Bangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network

Abstract

Vehicle type classification plays an essential role in developing an intelligent transportation system (ITS). Based on the modern accomplishments of deep learning (DL) on image classification, we proposed a model based on transfer learning, incorporating data augmentation, for the recognition and classification of Bangladeshi native vehicle types. An extensive dataset of Bangladeshi native vehicles, encompassing 10,440 images, was developed. Here, the images are categorized into 13 common vehicle classes in Bangladesh. The method utilized was a residual network (ResNet-50)-based model, with extra classification blocks added to improve performance. Here, vehicle type features were automatically extracted and categorized. While conducting the analysis, a variety of metrics was used for the evaluation, including accuracy, precision, recall, and F1 − Score. In spite of the changing physical properties of the vehicles, the proposed model achieved progressive accuracy. Our proposed method surpasses the existing baseline method as well as two pre-trained DL approaches, AlexNet and VGG-16. Based on result comparisons, we have seen that, in the classification of Bangladeshi native vehicle types, our suggested ResNet-50 pre-trained model achieves an accuracy of 98.00%.

Vehicle Make Detection Using the Transfer Learning Approach

“…Convolutional Neural Networks are widely used in computer vision tasks to classify objects such as cars, pedestrians, and more [11]. To learn how to replicate human intellect, this supervised machine learning technique requires labeled data [12].…”

“…To learn how to replicate human intellect, this supervised machine learning technique requires labeled data [12]. The basic CNN consists of convolutional, polling, and fully connected layers that classify the final classes, where the convolutional layer extracts low-and high-level visual features using a weightsharing mechanism [11].…”

Convolutional Neural Network-Based Vehicle Classification in Low-Quality Imaging Conditions for Internet of Things Devices

“…In fact, the use of CNNs is very popular among the research community due to the several reasons, such as working well on both large and small datasets, extracting both low-and high-level features from images, and achieving the same performance with fewer computational resources compared to other DL approaches. They have been shown to achieve state-of-the-art performance on a variety of vehicle image datasets [13][14][15][16][17][18][19][20][21][22][23][24]. In [13], a method based on a semi-supervised CNN is provided for vehicle classification from vehicle frontal view images.…”

“…In [22], the use of various CNN-based models on non-laned heterogeneous traffic images for vehicle classification is presented. Moreover, a vehicle classification model based on transfer learning with a deep CNN is proposed in [23].…”

“…The methods presented in [13][14][15][16][17][18][19][20][21][22][23][24] are proposed for real-time ITS applications that use high-quality monitoring cameras. Although these types of cameras provide high-resolution (or frame rate) videos or images, their higher cost leads to an important concern in the deployment of IoT-based ITS applications.…”