury cars and hybrid power-house SUVs. The used in this work is derived from Stanford car dataset
that contains almost 196 cars and vehicle classes. After performing appropriate data preparation
and preprocessing steps, feature learning and extraction is carried out using pre-trained VGG16 first
that learns and extracts deep features from the set of input images. These features are then taken
out of the last fully connected layer of VGG16, and feature optimization phase is carried out using
evolution-based nature-inspired optimization model Genetic Algorithm (GA). The classification
is performed using numerous SVM kernels where Cubic SVM achieves an accuracy of 99.7% and
outperforms other kernels as well as excels in terns of performance as compared to the existing works.
Keywords: convolutional neural network; fused deep earning; vehicle classification
1. Introduction
The evolution of the modern era has had a significant impact on the automobile
industry, which has progressed rapidly. Nowadays, vehicles of the same companies are
being released with various colors, models, and physical attributes, making it difficult to
differentiate them without having some prior knowledge about those models that makes
developing a system that could perform vehicle classification an even bigger challenge. The
emerging concept of smart cities relies on an intelligent traffic monitoring and classification
system that could detect and surveil different vehicles for traffic rule obstruction, security,
and emergency situations [1]. The ever-increasing demand, production and usage of
vehicles of all kinds of makes, colors and models, it becomes very difficult for a human
agent to perform vehicle monitoring, record keeping, surveillance and detection for any
kind of obstruction [2]. Therefore, establishing an automated system that can discriminate
between various vehicle types is necessary. A model like this could have applications in the
area of security, smart traffic systems, self-driving vehicles for environmental understanding
and collision avoidance, criminal activity reduction, and vehicle-type detection [3].
An intelligent traffic system could also assist in crime reduction and criminal activity
tracking, given that most criminal activities involve the use of some kind of vehicle for
Electronics 2023, 12, 280. https://doi.org/10.3390/electronics12020280 https://www.mdpi.com/journal/electronics