Unconstrained Road Marking Recognition with Generative Adversarial Networks

TL;DR

This paper introduces a GAN-based approach for unconstrained road marking recognition that enhances data quality and quantity, leading to improved accuracy in diverse, real-world conditions.

Contribution

It presents a novel deblurring GAN and a mutual information-based data augmentation method to improve recognition performance under unconstrained conditions.

Findings

The deblurring GAN effectively recovers clean road markings from blurry images.

The data augmentation method increases training data diversity and semantic consistency.

The framework outperforms existing methods on unconstrained datasets.

Abstract

Recent road marking recognition has achieved great success in the past few years along with the rapid development of deep learning. Although considerable advances have been made, they are often over-dependent on unrepresentative datasets and constrained conditions. In this paper, to overcome these drawbacks, we propose an alternative method that achieves higher accuracy and generates high-quality samples as data augmentation. With the following two major contributions: 1) The proposed deblurring network can successfully recover a clean road marking from a blurred one by adopting generative adversarial networks (GAN). 2) The proposed data augmentation method, based on mutual information, can preserve and learn semantic context from the given dataset. We construct and train a class-conditional GAN to increase the size of training set, which makes it suitable to recognize target. The experimental results have shown that our proposed framework generates deblurred clean samples from blurry ones, and outperforms other methods even with unconstrained road marking datasets.