Classifying logistic vehicles in cities using Deep learning

TL;DR

This paper presents a deep learning approach for classifying logistic vehicles in urban environments, creating a large annotated dataset and achieving over 90% accuracy with CNN models.

Contribution

It introduces a novel architecture for building a balanced vehicle dataset and retrains CNNs for accurate logistic vehicle classification.

Findings

Created a database of 72,000 images across 4 vehicle classes.

Achieved over 90% classification accuracy with InceptionV3 and MobileNetV2.

Demonstrated the effectiveness of deep learning for urban vehicle classification.

Abstract

Rapid growth in delivery and freight transportation is increasing in urban areas; as a result the use of delivery trucks and light commercial vehicles is evolving. Major cities can use traffic counting as a tool to monitor the presence of delivery vehicles in order to implement intelligent city planning measures. Classical methods for counting vehicles use mechanical, electromagnetic or pneumatic sensors, but these devices are costly, difficult to implement and only detect the presence of vehicles without giving information about their category, model or trajectory. This paper proposes a Deep Learning tool for classifying vehicles in a given image while considering different categories of logistic vehicles, namely: light-duty, medium-duty and heavy-duty vehicles. The proposed approach yields two main contributions: first we developed an architecture to create an annotated and balanced database of logistic vehicles, reducing manual annotation efforts. Second, we built a classifier that accurately classifies the logistic vehicles passing through a given road. The results of this work are: first, a database of 72 000 images for 4 vehicles classes; and second two retrained convolutional neural networks (InceptionV3 and MobileNetV2) capable of classifying vehicles with accuracies over 90%.