Image-based Vehicle Analysis using Deep Neural Network: A Systematic Study

TL;DR

This paper explores vehicle detection and classification using deep neural networks, focusing on feature selection, model extension for limited data, and robustness under extreme lighting conditions, achieving superior results over existing methods.

Contribution

It introduces a novel approach that enhances vehicle detection and classification performance, especially under challenging lighting, surpassing current state-of-the-art techniques.

Findings

Outperforms existing methods in vehicle detection and classification.

Effective model extension for limited datasets.

Robust performance under extreme lighting conditions.

Abstract

We address the vehicle detection and classification problems using Deep Neural Networks (DNNs) approaches. Here we answer to questions that are specific to our application including how to utilize DNN for vehicle detection, what features are useful for vehicle classification, and how to extend a model trained on a limited size dataset, to the cases of extreme lighting condition. Answering these questions we propose our approach that outperforms state-of-the-art methods, and achieves promising results on image with extreme lighting conditions.