Monocular Vision-based Vehicle Localization Aided by Fine-grained Classification

TL;DR

This paper presents a novel monocular vision-based vehicle localization method using deep learning and computer vision techniques, achieving high accuracy in position and orientation estimation for intelligent transportation applications.

Contribution

The paper introduces a new algorithm that combines fine-grained vehicle classification with vision techniques to accurately estimate vehicle location and orientation from monocular images.

Findings

Achieves 3.79% position accuracy

Attains 2.5 degrees orientation accuracy

Enables new intelligent transportation applications

Abstract

Monocular camera systems are prevailing in intelligent transportation systems, but by far they have rarely been used for dimensional purposes such as to accurately estimate the localization information of a vehicle. In this paper, we show that this capability can be realized. By integrating a series of advanced computer vision techniques including foreground extraction, edge and line detection, etc., and by utilizing deep learning networks for fine-grained vehicle model classification, we developed an algorithm which can estimate vehicles location (position, orientation and boundaries) within the environment down to 3.79 percent position accuracy and 2.5 degrees orientation accuracy. With this enhancement, current massive surveillance camera systems can potentially play the role of e-traffic police and trigger many new intelligent transportation applications, for example, to guide vehicles for parking or even for autonomous driving.