Improving benchmarks for autonomous vehicles testing using synthetically generated images

TL;DR

This paper proposes a method to enhance autonomous vehicle testing benchmarks by generating synthetic images, improving model performance especially in regions with limited real-world data.

Contribution

The study introduces a synthetic image generation approach to augment datasets, enabling small dataset updates for better autonomous vehicle perception in data-scarce regions.

Findings

Approximately 10% improvement in model accuracy

Synthetic data effectively enhances traffic sign recognition

Potential for further improvements with future experiments

Abstract

Nowadays autonomous technologies are a very heavily explored area and particularly computer vision as the main component of vehicle perception. The quality of the whole vision system based on neural networks relies on the dataset it was trained on. It is extremely difficult to find traffic sign datasets from most of the counties of the world. Meaning autonomous vehicle from the USA will not be able to drive though Lithuania recognizing all road signs on the way. In this paper, we propose a solution on how to update model using a small dataset from the country vehicle will be used in. It is important to mention that is not panacea, rather small upgrade which can boost autonomous car development in countries with limited data access. We achieved about 10 percent quality raise and expect even better results during future experiments.